diff options
| author |   José Pekkarinen <jose.pekkarinen@nokia.com> | 2016-04-11 10:41:07 +0300 |
|---|---|---|
| committer | José Pekkarinen <jose.pekkarinen@nokia.com> | 2016-04-13 08:17:18 +0300 |
| commit | e09b41010ba33a20a87472ee821fa407a5b8da36 (patch) | |
| tree | d10dc367189862e7ca5c592f033dc3726e1df4e3 /kernel/include/linux | |
| parent | f93b97fd65072de626c074dbe099a1fff05ce060 (diff) | |
These changes are the raw update to linux-4.4.6-rt14. Kernel sources
are taken from kernel.org, and rt patch from the rt wiki download page.
During the rebasing, the following patch collided:
Force tick interrupt and get rid of softirq magic(I70131fb85).
Collisions have been removed because its logic was found on the
source already.
Change-Id: I7f57a4081d9deaa0d9ccfc41a6c8daccdee3b769
Signed-off-by: José Pekkarinen <jose.pekkarinen@nokia.com>
Diffstat (limited to 'kernel/include/linux')
636 files changed, 35664 insertions, 12128 deletions
diff --git a/kernel/include/linux/acpi.h b/kernel/include/linux/acpi.h index 808c43afa..1991aea2e 100644 --- a/kernel/include/linux/acpi.h +++ b/kernel/include/linux/acpi.h @@ -15,10 +15,6 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - * * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ */ @@ -53,14 +49,27 @@ static inline acpi_handle acpi_device_handle(struct acpi_device *adev) return adev ? adev->handle : NULL; } -#define ACPI_COMPANION(dev) acpi_node((dev)->fwnode) +#define ACPI_COMPANION(dev) to_acpi_device_node((dev)->fwnode) #define ACPI_COMPANION_SET(dev, adev) set_primary_fwnode(dev, (adev) ? \ acpi_fwnode_handle(adev) : NULL) #define ACPI_HANDLE(dev) acpi_device_handle(ACPI_COMPANION(dev)) +/** + * ACPI_DEVICE_CLASS - macro used to describe an ACPI device with + * the PCI-defined class-code information + * + * @_cls : the class, subclass, prog-if triple for this device + * @_msk : the class mask for this device + * + * This macro is used to create a struct acpi_device_id that matches a + * specific PCI class. The .id and .driver_data fields will be left + * initialized with the default value. + */ +#define ACPI_DEVICE_CLASS(_cls, _msk) .cls = (_cls), .cls_msk = (_msk), + static inline bool has_acpi_companion(struct device *dev) { - return is_acpi_node(dev->fwnode); + return is_acpi_device_node(dev->fwnode); } static inline void acpi_preset_companion(struct device *dev, @@ -122,6 +131,12 @@ static inline void acpi_initrd_override(void *data, size_t size) (!entry) || (unsigned long)entry + sizeof(*entry) > end || \ ((struct acpi_subtable_header *)entry)->length < sizeof(*entry)) +struct acpi_subtable_proc { + int id; + acpi_tbl_entry_handler handler; + int count; +}; + char * __acpi_map_table (unsigned long phys_addr, unsigned long size); void __acpi_unmap_table(char *map, unsigned long size); int early_acpi_boot_init(void); @@ -137,9 +152,16 @@ int __init acpi_parse_entries(char *id, unsigned long table_size, struct acpi_table_header *table_header, int entry_id, unsigned int max_entries); int __init acpi_table_parse_entries(char *id, unsigned long table_size, - int entry_id, - acpi_tbl_entry_handler handler, - unsigned int max_entries); + int entry_id, + acpi_tbl_entry_handler handler, + unsigned int max_entries); +int __init acpi_table_parse_entries(char *id, unsigned long table_size, + int entry_id, + acpi_tbl_entry_handler handler, + unsigned int max_entries); +int __init acpi_table_parse_entries_array(char *id, unsigned long table_size, + struct acpi_subtable_proc *proc, int proc_num, + unsigned int max_entries); int acpi_table_parse_madt(enum acpi_madt_type id, acpi_tbl_entry_handler handler, unsigned int max_entries); @@ -158,6 +180,16 @@ typedef u32 phys_cpuid_t; #define PHYS_CPUID_INVALID (phys_cpuid_t)(-1) #endif +static inline bool invalid_logical_cpuid(u32 cpuid) +{ + return (int)cpuid < 0; +} + +static inline bool invalid_phys_cpuid(phys_cpuid_t phys_id) +{ + return phys_id == PHYS_CPUID_INVALID; +} + #ifdef CONFIG_ACPI_HOTPLUG_CPU /* Arch dependent functions for cpu hotplug support */ int acpi_map_cpu(acpi_handle handle, phys_cpuid_t physid, int *pcpu); @@ -174,6 +206,12 @@ int acpi_ioapic_registered(acpi_handle handle, u32 gsi_base); void acpi_irq_stats_init(void); extern u32 acpi_irq_handled; extern u32 acpi_irq_not_handled; +extern unsigned int acpi_sci_irq; +#define INVALID_ACPI_IRQ ((unsigned)-1) +static inline bool acpi_sci_irq_valid(void) +{ + return acpi_sci_irq != INVALID_ACPI_IRQ; +} extern int sbf_port; extern unsigned long acpi_realmode_flags; @@ -182,6 +220,9 @@ int acpi_register_gsi (struct device *dev, u32 gsi, int triggering, int polarity int acpi_gsi_to_irq (u32 gsi, unsigned int *irq); int acpi_isa_irq_to_gsi (unsigned isa_irq, u32 *gsi); +void acpi_set_irq_model(enum acpi_irq_model_id model, + struct fwnode_handle *fwnode); + #ifdef CONFIG_X86_IO_APIC extern int acpi_get_override_irq(u32 gsi, int *trigger, int *polarity); #else @@ -198,6 +239,7 @@ struct pci_dev; int acpi_pci_irq_enable (struct pci_dev *dev); void acpi_penalize_isa_irq(int irq, int active); +bool acpi_isa_irq_available(int irq); void acpi_penalize_sci_irq(int irq, int trigger, int polarity); void acpi_pci_irq_disable (struct pci_dev *dev); @@ -243,54 +285,21 @@ extern bool wmi_has_guid(const char *guid); #define ACPI_VIDEO_OUTPUT_SWITCHING_DMI_VENDOR 0x0400 #define ACPI_VIDEO_OUTPUT_SWITCHING_DMI_VIDEO 0x0800 -#if defined(CONFIG_ACPI_VIDEO) || defined(CONFIG_ACPI_VIDEO_MODULE) - -extern long acpi_video_get_capabilities(acpi_handle graphics_dev_handle); +extern char acpi_video_backlight_string[]; extern long acpi_is_video_device(acpi_handle handle); -extern void acpi_video_dmi_promote_vendor(void); -extern void acpi_video_dmi_demote_vendor(void); -extern int acpi_video_backlight_support(void); -extern int acpi_video_display_switch_support(void); - -#else - -static inline long acpi_video_get_capabilities(acpi_handle graphics_dev_handle) -{ - return 0; -} - -static inline long acpi_is_video_device(acpi_handle handle) -{ - return 0; -} - -static inline void acpi_video_dmi_promote_vendor(void) -{ -} - -static inline void acpi_video_dmi_demote_vendor(void) -{ -} - -static inline int acpi_video_backlight_support(void) -{ - return 0; -} - -static inline int acpi_video_display_switch_support(void) -{ - return 0; -} - -#endif /* defined(CONFIG_ACPI_VIDEO) || defined(CONFIG_ACPI_VIDEO_MODULE) */ - extern int acpi_blacklisted(void); extern void acpi_dmi_osi_linux(int enable, const struct dmi_system_id *d); extern void acpi_osi_setup(char *str); +extern bool acpi_osi_is_win8(void); #ifdef CONFIG_ACPI_NUMA +int acpi_map_pxm_to_online_node(int pxm); int acpi_get_node(acpi_handle handle); #else +static inline int acpi_map_pxm_to_online_node(int pxm) +{ + return 0; +} static inline int acpi_get_node(acpi_handle handle) { return 0; @@ -466,6 +475,7 @@ struct platform_device *acpi_create_platform_device(struct acpi_device *); #define ACPI_COMPANION(dev) (NULL) #define ACPI_COMPANION_SET(dev, adev) do { } while (0) #define ACPI_HANDLE(dev) (NULL) +#define ACPI_DEVICE_CLASS(_cls, _msk) .cls = (0), .cls_msk = (0), struct fwnode_handle; @@ -474,7 +484,22 @@ static inline bool is_acpi_node(struct fwnode_handle *fwnode) return false; } -static inline struct acpi_device *acpi_node(struct fwnode_handle *fwnode) +static inline bool is_acpi_device_node(struct fwnode_handle *fwnode) +{ + return false; +} + +static inline struct acpi_device *to_acpi_device_node(struct fwnode_handle *fwnode) +{ + return NULL; +} + +static inline bool is_acpi_data_node(struct fwnode_handle *fwnode) +{ + return false; +} + +static inline struct acpi_data_node *to_acpi_data_node(struct fwnode_handle *fwnode) { return NULL; } @@ -489,6 +514,11 @@ static inline bool has_acpi_companion(struct device *dev) return false; } +static inline void acpi_preset_companion(struct device *dev, + struct acpi_device *parent, u64 addr) +{ +} + static inline const char *acpi_dev_name(struct acpi_device *adev) { return NULL; @@ -571,6 +601,16 @@ static inline int acpi_device_modalias(struct device *dev, return -ENODEV; } +static inline bool acpi_dma_supported(struct acpi_device *adev) +{ + return false; +} + +static inline enum dev_dma_attr acpi_get_dma_attr(struct acpi_device *adev) +{ + return DEV_DMA_NOT_SUPPORTED; +} + #define ACPI_PTR(_ptr) (NULL) #endif /* !CONFIG_ACPI */ @@ -723,6 +763,8 @@ static inline void acpi_dev_remove_driver_gpios(struct acpi_device *adev) if (adev) adev->driver_gpios = NULL; } + +int acpi_dev_gpio_irq_get(struct acpi_device *adev, int index); #else static inline int acpi_dev_add_driver_gpios(struct acpi_device *adev, const struct acpi_gpio_mapping *gpios) @@ -730,6 +772,11 @@ static inline int acpi_dev_add_driver_gpios(struct acpi_device *adev, return -ENXIO; } static inline void acpi_dev_remove_driver_gpios(struct acpi_device *adev) {} + +static inline int acpi_dev_gpio_irq_get(struct acpi_device *adev, int index) +{ + return -ENXIO; +} #endif /* Device properties */ @@ -744,22 +791,76 @@ struct acpi_reference_args { #ifdef CONFIG_ACPI int acpi_dev_get_property(struct acpi_device *adev, const char *name, acpi_object_type type, const union acpi_object **obj); -int acpi_dev_get_property_array(struct acpi_device *adev, const char *name, - acpi_object_type type, - const union acpi_object **obj); -int acpi_dev_get_property_reference(struct acpi_device *adev, - const char *name, size_t index, - struct acpi_reference_args *args); - -int acpi_dev_prop_get(struct acpi_device *adev, const char *propname, - void **valptr); +int acpi_node_get_property_reference(struct fwnode_handle *fwnode, + const char *name, size_t index, + struct acpi_reference_args *args); + +int acpi_node_prop_get(struct fwnode_handle *fwnode, const char *propname, + void **valptr); int acpi_dev_prop_read_single(struct acpi_device *adev, const char *propname, enum dev_prop_type proptype, void *val); +int acpi_node_prop_read(struct fwnode_handle *fwnode, const char *propname, + enum dev_prop_type proptype, void *val, size_t nval); int acpi_dev_prop_read(struct acpi_device *adev, const char *propname, enum dev_prop_type proptype, void *val, size_t nval); -struct acpi_device *acpi_get_next_child(struct device *dev, - struct acpi_device *child); +struct fwnode_handle *acpi_get_next_subnode(struct device *dev, + struct fwnode_handle *subnode); + +struct acpi_probe_entry; +typedef bool (*acpi_probe_entry_validate_subtbl)(struct acpi_subtable_header *, + struct acpi_probe_entry *); + +#define ACPI_TABLE_ID_LEN 5 + +/** + * struct acpi_probe_entry - boot-time probing entry + * @id: ACPI table name + * @type: Optional subtable type to match + * (if @id contains subtables) + * @subtable_valid: Optional callback to check the validity of + * the subtable + * @probe_table: Callback to the driver being probed when table + * match is successful + * @probe_subtbl: Callback to the driver being probed when table and + * subtable match (and optional callback is successful) + * @driver_data: Sideband data provided back to the driver + */ +struct acpi_probe_entry { + __u8 id[ACPI_TABLE_ID_LEN]; + __u8 type; + acpi_probe_entry_validate_subtbl subtable_valid; + union { + acpi_tbl_table_handler probe_table; + acpi_tbl_entry_handler probe_subtbl; + }; + kernel_ulong_t driver_data; +}; + +#define ACPI_DECLARE_PROBE_ENTRY(table, name, table_id, subtable, valid, data, fn) \ + static const struct acpi_probe_entry __acpi_probe_##name \ + __used __section(__##table##_acpi_probe_table) \ + = { \ + .id = table_id, \ + .type = subtable, \ + .subtable_valid = valid, \ + .probe_table = (acpi_tbl_table_handler)fn, \ + .driver_data = data, \ + } + +#define ACPI_PROBE_TABLE(name) __##name##_acpi_probe_table +#define ACPI_PROBE_TABLE_END(name) __##name##_acpi_probe_table_end + +int __acpi_probe_device_table(struct acpi_probe_entry *start, int nr); + +#define acpi_probe_device_table(t) \ + ({ \ + extern struct acpi_probe_entry ACPI_PROBE_TABLE(t), \ + ACPI_PROBE_TABLE_END(t); \ + __acpi_probe_device_table(&ACPI_PROBE_TABLE(t), \ + (&ACPI_PROBE_TABLE_END(t) - \ + &ACPI_PROBE_TABLE(t))); \ + }) #else static inline int acpi_dev_get_property(struct acpi_device *adev, const char *name, acpi_object_type type, @@ -767,16 +868,17 @@ static inline int acpi_dev_get_property(struct acpi_device *adev, { return -ENXIO; } -static inline int acpi_dev_get_property_array(struct acpi_device *adev, - const char *name, - acpi_object_type type, - const union acpi_object **obj) + +static inline int acpi_node_get_property_reference(struct fwnode_handle *fwnode, + const char *name, size_t index, + struct acpi_reference_args *args) { return -ENXIO; } -static inline int acpi_dev_get_property_reference(struct acpi_device *adev, - const char *name, const char *cells_name, - size_t index, struct acpi_reference_args *args) + +static inline int acpi_node_prop_get(struct fwnode_handle *fwnode, + const char *propname, + void **valptr) { return -ENXIO; } @@ -796,6 +898,14 @@ static inline int acpi_dev_prop_read_single(struct acpi_device *adev, return -ENXIO; } +static inline int acpi_node_prop_read(struct fwnode_handle *fwnode, + const char *propname, + enum dev_prop_type proptype, + void *val, size_t nval) +{ + return -ENXIO; +} + static inline int acpi_dev_prop_read(struct acpi_device *adev, const char *propname, enum dev_prop_type proptype, @@ -804,12 +914,22 @@ static inline int acpi_dev_prop_read(struct acpi_device *adev, return -ENXIO; } -static inline struct acpi_device *acpi_get_next_child(struct device *dev, - struct acpi_device *child) +static inline struct fwnode_handle *acpi_get_next_subnode(struct device *dev, + struct fwnode_handle *subnode) { return NULL; } +#define ACPI_DECLARE_PROBE_ENTRY(table, name, table_id, subtable, validate, data, fn) \ + static const void * __acpi_table_##name[] \ + __attribute__((unused)) \ + = { (void *) table_id, \ + (void *) subtable, \ + (void *) valid, \ + (void *) fn, \ + (void *) data } + +#define acpi_probe_device_table(t) ({ int __r = 0; __r;}) #endif #endif /*_LINUX_ACPI_H*/ diff --git a/kernel/include/linux/acpi_irq.h b/kernel/include/linux/acpi_irq.h deleted file mode 100644 index f10c87265..000000000 --- a/kernel/include/linux/acpi_irq.h +++ /dev/null @@ -1,10 +0,0 @@ -#ifndef _LINUX_ACPI_IRQ_H -#define _LINUX_ACPI_IRQ_H - -#include <linux/irq.h> - -#ifndef acpi_irq_init -static inline void acpi_irq_init(void) { } -#endif - -#endif /* _LINUX_ACPI_IRQ_H */ diff --git a/kernel/include/linux/aer.h b/kernel/include/linux/aer.h index 4fef65e57..744b997d6 100644 --- a/kernel/include/linux/aer.h +++ b/kernel/include/linux/aer.h @@ -42,6 +42,7 @@ struct aer_capability_regs { int pci_enable_pcie_error_reporting(struct pci_dev *dev); int pci_disable_pcie_error_reporting(struct pci_dev *dev); int pci_cleanup_aer_uncorrect_error_status(struct pci_dev *dev); +int pci_cleanup_aer_error_status_regs(struct pci_dev *dev); #else static inline int pci_enable_pcie_error_reporting(struct pci_dev *dev) { @@ -55,6 +56,10 @@ static inline int pci_cleanup_aer_uncorrect_error_status(struct pci_dev *dev) { return -EINVAL; } +static inline int pci_cleanup_aer_error_status_regs(struct pci_dev *dev) +{ + return -EINVAL; +} #endif void cper_print_aer(struct pci_dev *dev, int cper_severity, diff --git a/kernel/include/linux/alarmtimer.h b/kernel/include/linux/alarmtimer.h index a899402a5..52f3b7da4 100644 --- a/kernel/include/linux/alarmtimer.h +++ b/kernel/include/linux/alarmtimer.h @@ -43,8 +43,8 @@ struct alarm { void alarm_init(struct alarm *alarm, enum alarmtimer_type type, enum alarmtimer_restart (*function)(struct alarm *, ktime_t)); -int alarm_start(struct alarm *alarm, ktime_t start); -int alarm_start_relative(struct alarm *alarm, ktime_t start); +void alarm_start(struct alarm *alarm, ktime_t start); +void alarm_start_relative(struct alarm *alarm, ktime_t start); void alarm_restart(struct alarm *alarm); int alarm_try_to_cancel(struct alarm *alarm); int alarm_cancel(struct alarm *alarm); diff --git a/kernel/include/linux/amba/bus.h b/kernel/include/linux/amba/bus.h index 50fc66868..9006c4e75 100644 --- a/kernel/include/linux/amba/bus.h +++ b/kernel/include/linux/amba/bus.h @@ -41,8 +41,6 @@ struct amba_driver { int (*probe)(struct amba_device *, const struct amba_id *); int (*remove)(struct amba_device *); void (*shutdown)(struct amba_device *); - int (*suspend)(struct amba_device *, pm_message_t); - int (*resume)(struct amba_device *); const struct amba_id *id_table; }; diff --git a/kernel/include/linux/amba/sp810.h b/kernel/include/linux/amba/sp810.h index c7df89f99..58fe9e8b6 100644 --- a/kernel/include/linux/amba/sp810.h +++ b/kernel/include/linux/amba/sp810.h @@ -2,7 +2,7 @@ * ARM PrimeXsys System Controller SP810 header file * * Copyright (C) 2009 ST Microelectronics - * Viresh Kumar <viresh.linux@gmail.com> + * Viresh Kumar <vireshk@kernel.org> * * This file is licensed under the terms of the GNU General Public * License version 2. This program is licensed "as is" without any diff --git a/kernel/include/linux/arcdevice.h b/kernel/include/linux/arcdevice.h deleted file mode 100644 index df0356220..000000000 --- a/kernel/include/linux/arcdevice.h +++ /dev/null @@ -1,342 +0,0 @@ -/* - * INET An implementation of the TCP/IP protocol suite for the LINUX - * operating system. NET is implemented using the BSD Socket - * interface as the means of communication with the user level. - * - * Definitions used by the ARCnet driver. - * - * Authors: Avery Pennarun and David Woodhouse - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * - */ -#ifndef _LINUX_ARCDEVICE_H -#define _LINUX_ARCDEVICE_H - -#include <asm/timex.h> -#include <linux/if_arcnet.h> - -#ifdef __KERNEL__ -#include <linux/irqreturn.h> - -/* - * RECON_THRESHOLD is the maximum number of RECON messages to receive - * within one minute before printing a "cabling problem" warning. The - * default value should be fine. - * - * After that, a "cabling restored" message will be printed on the next IRQ - * if no RECON messages have been received for 10 seconds. - * - * Do not define RECON_THRESHOLD at all if you want to disable this feature. - */ -#define RECON_THRESHOLD 30 - - -/* - * Define this to the minimum "timeout" value. If a transmit takes longer - * than TX_TIMEOUT jiffies, Linux will abort the TX and retry. On a large - * network, or one with heavy network traffic, this timeout may need to be - * increased. The larger it is, though, the longer it will be between - * necessary transmits - don't set this too high. - */ -#define TX_TIMEOUT (HZ * 200 / 1000) - - -/* Display warnings about the driver being an ALPHA version. */ -#undef ALPHA_WARNING - - -/* - * Debugging bitflags: each option can be enabled individually. - * - * Note: only debug flags included in the ARCNET_DEBUG_MAX define will - * actually be available. GCC will (at least, GCC 2.7.0 will) notice - * lines using a BUGLVL not in ARCNET_DEBUG_MAX and automatically optimize - * them out. - */ -#define D_NORMAL 1 /* important operational info */ -#define D_EXTRA 2 /* useful, but non-vital information */ -#define D_INIT 4 /* show init/probe messages */ -#define D_INIT_REASONS 8 /* show reasons for discarding probes */ -#define D_RECON 32 /* print a message whenever token is lost */ -#define D_PROTO 64 /* debug auto-protocol support */ -/* debug levels below give LOTS of output during normal operation! */ -#define D_DURING 128 /* trace operations (including irq's) */ -#define D_TX 256 /* show tx packets */ -#define D_RX 512 /* show rx packets */ -#define D_SKB 1024 /* show skb's */ -#define D_SKB_SIZE 2048 /* show skb sizes */ -#define D_TIMING 4096 /* show time needed to copy buffers to card */ -#define D_DEBUG 8192 /* Very detailed debug line for line */ - -#ifndef ARCNET_DEBUG_MAX -#define ARCNET_DEBUG_MAX (127) /* change to ~0 if you want detailed debugging */ -#endif - -#ifndef ARCNET_DEBUG -#define ARCNET_DEBUG (D_NORMAL|D_EXTRA) -#endif -extern int arcnet_debug; - -/* macros to simplify debug checking */ -#define BUGLVL(x) if ((ARCNET_DEBUG_MAX)&arcnet_debug&(x)) -#define BUGMSG2(x,msg,args...) do { BUGLVL(x) printk(msg, ## args); } while (0) -#define BUGMSG(x,msg,args...) \ - BUGMSG2(x, "%s%6s: " msg, \ - x==D_NORMAL ? KERN_WARNING \ - : x < D_DURING ? KERN_INFO : KERN_DEBUG, \ - dev->name , ## args) - -/* see how long a function call takes to run, expressed in CPU cycles */ -#define TIME(name, bytes, call) BUGLVL(D_TIMING) { \ - unsigned long _x, _y; \ - _x = get_cycles(); \ - call; \ - _y = get_cycles(); \ - BUGMSG(D_TIMING, \ - "%s: %d bytes in %lu cycles == " \ - "%lu Kbytes/100Mcycle\n",\ - name, bytes, _y - _x, \ - 100000000 / 1024 * bytes / (_y - _x + 1));\ - } \ - else { \ - call;\ - } - - -/* - * Time needed to reset the card - in ms (milliseconds). This works on my - * SMC PC100. I can't find a reference that tells me just how long I - * should wait. - */ -#define RESETtime (300) - -/* - * These are the max/min lengths of packet payload, not including the - * arc_hardware header, but definitely including the soft header. - * - * Note: packet sizes 254, 255, 256 are impossible because of the way - * ARCnet registers work That's why RFC1201 defines "exception" packets. - * In non-RFC1201 protocols, we have to just tack some extra bytes on the - * end. - */ -#define MTU 253 /* normal packet max size */ -#define MinTU 257 /* extended packet min size */ -#define XMTU 508 /* extended packet max size */ - -/* status/interrupt mask bit fields */ -#define TXFREEflag 0x01 /* transmitter available */ -#define TXACKflag 0x02 /* transmitted msg. ackd */ -#define RECONflag 0x04 /* network reconfigured */ -#define TESTflag 0x08 /* test flag */ -#define EXCNAKflag 0x08 /* excesive nak flag */ -#define RESETflag 0x10 /* power-on-reset */ -#define RES1flag 0x20 /* reserved - usually set by jumper */ -#define RES2flag 0x40 /* reserved - usually set by jumper */ -#define NORXflag 0x80 /* receiver inhibited */ - -/* Flags used for IO-mapped memory operations */ -#define AUTOINCflag 0x40 /* Increase location with each access */ -#define IOMAPflag 0x02 /* (for 90xx) Use IO mapped memory, not mmap */ -#define ENABLE16flag 0x80 /* (for 90xx) Enable 16-bit mode */ - -/* in the command register, the following bits have these meanings: - * 0-2 command - * 3-4 page number (for enable rcv/xmt command) - * 7 receive broadcasts - */ -#define NOTXcmd 0x01 /* disable transmitter */ -#define NORXcmd 0x02 /* disable receiver */ -#define TXcmd 0x03 /* enable transmitter */ -#define RXcmd 0x04 /* enable receiver */ -#define CONFIGcmd 0x05 /* define configuration */ -#define CFLAGScmd 0x06 /* clear flags */ -#define TESTcmd 0x07 /* load test flags */ - -/* flags for "clear flags" command */ -#define RESETclear 0x08 /* power-on-reset */ -#define CONFIGclear 0x10 /* system reconfigured */ - -#define EXCNAKclear 0x0E /* Clear and acknowledge the excive nak bit */ - -/* flags for "load test flags" command */ -#define TESTload 0x08 /* test flag (diagnostic) */ - -/* byte deposited into first address of buffers on reset */ -#define TESTvalue 0321 /* that's octal for 0xD1 :) */ - -/* for "enable receiver" command */ -#define RXbcasts 0x80 /* receive broadcasts */ - -/* flags for "define configuration" command */ -#define NORMALconf 0x00 /* 1-249 byte packets */ -#define EXTconf 0x08 /* 250-504 byte packets */ - -/* card feature flags, set during auto-detection. - * (currently only used by com20020pci) - */ -#define ARC_IS_5MBIT 1 /* card default speed is 5MBit */ -#define ARC_CAN_10MBIT 2 /* card uses COM20022, supporting 10MBit, - but default is 2.5MBit. */ - - -/* information needed to define an encapsulation driver */ -struct ArcProto { - char suffix; /* a for RFC1201, e for ether-encap, etc. */ - int mtu; /* largest possible packet */ - int is_ip; /* This is a ip plugin - not a raw thing */ - - void (*rx) (struct net_device * dev, int bufnum, - struct archdr * pkthdr, int length); - int (*build_header) (struct sk_buff * skb, struct net_device *dev, - unsigned short ethproto, uint8_t daddr); - - /* these functions return '1' if the skb can now be freed */ - int (*prepare_tx) (struct net_device * dev, struct archdr * pkt, int length, - int bufnum); - int (*continue_tx) (struct net_device * dev, int bufnum); - int (*ack_tx) (struct net_device * dev, int acked); -}; - -extern struct ArcProto *arc_proto_map[256], *arc_proto_default, - *arc_bcast_proto, *arc_raw_proto; - - -/* - * "Incoming" is information needed for each address that could be sending - * to us. Mostly for partially-received split packets. - */ -struct Incoming { - struct sk_buff *skb; /* packet data buffer */ - __be16 sequence; /* sequence number of assembly */ - uint8_t lastpacket, /* number of last packet (from 1) */ - numpackets; /* number of packets in split */ -}; - - -/* only needed for RFC1201 */ -struct Outgoing { - struct ArcProto *proto; /* protocol driver that owns this: - * if NULL, no packet is pending. - */ - struct sk_buff *skb; /* buffer from upper levels */ - struct archdr *pkt; /* a pointer into the skb */ - uint16_t length, /* bytes total */ - dataleft, /* bytes left */ - segnum, /* segment being sent */ - numsegs; /* number of segments */ -}; - - -struct arcnet_local { - uint8_t config, /* current value of CONFIG register */ - timeout, /* Extended timeout for COM20020 */ - backplane, /* Backplane flag for COM20020 */ - clockp, /* COM20020 clock divider */ - clockm, /* COM20020 clock multiplier flag */ - setup, /* Contents of setup1 register */ - setup2, /* Contents of setup2 register */ - intmask; /* current value of INTMASK register */ - uint8_t default_proto[256]; /* default encap to use for each host */ - int cur_tx, /* buffer used by current transmit, or -1 */ - next_tx, /* buffer where a packet is ready to send */ - cur_rx; /* current receive buffer */ - int lastload_dest, /* can last loaded packet be acked? */ - lasttrans_dest; /* can last TX'd packet be acked? */ - int timed_out; /* need to process TX timeout and drop packet */ - unsigned long last_timeout; /* time of last reported timeout */ - char *card_name; /* card ident string */ - int card_flags; /* special card features */ - - - /* On preemtive and SMB a lock is needed */ - spinlock_t lock; - - /* - * Buffer management: an ARCnet card has 4 x 512-byte buffers, each of - * which can be used for either sending or receiving. The new dynamic - * buffer management routines use a simple circular queue of available - * buffers, and take them as they're needed. This way, we simplify - * situations in which we (for example) want to pre-load a transmit - * buffer, or start receiving while we copy a received packet to - * memory. - * - * The rules: only the interrupt handler is allowed to _add_ buffers to - * the queue; thus, this doesn't require a lock. Both the interrupt - * handler and the transmit function will want to _remove_ buffers, so - * we need to handle the situation where they try to do it at the same - * time. - * - * If next_buf == first_free_buf, the queue is empty. Since there are - * only four possible buffers, the queue should never be full. - */ - atomic_t buf_lock; - int buf_queue[5]; - int next_buf, first_free_buf; - - /* network "reconfiguration" handling */ - unsigned long first_recon; /* time of "first" RECON message to count */ - unsigned long last_recon; /* time of most recent RECON */ - int num_recons; /* number of RECONs between first and last. */ - int network_down; /* do we think the network is down? */ - - int excnak_pending; /* We just got an excesive nak interrupt */ - - struct { - uint16_t sequence; /* sequence number (incs with each packet) */ - __be16 aborted_seq; - - struct Incoming incoming[256]; /* one from each address */ - } rfc1201; - - /* really only used by rfc1201, but we'll pretend it's not */ - struct Outgoing outgoing; /* packet currently being sent */ - - /* hardware-specific functions */ - struct { - struct module *owner; - void (*command) (struct net_device * dev, int cmd); - int (*status) (struct net_device * dev); - void (*intmask) (struct net_device * dev, int mask); - int (*reset) (struct net_device * dev, int really_reset); - void (*open) (struct net_device * dev); - void (*close) (struct net_device * dev); - - void (*copy_to_card) (struct net_device * dev, int bufnum, int offset, - void *buf, int count); - void (*copy_from_card) (struct net_device * dev, int bufnum, int offset, - void *buf, int count); - } hw; - - void __iomem *mem_start; /* pointer to ioremap'ed MMIO */ -}; - - -#define ARCRESET(x) (lp->hw.reset(dev, (x))) -#define ACOMMAND(x) (lp->hw.command(dev, (x))) -#define ASTATUS() (lp->hw.status(dev)) -#define AINTMASK(x) (lp->hw.intmask(dev, (x))) - - - -#if ARCNET_DEBUG_MAX & D_SKB -void arcnet_dump_skb(struct net_device *dev, struct sk_buff *skb, char *desc); -#else -#define arcnet_dump_skb(dev,skb,desc) ; -#endif - -void arcnet_unregister_proto(struct ArcProto *proto); -irqreturn_t arcnet_interrupt(int irq, void *dev_id); -struct net_device *alloc_arcdev(const char *name); - -int arcnet_open(struct net_device *dev); -int arcnet_close(struct net_device *dev); -netdev_tx_t arcnet_send_packet(struct sk_buff *skb, - struct net_device *dev); -void arcnet_timeout(struct net_device *dev); - -#endif /* __KERNEL__ */ -#endif /* _LINUX_ARCDEVICE_H */ diff --git a/kernel/include/linux/asn1_ber_bytecode.h b/kernel/include/linux/asn1_ber_bytecode.h index 945d44ae5..ab3a6c002 100644 --- a/kernel/include/linux/asn1_ber_bytecode.h +++ b/kernel/include/linux/asn1_ber_bytecode.h @@ -45,23 +45,27 @@ enum asn1_opcode { ASN1_OP_MATCH_JUMP = 0x04, ASN1_OP_MATCH_JUMP_OR_SKIP = 0x05, ASN1_OP_MATCH_ANY = 0x08, + ASN1_OP_MATCH_ANY_OR_SKIP = 0x09, ASN1_OP_MATCH_ANY_ACT = 0x0a, + ASN1_OP_MATCH_ANY_ACT_OR_SKIP = 0x0b, /* Everything before here matches unconditionally */ ASN1_OP_COND_MATCH_OR_SKIP = 0x11, ASN1_OP_COND_MATCH_ACT_OR_SKIP = 0x13, ASN1_OP_COND_MATCH_JUMP_OR_SKIP = 0x15, ASN1_OP_COND_MATCH_ANY = 0x18, + ASN1_OP_COND_MATCH_ANY_OR_SKIP = 0x19, ASN1_OP_COND_MATCH_ANY_ACT = 0x1a, + ASN1_OP_COND_MATCH_ANY_ACT_OR_SKIP = 0x1b, /* Everything before here will want a tag from the data */ -#define ASN1_OP__MATCHES_TAG ASN1_OP_COND_MATCH_ANY_ACT +#define ASN1_OP__MATCHES_TAG ASN1_OP_COND_MATCH_ANY_ACT_OR_SKIP /* These are here to help fill up space */ - ASN1_OP_COND_FAIL = 0x1b, - ASN1_OP_COMPLETE = 0x1c, - ASN1_OP_ACT = 0x1d, - ASN1_OP_RETURN = 0x1e, + ASN1_OP_COND_FAIL = 0x1c, + ASN1_OP_COMPLETE = 0x1d, + ASN1_OP_ACT = 0x1e, + ASN1_OP_MAYBE_ACT = 0x1f, /* The following eight have bit 0 -> SET, 1 -> OF, 2 -> ACT */ ASN1_OP_END_SEQ = 0x20, @@ -76,6 +80,8 @@ enum asn1_opcode { #define ASN1_OP_END__OF 0x02 #define ASN1_OP_END__ACT 0x04 + ASN1_OP_RETURN = 0x28, + ASN1_OP__NR }; diff --git a/kernel/include/linux/ata.h b/kernel/include/linux/ata.h index 5dfbcd888..c1a2f345c 100644 --- a/kernel/include/linux/ata.h +++ b/kernel/include/linux/ata.h @@ -487,8 +487,8 @@ enum ata_tf_protocols { }; enum ata_ioctls { - ATA_IOC_GET_IO32 = 0x309, - ATA_IOC_SET_IO32 = 0x324, + ATA_IOC_GET_IO32 = 0x309, /* HDIO_GET_32BIT */ + ATA_IOC_SET_IO32 = 0x324, /* HDIO_SET_32BIT */ }; /* core structures */ @@ -701,9 +701,19 @@ static inline bool ata_id_wcache_enabled(const u16 *id) static inline bool ata_id_has_read_log_dma_ext(const u16 *id) { + /* Word 86 must have bit 15 set */ if (!(id[ATA_ID_CFS_ENABLE_2] & (1 << 15))) return false; - return id[ATA_ID_COMMAND_SET_3] & (1 << 3); + + /* READ LOG DMA EXT support can be signaled either from word 119 + * or from word 120. The format is the same for both words: Bit + * 15 must be cleared, bit 14 set and bit 3 set. + */ + if ((id[ATA_ID_COMMAND_SET_3] & 0xC008) == 0x4008 || + (id[ATA_ID_COMMAND_SET_4] & 0xC008) == 0x4008) + return true; + + return false; } /** diff --git a/kernel/include/linux/atmel_serial.h b/kernel/include/linux/atmel_serial.h index 00beddf6b..ee696d7e8 100644 --- a/kernel/include/linux/atmel_serial.h +++ b/kernel/include/linux/atmel_serial.h @@ -16,115 +16,151 @@ #ifndef ATMEL_SERIAL_H #define ATMEL_SERIAL_H -#define ATMEL_US_CR 0x00 /* Control Register */ -#define ATMEL_US_RSTRX (1 << 2) /* Reset Receiver */ -#define ATMEL_US_RSTTX (1 << 3) /* Reset Transmitter */ -#define ATMEL_US_RXEN (1 << 4) /* Receiver Enable */ -#define ATMEL_US_RXDIS (1 << 5) /* Receiver Disable */ -#define ATMEL_US_TXEN (1 << 6) /* Transmitter Enable */ -#define ATMEL_US_TXDIS (1 << 7) /* Transmitter Disable */ -#define ATMEL_US_RSTSTA (1 << 8) /* Reset Status Bits */ -#define ATMEL_US_STTBRK (1 << 9) /* Start Break */ -#define ATMEL_US_STPBRK (1 << 10) /* Stop Break */ -#define ATMEL_US_STTTO (1 << 11) /* Start Time-out */ -#define ATMEL_US_SENDA (1 << 12) /* Send Address */ -#define ATMEL_US_RSTIT (1 << 13) /* Reset Iterations */ -#define ATMEL_US_RSTNACK (1 << 14) /* Reset Non Acknowledge */ -#define ATMEL_US_RETTO (1 << 15) /* Rearm Time-out */ -#define ATMEL_US_DTREN (1 << 16) /* Data Terminal Ready Enable [AT91RM9200 only] */ -#define ATMEL_US_DTRDIS (1 << 17) /* Data Terminal Ready Disable [AT91RM9200 only] */ -#define ATMEL_US_RTSEN (1 << 18) /* Request To Send Enable */ -#define ATMEL_US_RTSDIS (1 << 19) /* Request To Send Disable */ +#define ATMEL_US_CR 0x00 /* Control Register */ +#define ATMEL_US_RSTRX BIT(2) /* Reset Receiver */ +#define ATMEL_US_RSTTX BIT(3) /* Reset Transmitter */ +#define ATMEL_US_RXEN BIT(4) /* Receiver Enable */ +#define ATMEL_US_RXDIS BIT(5) /* Receiver Disable */ +#define ATMEL_US_TXEN BIT(6) /* Transmitter Enable */ +#define ATMEL_US_TXDIS BIT(7) /* Transmitter Disable */ +#define ATMEL_US_RSTSTA BIT(8) /* Reset Status Bits */ +#define ATMEL_US_STTBRK BIT(9) /* Start Break */ +#define ATMEL_US_STPBRK BIT(10) /* Stop Break */ +#define ATMEL_US_STTTO BIT(11) /* Start Time-out */ +#define ATMEL_US_SENDA BIT(12) /* Send Address */ +#define ATMEL_US_RSTIT BIT(13) /* Reset Iterations */ +#define ATMEL_US_RSTNACK BIT(14) /* Reset Non Acknowledge */ +#define ATMEL_US_RETTO BIT(15) /* Rearm Time-out */ +#define ATMEL_US_DTREN BIT(16) /* Data Terminal Ready Enable */ +#define ATMEL_US_DTRDIS BIT(17) /* Data Terminal Ready Disable */ +#define ATMEL_US_RTSEN BIT(18) /* Request To Send Enable */ +#define ATMEL_US_RTSDIS BIT(19) /* Request To Send Disable */ +#define ATMEL_US_TXFCLR BIT(24) /* Transmit FIFO Clear */ +#define ATMEL_US_RXFCLR BIT(25) /* Receive FIFO Clear */ +#define ATMEL_US_TXFLCLR BIT(26) /* Transmit FIFO Lock Clear */ +#define ATMEL_US_FIFOEN BIT(30) /* FIFO enable */ +#define ATMEL_US_FIFODIS BIT(31) /* FIFO disable */ -#define ATMEL_US_MR 0x04 /* Mode Register */ -#define ATMEL_US_USMODE (0xf << 0) /* Mode of the USART */ -#define ATMEL_US_USMODE_NORMAL 0 -#define ATMEL_US_USMODE_RS485 1 -#define ATMEL_US_USMODE_HWHS 2 -#define ATMEL_US_USMODE_MODEM 3 -#define ATMEL_US_USMODE_ISO7816_T0 4 -#define ATMEL_US_USMODE_ISO7816_T1 6 -#define ATMEL_US_USMODE_IRDA 8 -#define ATMEL_US_USCLKS (3 << 4) /* Clock Selection */ -#define ATMEL_US_USCLKS_MCK (0 << 4) -#define ATMEL_US_USCLKS_MCK_DIV8 (1 << 4) -#define ATMEL_US_USCLKS_SCK (3 << 4) -#define ATMEL_US_CHRL (3 << 6) /* Character Length */ -#define ATMEL_US_CHRL_5 (0 << 6) -#define ATMEL_US_CHRL_6 (1 << 6) -#define ATMEL_US_CHRL_7 (2 << 6) -#define ATMEL_US_CHRL_8 (3 << 6) -#define ATMEL_US_SYNC (1 << 8) /* Synchronous Mode Select */ -#define ATMEL_US_PAR (7 << 9) /* Parity Type */ -#define ATMEL_US_PAR_EVEN (0 << 9) -#define ATMEL_US_PAR_ODD (1 << 9) -#define ATMEL_US_PAR_SPACE (2 << 9) -#define ATMEL_US_PAR_MARK (3 << 9) -#define ATMEL_US_PAR_NONE (4 << 9) -#define ATMEL_US_PAR_MULTI_DROP (6 << 9) -#define ATMEL_US_NBSTOP (3 << 12) /* Number of Stop Bits */ -#define ATMEL_US_NBSTOP_1 (0 << 12) -#define ATMEL_US_NBSTOP_1_5 (1 << 12) -#define ATMEL_US_NBSTOP_2 (2 << 12) -#define ATMEL_US_CHMODE (3 << 14) /* Channel Mode */ -#define ATMEL_US_CHMODE_NORMAL (0 << 14) -#define ATMEL_US_CHMODE_ECHO (1 << 14) -#define ATMEL_US_CHMODE_LOC_LOOP (2 << 14) -#define ATMEL_US_CHMODE_REM_LOOP (3 << 14) -#define ATMEL_US_MSBF (1 << 16) /* Bit Order */ -#define ATMEL_US_MODE9 (1 << 17) /* 9-bit Character Length */ -#define ATMEL_US_CLKO (1 << 18) /* Clock Output Select */ -#define ATMEL_US_OVER (1 << 19) /* Oversampling Mode */ -#define ATMEL_US_INACK (1 << 20) /* Inhibit Non Acknowledge */ -#define ATMEL_US_DSNACK (1 << 21) /* Disable Successive NACK */ -#define ATMEL_US_MAX_ITER (7 << 24) /* Max Iterations */ -#define ATMEL_US_FILTER (1 << 28) /* Infrared Receive Line Filter */ +#define ATMEL_US_MR 0x04 /* Mode Register */ +#define ATMEL_US_USMODE GENMASK(3, 0) /* Mode of the USART */ +#define ATMEL_US_USMODE_NORMAL 0 +#define ATMEL_US_USMODE_RS485 1 +#define ATMEL_US_USMODE_HWHS 2 +#define ATMEL_US_USMODE_MODEM 3 +#define ATMEL_US_USMODE_ISO7816_T0 4 +#define ATMEL_US_USMODE_ISO7816_T1 6 +#define ATMEL_US_USMODE_IRDA 8 +#define ATMEL_US_USCLKS GENMASK(5, 4) /* Clock Selection */ +#define ATMEL_US_USCLKS_MCK (0 << 4) +#define ATMEL_US_USCLKS_MCK_DIV8 (1 << 4) +#define ATMEL_US_USCLKS_SCK (3 << 4) +#define ATMEL_US_CHRL GENMASK(7, 6) /* Character Length */ +#define ATMEL_US_CHRL_5 (0 << 6) +#define ATMEL_US_CHRL_6 (1 << 6) +#define ATMEL_US_CHRL_7 (2 << 6) +#define ATMEL_US_CHRL_8 (3 << 6) +#define ATMEL_US_SYNC BIT(8) /* Synchronous Mode Select */ +#define ATMEL_US_PAR GENMASK(11, 9) /* Parity Type */ +#define ATMEL_US_PAR_EVEN (0 << 9) +#define ATMEL_US_PAR_ODD (1 << 9) +#define ATMEL_US_PAR_SPACE (2 << 9) +#define ATMEL_US_PAR_MARK (3 << 9) +#define ATMEL_US_PAR_NONE (4 << 9) +#define ATMEL_US_PAR_MULTI_DROP (6 << 9) +#define ATMEL_US_NBSTOP GENMASK(13, 12) /* Number of Stop Bits */ +#define ATMEL_US_NBSTOP_1 (0 << 12) +#define ATMEL_US_NBSTOP_1_5 (1 << 12) +#define ATMEL_US_NBSTOP_2 (2 << 12) +#define ATMEL_US_CHMODE GENMASK(15, 14) /* Channel Mode */ +#define ATMEL_US_CHMODE_NORMAL (0 << 14) +#define ATMEL_US_CHMODE_ECHO (1 << 14) +#define ATMEL_US_CHMODE_LOC_LOOP (2 << 14) +#define ATMEL_US_CHMODE_REM_LOOP (3 << 14) +#define ATMEL_US_MSBF BIT(16) /* Bit Order */ +#define ATMEL_US_MODE9 BIT(17) /* 9-bit Character Length */ +#define ATMEL_US_CLKO BIT(18) /* Clock Output Select */ +#define ATMEL_US_OVER BIT(19) /* Oversampling Mode */ +#define ATMEL_US_INACK BIT(20) /* Inhibit Non Acknowledge */ +#define ATMEL_US_DSNACK BIT(21) /* Disable Successive NACK */ +#define ATMEL_US_MAX_ITER GENMASK(26, 24) /* Max Iterations */ +#define ATMEL_US_FILTER BIT(28) /* Infrared Receive Line Filter */ -#define ATMEL_US_IER 0x08 /* Interrupt Enable Register */ -#define ATMEL_US_RXRDY (1 << 0) /* Receiver Ready */ -#define ATMEL_US_TXRDY (1 << 1) /* Transmitter Ready */ -#define ATMEL_US_RXBRK (1 << 2) /* Break Received / End of Break */ -#define ATMEL_US_ENDRX (1 << 3) /* End of Receiver Transfer */ -#define ATMEL_US_ENDTX (1 << 4) /* End of Transmitter Transfer */ -#define ATMEL_US_OVRE (1 << 5) /* Overrun Error */ -#define ATMEL_US_FRAME (1 << 6) /* Framing Error */ -#define ATMEL_US_PARE (1 << 7) /* Parity Error */ -#define ATMEL_US_TIMEOUT (1 << 8) /* Receiver Time-out */ -#define ATMEL_US_TXEMPTY (1 << 9) /* Transmitter Empty */ -#define ATMEL_US_ITERATION (1 << 10) /* Max number of Repetitions Reached */ -#define ATMEL_US_TXBUFE (1 << 11) /* Transmission Buffer Empty */ -#define ATMEL_US_RXBUFF (1 << 12) /* Reception Buffer Full */ -#define ATMEL_US_NACK (1 << 13) /* Non Acknowledge */ -#define ATMEL_US_RIIC (1 << 16) /* Ring Indicator Input Change [AT91RM9200 only] */ -#define ATMEL_US_DSRIC (1 << 17) /* Data Set Ready Input Change [AT91RM9200 only] */ -#define ATMEL_US_DCDIC (1 << 18) /* Data Carrier Detect Input Change [AT91RM9200 only] */ -#define ATMEL_US_CTSIC (1 << 19) /* Clear to Send Input Change */ -#define ATMEL_US_RI (1 << 20) /* RI */ -#define ATMEL_US_DSR (1 << 21) /* DSR */ -#define ATMEL_US_DCD (1 << 22) /* DCD */ -#define ATMEL_US_CTS (1 << 23) /* CTS */ +#define ATMEL_US_IER 0x08 /* Interrupt Enable Register */ +#define ATMEL_US_RXRDY BIT(0) /* Receiver Ready */ +#define ATMEL_US_TXRDY BIT(1) /* Transmitter Ready */ +#define ATMEL_US_RXBRK BIT(2) /* Break Received / End of Break */ +#define ATMEL_US_ENDRX BIT(3) /* End of Receiver Transfer */ +#define ATMEL_US_ENDTX BIT(4) /* End of Transmitter Transfer */ +#define ATMEL_US_OVRE BIT(5) /* Overrun Error */ +#define ATMEL_US_FRAME BIT(6) /* Framing Error */ +#define ATMEL_US_PARE BIT(7) /* Parity Error */ +#define ATMEL_US_TIMEOUT BIT(8) /* Receiver Time-out */ +#define ATMEL_US_TXEMPTY BIT(9) /* Transmitter Empty */ +#define ATMEL_US_ITERATION BIT(10) /* Max number of Repetitions Reached */ +#define ATMEL_US_TXBUFE BIT(11) /* Transmission Buffer Empty */ +#define ATMEL_US_RXBUFF BIT(12) /* Reception Buffer Full */ +#define ATMEL_US_NACK BIT(13) /* Non Acknowledge */ +#define ATMEL_US_RIIC BIT(16) /* Ring Indicator Input Change */ +#define ATMEL_US_DSRIC BIT(17) /* Data Set Ready Input Change */ +#define ATMEL_US_DCDIC BIT(18) /* Data Carrier Detect Input Change */ +#define ATMEL_US_CTSIC BIT(19) /* Clear to Send Input Change */ +#define ATMEL_US_RI BIT(20) /* RI */ +#define ATMEL_US_DSR BIT(21) /* DSR */ +#define ATMEL_US_DCD BIT(22) /* DCD */ +#define ATMEL_US_CTS BIT(23) /* CTS */ -#define ATMEL_US_IDR 0x0c /* Interrupt Disable Register */ -#define ATMEL_US_IMR 0x10 /* Interrupt Mask Register */ -#define ATMEL_US_CSR 0x14 /* Channel Status Register */ -#define ATMEL_US_RHR 0x18 /* Receiver Holding Register */ -#define ATMEL_US_THR 0x1c /* Transmitter Holding Register */ -#define ATMEL_US_SYNH (1 << 15) /* Transmit/Receive Sync [AT91SAM9261 only] */ +#define ATMEL_US_IDR 0x0c /* Interrupt Disable Register */ +#define ATMEL_US_IMR 0x10 /* Interrupt Mask Register */ +#define ATMEL_US_CSR 0x14 /* Channel Status Register */ +#define ATMEL_US_RHR 0x18 /* Receiver Holding Register */ +#define ATMEL_US_THR 0x1c /* Transmitter Holding Register */ +#define ATMEL_US_SYNH BIT(15) /* Transmit/Receive Sync */ -#define ATMEL_US_BRGR 0x20 /* Baud Rate Generator Register */ -#define ATMEL_US_CD (0xffff << 0) /* Clock Divider */ +#define ATMEL_US_BRGR 0x20 /* Baud Rate Generator Register */ +#define ATMEL_US_CD GENMASK(15, 0) /* Clock Divider */ -#define ATMEL_US_RTOR 0x24 /* Receiver Time-out Register */ -#define ATMEL_US_TO (0xffff << 0) /* Time-out Value */ +#define ATMEL_US_RTOR 0x24 /* Receiver Time-out Register */ +#define ATMEL_US_TO GENMASK(15, 0) /* Time-out Value */ -#define ATMEL_US_TTGR 0x28 /* Transmitter Timeguard Register */ -#define ATMEL_US_TG (0xff << 0) /* Timeguard Value */ +#define ATMEL_US_TTGR 0x28 /* Transmitter Timeguard Register */ +#define ATMEL_US_TG GENMASK(7, 0) /* Timeguard Value */ -#define ATMEL_US_FIDI 0x40 /* FI DI Ratio Register */ -#define ATMEL_US_NER 0x44 /* Number of Errors Register */ -#define ATMEL_US_IF 0x4c /* IrDA Filter Register */ +#define ATMEL_US_FIDI 0x40 /* FI DI Ratio Register */ +#define ATMEL_US_NER 0x44 /* Number of Errors Register */ +#define ATMEL_US_IF 0x4c /* IrDA Filter Register */ -#define ATMEL_US_NAME 0xf0 /* Ip Name */ -#define ATMEL_US_VERSION 0xfc /* Ip Version */ +#define ATMEL_US_CMPR 0x90 /* Comparaison Register */ +#define ATMEL_US_FMR 0xa0 /* FIFO Mode Register */ +#define ATMEL_US_TXRDYM(data) (((data) & 0x3) << 0) /* TX Ready Mode */ +#define ATMEL_US_RXRDYM(data) (((data) & 0x3) << 4) /* RX Ready Mode */ +#define ATMEL_US_ONE_DATA 0x0 +#define ATMEL_US_TWO_DATA 0x1 +#define ATMEL_US_FOUR_DATA 0x2 +#define ATMEL_US_FRTSC BIT(7) /* FIFO RTS pin Control */ +#define ATMEL_US_TXFTHRES(thr) (((thr) & 0x3f) << 8) /* TX FIFO Threshold */ +#define ATMEL_US_RXFTHRES(thr) (((thr) & 0x3f) << 16) /* RX FIFO Threshold */ +#define ATMEL_US_RXFTHRES2(thr) (((thr) & 0x3f) << 24) /* RX FIFO Threshold2 */ + +#define ATMEL_US_FLR 0xa4 /* FIFO Level Register */ +#define ATMEL_US_TXFL(reg) (((reg) >> 0) & 0x3f) /* TX FIFO Level */ +#define ATMEL_US_RXFL(reg) (((reg) >> 16) & 0x3f) /* RX FIFO Level */ + +#define ATMEL_US_FIER 0xa8 /* FIFO Interrupt Enable Register */ +#define ATMEL_US_FIDR 0xac /* FIFO Interrupt Disable Register */ +#define ATMEL_US_FIMR 0xb0 /* FIFO Interrupt Mask Register */ +#define ATMEL_US_FESR 0xb4 /* FIFO Event Status Register */ +#define ATMEL_US_TXFEF BIT(0) /* Transmit FIFO Empty Flag */ +#define ATMEL_US_TXFFF BIT(1) /* Transmit FIFO Full Flag */ +#define ATMEL_US_TXFTHF BIT(2) /* Transmit FIFO Threshold Flag */ +#define ATMEL_US_RXFEF BIT(3) /* Receive FIFO Empty Flag */ +#define ATMEL_US_RXFFF BIT(4) /* Receive FIFO Full Flag */ +#define ATMEL_US_RXFTHF BIT(5) /* Receive FIFO Threshold Flag */ +#define ATMEL_US_TXFPTEF BIT(6) /* Transmit FIFO Pointer Error Flag */ +#define ATMEL_US_RXFPTEF BIT(7) /* Receive FIFO Pointer Error Flag */ +#define ATMEL_US_TXFLOCK BIT(8) /* Transmit FIFO Lock (FESR only) */ +#define ATMEL_US_RXFTHF2 BIT(9) /* Receive FIFO Threshold Flag 2 */ + +#define ATMEL_US_NAME 0xf0 /* Ip Name */ +#define ATMEL_US_VERSION 0xfc /* Ip Version */ #endif diff --git a/kernel/include/linux/atmel_tc.h b/kernel/include/linux/atmel_tc.h index b87c1c7c2..468fdfa64 100644 --- a/kernel/include/linux/atmel_tc.h +++ b/kernel/include/linux/atmel_tc.h @@ -67,6 +67,7 @@ struct atmel_tc { const struct atmel_tcb_config *tcb_config; int irq[3]; struct clk *clk[3]; + struct clk *slow_clk; struct list_head node; bool allocated; }; diff --git a/kernel/include/linux/atomic.h b/kernel/include/linux/atomic.h index 5b08a8540..301de78d6 100644 --- a/kernel/include/linux/atomic.h +++ b/kernel/include/linux/atomic.h @@ -2,6 +2,426 @@ #ifndef _LINUX_ATOMIC_H #define _LINUX_ATOMIC_H #include <asm/atomic.h> +#include <asm/barrier.h> + +/* + * Relaxed variants of xchg, cmpxchg and some atomic operations. + * + * We support four variants: + * + * - Fully ordered: The default implementation, no suffix required. + * - Acquire: Provides ACQUIRE semantics, _acquire suffix. + * - Release: Provides RELEASE semantics, _release suffix. + * - Relaxed: No ordering guarantees, _relaxed suffix. + * + * For compound atomics performing both a load and a store, ACQUIRE + * semantics apply only to the load and RELEASE semantics only to the + * store portion of the operation. Note that a failed cmpxchg_acquire + * does -not- imply any memory ordering constraints. + * + * See Documentation/memory-barriers.txt for ACQUIRE/RELEASE definitions. + */ + +#ifndef atomic_read_acquire +#define atomic_read_acquire(v) smp_load_acquire(&(v)->counter) +#endif + +#ifndef atomic_set_release +#define atomic_set_release(v, i) smp_store_release(&(v)->counter, (i)) +#endif + +/* + * The idea here is to build acquire/release variants by adding explicit + * barriers on top of the relaxed variant. In the case where the relaxed + * variant is already fully ordered, no additional barriers are needed. + */ +#define __atomic_op_acquire(op, args...) \ +({ \ + typeof(op##_relaxed(args)) __ret = op##_relaxed(args); \ + smp_mb__after_atomic(); \ + __ret; \ +}) + +#define __atomic_op_release(op, args...) \ +({ \ + smp_mb__before_atomic(); \ + op##_relaxed(args); \ +}) + +#define __atomic_op_fence(op, args...) \ +({ \ + typeof(op##_relaxed(args)) __ret; \ + smp_mb__before_atomic(); \ + __ret = op##_relaxed(args); \ + smp_mb__after_atomic(); \ + __ret; \ +}) + +/* atomic_add_return_relaxed */ +#ifndef atomic_add_return_relaxed +#define atomic_add_return_relaxed atomic_add_return +#define atomic_add_return_acquire atomic_add_return +#define atomic_add_return_release atomic_add_return + +#else /* atomic_add_return_relaxed */ + +#ifndef atomic_add_return_acquire +#define atomic_add_return_acquire(...) \ + __atomic_op_acquire(atomic_add_return, __VA_ARGS__) +#endif + +#ifndef atomic_add_return_release +#define atomic_add_return_release(...) \ + __atomic_op_release(atomic_add_return, __VA_ARGS__) +#endif + +#ifndef atomic_add_return +#define atomic_add_return(...) \ + __atomic_op_fence(atomic_add_return, __VA_ARGS__) +#endif +#endif /* atomic_add_return_relaxed */ + +/* atomic_inc_return_relaxed */ +#ifndef atomic_inc_return_relaxed +#define atomic_inc_return_relaxed atomic_inc_return +#define atomic_inc_return_acquire atomic_inc_return +#define atomic_inc_return_release atomic_inc_return + +#else /* atomic_inc_return_relaxed */ + +#ifndef atomic_inc_return_acquire +#define atomic_inc_return_acquire(...) \ + __atomic_op_acquire(atomic_inc_return, __VA_ARGS__) +#endif + +#ifndef atomic_inc_return_release +#define atomic_inc_return_release(...) \ + __atomic_op_release(atomic_inc_return, __VA_ARGS__) +#endif + +#ifndef atomic_inc_return +#define atomic_inc_return(...) \ + __atomic_op_fence(atomic_inc_return, __VA_ARGS__) +#endif +#endif /* atomic_inc_return_relaxed */ + +/* atomic_sub_return_relaxed */ +#ifndef atomic_sub_return_relaxed +#define atomic_sub_return_relaxed atomic_sub_return +#define atomic_sub_return_acquire atomic_sub_return +#define atomic_sub_return_release atomic_sub_return + +#else /* atomic_sub_return_relaxed */ + +#ifndef atomic_sub_return_acquire +#define atomic_sub_return_acquire(...) \ + __atomic_op_acquire(atomic_sub_return, __VA_ARGS__) +#endif + +#ifndef atomic_sub_return_release +#define atomic_sub_return_release(...) \ + __atomic_op_release(atomic_sub_return, __VA_ARGS__) +#endif + +#ifndef atomic_sub_return +#define atomic_sub_return(...) \ + __atomic_op_fence(atomic_sub_return, __VA_ARGS__) +#endif +#endif /* atomic_sub_return_relaxed */ + +/* atomic_dec_return_relaxed */ +#ifndef atomic_dec_return_relaxed +#define atomic_dec_return_relaxed atomic_dec_return +#define atomic_dec_return_acquire atomic_dec_return +#define atomic_dec_return_release atomic_dec_return + +#else /* atomic_dec_return_relaxed */ + +#ifndef atomic_dec_return_acquire +#define atomic_dec_return_acquire(...) \ + __atomic_op_acquire(atomic_dec_return, __VA_ARGS__) +#endif + +#ifndef atomic_dec_return_release +#define atomic_dec_return_release(...) \ + __atomic_op_release(atomic_dec_return, __VA_ARGS__) +#endif + +#ifndef atomic_dec_return +#define atomic_dec_return(...) \ + __atomic_op_fence(atomic_dec_return, __VA_ARGS__) +#endif +#endif /* atomic_dec_return_relaxed */ + +/* atomic_xchg_relaxed */ +#ifndef atomic_xchg_relaxed +#define atomic_xchg_relaxed atomic_xchg +#define atomic_xchg_acquire atomic_xchg +#define atomic_xchg_release atomic_xchg + +#else /* atomic_xchg_relaxed */ + +#ifndef atomic_xchg_acquire +#define atomic_xchg_acquire(...) \ + __atomic_op_acquire(atomic_xchg, __VA_ARGS__) +#endif + +#ifndef atomic_xchg_release +#define atomic_xchg_release(...) \ + __atomic_op_release(atomic_xchg, __VA_ARGS__) +#endif + +#ifndef atomic_xchg +#define atomic_xchg(...) \ + __atomic_op_fence(atomic_xchg, __VA_ARGS__) +#endif +#endif /* atomic_xchg_relaxed */ + +/* atomic_cmpxchg_relaxed */ +#ifndef atomic_cmpxchg_relaxed +#define atomic_cmpxchg_relaxed atomic_cmpxchg +#define atomic_cmpxchg_acquire atomic_cmpxchg +#define atomic_cmpxchg_release atomic_cmpxchg + +#else /* atomic_cmpxchg_relaxed */ + +#ifndef atomic_cmpxchg_acquire +#define atomic_cmpxchg_acquire(...) \ + __atomic_op_acquire(atomic_cmpxchg, __VA_ARGS__) +#endif + +#ifndef atomic_cmpxchg_release +#define atomic_cmpxchg_release(...) \ + __atomic_op_release(atomic_cmpxchg, __VA_ARGS__) +#endif + +#ifndef atomic_cmpxchg +#define atomic_cmpxchg(...) \ + __atomic_op_fence(atomic_cmpxchg, __VA_ARGS__) +#endif +#endif /* atomic_cmpxchg_relaxed */ + +#ifndef atomic64_read_acquire +#define atomic64_read_acquire(v) smp_load_acquire(&(v)->counter) +#endif + +#ifndef atomic64_set_release +#define atomic64_set_release(v, i) smp_store_release(&(v)->counter, (i)) +#endif + +/* atomic64_add_return_relaxed */ +#ifndef atomic64_add_return_relaxed +#define atomic64_add_return_relaxed atomic64_add_return +#define atomic64_add_return_acquire atomic64_add_return +#define atomic64_add_return_release atomic64_add_return + +#else /* atomic64_add_return_relaxed */ + +#ifndef atomic64_add_return_acquire +#define atomic64_add_return_acquire(...) \ + __atomic_op_acquire(atomic64_add_return, __VA_ARGS__) +#endif + +#ifndef atomic64_add_return_release +#define atomic64_add_return_release(...) \ + __atomic_op_release(atomic64_add_return, __VA_ARGS__) +#endif + +#ifndef atomic64_add_return +#define atomic64_add_return(...) \ + __atomic_op_fence(atomic64_add_return, __VA_ARGS__) +#endif +#endif /* atomic64_add_return_relaxed */ + +/* atomic64_inc_return_relaxed */ +#ifndef atomic64_inc_return_relaxed +#define atomic64_inc_return_relaxed atomic64_inc_return +#define atomic64_inc_return_acquire atomic64_inc_return +#define atomic64_inc_return_release atomic64_inc_return + +#else /* atomic64_inc_return_relaxed */ + +#ifndef atomic64_inc_return_acquire +#define atomic64_inc_return_acquire(...) \ + __atomic_op_acquire(atomic64_inc_return, __VA_ARGS__) +#endif + +#ifndef atomic64_inc_return_release +#define atomic64_inc_return_release(...) \ + __atomic_op_release(atomic64_inc_return, __VA_ARGS__) +#endif + +#ifndef atomic64_inc_return +#define atomic64_inc_return(...) \ + __atomic_op_fence(atomic64_inc_return, __VA_ARGS__) +#endif +#endif /* atomic64_inc_return_relaxed */ + + +/* atomic64_sub_return_relaxed */ +#ifndef atomic64_sub_return_relaxed +#define atomic64_sub_return_relaxed atomic64_sub_return +#define atomic64_sub_return_acquire atomic64_sub_return +#define atomic64_sub_return_release atomic64_sub_return + +#else /* atomic64_sub_return_relaxed */ + +#ifndef atomic64_sub_return_acquire +#define atomic64_sub_return_acquire(...) \ + __atomic_op_acquire(atomic64_sub_return, __VA_ARGS__) +#endif + +#ifndef atomic64_sub_return_release +#define atomic64_sub_return_release(...) \ + __atomic_op_release(atomic64_sub_return, __VA_ARGS__) +#endif + +#ifndef atomic64_sub_return +#define atomic64_sub_return(...) \ + __atomic_op_fence(atomic64_sub_return, __VA_ARGS__) +#endif +#endif /* atomic64_sub_return_relaxed */ + +/* atomic64_dec_return_relaxed */ +#ifndef atomic64_dec_return_relaxed +#define atomic64_dec_return_relaxed atomic64_dec_return +#define atomic64_dec_return_acquire atomic64_dec_return +#define atomic64_dec_return_release atomic64_dec_return + +#else /* atomic64_dec_return_relaxed */ + +#ifndef atomic64_dec_return_acquire +#define atomic64_dec_return_acquire(...) \ + __atomic_op_acquire(atomic64_dec_return, __VA_ARGS__) +#endif + +#ifndef atomic64_dec_return_release +#define atomic64_dec_return_release(...) \ + __atomic_op_release(atomic64_dec_return, __VA_ARGS__) +#endif + +#ifndef atomic64_dec_return +#define atomic64_dec_return(...) \ + __atomic_op_fence(atomic64_dec_return, __VA_ARGS__) +#endif +#endif /* atomic64_dec_return_relaxed */ + +/* atomic64_xchg_relaxed */ +#ifndef atomic64_xchg_relaxed +#define atomic64_xchg_relaxed atomic64_xchg +#define atomic64_xchg_acquire atomic64_xchg +#define atomic64_xchg_release atomic64_xchg + +#else /* atomic64_xchg_relaxed */ + +#ifndef atomic64_xchg_acquire +#define atomic64_xchg_acquire(...) \ + __atomic_op_acquire(atomic64_xchg, __VA_ARGS__) +#endif + +#ifndef atomic64_xchg_release +#define atomic64_xchg_release(...) \ + __atomic_op_release(atomic64_xchg, __VA_ARGS__) +#endif + +#ifndef atomic64_xchg +#define atomic64_xchg(...) \ + __atomic_op_fence(atomic64_xchg, __VA_ARGS__) +#endif +#endif /* atomic64_xchg_relaxed */ + +/* atomic64_cmpxchg_relaxed */ +#ifndef atomic64_cmpxchg_relaxed +#define atomic64_cmpxchg_relaxed atomic64_cmpxchg +#define atomic64_cmpxchg_acquire atomic64_cmpxchg +#define atomic64_cmpxchg_release atomic64_cmpxchg + +#else /* atomic64_cmpxchg_relaxed */ + +#ifndef atomic64_cmpxchg_acquire +#define atomic64_cmpxchg_acquire(...) \ + __atomic_op_acquire(atomic64_cmpxchg, __VA_ARGS__) +#endif + +#ifndef atomic64_cmpxchg_release +#define atomic64_cmpxchg_release(...) \ + __atomic_op_release(atomic64_cmpxchg, __VA_ARGS__) +#endif + +#ifndef atomic64_cmpxchg +#define atomic64_cmpxchg(...) \ + __atomic_op_fence(atomic64_cmpxchg, __VA_ARGS__) +#endif +#endif /* atomic64_cmpxchg_relaxed */ + +/* cmpxchg_relaxed */ +#ifndef cmpxchg_relaxed +#define cmpxchg_relaxed cmpxchg +#define cmpxchg_acquire cmpxchg +#define cmpxchg_release cmpxchg + +#else /* cmpxchg_relaxed */ + +#ifndef cmpxchg_acquire +#define cmpxchg_acquire(...) \ + __atomic_op_acquire(cmpxchg, __VA_ARGS__) +#endif + +#ifndef cmpxchg_release +#define cmpxchg_release(...) \ + __atomic_op_release(cmpxchg, __VA_ARGS__) +#endif + +#ifndef cmpxchg +#define cmpxchg(...) \ + __atomic_op_fence(cmpxchg, __VA_ARGS__) +#endif +#endif /* cmpxchg_relaxed */ + +/* cmpxchg64_relaxed */ +#ifndef cmpxchg64_relaxed +#define cmpxchg64_relaxed cmpxchg64 +#define cmpxchg64_acquire cmpxchg64 +#define cmpxchg64_release cmpxchg64 + +#else /* cmpxchg64_relaxed */ + +#ifndef cmpxchg64_acquire +#define cmpxchg64_acquire(...) \ + __atomic_op_acquire(cmpxchg64, __VA_ARGS__) +#endif + +#ifndef cmpxchg64_release +#define cmpxchg64_release(...) \ + __atomic_op_release(cmpxchg64, __VA_ARGS__) +#endif + +#ifndef cmpxchg64 +#define cmpxchg64(...) \ + __atomic_op_fence(cmpxchg64, __VA_ARGS__) +#endif +#endif /* cmpxchg64_relaxed */ + +/* xchg_relaxed */ +#ifndef xchg_relaxed +#define xchg_relaxed xchg +#define xchg_acquire xchg +#define xchg_release xchg + +#else /* xchg_relaxed */ + +#ifndef xchg_acquire +#define xchg_acquire(...) __atomic_op_acquire(xchg, __VA_ARGS__) +#endif + +#ifndef xchg_release +#define xchg_release(...) __atomic_op_release(xchg, __VA_ARGS__) +#endif + +#ifndef xchg +#define xchg(...) __atomic_op_fence(xchg, __VA_ARGS__) +#endif +#endif /* xchg_relaxed */ /** * atomic_add_unless - add unless the number is already a given value @@ -28,6 +448,23 @@ static inline int atomic_add_unless(atomic_t *v, int a, int u) #define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0) #endif +#ifndef atomic_andnot +static inline void atomic_andnot(int i, atomic_t *v) +{ + atomic_and(~i, v); +} +#endif + +static inline __deprecated void atomic_clear_mask(unsigned int mask, atomic_t *v) +{ + atomic_andnot(mask, v); +} + +static inline __deprecated void atomic_set_mask(unsigned int mask, atomic_t *v) +{ + atomic_or(mask, v); +} + /** * atomic_inc_not_zero_hint - increment if not null * @v: pointer of type atomic_t @@ -111,21 +548,17 @@ static inline int atomic_dec_if_positive(atomic_t *v) } #endif -#ifndef CONFIG_ARCH_HAS_ATOMIC_OR -static inline void atomic_or(int i, atomic_t *v) -{ - int old; - int new; +#ifdef CONFIG_GENERIC_ATOMIC64 +#include <asm-generic/atomic64.h> +#endif - do { - old = atomic_read(v); - new = old | i; - } while (atomic_cmpxchg(v, old, new) != old); +#ifndef atomic64_andnot +static inline void atomic64_andnot(long long i, atomic64_t *v) +{ + atomic64_and(~i, v); } -#endif /* #ifndef CONFIG_ARCH_HAS_ATOMIC_OR */ +#endif #include <asm-generic/atomic-long.h> -#ifdef CONFIG_GENERIC_ATOMIC64 -#include <asm-generic/atomic64.h> -#endif + #endif /* _LINUX_ATOMIC_H */ diff --git a/kernel/include/linux/audit.h b/kernel/include/linux/audit.h index c2e7e3a83..20eba1eb0 100644 --- a/kernel/include/linux/audit.h +++ b/kernel/include/linux/audit.h @@ -27,6 +27,9 @@ #include <linux/ptrace.h> #include <uapi/linux/audit.h> +#define AUDIT_INO_UNSET ((unsigned long)-1) +#define AUDIT_DEV_UNSET ((dev_t)-1) + struct audit_sig_info { uid_t uid; pid_t pid; @@ -59,6 +62,7 @@ struct audit_krule { struct audit_field *inode_f; /* quick access to an inode field */ struct audit_watch *watch; /* associated watch */ struct audit_tree *tree; /* associated watched tree */ + struct audit_fsnotify_mark *exe; struct list_head rlist; /* entry in audit_{watch,tree}.rules list */ struct list_head list; /* for AUDIT_LIST* purposes only */ u64 prio; @@ -139,7 +143,7 @@ extern void __audit_inode_child(const struct inode *parent, extern void __audit_seccomp(unsigned long syscall, long signr, int code); extern void __audit_ptrace(struct task_struct *t); -static inline int audit_dummy_context(void) +static inline bool audit_dummy_context(void) { void *p = current->audit_context; return !p || *(int *)p; @@ -341,9 +345,9 @@ static inline void audit_syscall_entry(int major, unsigned long a0, { } static inline void audit_syscall_exit(void *pt_regs) { } -static inline int audit_dummy_context(void) +static inline bool audit_dummy_context(void) { - return 1; + return true; } static inline struct filename *audit_reusename(const __user char *name) { @@ -453,7 +457,7 @@ extern struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp extern __printf(2, 3) void audit_log_format(struct audit_buffer *ab, const char *fmt, ...); extern void audit_log_end(struct audit_buffer *ab); -extern int audit_string_contains_control(const char *string, +extern bool audit_string_contains_control(const char *string, size_t len); extern void audit_log_n_hex(struct audit_buffer *ab, const unsigned char *buf, diff --git a/kernel/include/linux/average.h b/kernel/include/linux/average.h index c6028fd74..d04aa5828 100644 --- a/kernel/include/linux/average.h +++ b/kernel/include/linux/average.h @@ -3,28 +3,43 @@ /* Exponentially weighted moving average (EWMA) */ -/* For more documentation see lib/average.c */ - -struct ewma { - unsigned long internal; - unsigned long factor; - unsigned long weight; -}; - -extern void ewma_init(struct ewma *avg, unsigned long factor, - unsigned long weight); - -extern struct ewma *ewma_add(struct ewma *avg, unsigned long val); - -/** - * ewma_read() - Get average value - * @avg: Average structure - * - * Returns the average value held in @avg. - */ -static inline unsigned long ewma_read(const struct ewma *avg) -{ - return avg->internal >> avg->factor; -} +#define DECLARE_EWMA(name, _factor, _weight) \ + struct ewma_##name { \ + unsigned long internal; \ + }; \ + static inline void ewma_##name##_init(struct ewma_##name *e) \ + { \ + BUILD_BUG_ON(!__builtin_constant_p(_factor)); \ + BUILD_BUG_ON(!__builtin_constant_p(_weight)); \ + BUILD_BUG_ON_NOT_POWER_OF_2(_factor); \ + BUILD_BUG_ON_NOT_POWER_OF_2(_weight); \ + e->internal = 0; \ + } \ + static inline unsigned long \ + ewma_##name##_read(struct ewma_##name *e) \ + { \ + BUILD_BUG_ON(!__builtin_constant_p(_factor)); \ + BUILD_BUG_ON(!__builtin_constant_p(_weight)); \ + BUILD_BUG_ON_NOT_POWER_OF_2(_factor); \ + BUILD_BUG_ON_NOT_POWER_OF_2(_weight); \ + return e->internal >> ilog2(_factor); \ + } \ + static inline void ewma_##name##_add(struct ewma_##name *e, \ + unsigned long val) \ + { \ + unsigned long internal = ACCESS_ONCE(e->internal); \ + unsigned long weight = ilog2(_weight); \ + unsigned long factor = ilog2(_factor); \ + \ + BUILD_BUG_ON(!__builtin_constant_p(_factor)); \ + BUILD_BUG_ON(!__builtin_constant_p(_weight)); \ + BUILD_BUG_ON_NOT_POWER_OF_2(_factor); \ + BUILD_BUG_ON_NOT_POWER_OF_2(_weight); \ + \ + ACCESS_ONCE(e->internal) = internal ? \ + (((internal << weight) - internal) + \ + (val << factor)) >> weight : \ + (val << factor); \ + } #endif /* _LINUX_AVERAGE_H */ diff --git a/kernel/include/linux/backing-dev-defs.h b/kernel/include/linux/backing-dev-defs.h new file mode 100644 index 000000000..1b4d69f68 --- /dev/null +++ b/kernel/include/linux/backing-dev-defs.h @@ -0,0 +1,259 @@ +#ifndef __LINUX_BACKING_DEV_DEFS_H +#define __LINUX_BACKING_DEV_DEFS_H + +#include <linux/list.h> +#include <linux/radix-tree.h> +#include <linux/rbtree.h> +#include <linux/spinlock.h> +#include <linux/percpu_counter.h> +#include <linux/percpu-refcount.h> +#include <linux/flex_proportions.h> +#include <linux/timer.h> +#include <linux/workqueue.h> + +struct page; +struct device; +struct dentry; + +/* + * Bits in bdi_writeback.state + */ +enum wb_state { + WB_registered, /* bdi_register() was done */ + WB_writeback_running, /* Writeback is in progress */ + WB_has_dirty_io, /* Dirty inodes on ->b_{dirty|io|more_io} */ +}; + +enum wb_congested_state { + WB_async_congested, /* The async (write) queue is getting full */ + WB_sync_congested, /* The sync queue is getting full */ +}; + +typedef int (congested_fn)(void *, int); + +enum wb_stat_item { + WB_RECLAIMABLE, + WB_WRITEBACK, + WB_DIRTIED, + WB_WRITTEN, + NR_WB_STAT_ITEMS +}; + +#define WB_STAT_BATCH (8*(1+ilog2(nr_cpu_ids))) + +/* + * For cgroup writeback, multiple wb's may map to the same blkcg. Those + * wb's can operate mostly independently but should share the congested + * state. To facilitate such sharing, the congested state is tracked using + * the following struct which is created on demand, indexed by blkcg ID on + * its bdi, and refcounted. + */ +struct bdi_writeback_congested { + unsigned long state; /* WB_[a]sync_congested flags */ + atomic_t refcnt; /* nr of attached wb's and blkg */ + +#ifdef CONFIG_CGROUP_WRITEBACK + struct backing_dev_info *bdi; /* the associated bdi */ + int blkcg_id; /* ID of the associated blkcg */ + struct rb_node rb_node; /* on bdi->cgwb_congestion_tree */ +#endif +}; + +/* + * Each wb (bdi_writeback) can perform writeback operations, is measured + * and throttled, independently. Without cgroup writeback, each bdi + * (bdi_writeback) is served by its embedded bdi->wb. + * + * On the default hierarchy, blkcg implicitly enables memcg. This allows + * using memcg's page ownership for attributing writeback IOs, and every + * memcg - blkcg combination can be served by its own wb by assigning a + * dedicated wb to each memcg, which enables isolation across different + * cgroups and propagation of IO back pressure down from the IO layer upto + * the tasks which are generating the dirty pages to be written back. + * + * A cgroup wb is indexed on its bdi by the ID of the associated memcg, + * refcounted with the number of inodes attached to it, and pins the memcg + * and the corresponding blkcg. As the corresponding blkcg for a memcg may + * change as blkcg is disabled and enabled higher up in the hierarchy, a wb + * is tested for blkcg after lookup and removed from index on mismatch so + * that a new wb for the combination can be created. + */ +struct bdi_writeback { + struct backing_dev_info *bdi; /* our parent bdi */ + + unsigned long state; /* Always use atomic bitops on this */ + unsigned long last_old_flush; /* last old data flush */ + + struct list_head b_dirty; /* dirty inodes */ + struct list_head b_io; /* parked for writeback */ + struct list_head b_more_io; /* parked for more writeback */ + struct list_head b_dirty_time; /* time stamps are dirty */ + spinlock_t list_lock; /* protects the b_* lists */ + + struct percpu_counter stat[NR_WB_STAT_ITEMS]; + + struct bdi_writeback_congested *congested; + + unsigned long bw_time_stamp; /* last time write bw is updated */ + unsigned long dirtied_stamp; + unsigned long written_stamp; /* pages written at bw_time_stamp */ + unsigned long write_bandwidth; /* the estimated write bandwidth */ + unsigned long avg_write_bandwidth; /* further smoothed write bw, > 0 */ + + /* + * The base dirty throttle rate, re-calculated on every 200ms. + * All the bdi tasks' dirty rate will be curbed under it. + * @dirty_ratelimit tracks the estimated @balanced_dirty_ratelimit + * in small steps and is much more smooth/stable than the latter. + */ + unsigned long dirty_ratelimit; + unsigned long balanced_dirty_ratelimit; + + struct fprop_local_percpu completions; + int dirty_exceeded; + + spinlock_t work_lock; /* protects work_list & dwork scheduling */ + struct list_head work_list; + struct delayed_work dwork; /* work item used for writeback */ + + struct list_head bdi_node; /* anchored at bdi->wb_list */ + +#ifdef CONFIG_CGROUP_WRITEBACK + struct percpu_ref refcnt; /* used only for !root wb's */ + struct fprop_local_percpu memcg_completions; + struct cgroup_subsys_state *memcg_css; /* the associated memcg */ + struct cgroup_subsys_state *blkcg_css; /* and blkcg */ + struct list_head memcg_node; /* anchored at memcg->cgwb_list */ + struct list_head blkcg_node; /* anchored at blkcg->cgwb_list */ + + union { + struct work_struct release_work; + struct rcu_head rcu; + }; +#endif +}; + +struct backing_dev_info { + struct list_head bdi_list; + unsigned long ra_pages; /* max readahead in PAGE_CACHE_SIZE units */ + unsigned int capabilities; /* Device capabilities */ + congested_fn *congested_fn; /* Function pointer if device is md/dm */ + void *congested_data; /* Pointer to aux data for congested func */ + + char *name; + + unsigned int min_ratio; + unsigned int max_ratio, max_prop_frac; + + /* + * Sum of avg_write_bw of wbs with dirty inodes. > 0 if there are + * any dirty wbs, which is depended upon by bdi_has_dirty(). + */ + atomic_long_t tot_write_bandwidth; + + struct bdi_writeback wb; /* the root writeback info for this bdi */ + struct list_head wb_list; /* list of all wbs */ +#ifdef CONFIG_CGROUP_WRITEBACK + struct radix_tree_root cgwb_tree; /* radix tree of active cgroup wbs */ + struct rb_root cgwb_congested_tree; /* their congested states */ + atomic_t usage_cnt; /* counts both cgwbs and cgwb_contested's */ +#else + struct bdi_writeback_congested *wb_congested; +#endif + wait_queue_head_t wb_waitq; + + struct device *dev; + + struct timer_list laptop_mode_wb_timer; + +#ifdef CONFIG_DEBUG_FS + struct dentry *debug_dir; + struct dentry *debug_stats; +#endif +}; + +enum { + BLK_RW_ASYNC = 0, + BLK_RW_SYNC = 1, +}; + +void clear_wb_congested(struct bdi_writeback_congested *congested, int sync); +void set_wb_congested(struct bdi_writeback_congested *congested, int sync); + +static inline void clear_bdi_congested(struct backing_dev_info *bdi, int sync) +{ + clear_wb_congested(bdi->wb.congested, sync); +} + +static inline void set_bdi_congested(struct backing_dev_info *bdi, int sync) +{ + set_wb_congested(bdi->wb.congested, sync); +} + +#ifdef CONFIG_CGROUP_WRITEBACK + +/** + * wb_tryget - try to increment a wb's refcount + * @wb: bdi_writeback to get + */ +static inline bool wb_tryget(struct bdi_writeback *wb) +{ + if (wb != &wb->bdi->wb) + return percpu_ref_tryget(&wb->refcnt); + return true; +} + +/** + * wb_get - increment a wb's refcount + * @wb: bdi_writeback to get + */ +static inline void wb_get(struct bdi_writeback *wb) +{ + if (wb != &wb->bdi->wb) + percpu_ref_get(&wb->refcnt); +} + +/** + * wb_put - decrement a wb's refcount + * @wb: bdi_writeback to put + */ +static inline void wb_put(struct bdi_writeback *wb) +{ + if (wb != &wb->bdi->wb) + percpu_ref_put(&wb->refcnt); +} + +/** + * wb_dying - is a wb dying? + * @wb: bdi_writeback of interest + * + * Returns whether @wb is unlinked and being drained. + */ +static inline bool wb_dying(struct bdi_writeback *wb) +{ + return percpu_ref_is_dying(&wb->refcnt); +} + +#else /* CONFIG_CGROUP_WRITEBACK */ + +static inline bool wb_tryget(struct bdi_writeback *wb) +{ + return true; +} + +static inline void wb_get(struct bdi_writeback *wb) +{ +} + +static inline void wb_put(struct bdi_writeback *wb) +{ +} + +static inline bool wb_dying(struct bdi_writeback *wb) +{ + return false; +} + +#endif /* CONFIG_CGROUP_WRITEBACK */ + +#endif /* __LINUX_BACKING_DEV_DEFS_H */ diff --git a/kernel/include/linux/backing-dev.h b/kernel/include/linux/backing-dev.h index d87d8eced..c82794f20 100644 --- a/kernel/include/linux/backing-dev.h +++ b/kernel/include/linux/backing-dev.h @@ -8,206 +8,120 @@ #ifndef _LINUX_BACKING_DEV_H #define _LINUX_BACKING_DEV_H -#include <linux/percpu_counter.h> -#include <linux/log2.h> -#include <linux/flex_proportions.h> #include <linux/kernel.h> #include <linux/fs.h> #include <linux/sched.h> -#include <linux/timer.h> +#include <linux/blkdev.h> #include <linux/writeback.h> -#include <linux/atomic.h> -#include <linux/sysctl.h> -#include <linux/workqueue.h> - -struct page; -struct device; -struct dentry; - -/* - * Bits in backing_dev_info.state - */ -enum bdi_state { - BDI_async_congested, /* The async (write) queue is getting full */ - BDI_sync_congested, /* The sync queue is getting full */ - BDI_registered, /* bdi_register() was done */ - BDI_writeback_running, /* Writeback is in progress */ -}; - -typedef int (congested_fn)(void *, int); - -enum bdi_stat_item { - BDI_RECLAIMABLE, - BDI_WRITEBACK, - BDI_DIRTIED, - BDI_WRITTEN, - NR_BDI_STAT_ITEMS -}; - -#define BDI_STAT_BATCH (8*(1+ilog2(nr_cpu_ids))) - -struct bdi_writeback { - struct backing_dev_info *bdi; /* our parent bdi */ - - unsigned long last_old_flush; /* last old data flush */ - - struct delayed_work dwork; /* work item used for writeback */ - struct list_head b_dirty; /* dirty inodes */ - struct list_head b_io; /* parked for writeback */ - struct list_head b_more_io; /* parked for more writeback */ - struct list_head b_dirty_time; /* time stamps are dirty */ - spinlock_t list_lock; /* protects the b_* lists */ -}; - -struct backing_dev_info { - struct list_head bdi_list; - unsigned long ra_pages; /* max readahead in PAGE_CACHE_SIZE units */ - unsigned long state; /* Always use atomic bitops on this */ - unsigned int capabilities; /* Device capabilities */ - congested_fn *congested_fn; /* Function pointer if device is md/dm */ - void *congested_data; /* Pointer to aux data for congested func */ - - char *name; - - struct percpu_counter bdi_stat[NR_BDI_STAT_ITEMS]; - - unsigned long bw_time_stamp; /* last time write bw is updated */ - unsigned long dirtied_stamp; - unsigned long written_stamp; /* pages written at bw_time_stamp */ - unsigned long write_bandwidth; /* the estimated write bandwidth */ - unsigned long avg_write_bandwidth; /* further smoothed write bw */ - - /* - * The base dirty throttle rate, re-calculated on every 200ms. - * All the bdi tasks' dirty rate will be curbed under it. - * @dirty_ratelimit tracks the estimated @balanced_dirty_ratelimit - * in small steps and is much more smooth/stable than the latter. - */ - unsigned long dirty_ratelimit; - unsigned long balanced_dirty_ratelimit; - - struct fprop_local_percpu completions; - int dirty_exceeded; - - unsigned int min_ratio; - unsigned int max_ratio, max_prop_frac; - - struct bdi_writeback wb; /* default writeback info for this bdi */ - spinlock_t wb_lock; /* protects work_list & wb.dwork scheduling */ - - struct list_head work_list; - - struct device *dev; - - struct timer_list laptop_mode_wb_timer; - -#ifdef CONFIG_DEBUG_FS - struct dentry *debug_dir; - struct dentry *debug_stats; -#endif -}; - -struct backing_dev_info *inode_to_bdi(struct inode *inode); +#include <linux/blk-cgroup.h> +#include <linux/backing-dev-defs.h> +#include <linux/slab.h> int __must_check bdi_init(struct backing_dev_info *bdi); -void bdi_destroy(struct backing_dev_info *bdi); +void bdi_exit(struct backing_dev_info *bdi); __printf(3, 4) int bdi_register(struct backing_dev_info *bdi, struct device *parent, const char *fmt, ...); int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev); +void bdi_unregister(struct backing_dev_info *bdi); + int __must_check bdi_setup_and_register(struct backing_dev_info *, char *); -void bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages, - enum wb_reason reason); -void bdi_start_background_writeback(struct backing_dev_info *bdi); -void bdi_writeback_workfn(struct work_struct *work); -int bdi_has_dirty_io(struct backing_dev_info *bdi); -void bdi_wakeup_thread_delayed(struct backing_dev_info *bdi); +void bdi_destroy(struct backing_dev_info *bdi); + +void wb_start_writeback(struct bdi_writeback *wb, long nr_pages, + bool range_cyclic, enum wb_reason reason); +void wb_start_background_writeback(struct bdi_writeback *wb); +void wb_workfn(struct work_struct *work); +void wb_wakeup_delayed(struct bdi_writeback *wb); extern spinlock_t bdi_lock; extern struct list_head bdi_list; extern struct workqueue_struct *bdi_wq; -static inline int wb_has_dirty_io(struct bdi_writeback *wb) +static inline bool wb_has_dirty_io(struct bdi_writeback *wb) { - return !list_empty(&wb->b_dirty) || - !list_empty(&wb->b_io) || - !list_empty(&wb->b_more_io); + return test_bit(WB_has_dirty_io, &wb->state); } -static inline void __add_bdi_stat(struct backing_dev_info *bdi, - enum bdi_stat_item item, s64 amount) +static inline bool bdi_has_dirty_io(struct backing_dev_info *bdi) { - __percpu_counter_add(&bdi->bdi_stat[item], amount, BDI_STAT_BATCH); + /* + * @bdi->tot_write_bandwidth is guaranteed to be > 0 if there are + * any dirty wbs. See wb_update_write_bandwidth(). + */ + return atomic_long_read(&bdi->tot_write_bandwidth); +} + +static inline void __add_wb_stat(struct bdi_writeback *wb, + enum wb_stat_item item, s64 amount) +{ + __percpu_counter_add(&wb->stat[item], amount, WB_STAT_BATCH); } -static inline void __inc_bdi_stat(struct backing_dev_info *bdi, - enum bdi_stat_item item) +static inline void __inc_wb_stat(struct bdi_writeback *wb, + enum wb_stat_item item) { - __add_bdi_stat(bdi, item, 1); + __add_wb_stat(wb, item, 1); } -static inline void inc_bdi_stat(struct backing_dev_info *bdi, - enum bdi_stat_item item) +static inline void inc_wb_stat(struct bdi_writeback *wb, enum wb_stat_item item) { unsigned long flags; local_irq_save(flags); - __inc_bdi_stat(bdi, item); + __inc_wb_stat(wb, item); local_irq_restore(flags); } -static inline void __dec_bdi_stat(struct backing_dev_info *bdi, - enum bdi_stat_item item) +static inline void __dec_wb_stat(struct bdi_writeback *wb, + enum wb_stat_item item) { - __add_bdi_stat(bdi, item, -1); + __add_wb_stat(wb, item, -1); } -static inline void dec_bdi_stat(struct backing_dev_info *bdi, - enum bdi_stat_item item) +static inline void dec_wb_stat(struct bdi_writeback *wb, enum wb_stat_item item) { unsigned long flags; local_irq_save(flags); - __dec_bdi_stat(bdi, item); + __dec_wb_stat(wb, item); local_irq_restore(flags); } -static inline s64 bdi_stat(struct backing_dev_info *bdi, - enum bdi_stat_item item) +static inline s64 wb_stat(struct bdi_writeback *wb, enum wb_stat_item item) { - return percpu_counter_read_positive(&bdi->bdi_stat[item]); + return percpu_counter_read_positive(&wb->stat[item]); } -static inline s64 __bdi_stat_sum(struct backing_dev_info *bdi, - enum bdi_stat_item item) +static inline s64 __wb_stat_sum(struct bdi_writeback *wb, + enum wb_stat_item item) { - return percpu_counter_sum_positive(&bdi->bdi_stat[item]); + return percpu_counter_sum_positive(&wb->stat[item]); } -static inline s64 bdi_stat_sum(struct backing_dev_info *bdi, - enum bdi_stat_item item) +static inline s64 wb_stat_sum(struct bdi_writeback *wb, enum wb_stat_item item) { s64 sum; unsigned long flags; local_irq_save(flags); - sum = __bdi_stat_sum(bdi, item); + sum = __wb_stat_sum(wb, item); local_irq_restore(flags); return sum; } -extern void bdi_writeout_inc(struct backing_dev_info *bdi); +extern void wb_writeout_inc(struct bdi_writeback *wb); /* * maximal error of a stat counter. */ -static inline unsigned long bdi_stat_error(struct backing_dev_info *bdi) +static inline unsigned long wb_stat_error(struct bdi_writeback *wb) { #ifdef CONFIG_SMP - return nr_cpu_ids * BDI_STAT_BATCH; + return nr_cpu_ids * WB_STAT_BATCH; #else return 1; #endif @@ -231,50 +145,57 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio); * BDI_CAP_NO_WRITEBACK: Don't write pages back * BDI_CAP_NO_ACCT_WB: Don't automatically account writeback pages * BDI_CAP_STRICTLIMIT: Keep number of dirty pages below bdi threshold. + * + * BDI_CAP_CGROUP_WRITEBACK: Supports cgroup-aware writeback. */ #define BDI_CAP_NO_ACCT_DIRTY 0x00000001 #define BDI_CAP_NO_WRITEBACK 0x00000002 #define BDI_CAP_NO_ACCT_WB 0x00000004 #define BDI_CAP_STABLE_WRITES 0x00000008 #define BDI_CAP_STRICTLIMIT 0x00000010 +#define BDI_CAP_CGROUP_WRITEBACK 0x00000020 #define BDI_CAP_NO_ACCT_AND_WRITEBACK \ (BDI_CAP_NO_WRITEBACK | BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_ACCT_WB) extern struct backing_dev_info noop_backing_dev_info; -int writeback_in_progress(struct backing_dev_info *bdi); - -static inline int bdi_congested(struct backing_dev_info *bdi, int bdi_bits) +/** + * writeback_in_progress - determine whether there is writeback in progress + * @wb: bdi_writeback of interest + * + * Determine whether there is writeback waiting to be handled against a + * bdi_writeback. + */ +static inline bool writeback_in_progress(struct bdi_writeback *wb) { - if (bdi->congested_fn) - return bdi->congested_fn(bdi->congested_data, bdi_bits); - return (bdi->state & bdi_bits); + return test_bit(WB_writeback_running, &wb->state); } -static inline int bdi_read_congested(struct backing_dev_info *bdi) +static inline struct backing_dev_info *inode_to_bdi(struct inode *inode) { - return bdi_congested(bdi, 1 << BDI_sync_congested); -} + struct super_block *sb; -static inline int bdi_write_congested(struct backing_dev_info *bdi) -{ - return bdi_congested(bdi, 1 << BDI_async_congested); + if (!inode) + return &noop_backing_dev_info; + + sb = inode->i_sb; +#ifdef CONFIG_BLOCK + if (sb_is_blkdev_sb(sb)) + return blk_get_backing_dev_info(I_BDEV(inode)); +#endif + return sb->s_bdi; } -static inline int bdi_rw_congested(struct backing_dev_info *bdi) +static inline int wb_congested(struct bdi_writeback *wb, int cong_bits) { - return bdi_congested(bdi, (1 << BDI_sync_congested) | - (1 << BDI_async_congested)); -} + struct backing_dev_info *bdi = wb->bdi; -enum { - BLK_RW_ASYNC = 0, - BLK_RW_SYNC = 1, -}; + if (bdi->congested_fn) + return bdi->congested_fn(bdi->congested_data, cong_bits); + return wb->congested->state & cong_bits; +} -void clear_bdi_congested(struct backing_dev_info *bdi, int sync); -void set_bdi_congested(struct backing_dev_info *bdi, int sync); long congestion_wait(int sync, long timeout); long wait_iff_congested(struct zone *zone, int sync, long timeout); int pdflush_proc_obsolete(struct ctl_table *table, int write, @@ -318,4 +239,279 @@ static inline int bdi_sched_wait(void *word) return 0; } -#endif /* _LINUX_BACKING_DEV_H */ +#ifdef CONFIG_CGROUP_WRITEBACK + +struct bdi_writeback_congested * +wb_congested_get_create(struct backing_dev_info *bdi, int blkcg_id, gfp_t gfp); +void wb_congested_put(struct bdi_writeback_congested *congested); +struct bdi_writeback *wb_get_create(struct backing_dev_info *bdi, + struct cgroup_subsys_state *memcg_css, + gfp_t gfp); +void wb_memcg_offline(struct mem_cgroup *memcg); +void wb_blkcg_offline(struct blkcg *blkcg); +int inode_congested(struct inode *inode, int cong_bits); + +/** + * inode_cgwb_enabled - test whether cgroup writeback is enabled on an inode + * @inode: inode of interest + * + * cgroup writeback requires support from both the bdi and filesystem. + * Also, both memcg and iocg have to be on the default hierarchy. Test + * whether all conditions are met. + * + * Note that the test result may change dynamically on the same inode + * depending on how memcg and iocg are configured. + */ +static inline bool inode_cgwb_enabled(struct inode *inode) +{ + struct backing_dev_info *bdi = inode_to_bdi(inode); + + return cgroup_subsys_on_dfl(memory_cgrp_subsys) && + cgroup_subsys_on_dfl(io_cgrp_subsys) && + bdi_cap_account_dirty(bdi) && + (bdi->capabilities & BDI_CAP_CGROUP_WRITEBACK) && + (inode->i_sb->s_iflags & SB_I_CGROUPWB); +} + +/** + * wb_find_current - find wb for %current on a bdi + * @bdi: bdi of interest + * + * Find the wb of @bdi which matches both the memcg and blkcg of %current. + * Must be called under rcu_read_lock() which protects the returend wb. + * NULL if not found. + */ +static inline struct bdi_writeback *wb_find_current(struct backing_dev_info *bdi) +{ + struct cgroup_subsys_state *memcg_css; + struct bdi_writeback *wb; + + memcg_css = task_css(current, memory_cgrp_id); + if (!memcg_css->parent) + return &bdi->wb; + + wb = radix_tree_lookup(&bdi->cgwb_tree, memcg_css->id); + + /* + * %current's blkcg equals the effective blkcg of its memcg. No + * need to use the relatively expensive cgroup_get_e_css(). + */ + if (likely(wb && wb->blkcg_css == task_css(current, io_cgrp_id))) + return wb; + return NULL; +} + +/** + * wb_get_create_current - get or create wb for %current on a bdi + * @bdi: bdi of interest + * @gfp: allocation mask + * + * Equivalent to wb_get_create() on %current's memcg. This function is + * called from a relatively hot path and optimizes the common cases using + * wb_find_current(). + */ +static inline struct bdi_writeback * +wb_get_create_current(struct backing_dev_info *bdi, gfp_t gfp) +{ + struct bdi_writeback *wb; + + rcu_read_lock(); + wb = wb_find_current(bdi); + if (wb && unlikely(!wb_tryget(wb))) + wb = NULL; + rcu_read_unlock(); + + if (unlikely(!wb)) { + struct cgroup_subsys_state *memcg_css; + + memcg_css = task_get_css(current, memory_cgrp_id); + wb = wb_get_create(bdi, memcg_css, gfp); + css_put(memcg_css); + } + return wb; +} + +/** + * inode_to_wb_is_valid - test whether an inode has a wb associated + * @inode: inode of interest + * + * Returns %true if @inode has a wb associated. May be called without any + * locking. + */ +static inline bool inode_to_wb_is_valid(struct inode *inode) +{ + return inode->i_wb; +} + +/** + * inode_to_wb - determine the wb of an inode + * @inode: inode of interest + * + * Returns the wb @inode is currently associated with. The caller must be + * holding either @inode->i_lock, @inode->i_mapping->tree_lock, or the + * associated wb's list_lock. + */ +static inline struct bdi_writeback *inode_to_wb(struct inode *inode) +{ +#ifdef CONFIG_LOCKDEP + WARN_ON_ONCE(debug_locks && + (!lockdep_is_held(&inode->i_lock) && + !lockdep_is_held(&inode->i_mapping->tree_lock) && + !lockdep_is_held(&inode->i_wb->list_lock))); +#endif + return inode->i_wb; +} + +/** + * unlocked_inode_to_wb_begin - begin unlocked inode wb access transaction + * @inode: target inode + * @lockedp: temp bool output param, to be passed to the end function + * + * The caller wants to access the wb associated with @inode but isn't + * holding inode->i_lock, mapping->tree_lock or wb->list_lock. This + * function determines the wb associated with @inode and ensures that the + * association doesn't change until the transaction is finished with + * unlocked_inode_to_wb_end(). + * + * The caller must call unlocked_inode_to_wb_end() with *@lockdep + * afterwards and can't sleep during transaction. IRQ may or may not be + * disabled on return. + */ +static inline struct bdi_writeback * +unlocked_inode_to_wb_begin(struct inode *inode, bool *lockedp) +{ + rcu_read_lock(); + + /* + * Paired with store_release in inode_switch_wb_work_fn() and + * ensures that we see the new wb if we see cleared I_WB_SWITCH. + */ + *lockedp = smp_load_acquire(&inode->i_state) & I_WB_SWITCH; + + if (unlikely(*lockedp)) + spin_lock_irq(&inode->i_mapping->tree_lock); + + /* + * Protected by either !I_WB_SWITCH + rcu_read_lock() or tree_lock. + * inode_to_wb() will bark. Deref directly. + */ + return inode->i_wb; +} + +/** + * unlocked_inode_to_wb_end - end inode wb access transaction + * @inode: target inode + * @locked: *@lockedp from unlocked_inode_to_wb_begin() + */ +static inline void unlocked_inode_to_wb_end(struct inode *inode, bool locked) +{ + if (unlikely(locked)) + spin_unlock_irq(&inode->i_mapping->tree_lock); + + rcu_read_unlock(); +} + +#else /* CONFIG_CGROUP_WRITEBACK */ + +static inline bool inode_cgwb_enabled(struct inode *inode) +{ + return false; +} + +static inline struct bdi_writeback_congested * +wb_congested_get_create(struct backing_dev_info *bdi, int blkcg_id, gfp_t gfp) +{ + atomic_inc(&bdi->wb_congested->refcnt); + return bdi->wb_congested; +} + +static inline void wb_congested_put(struct bdi_writeback_congested *congested) +{ + if (atomic_dec_and_test(&congested->refcnt)) + kfree(congested); +} + +static inline struct bdi_writeback *wb_find_current(struct backing_dev_info *bdi) +{ + return &bdi->wb; +} + +static inline struct bdi_writeback * +wb_get_create_current(struct backing_dev_info *bdi, gfp_t gfp) +{ + return &bdi->wb; +} + +static inline bool inode_to_wb_is_valid(struct inode *inode) +{ + return true; +} + +static inline struct bdi_writeback *inode_to_wb(struct inode *inode) +{ + return &inode_to_bdi(inode)->wb; +} + +static inline struct bdi_writeback * +unlocked_inode_to_wb_begin(struct inode *inode, bool *lockedp) +{ + return inode_to_wb(inode); +} + +static inline void unlocked_inode_to_wb_end(struct inode *inode, bool locked) +{ +} + +static inline void wb_memcg_offline(struct mem_cgroup *memcg) +{ +} + +static inline void wb_blkcg_offline(struct blkcg *blkcg) +{ +} + +static inline int inode_congested(struct inode *inode, int cong_bits) +{ + return wb_congested(&inode_to_bdi(inode)->wb, cong_bits); +} + +#endif /* CONFIG_CGROUP_WRITEBACK */ + +static inline int inode_read_congested(struct inode *inode) +{ + return inode_congested(inode, 1 << WB_sync_congested); +} + +static inline int inode_write_congested(struct inode *inode) +{ + return inode_congested(inode, 1 << WB_async_congested); +} + +static inline int inode_rw_congested(struct inode *inode) +{ + return inode_congested(inode, (1 << WB_sync_congested) | + (1 << WB_async_congested)); +} + +static inline int bdi_congested(struct backing_dev_info *bdi, int cong_bits) +{ + return wb_congested(&bdi->wb, cong_bits); +} + +static inline int bdi_read_congested(struct backing_dev_info *bdi) +{ + return bdi_congested(bdi, 1 << WB_sync_congested); +} + +static inline int bdi_write_congested(struct backing_dev_info *bdi) +{ + return bdi_congested(bdi, 1 << WB_async_congested); +} + +static inline int bdi_rw_congested(struct backing_dev_info *bdi) +{ + return bdi_congested(bdi, (1 << WB_sync_congested) | + (1 << WB_async_congested)); +} + +#endif /* _LINUX_BACKING_DEV_H */ diff --git a/kernel/include/linux/backlight.h b/kernel/include/linux/backlight.h index adb14a861..1e7a69adb 100644 --- a/kernel/include/linux/backlight.h +++ b/kernel/include/linux/backlight.h @@ -117,12 +117,16 @@ struct backlight_device { int use_count; }; -static inline void backlight_update_status(struct backlight_device *bd) +static inline int backlight_update_status(struct backlight_device *bd) { + int ret = -ENOENT; + mutex_lock(&bd->update_lock); if (bd->ops && bd->ops->update_status) - bd->ops->update_status(bd); + ret = bd->ops->update_status(bd); mutex_unlock(&bd->update_lock); + + return ret; } extern struct backlight_device *backlight_device_register(const char *name, diff --git a/kernel/include/linux/basic_mmio_gpio.h b/kernel/include/linux/basic_mmio_gpio.h index 0e97856b2..ed3768f4e 100644 --- a/kernel/include/linux/basic_mmio_gpio.h +++ b/kernel/include/linux/basic_mmio_gpio.h @@ -74,5 +74,7 @@ int bgpio_init(struct bgpio_chip *bgc, struct device *dev, #define BGPIOF_UNREADABLE_REG_SET BIT(1) /* reg_set is unreadable */ #define BGPIOF_UNREADABLE_REG_DIR BIT(2) /* reg_dir is unreadable */ #define BGPIOF_BIG_ENDIAN_BYTE_ORDER BIT(3) +#define BGPIOF_READ_OUTPUT_REG_SET BIT(4) /* reg_set stores output value */ +#define BGPIOF_NO_OUTPUT BIT(5) /* only input */ #endif /* __BASIC_MMIO_GPIO_H */ diff --git a/kernel/include/linux/bcm47xx_nvram.h b/kernel/include/linux/bcm47xx_nvram.h index b12b07e75..2793652fb 100644 --- a/kernel/include/linux/bcm47xx_nvram.h +++ b/kernel/include/linux/bcm47xx_nvram.h @@ -10,11 +10,17 @@ #include <linux/types.h> #include <linux/kernel.h> +#include <linux/vmalloc.h> -#ifdef CONFIG_BCM47XX +#ifdef CONFIG_BCM47XX_NVRAM int bcm47xx_nvram_init_from_mem(u32 base, u32 lim); int bcm47xx_nvram_getenv(const char *name, char *val, size_t val_len); int bcm47xx_nvram_gpio_pin(const char *name); +char *bcm47xx_nvram_get_contents(size_t *val_len); +static inline void bcm47xx_nvram_release_contents(char *nvram) +{ + vfree(nvram); +}; #else static inline int bcm47xx_nvram_init_from_mem(u32 base, u32 lim) { @@ -29,6 +35,15 @@ static inline int bcm47xx_nvram_gpio_pin(const char *name) { return -ENOTSUPP; }; + +static inline char *bcm47xx_nvram_get_contents(size_t *val_len) +{ + return NULL; +}; + +static inline void bcm47xx_nvram_release_contents(char *nvram) +{ +}; #endif #endif /* __BCM47XX_NVRAM_H */ diff --git a/kernel/include/linux/bcma/bcma.h b/kernel/include/linux/bcma/bcma.h index e34f90664..3feb1b2d7 100644 --- a/kernel/include/linux/bcma/bcma.h +++ b/kernel/include/linux/bcma/bcma.h @@ -151,6 +151,8 @@ struct bcma_host_ops { #define BCMA_CORE_PCIE2 0x83C /* PCI Express Gen2 */ #define BCMA_CORE_USB30_DEV 0x83D #define BCMA_CORE_ARM_CR4 0x83E +#define BCMA_CORE_ARM_CA7 0x847 +#define BCMA_CORE_SYS_MEM 0x849 #define BCMA_CORE_DEFAULT 0xFFF #define BCMA_MAX_NR_CORES 16 @@ -305,6 +307,15 @@ int __bcma_driver_register(struct bcma_driver *drv, struct module *owner); extern void bcma_driver_unregister(struct bcma_driver *drv); +/* module_bcma_driver() - Helper macro for drivers that don't do + * anything special in module init/exit. This eliminates a lot of + * boilerplate. Each module may only use this macro once, and + * calling it replaces module_init() and module_exit() + */ +#define module_bcma_driver(__bcma_driver) \ + module_driver(__bcma_driver, bcma_driver_register, \ + bcma_driver_unregister) + /* Set a fallback SPROM. * See kdoc at the function definition for complete documentation. */ extern int bcma_arch_register_fallback_sprom( diff --git a/kernel/include/linux/bcma/bcma_driver_chipcommon.h b/kernel/include/linux/bcma/bcma_driver_chipcommon.h index 6cceedf65..cf038431a 100644 --- a/kernel/include/linux/bcma/bcma_driver_chipcommon.h +++ b/kernel/include/linux/bcma/bcma_driver_chipcommon.h @@ -640,7 +640,6 @@ struct bcma_drv_cc { spinlock_t gpio_lock; #ifdef CONFIG_BCMA_DRIVER_GPIO struct gpio_chip gpio; - struct irq_domain *irq_domain; #endif }; diff --git a/kernel/include/linux/bcma/bcma_driver_pci.h b/kernel/include/linux/bcma/bcma_driver_pci.h index 5ba6918ca..9657f11d4 100644 --- a/kernel/include/linux/bcma/bcma_driver_pci.h +++ b/kernel/include/linux/bcma/bcma_driver_pci.h @@ -246,7 +246,18 @@ static inline void bcma_core_pci_power_save(struct bcma_bus *bus, bool up) } #endif +#ifdef CONFIG_BCMA_DRIVER_PCI_HOSTMODE extern int bcma_core_pci_pcibios_map_irq(const struct pci_dev *dev); extern int bcma_core_pci_plat_dev_init(struct pci_dev *dev); +#else +static inline int bcma_core_pci_pcibios_map_irq(const struct pci_dev *dev) +{ + return -ENOTSUPP; +} +static inline int bcma_core_pci_plat_dev_init(struct pci_dev *dev) +{ + return -ENOTSUPP; +} +#endif #endif /* LINUX_BCMA_DRIVER_PCI_H_ */ diff --git a/kernel/include/linux/bio.h b/kernel/include/linux/bio.h index da3a127c9..fbe47bc70 100644 --- a/kernel/include/linux/bio.h +++ b/kernel/include/linux/bio.h @@ -187,17 +187,6 @@ static inline void *bio_data(struct bio *bio) __BIO_SEG_BOUNDARY(bvec_to_phys((b1)), bvec_to_phys((b2)) + (b2)->bv_len, queue_segment_boundary((q))) /* - * Check if adding a bio_vec after bprv with offset would create a gap in - * the SG list. Most drivers don't care about this, but some do. - */ -static inline bool bvec_gap_to_prev(struct bio_vec *bprv, unsigned int offset) -{ - return offset || ((bprv->bv_offset + bprv->bv_len) & (PAGE_SIZE - 1)); -} - -#define bio_io_error(bio) bio_endio((bio), -EIO) - -/* * drivers should _never_ use the all version - the bio may have been split * before it got to the driver and the driver won't own all of it */ @@ -290,7 +279,68 @@ static inline unsigned bio_segments(struct bio *bio) * returns. and then bio would be freed memory when if (bio->bi_flags ...) * runs */ -#define bio_get(bio) atomic_inc(&(bio)->bi_cnt) +static inline void bio_get(struct bio *bio) +{ + bio->bi_flags |= (1 << BIO_REFFED); + smp_mb__before_atomic(); + atomic_inc(&bio->__bi_cnt); +} + +static inline void bio_cnt_set(struct bio *bio, unsigned int count) +{ + if (count != 1) { + bio->bi_flags |= (1 << BIO_REFFED); + smp_mb__before_atomic(); + } + atomic_set(&bio->__bi_cnt, count); +} + +static inline bool bio_flagged(struct bio *bio, unsigned int bit) +{ + return (bio->bi_flags & (1U << bit)) != 0; +} + +static inline void bio_set_flag(struct bio *bio, unsigned int bit) +{ + bio->bi_flags |= (1U << bit); +} + +static inline void bio_clear_flag(struct bio *bio, unsigned int bit) +{ + bio->bi_flags &= ~(1U << bit); +} + +static inline void bio_get_first_bvec(struct bio *bio, struct bio_vec *bv) +{ + *bv = bio_iovec(bio); +} + +static inline void bio_get_last_bvec(struct bio *bio, struct bio_vec *bv) +{ + struct bvec_iter iter = bio->bi_iter; + int idx; + + if (unlikely(!bio_multiple_segments(bio))) { + *bv = bio_iovec(bio); + return; + } + + bio_advance_iter(bio, &iter, iter.bi_size); + + if (!iter.bi_bvec_done) + idx = iter.bi_idx - 1; + else /* in the middle of bvec */ + idx = iter.bi_idx; + + *bv = bio->bi_io_vec[idx]; + + /* + * iter.bi_bvec_done records actual length of the last bvec + * if this bio ends in the middle of one io vector + */ + if (iter.bi_bvec_done) + bv->bv_len = iter.bi_bvec_done; +} enum bip_flags { BIP_BLOCK_INTEGRITY = 1 << 0, /* block layer owns integrity data */ @@ -412,8 +462,14 @@ static inline struct bio *bio_clone_kmalloc(struct bio *bio, gfp_t gfp_mask) } -extern void bio_endio(struct bio *, int); -extern void bio_endio_nodec(struct bio *, int); +extern void bio_endio(struct bio *); + +static inline void bio_io_error(struct bio *bio) +{ + bio->bi_error = -EIO; + bio_endio(bio); +} + struct request_queue; extern int bio_phys_segments(struct request_queue *, struct bio *); @@ -427,7 +483,6 @@ void bio_chain(struct bio *, struct bio *); extern int bio_add_page(struct bio *, struct page *, unsigned int,unsigned int); extern int bio_add_pc_page(struct request_queue *, struct bio *, struct page *, unsigned int, unsigned int); -extern int bio_get_nr_vecs(struct block_device *); struct rq_map_data; extern struct bio *bio_map_user_iov(struct request_queue *, const struct iov_iter *, gfp_t); @@ -469,9 +524,12 @@ extern void bvec_free(mempool_t *, struct bio_vec *, unsigned int); extern unsigned int bvec_nr_vecs(unsigned short idx); #ifdef CONFIG_BLK_CGROUP +int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css); int bio_associate_current(struct bio *bio); void bio_disassociate_task(struct bio *bio); #else /* CONFIG_BLK_CGROUP */ +static inline int bio_associate_blkcg(struct bio *bio, + struct cgroup_subsys_state *blkcg_css) { return 0; } static inline int bio_associate_current(struct bio *bio) { return -ENOENT; } static inline void bio_disassociate_task(struct bio *bio) { } #endif /* CONFIG_BLK_CGROUP */ @@ -701,7 +759,7 @@ extern void bio_integrity_free(struct bio *); extern int bio_integrity_add_page(struct bio *, struct page *, unsigned int, unsigned int); extern bool bio_integrity_enabled(struct bio *bio); extern int bio_integrity_prep(struct bio *); -extern void bio_integrity_endio(struct bio *, int); +extern void bio_integrity_endio(struct bio *); extern void bio_integrity_advance(struct bio *, unsigned int); extern void bio_integrity_trim(struct bio *, unsigned int, unsigned int); extern int bio_integrity_clone(struct bio *, struct bio *, gfp_t); diff --git a/kernel/include/linux/bitmap.h b/kernel/include/linux/bitmap.h index ea17cca9e..9653fdb76 100644 --- a/kernel/include/linux/bitmap.h +++ b/kernel/include/linux/bitmap.h @@ -295,7 +295,7 @@ static inline int bitmap_full(const unsigned long *src, unsigned int nbits) return find_first_zero_bit(src, nbits) == nbits; } -static inline int bitmap_weight(const unsigned long *src, unsigned int nbits) +static __always_inline int bitmap_weight(const unsigned long *src, unsigned int nbits) { if (small_const_nbits(nbits)) return hweight_long(*src & BITMAP_LAST_WORD_MASK(nbits)); diff --git a/kernel/include/linux/bitops.h b/kernel/include/linux/bitops.h index 297f5bda4..defeaac07 100644 --- a/kernel/include/linux/bitops.h +++ b/kernel/include/linux/bitops.h @@ -57,7 +57,7 @@ extern unsigned long __sw_hweight64(__u64 w); (bit) < (size); \ (bit) = find_next_zero_bit((addr), (size), (bit) + 1)) -static __inline__ int get_bitmask_order(unsigned int count) +static inline int get_bitmask_order(unsigned int count) { int order; @@ -65,7 +65,7 @@ static __inline__ int get_bitmask_order(unsigned int count) return order; /* We could be slightly more clever with -1 here... */ } -static __inline__ int get_count_order(unsigned int count) +static inline int get_count_order(unsigned int count) { int order; @@ -75,7 +75,7 @@ static __inline__ int get_count_order(unsigned int count) return order; } -static inline unsigned long hweight_long(unsigned long w) +static __always_inline unsigned long hweight_long(unsigned long w) { return sizeof(w) == 4 ? hweight32(w) : hweight64(w); } @@ -107,7 +107,7 @@ static inline __u64 ror64(__u64 word, unsigned int shift) */ static inline __u32 rol32(__u32 word, unsigned int shift) { - return (word << shift) | (word >> (32 - shift)); + return (word << shift) | (word >> ((-shift) & 31)); } /** @@ -164,6 +164,8 @@ static inline __u8 ror8(__u8 word, unsigned int shift) * sign_extend32 - sign extend a 32-bit value using specified bit as sign-bit * @value: value to sign extend * @index: 0 based bit index (0<=index<32) to sign bit + * + * This is safe to use for 16- and 8-bit types as well. */ static inline __s32 sign_extend32(__u32 value, int index) { @@ -171,6 +173,17 @@ static inline __s32 sign_extend32(__u32 value, int index) return (__s32)(value << shift) >> shift; } +/** + * sign_extend64 - sign extend a 64-bit value using specified bit as sign-bit + * @value: value to sign extend + * @index: 0 based bit index (0<=index<64) to sign bit + */ +static inline __s64 sign_extend64(__u64 value, int index) +{ + __u8 shift = 63 - index; + return (__s64)(value << shift) >> shift; +} + static inline unsigned fls_long(unsigned long l) { if (sizeof(l) == 4) diff --git a/kernel/include/linux/blk-cgroup.h b/kernel/include/linux/blk-cgroup.h new file mode 100644 index 000000000..c02e66994 --- /dev/null +++ b/kernel/include/linux/blk-cgroup.h @@ -0,0 +1,786 @@ +#ifndef _BLK_CGROUP_H +#define _BLK_CGROUP_H +/* + * Common Block IO controller cgroup interface + * + * Based on ideas and code from CFQ, CFS and BFQ: + * Copyright (C) 2003 Jens Axboe <axboe@kernel.dk> + * + * Copyright (C) 2008 Fabio Checconi <fabio@gandalf.sssup.it> + * Paolo Valente <paolo.valente@unimore.it> + * + * Copyright (C) 2009 Vivek Goyal <vgoyal@redhat.com> + * Nauman Rafique <nauman@google.com> + */ + +#include <linux/cgroup.h> +#include <linux/percpu_counter.h> +#include <linux/seq_file.h> +#include <linux/radix-tree.h> +#include <linux/blkdev.h> +#include <linux/atomic.h> + +/* percpu_counter batch for blkg_[rw]stats, per-cpu drift doesn't matter */ +#define BLKG_STAT_CPU_BATCH (INT_MAX / 2) + +/* Max limits for throttle policy */ +#define THROTL_IOPS_MAX UINT_MAX + +#ifdef CONFIG_BLK_CGROUP + +enum blkg_rwstat_type { + BLKG_RWSTAT_READ, + BLKG_RWSTAT_WRITE, + BLKG_RWSTAT_SYNC, + BLKG_RWSTAT_ASYNC, + + BLKG_RWSTAT_NR, + BLKG_RWSTAT_TOTAL = BLKG_RWSTAT_NR, +}; + +struct blkcg_gq; + +struct blkcg { + struct cgroup_subsys_state css; + spinlock_t lock; + + struct radix_tree_root blkg_tree; + struct blkcg_gq *blkg_hint; + struct hlist_head blkg_list; + + struct blkcg_policy_data *cpd[BLKCG_MAX_POLS]; + + struct list_head all_blkcgs_node; +#ifdef CONFIG_CGROUP_WRITEBACK + struct list_head cgwb_list; +#endif +}; + +/* + * blkg_[rw]stat->aux_cnt is excluded for local stats but included for + * recursive. Used to carry stats of dead children, and, for blkg_rwstat, + * to carry result values from read and sum operations. + */ +struct blkg_stat { + struct percpu_counter cpu_cnt; + atomic64_t aux_cnt; +}; + +struct blkg_rwstat { + struct percpu_counter cpu_cnt[BLKG_RWSTAT_NR]; + atomic64_t aux_cnt[BLKG_RWSTAT_NR]; +}; + +/* + * A blkcg_gq (blkg) is association between a block cgroup (blkcg) and a + * request_queue (q). This is used by blkcg policies which need to track + * information per blkcg - q pair. + * + * There can be multiple active blkcg policies and each blkg:policy pair is + * represented by a blkg_policy_data which is allocated and freed by each + * policy's pd_alloc/free_fn() methods. A policy can allocate private data + * area by allocating larger data structure which embeds blkg_policy_data + * at the beginning. + */ +struct blkg_policy_data { + /* the blkg and policy id this per-policy data belongs to */ + struct blkcg_gq *blkg; + int plid; +}; + +/* + * Policies that need to keep per-blkcg data which is independent from any + * request_queue associated to it should implement cpd_alloc/free_fn() + * methods. A policy can allocate private data area by allocating larger + * data structure which embeds blkcg_policy_data at the beginning. + * cpd_init() is invoked to let each policy handle per-blkcg data. + */ +struct blkcg_policy_data { + /* the blkcg and policy id this per-policy data belongs to */ + struct blkcg *blkcg; + int plid; +}; + +/* association between a blk cgroup and a request queue */ +struct blkcg_gq { + /* Pointer to the associated request_queue */ + struct request_queue *q; + struct list_head q_node; + struct hlist_node blkcg_node; + struct blkcg *blkcg; + + /* + * Each blkg gets congested separately and the congestion state is + * propagated to the matching bdi_writeback_congested. + */ + struct bdi_writeback_congested *wb_congested; + + /* all non-root blkcg_gq's are guaranteed to have access to parent */ + struct blkcg_gq *parent; + + /* request allocation list for this blkcg-q pair */ + struct request_list rl; + + /* reference count */ + atomic_t refcnt; + + /* is this blkg online? protected by both blkcg and q locks */ + bool online; + + struct blkg_rwstat stat_bytes; + struct blkg_rwstat stat_ios; + + struct blkg_policy_data *pd[BLKCG_MAX_POLS]; + + struct rcu_head rcu_head; +}; + +typedef struct blkcg_policy_data *(blkcg_pol_alloc_cpd_fn)(gfp_t gfp); +typedef void (blkcg_pol_init_cpd_fn)(struct blkcg_policy_data *cpd); +typedef void (blkcg_pol_free_cpd_fn)(struct blkcg_policy_data *cpd); +typedef void (blkcg_pol_bind_cpd_fn)(struct blkcg_policy_data *cpd); +typedef struct blkg_policy_data *(blkcg_pol_alloc_pd_fn)(gfp_t gfp, int node); +typedef void (blkcg_pol_init_pd_fn)(struct blkg_policy_data *pd); +typedef void (blkcg_pol_online_pd_fn)(struct blkg_policy_data *pd); +typedef void (blkcg_pol_offline_pd_fn)(struct blkg_policy_data *pd); +typedef void (blkcg_pol_free_pd_fn)(struct blkg_policy_data *pd); +typedef void (blkcg_pol_reset_pd_stats_fn)(struct blkg_policy_data *pd); + +struct blkcg_policy { + int plid; + /* cgroup files for the policy */ + struct cftype *dfl_cftypes; + struct cftype *legacy_cftypes; + + /* operations */ + blkcg_pol_alloc_cpd_fn *cpd_alloc_fn; + blkcg_pol_init_cpd_fn *cpd_init_fn; + blkcg_pol_free_cpd_fn *cpd_free_fn; + blkcg_pol_bind_cpd_fn *cpd_bind_fn; + + blkcg_pol_alloc_pd_fn *pd_alloc_fn; + blkcg_pol_init_pd_fn *pd_init_fn; + blkcg_pol_online_pd_fn *pd_online_fn; + blkcg_pol_offline_pd_fn *pd_offline_fn; + blkcg_pol_free_pd_fn *pd_free_fn; + blkcg_pol_reset_pd_stats_fn *pd_reset_stats_fn; +}; + +extern struct blkcg blkcg_root; +extern struct cgroup_subsys_state * const blkcg_root_css; + +struct blkcg_gq *blkg_lookup_slowpath(struct blkcg *blkcg, + struct request_queue *q, bool update_hint); +struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg, + struct request_queue *q); +int blkcg_init_queue(struct request_queue *q); +void blkcg_drain_queue(struct request_queue *q); +void blkcg_exit_queue(struct request_queue *q); + +/* Blkio controller policy registration */ +int blkcg_policy_register(struct blkcg_policy *pol); +void blkcg_policy_unregister(struct blkcg_policy *pol); +int blkcg_activate_policy(struct request_queue *q, + const struct blkcg_policy *pol); +void blkcg_deactivate_policy(struct request_queue *q, + const struct blkcg_policy *pol); + +const char *blkg_dev_name(struct blkcg_gq *blkg); +void blkcg_print_blkgs(struct seq_file *sf, struct blkcg *blkcg, + u64 (*prfill)(struct seq_file *, + struct blkg_policy_data *, int), + const struct blkcg_policy *pol, int data, + bool show_total); +u64 __blkg_prfill_u64(struct seq_file *sf, struct blkg_policy_data *pd, u64 v); +u64 __blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd, + const struct blkg_rwstat *rwstat); +u64 blkg_prfill_stat(struct seq_file *sf, struct blkg_policy_data *pd, int off); +u64 blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd, + int off); +int blkg_print_stat_bytes(struct seq_file *sf, void *v); +int blkg_print_stat_ios(struct seq_file *sf, void *v); +int blkg_print_stat_bytes_recursive(struct seq_file *sf, void *v); +int blkg_print_stat_ios_recursive(struct seq_file *sf, void *v); + +u64 blkg_stat_recursive_sum(struct blkcg_gq *blkg, + struct blkcg_policy *pol, int off); +struct blkg_rwstat blkg_rwstat_recursive_sum(struct blkcg_gq *blkg, + struct blkcg_policy *pol, int off); + +struct blkg_conf_ctx { + struct gendisk *disk; + struct blkcg_gq *blkg; + char *body; +}; + +int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol, + char *input, struct blkg_conf_ctx *ctx); +void blkg_conf_finish(struct blkg_conf_ctx *ctx); + + +static inline struct blkcg *css_to_blkcg(struct cgroup_subsys_state *css) +{ + return css ? container_of(css, struct blkcg, css) : NULL; +} + +static inline struct blkcg *task_blkcg(struct task_struct *tsk) +{ + return css_to_blkcg(task_css(tsk, io_cgrp_id)); +} + +static inline struct blkcg *bio_blkcg(struct bio *bio) +{ + if (bio && bio->bi_css) + return css_to_blkcg(bio->bi_css); + return task_blkcg(current); +} + +static inline struct cgroup_subsys_state * +task_get_blkcg_css(struct task_struct *task) +{ + return task_get_css(task, io_cgrp_id); +} + +/** + * blkcg_parent - get the parent of a blkcg + * @blkcg: blkcg of interest + * + * Return the parent blkcg of @blkcg. Can be called anytime. + */ +static inline struct blkcg *blkcg_parent(struct blkcg *blkcg) +{ + return css_to_blkcg(blkcg->css.parent); +} + +/** + * __blkg_lookup - internal version of blkg_lookup() + * @blkcg: blkcg of interest + * @q: request_queue of interest + * @update_hint: whether to update lookup hint with the result or not + * + * This is internal version and shouldn't be used by policy + * implementations. Looks up blkgs for the @blkcg - @q pair regardless of + * @q's bypass state. If @update_hint is %true, the caller should be + * holding @q->queue_lock and lookup hint is updated on success. + */ +static inline struct blkcg_gq *__blkg_lookup(struct blkcg *blkcg, + struct request_queue *q, + bool update_hint) +{ + struct blkcg_gq *blkg; + + if (blkcg == &blkcg_root) + return q->root_blkg; + + blkg = rcu_dereference(blkcg->blkg_hint); + if (blkg && blkg->q == q) + return blkg; + + return blkg_lookup_slowpath(blkcg, q, update_hint); +} + +/** + * blkg_lookup - lookup blkg for the specified blkcg - q pair + * @blkcg: blkcg of interest + * @q: request_queue of interest + * + * Lookup blkg for the @blkcg - @q pair. This function should be called + * under RCU read lock and is guaranteed to return %NULL if @q is bypassing + * - see blk_queue_bypass_start() for details. + */ +static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, + struct request_queue *q) +{ + WARN_ON_ONCE(!rcu_read_lock_held()); + + if (unlikely(blk_queue_bypass(q))) + return NULL; + return __blkg_lookup(blkcg, q, false); +} + +/** + * blkg_to_pdata - get policy private data + * @blkg: blkg of interest + * @pol: policy of interest + * + * Return pointer to private data associated with the @blkg-@pol pair. + */ +static inline struct blkg_policy_data *blkg_to_pd(struct blkcg_gq *blkg, + struct blkcg_policy *pol) +{ + return blkg ? blkg->pd[pol->plid] : NULL; +} + +static inline struct blkcg_policy_data *blkcg_to_cpd(struct blkcg *blkcg, + struct blkcg_policy *pol) +{ + return blkcg ? blkcg->cpd[pol->plid] : NULL; +} + +/** + * pdata_to_blkg - get blkg associated with policy private data + * @pd: policy private data of interest + * + * @pd is policy private data. Determine the blkg it's associated with. + */ +static inline struct blkcg_gq *pd_to_blkg(struct blkg_policy_data *pd) +{ + return pd ? pd->blkg : NULL; +} + +static inline struct blkcg *cpd_to_blkcg(struct blkcg_policy_data *cpd) +{ + return cpd ? cpd->blkcg : NULL; +} + +/** + * blkg_path - format cgroup path of blkg + * @blkg: blkg of interest + * @buf: target buffer + * @buflen: target buffer length + * + * Format the path of the cgroup of @blkg into @buf. + */ +static inline int blkg_path(struct blkcg_gq *blkg, char *buf, int buflen) +{ + char *p; + + p = cgroup_path(blkg->blkcg->css.cgroup, buf, buflen); + if (!p) { + strncpy(buf, "<unavailable>", buflen); + return -ENAMETOOLONG; + } + + memmove(buf, p, buf + buflen - p); + return 0; +} + +/** + * blkg_get - get a blkg reference + * @blkg: blkg to get + * + * The caller should be holding an existing reference. + */ +static inline void blkg_get(struct blkcg_gq *blkg) +{ + WARN_ON_ONCE(atomic_read(&blkg->refcnt) <= 0); + atomic_inc(&blkg->refcnt); +} + +void __blkg_release_rcu(struct rcu_head *rcu); + +/** + * blkg_put - put a blkg reference + * @blkg: blkg to put + */ +static inline void blkg_put(struct blkcg_gq *blkg) +{ + WARN_ON_ONCE(atomic_read(&blkg->refcnt) <= 0); + if (atomic_dec_and_test(&blkg->refcnt)) + call_rcu(&blkg->rcu_head, __blkg_release_rcu); +} + +/** + * blkg_for_each_descendant_pre - pre-order walk of a blkg's descendants + * @d_blkg: loop cursor pointing to the current descendant + * @pos_css: used for iteration + * @p_blkg: target blkg to walk descendants of + * + * Walk @c_blkg through the descendants of @p_blkg. Must be used with RCU + * read locked. If called under either blkcg or queue lock, the iteration + * is guaranteed to include all and only online blkgs. The caller may + * update @pos_css by calling css_rightmost_descendant() to skip subtree. + * @p_blkg is included in the iteration and the first node to be visited. + */ +#define blkg_for_each_descendant_pre(d_blkg, pos_css, p_blkg) \ + css_for_each_descendant_pre((pos_css), &(p_blkg)->blkcg->css) \ + if (((d_blkg) = __blkg_lookup(css_to_blkcg(pos_css), \ + (p_blkg)->q, false))) + +/** + * blkg_for_each_descendant_post - post-order walk of a blkg's descendants + * @d_blkg: loop cursor pointing to the current descendant + * @pos_css: used for iteration + * @p_blkg: target blkg to walk descendants of + * + * Similar to blkg_for_each_descendant_pre() but performs post-order + * traversal instead. Synchronization rules are the same. @p_blkg is + * included in the iteration and the last node to be visited. + */ +#define blkg_for_each_descendant_post(d_blkg, pos_css, p_blkg) \ + css_for_each_descendant_post((pos_css), &(p_blkg)->blkcg->css) \ + if (((d_blkg) = __blkg_lookup(css_to_blkcg(pos_css), \ + (p_blkg)->q, false))) + +/** + * blk_get_rl - get request_list to use + * @q: request_queue of interest + * @bio: bio which will be attached to the allocated request (may be %NULL) + * + * The caller wants to allocate a request from @q to use for @bio. Find + * the request_list to use and obtain a reference on it. Should be called + * under queue_lock. This function is guaranteed to return non-%NULL + * request_list. + */ +static inline struct request_list *blk_get_rl(struct request_queue *q, + struct bio *bio) +{ + struct blkcg *blkcg; + struct blkcg_gq *blkg; + + rcu_read_lock(); + + blkcg = bio_blkcg(bio); + + /* bypass blkg lookup and use @q->root_rl directly for root */ + if (blkcg == &blkcg_root) + goto root_rl; + + /* + * Try to use blkg->rl. blkg lookup may fail under memory pressure + * or if either the blkcg or queue is going away. Fall back to + * root_rl in such cases. + */ + blkg = blkg_lookup(blkcg, q); + if (unlikely(!blkg)) + goto root_rl; + + blkg_get(blkg); + rcu_read_unlock(); + return &blkg->rl; +root_rl: + rcu_read_unlock(); + return &q->root_rl; +} + +/** + * blk_put_rl - put request_list + * @rl: request_list to put + * + * Put the reference acquired by blk_get_rl(). Should be called under + * queue_lock. + */ +static inline void blk_put_rl(struct request_list *rl) +{ + if (rl->blkg->blkcg != &blkcg_root) + blkg_put(rl->blkg); +} + +/** + * blk_rq_set_rl - associate a request with a request_list + * @rq: request of interest + * @rl: target request_list + * + * Associate @rq with @rl so that accounting and freeing can know the + * request_list @rq came from. + */ +static inline void blk_rq_set_rl(struct request *rq, struct request_list *rl) +{ + rq->rl = rl; +} + +/** + * blk_rq_rl - return the request_list a request came from + * @rq: request of interest + * + * Return the request_list @rq is allocated from. + */ +static inline struct request_list *blk_rq_rl(struct request *rq) +{ + return rq->rl; +} + +struct request_list *__blk_queue_next_rl(struct request_list *rl, + struct request_queue *q); +/** + * blk_queue_for_each_rl - iterate through all request_lists of a request_queue + * + * Should be used under queue_lock. + */ +#define blk_queue_for_each_rl(rl, q) \ + for ((rl) = &(q)->root_rl; (rl); (rl) = __blk_queue_next_rl((rl), (q))) + +static inline int blkg_stat_init(struct blkg_stat *stat, gfp_t gfp) +{ + int ret; + + ret = percpu_counter_init(&stat->cpu_cnt, 0, gfp); + if (ret) + return ret; + + atomic64_set(&stat->aux_cnt, 0); + return 0; +} + +static inline void blkg_stat_exit(struct blkg_stat *stat) +{ + percpu_counter_destroy(&stat->cpu_cnt); +} + +/** + * blkg_stat_add - add a value to a blkg_stat + * @stat: target blkg_stat + * @val: value to add + * + * Add @val to @stat. The caller must ensure that IRQ on the same CPU + * don't re-enter this function for the same counter. + */ +static inline void blkg_stat_add(struct blkg_stat *stat, uint64_t val) +{ + __percpu_counter_add(&stat->cpu_cnt, val, BLKG_STAT_CPU_BATCH); +} + +/** + * blkg_stat_read - read the current value of a blkg_stat + * @stat: blkg_stat to read + */ +static inline uint64_t blkg_stat_read(struct blkg_stat *stat) +{ + return percpu_counter_sum_positive(&stat->cpu_cnt); +} + +/** + * blkg_stat_reset - reset a blkg_stat + * @stat: blkg_stat to reset + */ +static inline void blkg_stat_reset(struct blkg_stat *stat) +{ + percpu_counter_set(&stat->cpu_cnt, 0); + atomic64_set(&stat->aux_cnt, 0); +} + +/** + * blkg_stat_add_aux - add a blkg_stat into another's aux count + * @to: the destination blkg_stat + * @from: the source + * + * Add @from's count including the aux one to @to's aux count. + */ +static inline void blkg_stat_add_aux(struct blkg_stat *to, + struct blkg_stat *from) +{ + atomic64_add(blkg_stat_read(from) + atomic64_read(&from->aux_cnt), + &to->aux_cnt); +} + +static inline int blkg_rwstat_init(struct blkg_rwstat *rwstat, gfp_t gfp) +{ + int i, ret; + + for (i = 0; i < BLKG_RWSTAT_NR; i++) { + ret = percpu_counter_init(&rwstat->cpu_cnt[i], 0, gfp); + if (ret) { + while (--i >= 0) + percpu_counter_destroy(&rwstat->cpu_cnt[i]); + return ret; + } + atomic64_set(&rwstat->aux_cnt[i], 0); + } + return 0; +} + +static inline void blkg_rwstat_exit(struct blkg_rwstat *rwstat) +{ + int i; + + for (i = 0; i < BLKG_RWSTAT_NR; i++) + percpu_counter_destroy(&rwstat->cpu_cnt[i]); +} + +/** + * blkg_rwstat_add - add a value to a blkg_rwstat + * @rwstat: target blkg_rwstat + * @rw: mask of REQ_{WRITE|SYNC} + * @val: value to add + * + * Add @val to @rwstat. The counters are chosen according to @rw. The + * caller is responsible for synchronizing calls to this function. + */ +static inline void blkg_rwstat_add(struct blkg_rwstat *rwstat, + int rw, uint64_t val) +{ + struct percpu_counter *cnt; + + if (rw & REQ_WRITE) + cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_WRITE]; + else + cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_READ]; + + __percpu_counter_add(cnt, val, BLKG_STAT_CPU_BATCH); + + if (rw & REQ_SYNC) + cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_SYNC]; + else + cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_ASYNC]; + + __percpu_counter_add(cnt, val, BLKG_STAT_CPU_BATCH); +} + +/** + * blkg_rwstat_read - read the current values of a blkg_rwstat + * @rwstat: blkg_rwstat to read + * + * Read the current snapshot of @rwstat and return it in the aux counts. + */ +static inline struct blkg_rwstat blkg_rwstat_read(struct blkg_rwstat *rwstat) +{ + struct blkg_rwstat result; + int i; + + for (i = 0; i < BLKG_RWSTAT_NR; i++) + atomic64_set(&result.aux_cnt[i], + percpu_counter_sum_positive(&rwstat->cpu_cnt[i])); + return result; +} + +/** + * blkg_rwstat_total - read the total count of a blkg_rwstat + * @rwstat: blkg_rwstat to read + * + * Return the total count of @rwstat regardless of the IO direction. This + * function can be called without synchronization and takes care of u64 + * atomicity. + */ +static inline uint64_t blkg_rwstat_total(struct blkg_rwstat *rwstat) +{ + struct blkg_rwstat tmp = blkg_rwstat_read(rwstat); + + return atomic64_read(&tmp.aux_cnt[BLKG_RWSTAT_READ]) + + atomic64_read(&tmp.aux_cnt[BLKG_RWSTAT_WRITE]); +} + +/** + * blkg_rwstat_reset - reset a blkg_rwstat + * @rwstat: blkg_rwstat to reset + */ +static inline void blkg_rwstat_reset(struct blkg_rwstat *rwstat) +{ + int i; + + for (i = 0; i < BLKG_RWSTAT_NR; i++) { + percpu_counter_set(&rwstat->cpu_cnt[i], 0); + atomic64_set(&rwstat->aux_cnt[i], 0); + } +} + +/** + * blkg_rwstat_add_aux - add a blkg_rwstat into another's aux count + * @to: the destination blkg_rwstat + * @from: the source + * + * Add @from's count including the aux one to @to's aux count. + */ +static inline void blkg_rwstat_add_aux(struct blkg_rwstat *to, + struct blkg_rwstat *from) +{ + struct blkg_rwstat v = blkg_rwstat_read(from); + int i; + + for (i = 0; i < BLKG_RWSTAT_NR; i++) + atomic64_add(atomic64_read(&v.aux_cnt[i]) + + atomic64_read(&from->aux_cnt[i]), + &to->aux_cnt[i]); +} + +#ifdef CONFIG_BLK_DEV_THROTTLING +extern bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg, + struct bio *bio); +#else +static inline bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg, + struct bio *bio) { return false; } +#endif + +static inline bool blkcg_bio_issue_check(struct request_queue *q, + struct bio *bio) +{ + struct blkcg *blkcg; + struct blkcg_gq *blkg; + bool throtl = false; + + rcu_read_lock(); + blkcg = bio_blkcg(bio); + + blkg = blkg_lookup(blkcg, q); + if (unlikely(!blkg)) { + spin_lock_irq(q->queue_lock); + blkg = blkg_lookup_create(blkcg, q); + if (IS_ERR(blkg)) + blkg = NULL; + spin_unlock_irq(q->queue_lock); + } + + throtl = blk_throtl_bio(q, blkg, bio); + + if (!throtl) { + blkg = blkg ?: q->root_blkg; + blkg_rwstat_add(&blkg->stat_bytes, bio->bi_rw, + bio->bi_iter.bi_size); + blkg_rwstat_add(&blkg->stat_ios, bio->bi_rw, 1); + } + + rcu_read_unlock(); + return !throtl; +} + +#else /* CONFIG_BLK_CGROUP */ + +struct blkcg { +}; + +struct blkg_policy_data { +}; + +struct blkcg_policy_data { +}; + +struct blkcg_gq { +}; + +struct blkcg_policy { +}; + +#define blkcg_root_css ((struct cgroup_subsys_state *)ERR_PTR(-EINVAL)) + +static inline struct cgroup_subsys_state * +task_get_blkcg_css(struct task_struct *task) +{ + return NULL; +} + +#ifdef CONFIG_BLOCK + +static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, void *key) { return NULL; } +static inline int blkcg_init_queue(struct request_queue *q) { return 0; } +static inline void blkcg_drain_queue(struct request_queue *q) { } +static inline void blkcg_exit_queue(struct request_queue *q) { } +static inline int blkcg_policy_register(struct blkcg_policy *pol) { return 0; } +static inline void blkcg_policy_unregister(struct blkcg_policy *pol) { } +static inline int blkcg_activate_policy(struct request_queue *q, + const struct blkcg_policy *pol) { return 0; } +static inline void blkcg_deactivate_policy(struct request_queue *q, + const struct blkcg_policy *pol) { } + +static inline struct blkcg *bio_blkcg(struct bio *bio) { return NULL; } + +static inline struct blkg_policy_data *blkg_to_pd(struct blkcg_gq *blkg, + struct blkcg_policy *pol) { return NULL; } +static inline struct blkcg_gq *pd_to_blkg(struct blkg_policy_data *pd) { return NULL; } +static inline char *blkg_path(struct blkcg_gq *blkg) { return NULL; } +static inline void blkg_get(struct blkcg_gq *blkg) { } +static inline void blkg_put(struct blkcg_gq *blkg) { } + +static inline struct request_list *blk_get_rl(struct request_queue *q, + struct bio *bio) { return &q->root_rl; } +static inline void blk_put_rl(struct request_list *rl) { } +static inline void blk_rq_set_rl(struct request *rq, struct request_list *rl) { } +static inline struct request_list *blk_rq_rl(struct request *rq) { return &rq->q->root_rl; } + +static inline bool blkcg_bio_issue_check(struct request_queue *q, + struct bio *bio) { return true; } + +#define blk_queue_for_each_rl(rl, q) \ + for ((rl) = &(q)->root_rl; (rl); (rl) = NULL) + +#endif /* CONFIG_BLOCK */ +#endif /* CONFIG_BLK_CGROUP */ +#endif /* _BLK_CGROUP_H */ diff --git a/kernel/include/linux/blk-mq.h b/kernel/include/linux/blk-mq.h index e6ff990c9..463df8954 100644 --- a/kernel/include/linux/blk-mq.h +++ b/kernel/include/linux/blk-mq.h @@ -59,6 +59,9 @@ struct blk_mq_hw_ctx { struct blk_mq_cpu_notifier cpu_notifier; struct kobject kobj; + + unsigned long poll_invoked; + unsigned long poll_success; }; struct blk_mq_tag_set { @@ -96,6 +99,9 @@ typedef void (exit_request_fn)(void *, struct request *, unsigned int, typedef void (busy_iter_fn)(struct blk_mq_hw_ctx *, struct request *, void *, bool); +typedef void (busy_tag_iter_fn)(struct request *, void *, bool); +typedef int (poll_fn)(struct blk_mq_hw_ctx *, unsigned int); + struct blk_mq_ops { /* @@ -113,6 +119,11 @@ struct blk_mq_ops { */ timeout_fn *timeout; + /* + * Called to poll for completion of a specific tag. + */ + poll_fn *poll; + softirq_done_fn *complete; /* @@ -144,7 +155,6 @@ enum { BLK_MQ_F_SHOULD_MERGE = 1 << 0, BLK_MQ_F_TAG_SHARED = 1 << 1, BLK_MQ_F_SG_MERGE = 1 << 2, - BLK_MQ_F_SYSFS_UP = 1 << 3, BLK_MQ_F_DEFER_ISSUE = 1 << 4, BLK_MQ_F_ALLOC_POLICY_START_BIT = 8, BLK_MQ_F_ALLOC_POLICY_BITS = 1, @@ -166,7 +176,6 @@ enum { struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *); struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, struct request_queue *q); -void blk_mq_finish_init(struct request_queue *q); int blk_mq_register_disk(struct gendisk *); void blk_mq_unregister_disk(struct gendisk *); @@ -182,6 +191,7 @@ bool blk_mq_can_queue(struct blk_mq_hw_ctx *); struct request *blk_mq_alloc_request(struct request_queue *q, int rw, gfp_t gfp, bool reserved); struct request *blk_mq_tag_to_rq(struct blk_mq_tags *tags, unsigned int tag); +struct cpumask *blk_mq_tags_cpumask(struct blk_mq_tags *tags); enum { BLK_MQ_UNIQUE_TAG_BITS = 16, @@ -214,7 +224,7 @@ void blk_mq_add_to_requeue_list(struct request *rq, bool at_head); void blk_mq_cancel_requeue_work(struct request_queue *q); void blk_mq_kick_requeue_list(struct request_queue *q); void blk_mq_abort_requeue_list(struct request_queue *q); -void blk_mq_complete_request(struct request *rq); +void blk_mq_complete_request(struct request *rq, int error); void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx); void blk_mq_start_hw_queue(struct blk_mq_hw_ctx *hctx); @@ -223,7 +233,7 @@ void blk_mq_start_hw_queues(struct request_queue *q); void blk_mq_start_stopped_hw_queues(struct request_queue *q, bool async); void blk_mq_run_hw_queues(struct request_queue *q, bool async); void blk_mq_delay_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs); -void blk_mq_tag_busy_iter(struct blk_mq_hw_ctx *hctx, busy_iter_fn *fn, +void blk_mq_all_tag_busy_iter(struct blk_mq_tags *tags, busy_tag_iter_fn *fn, void *priv); void blk_mq_freeze_queue(struct request_queue *q); void blk_mq_unfreeze_queue(struct request_queue *q); diff --git a/kernel/include/linux/blk_types.h b/kernel/include/linux/blk_types.h index b7299febc..0fb65843e 100644 --- a/kernel/include/linux/blk_types.h +++ b/kernel/include/linux/blk_types.h @@ -14,7 +14,7 @@ struct page; struct block_device; struct io_context; struct cgroup_subsys_state; -typedef void (bio_end_io_t) (struct bio *, int); +typedef void (bio_end_io_t) (struct bio *); typedef void (bio_destructor_t) (struct bio *); /* @@ -46,7 +46,8 @@ struct bvec_iter { struct bio { struct bio *bi_next; /* request queue link */ struct block_device *bi_bdev; - unsigned long bi_flags; /* status, command, etc */ + unsigned int bi_flags; /* status, command, etc */ + int bi_error; unsigned long bi_rw; /* bottom bits READ/WRITE, * top bits priority */ @@ -65,7 +66,7 @@ struct bio { unsigned int bi_seg_front_size; unsigned int bi_seg_back_size; - atomic_t bi_remaining; + atomic_t __bi_remaining; bio_end_io_t *bi_end_io; @@ -92,7 +93,7 @@ struct bio { unsigned short bi_max_vecs; /* max bvl_vecs we can hold */ - atomic_t bi_cnt; /* pin count */ + atomic_t __bi_cnt; /* pin count */ struct bio_vec *bi_io_vec; /* the actual vec list */ @@ -111,17 +112,14 @@ struct bio { /* * bio flags */ -#define BIO_UPTODATE 0 /* ok after I/O completion */ -#define BIO_RW_BLOCK 1 /* RW_AHEAD set, and read/write would block */ -#define BIO_EOF 2 /* out-out-bounds error */ -#define BIO_SEG_VALID 3 /* bi_phys_segments valid */ -#define BIO_CLONED 4 /* doesn't own data */ -#define BIO_BOUNCED 5 /* bio is a bounce bio */ -#define BIO_USER_MAPPED 6 /* contains user pages */ -#define BIO_EOPNOTSUPP 7 /* not supported */ -#define BIO_NULL_MAPPED 8 /* contains invalid user pages */ -#define BIO_QUIET 9 /* Make BIO Quiet */ -#define BIO_SNAP_STABLE 10 /* bio data must be snapshotted during write */ +#define BIO_SEG_VALID 1 /* bi_phys_segments valid */ +#define BIO_CLONED 2 /* doesn't own data */ +#define BIO_BOUNCED 3 /* bio is a bounce bio */ +#define BIO_USER_MAPPED 4 /* contains user pages */ +#define BIO_NULL_MAPPED 5 /* contains invalid user pages */ +#define BIO_QUIET 6 /* Make BIO Quiet */ +#define BIO_CHAIN 7 /* chained bio, ->bi_remaining in effect */ +#define BIO_REFFED 8 /* bio has elevated ->bi_cnt */ /* * Flags starting here get preserved by bio_reset() - this includes @@ -130,14 +128,12 @@ struct bio { #define BIO_RESET_BITS 13 #define BIO_OWNS_VEC 13 /* bio_free() should free bvec */ -#define bio_flagged(bio, flag) ((bio)->bi_flags & (1 << (flag))) - /* * top 4 bits of bio flags indicate the pool this bio came from */ #define BIO_POOL_BITS (4) #define BIO_POOL_NONE ((1UL << BIO_POOL_BITS) - 1) -#define BIO_POOL_OFFSET (BITS_PER_LONG - BIO_POOL_BITS) +#define BIO_POOL_OFFSET (32 - BIO_POOL_BITS) #define BIO_POOL_MASK (1UL << BIO_POOL_OFFSET) #define BIO_POOL_IDX(bio) ((bio)->bi_flags >> BIO_POOL_OFFSET) @@ -248,4 +244,28 @@ enum rq_flag_bits { #define REQ_MQ_INFLIGHT (1ULL << __REQ_MQ_INFLIGHT) #define REQ_NO_TIMEOUT (1ULL << __REQ_NO_TIMEOUT) +typedef unsigned int blk_qc_t; +#define BLK_QC_T_NONE -1U +#define BLK_QC_T_SHIFT 16 + +static inline bool blk_qc_t_valid(blk_qc_t cookie) +{ + return cookie != BLK_QC_T_NONE; +} + +static inline blk_qc_t blk_tag_to_qc_t(unsigned int tag, unsigned int queue_num) +{ + return tag | (queue_num << BLK_QC_T_SHIFT); +} + +static inline unsigned int blk_qc_t_to_queue_num(blk_qc_t cookie) +{ + return cookie >> BLK_QC_T_SHIFT; +} + +static inline unsigned int blk_qc_t_to_tag(blk_qc_t cookie) +{ + return cookie & ((1u << BLK_QC_T_SHIFT) - 1); +} + #endif /* __LINUX_BLK_TYPES_H */ diff --git a/kernel/include/linux/blkdev.h b/kernel/include/linux/blkdev.h index 37faf63af..a8f18e02b 100644 --- a/kernel/include/linux/blkdev.h +++ b/kernel/include/linux/blkdev.h @@ -12,7 +12,7 @@ #include <linux/timer.h> #include <linux/workqueue.h> #include <linux/pagemap.h> -#include <linux/backing-dev.h> +#include <linux/backing-dev-defs.h> #include <linux/wait.h> #include <linux/mempool.h> #include <linux/bio.h> @@ -22,21 +22,20 @@ #include <linux/smp.h> #include <linux/rcupdate.h> #include <linux/percpu-refcount.h> - -#include <asm/scatterlist.h> +#include <linux/scatterlist.h> struct module; struct scsi_ioctl_command; struct request_queue; struct elevator_queue; -struct request_pm_state; struct blk_trace; struct request; struct sg_io_hdr; struct bsg_job; struct blkcg_gq; struct blk_flush_queue; +struct pr_ops; #define BLKDEV_MIN_RQ 4 #define BLKDEV_MAX_RQ 128 /* Default maximum */ @@ -75,18 +74,7 @@ struct request_list { enum rq_cmd_type_bits { REQ_TYPE_FS = 1, /* fs request */ REQ_TYPE_BLOCK_PC, /* scsi command */ - REQ_TYPE_SENSE, /* sense request */ - REQ_TYPE_PM_SUSPEND, /* suspend request */ - REQ_TYPE_PM_RESUME, /* resume request */ - REQ_TYPE_PM_SHUTDOWN, /* shutdown request */ - REQ_TYPE_SPECIAL, /* driver defined type */ - /* - * for ATA/ATAPI devices. this really doesn't belong here, ide should - * use REQ_TYPE_SPECIAL and use rq->cmd[0] with the range of driver - * private REQ_LB opcodes to differentiate what type of request this is - */ - REQ_TYPE_ATA_TASKFILE, - REQ_TYPE_ATA_PC, + REQ_TYPE_DRV_PRIV, /* driver defined types from here */ }; #define BLK_MAX_CDB 16 @@ -109,7 +97,7 @@ struct request { struct blk_mq_ctx *mq_ctx; u64 cmd_flags; - enum rq_cmd_type_bits cmd_type; + unsigned cmd_type; unsigned long atomic_flags; int cpu; @@ -217,37 +205,16 @@ static inline unsigned short req_get_ioprio(struct request *req) return req->ioprio; } -/* - * State information carried for REQ_TYPE_PM_SUSPEND and REQ_TYPE_PM_RESUME - * requests. Some step values could eventually be made generic. - */ -struct request_pm_state -{ - /* PM state machine step value, currently driver specific */ - int pm_step; - /* requested PM state value (S1, S2, S3, S4, ...) */ - u32 pm_state; - void* data; /* for driver use */ -}; - #include <linux/elevator.h> struct blk_queue_ctx; typedef void (request_fn_proc) (struct request_queue *q); -typedef void (make_request_fn) (struct request_queue *q, struct bio *bio); +typedef blk_qc_t (make_request_fn) (struct request_queue *q, struct bio *bio); typedef int (prep_rq_fn) (struct request_queue *, struct request *); typedef void (unprep_rq_fn) (struct request_queue *, struct request *); struct bio_vec; -struct bvec_merge_data { - struct block_device *bi_bdev; - sector_t bi_sector; - unsigned bi_size; - unsigned long bi_rw; -}; -typedef int (merge_bvec_fn) (struct request_queue *, struct bvec_merge_data *, - struct bio_vec *); typedef void (softirq_done_fn)(struct request *); typedef int (dma_drain_needed_fn)(struct request *); typedef int (lld_busy_fn) (struct request_queue *q); @@ -285,8 +252,10 @@ struct blk_queue_tag { struct queue_limits { unsigned long bounce_pfn; unsigned long seg_boundary_mask; + unsigned long virt_boundary_mask; unsigned int max_hw_sectors; + unsigned int max_dev_sectors; unsigned int chunk_sectors; unsigned int max_sectors; unsigned int max_segment_size; @@ -295,6 +264,7 @@ struct queue_limits { unsigned int io_min; unsigned int io_opt; unsigned int max_discard_sectors; + unsigned int max_hw_discard_sectors; unsigned int max_write_same_sectors; unsigned int discard_granularity; unsigned int discard_alignment; @@ -332,7 +302,6 @@ struct request_queue { make_request_fn *make_request_fn; prep_rq_fn *prep_rq_fn; unprep_rq_fn *unprep_rq_fn; - merge_bvec_fn *merge_bvec_fn; softirq_done_fn *softirq_done_fn; rq_timed_out_fn *rq_timed_out_fn; dma_drain_needed_fn *dma_drain_needed; @@ -403,6 +372,10 @@ struct request_queue { */ struct kobject mq_kobj; +#ifdef CONFIG_BLK_DEV_INTEGRITY + struct blk_integrity integrity; +#endif /* CONFIG_BLK_DEV_INTEGRITY */ + #ifdef CONFIG_PM struct device *dev; int rpm_status; @@ -470,7 +443,7 @@ struct request_queue { struct mutex sysfs_lock; int bypass_depth; - int mq_freeze_depth; + atomic_t mq_freeze_depth; #if defined(CONFIG_BLK_DEV_BSG) bsg_job_fn *bsg_job_fn; @@ -483,12 +456,15 @@ struct request_queue { struct throtl_data *td; #endif struct rcu_head rcu_head; - struct swait_head mq_freeze_wq; - struct percpu_ref mq_usage_counter; + struct swait_queue_head mq_freeze_wq; + struct percpu_ref q_usage_counter; struct list_head all_q_node; struct blk_mq_tag_set *tag_set; struct list_head tag_set_list; + struct bio_set *bio_split; + + bool mq_sysfs_init_done; }; #define QUEUE_FLAG_QUEUED 1 /* uses generic tag queueing */ @@ -513,7 +489,7 @@ struct request_queue { #define QUEUE_FLAG_DEAD 19 /* queue tear-down finished */ #define QUEUE_FLAG_INIT_DONE 20 /* queue is initialized */ #define QUEUE_FLAG_NO_SG_MERGE 21 /* don't attempt to merge SG segments*/ -#define QUEUE_FLAG_SG_GAPS 22 /* queue doesn't support SG gaps */ +#define QUEUE_FLAG_POLL 22 /* IO polling enabled if set */ #define QUEUE_FLAG_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ (1 << QUEUE_FLAG_STACKABLE) | \ @@ -611,10 +587,6 @@ static inline void queue_flag_clear(unsigned int flag, struct request_queue *q) (((rq)->cmd_flags & REQ_STARTED) && \ ((rq)->cmd_type == REQ_TYPE_FS)) -#define blk_pm_request(rq) \ - ((rq)->cmd_type == REQ_TYPE_PM_SUSPEND || \ - (rq)->cmd_type == REQ_TYPE_PM_RESUME) - #define blk_rq_cpu_valid(rq) ((rq)->cpu != -1) #define blk_bidi_rq(rq) ((rq)->next_rq != NULL) /* rq->queuelist of dequeued request must be list_empty() */ @@ -622,7 +594,7 @@ static inline void queue_flag_clear(unsigned int flag, struct request_queue *q) #define list_entry_rq(ptr) list_entry((ptr), struct request, queuelist) -#define rq_data_dir(rq) (((rq)->cmd_flags & 1) != 0) +#define rq_data_dir(rq) ((int)((rq)->cmd_flags & 1)) /* * Driver can handle struct request, if it either has an old style @@ -792,7 +764,7 @@ static inline void rq_flush_dcache_pages(struct request *rq) extern int blk_register_queue(struct gendisk *disk); extern void blk_unregister_queue(struct gendisk *disk); -extern void generic_make_request(struct bio *bio); +extern blk_qc_t generic_make_request(struct bio *bio); extern void blk_rq_init(struct request_queue *q, struct request *rq); extern void blk_put_request(struct request *); extern void __blk_put_request(struct request_queue *, struct request *); @@ -803,7 +775,6 @@ extern void blk_rq_set_block_pc(struct request *); extern void blk_requeue_request(struct request_queue *, struct request *); extern void blk_add_request_payload(struct request *rq, struct page *page, unsigned int len); -extern int blk_rq_check_limits(struct request_queue *q, struct request *rq); extern int blk_lld_busy(struct request_queue *q); extern int blk_rq_prep_clone(struct request *rq, struct request *rq_src, struct bio_set *bs, gfp_t gfp_mask, @@ -813,6 +784,8 @@ extern void blk_rq_unprep_clone(struct request *rq); extern int blk_insert_cloned_request(struct request_queue *q, struct request *rq); extern void blk_delay_queue(struct request_queue *, unsigned long); +extern void blk_queue_split(struct request_queue *, struct bio **, + struct bio_set *); extern void blk_recount_segments(struct request_queue *, struct bio *); extern int scsi_verify_blk_ioctl(struct block_device *, unsigned int); extern int scsi_cmd_blk_ioctl(struct block_device *, fmode_t, @@ -822,30 +795,15 @@ extern int scsi_cmd_ioctl(struct request_queue *, struct gendisk *, fmode_t, extern int sg_scsi_ioctl(struct request_queue *, struct gendisk *, fmode_t, struct scsi_ioctl_command __user *); -/* - * A queue has just exitted congestion. Note this in the global counter of - * congested queues, and wake up anyone who was waiting for requests to be - * put back. - */ -static inline void blk_clear_queue_congested(struct request_queue *q, int sync) -{ - clear_bdi_congested(&q->backing_dev_info, sync); -} - -/* - * A queue has just entered congestion. Flag that in the queue's VM-visible - * state flags and increment the global gounter of congested queues. - */ -static inline void blk_set_queue_congested(struct request_queue *q, int sync) -{ - set_bdi_congested(&q->backing_dev_info, sync); -} - +extern int blk_queue_enter(struct request_queue *q, gfp_t gfp); +extern void blk_queue_exit(struct request_queue *q); extern void blk_start_queue(struct request_queue *q); +extern void blk_start_queue_async(struct request_queue *q); extern void blk_stop_queue(struct request_queue *q); extern void blk_sync_queue(struct request_queue *q); extern void __blk_stop_queue(struct request_queue *q); extern void __blk_run_queue(struct request_queue *q); +extern void __blk_run_queue_uncond(struct request_queue *q); extern void blk_run_queue(struct request_queue *); extern void blk_run_queue_async(struct request_queue *q); extern int blk_rq_map_user(struct request_queue *, struct request *, @@ -861,6 +819,8 @@ extern int blk_execute_rq(struct request_queue *, struct gendisk *, extern void blk_execute_rq_nowait(struct request_queue *, struct gendisk *, struct request *, int, rq_end_io_fn *); +bool blk_poll(struct request_queue *q, blk_qc_t cookie); + static inline struct request_queue *bdev_get_queue(struct block_device *bdev) { return bdev->bd_disk->queue; /* this is never NULL */ @@ -934,7 +894,7 @@ static inline unsigned int blk_rq_get_max_sectors(struct request *rq) if (unlikely(rq->cmd_type == REQ_TYPE_BLOCK_PC)) return q->limits.max_hw_sectors; - if (!q->limits.chunk_sectors) + if (!q->limits.chunk_sectors || (rq->cmd_flags & REQ_DISCARD)) return blk_queue_get_max_sectors(q, rq->cmd_flags); return min(blk_max_size_offset(q, blk_rq_pos(rq)), @@ -1002,7 +962,6 @@ extern struct request_queue *blk_init_allocated_queue(struct request_queue *, extern void blk_cleanup_queue(struct request_queue *); extern void blk_queue_make_request(struct request_queue *, make_request_fn *); extern void blk_queue_bounce_limit(struct request_queue *, u64); -extern void blk_limits_max_hw_sectors(struct queue_limits *, unsigned int); extern void blk_queue_max_hw_sectors(struct request_queue *, unsigned int); extern void blk_queue_chunk_sectors(struct request_queue *, unsigned int); extern void blk_queue_max_segments(struct request_queue *, unsigned short); @@ -1035,9 +994,9 @@ extern int blk_queue_dma_drain(struct request_queue *q, void *buf, unsigned int size); extern void blk_queue_lld_busy(struct request_queue *q, lld_busy_fn *fn); extern void blk_queue_segment_boundary(struct request_queue *, unsigned long); +extern void blk_queue_virt_boundary(struct request_queue *, unsigned long); extern void blk_queue_prep_rq(struct request_queue *, prep_rq_fn *pfn); extern void blk_queue_unprep_rq(struct request_queue *, unprep_rq_fn *ufn); -extern void blk_queue_merge_bvec(struct request_queue *, merge_bvec_fn *); extern void blk_queue_dma_alignment(struct request_queue *, int); extern void blk_queue_update_dma_alignment(struct request_queue *, int); extern void blk_queue_softirq_done(struct request_queue *, softirq_done_fn *); @@ -1055,6 +1014,7 @@ bool __must_check blk_get_queue(struct request_queue *); struct request_queue *blk_alloc_queue(gfp_t); struct request_queue *blk_alloc_queue_node(gfp_t, int); extern void blk_put_queue(struct request_queue *); +extern void blk_set_queue_dying(struct request_queue *); /* * block layer runtime pm functions @@ -1186,6 +1146,7 @@ extern int blk_verify_command(unsigned char *cmd, fmode_t has_write_perm); enum blk_default_limits { BLK_MAX_SEGMENTS = 128, BLK_SAFE_MAX_SECTORS = 255, + BLK_DEF_MAX_SECTORS = 2560, BLK_MAX_SEGMENT_SIZE = 65536, BLK_SEG_BOUNDARY_MASK = 0xFFFFFFFFUL, }; @@ -1202,6 +1163,11 @@ static inline unsigned long queue_segment_boundary(struct request_queue *q) return q->limits.seg_boundary_mask; } +static inline unsigned long queue_virt_boundary(struct request_queue *q) +{ + return q->limits.virt_boundary_mask; +} + static inline unsigned int queue_max_sectors(struct request_queue *q) { return q->limits.max_sectors; @@ -1402,6 +1368,50 @@ static inline void put_dev_sector(Sector p) page_cache_release(p.v); } +static inline bool __bvec_gap_to_prev(struct request_queue *q, + struct bio_vec *bprv, unsigned int offset) +{ + return offset || + ((bprv->bv_offset + bprv->bv_len) & queue_virt_boundary(q)); +} + +/* + * Check if adding a bio_vec after bprv with offset would create a gap in + * the SG list. Most drivers don't care about this, but some do. + */ +static inline bool bvec_gap_to_prev(struct request_queue *q, + struct bio_vec *bprv, unsigned int offset) +{ + if (!queue_virt_boundary(q)) + return false; + return __bvec_gap_to_prev(q, bprv, offset); +} + +static inline bool bio_will_gap(struct request_queue *q, struct bio *prev, + struct bio *next) +{ + if (bio_has_data(prev) && queue_virt_boundary(q)) { + struct bio_vec pb, nb; + + bio_get_last_bvec(prev, &pb); + bio_get_first_bvec(next, &nb); + + return __bvec_gap_to_prev(q, &pb, nb.bv_offset); + } + + return false; +} + +static inline bool req_gap_back_merge(struct request *req, struct bio *bio) +{ + return bio_will_gap(req->q, req->biotail, bio); +} + +static inline bool req_gap_front_merge(struct request *req, struct bio *bio) +{ + return bio_will_gap(req->q, bio, req->bio); +} + struct work_struct; int kblockd_schedule_work(struct work_struct *work); int kblockd_schedule_delayed_work(struct delayed_work *dwork, unsigned long delay); @@ -1474,22 +1484,13 @@ struct blk_integrity_iter { typedef int (integrity_processing_fn) (struct blk_integrity_iter *); -struct blk_integrity { - integrity_processing_fn *generate_fn; - integrity_processing_fn *verify_fn; - - unsigned short flags; - unsigned short tuple_size; - unsigned short interval; - unsigned short tag_size; - - const char *name; - - struct kobject kobj; +struct blk_integrity_profile { + integrity_processing_fn *generate_fn; + integrity_processing_fn *verify_fn; + const char *name; }; -extern bool blk_integrity_is_initialized(struct gendisk *); -extern int blk_integrity_register(struct gendisk *, struct blk_integrity *); +extern void blk_integrity_register(struct gendisk *, struct blk_integrity *); extern void blk_integrity_unregister(struct gendisk *); extern int blk_integrity_compare(struct gendisk *, struct gendisk *); extern int blk_rq_map_integrity_sg(struct request_queue *, struct bio *, @@ -1500,15 +1501,20 @@ extern bool blk_integrity_merge_rq(struct request_queue *, struct request *, extern bool blk_integrity_merge_bio(struct request_queue *, struct request *, struct bio *); -static inline -struct blk_integrity *bdev_get_integrity(struct block_device *bdev) +static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk) { - return bdev->bd_disk->integrity; + struct blk_integrity *bi = &disk->queue->integrity; + + if (!bi->profile) + return NULL; + + return bi; } -static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk) +static inline +struct blk_integrity *bdev_get_integrity(struct block_device *bdev) { - return disk->integrity; + return blk_get_integrity(bdev->bd_disk); } static inline bool blk_integrity_rq(struct request *rq) @@ -1528,6 +1534,26 @@ queue_max_integrity_segments(struct request_queue *q) return q->limits.max_integrity_segments; } +static inline bool integrity_req_gap_back_merge(struct request *req, + struct bio *next) +{ + struct bio_integrity_payload *bip = bio_integrity(req->bio); + struct bio_integrity_payload *bip_next = bio_integrity(next); + + return bvec_gap_to_prev(req->q, &bip->bip_vec[bip->bip_vcnt - 1], + bip_next->bip_vec[0].bv_offset); +} + +static inline bool integrity_req_gap_front_merge(struct request *req, + struct bio *bio) +{ + struct bio_integrity_payload *bip = bio_integrity(bio); + struct bio_integrity_payload *bip_next = bio_integrity(req->bio); + + return bvec_gap_to_prev(req->q, &bip->bip_vec[bip->bip_vcnt - 1], + bip_next->bip_vec[0].bv_offset); +} + #else /* CONFIG_BLK_DEV_INTEGRITY */ struct bio; @@ -1562,10 +1588,9 @@ static inline int blk_integrity_compare(struct gendisk *a, struct gendisk *b) { return 0; } -static inline int blk_integrity_register(struct gendisk *d, +static inline void blk_integrity_register(struct gendisk *d, struct blk_integrity *b) { - return 0; } static inline void blk_integrity_unregister(struct gendisk *d) { @@ -1590,9 +1615,16 @@ static inline bool blk_integrity_merge_bio(struct request_queue *rq, { return true; } -static inline bool blk_integrity_is_initialized(struct gendisk *g) + +static inline bool integrity_req_gap_back_merge(struct request *req, + struct bio *next) { - return 0; + return false; +} +static inline bool integrity_req_gap_front_merge(struct request *req, + struct bio *bio) +{ + return false; } #endif /* CONFIG_BLK_DEV_INTEGRITY */ @@ -1603,8 +1635,8 @@ struct block_device_operations { int (*rw_page)(struct block_device *, sector_t, struct page *, int rw); int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); - long (*direct_access)(struct block_device *, sector_t, - void **, unsigned long *pfn, long size); + long (*direct_access)(struct block_device *, sector_t, void __pmem **, + unsigned long *pfn); unsigned int (*check_events) (struct gendisk *disk, unsigned int clearing); /* ->media_changed() is DEPRECATED, use ->check_events() instead */ @@ -1615,6 +1647,7 @@ struct block_device_operations { /* this callback is with swap_lock and sometimes page table lock held */ void (*swap_slot_free_notify) (struct block_device *, unsigned long); struct module *owner; + const struct pr_ops *pr_ops; }; extern int __blkdev_driver_ioctl(struct block_device *, fmode_t, unsigned int, @@ -1622,8 +1655,8 @@ extern int __blkdev_driver_ioctl(struct block_device *, fmode_t, unsigned int, extern int bdev_read_page(struct block_device *, sector_t, struct page *); extern int bdev_write_page(struct block_device *, sector_t, struct page *, struct writeback_control *); -extern long bdev_direct_access(struct block_device *, sector_t, void **addr, - unsigned long *pfn, long size); +extern long bdev_direct_access(struct block_device *, sector_t, + void __pmem **addr, unsigned long *pfn, long size); #else /* CONFIG_BLOCK */ struct block_device; diff --git a/kernel/include/linux/blkpg.h b/kernel/include/linux/blkpg.h new file mode 100644 index 000000000..bef124fde --- /dev/null +++ b/kernel/include/linux/blkpg.h @@ -0,0 +1,21 @@ +#ifndef _LINUX_BLKPG_H +#define _LINUX_BLKPG_H + +/* + * Partition table and disk geometry handling + */ + +#include <linux/compat.h> +#include <uapi/linux/blkpg.h> + +#ifdef CONFIG_COMPAT +/* For 32-bit/64-bit compatibility of struct blkpg_ioctl_arg */ +struct blkpg_compat_ioctl_arg { + compat_int_t op; + compat_int_t flags; + compat_int_t datalen; + compat_uptr_t data; +}; +#endif + +#endif /* _LINUX_BLKPG_H */ diff --git a/kernel/include/linux/bootmem.h b/kernel/include/linux/bootmem.h index 0995c2de8..f589222bf 100644 --- a/kernel/include/linux/bootmem.h +++ b/kernel/include/linux/bootmem.h @@ -357,12 +357,12 @@ extern void *alloc_large_system_hash(const char *tablename, /* Only NUMA needs hash distribution. 64bit NUMA architectures have * sufficient vmalloc space. */ -#if defined(CONFIG_NUMA) && defined(CONFIG_64BIT) -#define HASHDIST_DEFAULT 1 +#ifdef CONFIG_NUMA +#define HASHDIST_DEFAULT IS_ENABLED(CONFIG_64BIT) +extern int hashdist; /* Distribute hashes across NUMA nodes? */ #else -#define HASHDIST_DEFAULT 0 +#define hashdist (0) #endif -extern int hashdist; /* Distribute hashes across NUMA nodes? */ #endif /* _LINUX_BOOTMEM_H */ diff --git a/kernel/include/linux/bottom_half.h b/kernel/include/linux/bottom_half.h index 8ca938935..d07dbeec7 100644 --- a/kernel/include/linux/bottom_half.h +++ b/kernel/include/linux/bottom_half.h @@ -2,16 +2,37 @@ #define _LINUX_BH_H #include <linux/preempt.h> -#include <linux/preempt_mask.h> #ifdef CONFIG_PREEMPT_RT_FULL -extern void local_bh_disable(void); +extern void __local_bh_disable(void); extern void _local_bh_enable(void); -extern void local_bh_enable(void); -extern void local_bh_enable_ip(unsigned long ip); -extern void __local_bh_disable_ip(unsigned long ip, unsigned int cnt); -extern void __local_bh_enable_ip(unsigned long ip, unsigned int cnt); +extern void __local_bh_enable(void); + +static inline void local_bh_disable(void) +{ + __local_bh_disable(); +} + +static inline void __local_bh_disable_ip(unsigned long ip, unsigned int cnt) +{ + __local_bh_disable(); +} + +static inline void local_bh_enable(void) +{ + __local_bh_enable(); +} + +static inline void __local_bh_enable_ip(unsigned long ip, unsigned int cnt) +{ + __local_bh_enable(); +} + +static inline void local_bh_enable_ip(unsigned long ip) +{ + __local_bh_enable(); +} #else diff --git a/kernel/include/linux/bpf.h b/kernel/include/linux/bpf.h index d5cda0671..83d1926c6 100644 --- a/kernel/include/linux/bpf.h +++ b/kernel/include/linux/bpf.h @@ -24,6 +24,10 @@ struct bpf_map_ops { void *(*map_lookup_elem)(struct bpf_map *map, void *key); int (*map_update_elem)(struct bpf_map *map, void *key, void *value, u64 flags); int (*map_delete_elem)(struct bpf_map *map, void *key); + + /* funcs called by prog_array and perf_event_array map */ + void *(*map_fd_get_ptr) (struct bpf_map *map, int fd); + void (*map_fd_put_ptr) (void *ptr); }; struct bpf_map { @@ -32,8 +36,11 @@ struct bpf_map { u32 key_size; u32 value_size; u32 max_entries; + u32 pages; + struct user_struct *user; const struct bpf_map_ops *ops; struct work_struct work; + atomic_t usercnt; }; struct bpf_map_type_list { @@ -96,6 +103,8 @@ enum bpf_access_type { BPF_WRITE = 2 }; +struct bpf_prog; + struct bpf_verifier_ops { /* return eBPF function prototype for verification */ const struct bpf_func_proto *(*get_func_proto)(enum bpf_func_id func_id); @@ -105,8 +114,9 @@ struct bpf_verifier_ops { */ bool (*is_valid_access)(int off, int size, enum bpf_access_type type); - u32 (*convert_ctx_access)(int dst_reg, int src_reg, int ctx_off, - struct bpf_insn *insn); + u32 (*convert_ctx_access)(enum bpf_access_type type, int dst_reg, + int src_reg, int ctx_off, + struct bpf_insn *insn, struct bpf_prog *prog); }; struct bpf_prog_type_list { @@ -115,27 +125,63 @@ struct bpf_prog_type_list { enum bpf_prog_type type; }; -struct bpf_prog; - struct bpf_prog_aux { atomic_t refcnt; u32 used_map_cnt; const struct bpf_verifier_ops *ops; struct bpf_map **used_maps; struct bpf_prog *prog; - struct work_struct work; + struct user_struct *user; + union { + struct work_struct work; + struct rcu_head rcu; + }; }; +struct bpf_array { + struct bpf_map map; + u32 elem_size; + /* 'ownership' of prog_array is claimed by the first program that + * is going to use this map or by the first program which FD is stored + * in the map to make sure that all callers and callees have the same + * prog_type and JITed flag + */ + enum bpf_prog_type owner_prog_type; + bool owner_jited; + union { + char value[0] __aligned(8); + void *ptrs[0] __aligned(8); + }; +}; +#define MAX_TAIL_CALL_CNT 32 + +u64 bpf_tail_call(u64 ctx, u64 r2, u64 index, u64 r4, u64 r5); +void bpf_fd_array_map_clear(struct bpf_map *map); +bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *fp); +const struct bpf_func_proto *bpf_get_trace_printk_proto(void); + #ifdef CONFIG_BPF_SYSCALL void bpf_register_prog_type(struct bpf_prog_type_list *tl); void bpf_register_map_type(struct bpf_map_type_list *tl); struct bpf_prog *bpf_prog_get(u32 ufd); void bpf_prog_put(struct bpf_prog *prog); +void bpf_prog_put_rcu(struct bpf_prog *prog); -struct bpf_map *bpf_map_get(struct fd f); +struct bpf_map *bpf_map_get_with_uref(u32 ufd); +struct bpf_map *__bpf_map_get(struct fd f); +void bpf_map_inc(struct bpf_map *map, bool uref); +void bpf_map_put_with_uref(struct bpf_map *map); void bpf_map_put(struct bpf_map *map); +extern int sysctl_unprivileged_bpf_disabled; + +int bpf_map_new_fd(struct bpf_map *map); +int bpf_prog_new_fd(struct bpf_prog *prog); + +int bpf_obj_pin_user(u32 ufd, const char __user *pathname); +int bpf_obj_get_user(const char __user *pathname); + /* verify correctness of eBPF program */ int bpf_check(struct bpf_prog **fp, union bpf_attr *attr); #else @@ -160,5 +206,16 @@ extern const struct bpf_func_proto bpf_map_delete_elem_proto; extern const struct bpf_func_proto bpf_get_prandom_u32_proto; extern const struct bpf_func_proto bpf_get_smp_processor_id_proto; +extern const struct bpf_func_proto bpf_tail_call_proto; +extern const struct bpf_func_proto bpf_ktime_get_ns_proto; +extern const struct bpf_func_proto bpf_get_current_pid_tgid_proto; +extern const struct bpf_func_proto bpf_get_current_uid_gid_proto; +extern const struct bpf_func_proto bpf_get_current_comm_proto; +extern const struct bpf_func_proto bpf_skb_vlan_push_proto; +extern const struct bpf_func_proto bpf_skb_vlan_pop_proto; + +/* Shared helpers among cBPF and eBPF. */ +void bpf_user_rnd_init_once(void); +u64 bpf_user_rnd_u32(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); #endif /* _LINUX_BPF_H */ diff --git a/kernel/include/linux/brcmphy.h b/kernel/include/linux/brcmphy.h index 656da2a12..59f4a7304 100644 --- a/kernel/include/linux/brcmphy.h +++ b/kernel/include/linux/brcmphy.h @@ -1,6 +1,13 @@ #ifndef _LINUX_BRCMPHY_H #define _LINUX_BRCMPHY_H +#include <linux/phy.h> + +/* All Broadcom Ethernet switches have a pseudo-PHY at address 30 which is used + * to configure the switch internal registers via MDIO accesses. + */ +#define BRCM_PSEUDO_PHY_ADDR 30 + #define PHY_ID_BCM50610 0x0143bd60 #define PHY_ID_BCM50610M 0x0143bd70 #define PHY_ID_BCM5241 0x0143bc30 @@ -23,6 +30,8 @@ #define PHY_ID_BCM7439_2 0xae025080 #define PHY_ID_BCM7445 0x600d8510 +#define PHY_ID_BCM_CYGNUS 0xae025200 + #define PHY_BCM_OUI_MASK 0xfffffc00 #define PHY_BCM_OUI_1 0x00206000 #define PHY_BCM_OUI_2 0x0143bc00 @@ -131,7 +140,10 @@ /* 01010: Auto Power-Down */ #define BCM54XX_SHD_APD 0x0a +#define BCM_APD_CLR_MASK 0xFE9F /* clear bits 5, 6 & 8 */ #define BCM54XX_SHD_APD_EN 0x0020 +#define BCM_NO_ANEG_APD_EN 0x0060 /* bits 5 & 6 */ +#define BCM_APD_SINGLELP_EN 0x0100 /* Bit 8 */ #define BCM5482_SHD_LEDS1 0x0d /* 01101: LED Selector 1 */ /* LED3 / ~LINKSPD[2] selector */ @@ -202,27 +214,13 @@ #define MII_BRCM_FET_SHDW_AUXSTAT2 0x1b /* Auxiliary status 2 */ #define MII_BRCM_FET_SHDW_AS2_APDE 0x0020 /* Auto power down enable */ -/* - * Indirect register access functions for the 1000BASE-T/100BASE-TX/10BASE-T - * 0x1c shadow registers. - */ -static inline int bcm54xx_shadow_read(struct phy_device *phydev, u16 shadow) -{ - phy_write(phydev, MII_BCM54XX_SHD, MII_BCM54XX_SHD_VAL(shadow)); - return MII_BCM54XX_SHD_DATA(phy_read(phydev, MII_BCM54XX_SHD)); -} - -static inline int bcm54xx_shadow_write(struct phy_device *phydev, u16 shadow, - u16 val) -{ - return phy_write(phydev, MII_BCM54XX_SHD, - MII_BCM54XX_SHD_WRITE | - MII_BCM54XX_SHD_VAL(shadow) | - MII_BCM54XX_SHD_DATA(val)); -} - #define BRCM_CL45VEN_EEE_CONTROL 0x803d #define LPI_FEATURE_EN 0x8000 #define LPI_FEATURE_EN_DIG1000X 0x4000 +/* Core register definitions*/ +#define MII_BRCM_CORE_BASE1E 0x1E +#define MII_BRCM_CORE_EXPB0 0xB0 +#define MII_BRCM_CORE_EXPB1 0xB1 + #endif /* _LINUX_BRCMPHY_H */ diff --git a/kernel/include/linux/buffer_head.h b/kernel/include/linux/buffer_head.h index 6d25afd8b..4a201008b 100644 --- a/kernel/include/linux/buffer_head.h +++ b/kernel/include/linux/buffer_head.h @@ -77,8 +77,7 @@ struct buffer_head { atomic_t b_count; /* users using this buffer_head */ #ifdef CONFIG_PREEMPT_RT_BASE spinlock_t b_uptodate_lock; -#if defined(CONFIG_JBD) || defined(CONFIG_JBD_MODULE) || \ - defined(CONFIG_JBD2) || defined(CONFIG_JBD2_MODULE) +#if IS_ENABLED(CONFIG_JBD2) spinlock_t b_state_lock; spinlock_t b_journal_head_lock; #endif @@ -113,8 +112,7 @@ static inline void buffer_head_init_locks(struct buffer_head *bh) { #ifdef CONFIG_PREEMPT_RT_BASE spin_lock_init(&bh->b_uptodate_lock); -#if defined(CONFIG_JBD) || defined(CONFIG_JBD_MODULE) || \ - defined(CONFIG_JBD2) || defined(CONFIG_JBD2_MODULE) +#if IS_ENABLED(CONFIG_JBD2) spin_lock_init(&bh->b_state_lock); spin_lock_init(&bh->b_journal_head_lock); #endif @@ -271,8 +269,6 @@ int cont_write_begin(struct file *, struct address_space *, loff_t, get_block_t *, loff_t *); int generic_cont_expand_simple(struct inode *inode, loff_t size); int block_commit_write(struct page *page, unsigned from, unsigned to); -int __block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf, - get_block_t get_block); int block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf, get_block_t get_block); /* Convert errno to return value from ->page_mkwrite() call */ diff --git a/kernel/include/linux/cacheinfo.h b/kernel/include/linux/cacheinfo.h index 3daf5ed39..218993507 100644 --- a/kernel/include/linux/cacheinfo.h +++ b/kernel/include/linux/cacheinfo.h @@ -19,7 +19,7 @@ enum cache_type { /** * struct cacheinfo - represent a cache leaf node * @type: type of the cache - data, inst or unified - * @level: represents the hierarcy in the multi-level cache + * @level: represents the hierarchy in the multi-level cache * @coherency_line_size: size of each cache line usually representing * the minimum amount of data that gets transferred from memory * @number_of_sets: total number of sets, a set is a collection of cache diff --git a/kernel/include/linux/can/dev.h b/kernel/include/linux/can/dev.h index c3a9c8fc6..735f9f8c4 100644 --- a/kernel/include/linux/can/dev.h +++ b/kernel/include/linux/can/dev.h @@ -14,9 +14,10 @@ #define _CAN_DEV_H #include <linux/can.h> -#include <linux/can/netlink.h> #include <linux/can/error.h> #include <linux/can/led.h> +#include <linux/can/netlink.h> +#include <linux/netdevice.h> /* * CAN mode @@ -77,7 +78,7 @@ struct can_priv { #define get_canfd_dlc(i) (min_t(__u8, (i), CANFD_MAX_DLC)) /* Drop a given socketbuffer if it does not contain a valid CAN frame. */ -static inline int can_dropped_invalid_skb(struct net_device *dev, +static inline bool can_dropped_invalid_skb(struct net_device *dev, struct sk_buff *skb) { const struct canfd_frame *cfd = (struct canfd_frame *)skb->data; @@ -93,12 +94,12 @@ static inline int can_dropped_invalid_skb(struct net_device *dev, } else goto inval_skb; - return 0; + return false; inval_skb: kfree_skb(skb); dev->stats.tx_dropped++; - return 1; + return true; } static inline bool can_is_canfd_skb(const struct sk_buff *skb) diff --git a/kernel/include/linux/can/led.h b/kernel/include/linux/can/led.h index 146de4506..2746f7c2f 100644 --- a/kernel/include/linux/can/led.h +++ b/kernel/include/linux/can/led.h @@ -11,6 +11,7 @@ #include <linux/if.h> #include <linux/leds.h> +#include <linux/netdevice.h> enum can_led_event { CAN_LED_EVENT_OPEN, diff --git a/kernel/include/linux/ceph/ceph_features.h b/kernel/include/linux/ceph/ceph_features.h index 4763ad64e..f89b31d45 100644 --- a/kernel/include/linux/ceph/ceph_features.h +++ b/kernel/include/linux/ceph/ceph_features.h @@ -107,6 +107,7 @@ static inline u64 ceph_sanitize_features(u64 features) CEPH_FEATURE_OSDMAP_ENC | \ CEPH_FEATURE_CRUSH_TUNABLES3 | \ CEPH_FEATURE_OSD_PRIMARY_AFFINITY | \ + CEPH_FEATURE_MSGR_KEEPALIVE2 | \ CEPH_FEATURE_CRUSH_V4) #define CEPH_FEATURES_REQUIRED_DEFAULT \ diff --git a/kernel/include/linux/ceph/libceph.h b/kernel/include/linux/ceph/libceph.h index 30f92cefa..3e3799cdc 100644 --- a/kernel/include/linux/ceph/libceph.h +++ b/kernel/include/linux/ceph/libceph.h @@ -29,8 +29,9 @@ #define CEPH_OPT_NOSHARE (1<<1) /* don't share client with other sbs */ #define CEPH_OPT_MYIP (1<<2) /* specified my ip */ #define CEPH_OPT_NOCRC (1<<3) /* no data crc on writes */ -#define CEPH_OPT_NOMSGAUTH (1<<4) /* not require cephx message signature */ +#define CEPH_OPT_NOMSGAUTH (1<<4) /* don't require msg signing feat */ #define CEPH_OPT_TCP_NODELAY (1<<5) /* TCP_NODELAY on TCP sockets */ +#define CEPH_OPT_NOMSGSIGN (1<<6) /* don't sign msgs */ #define CEPH_OPT_DEFAULT (CEPH_OPT_TCP_NODELAY) @@ -43,9 +44,10 @@ struct ceph_options { int flags; struct ceph_fsid fsid; struct ceph_entity_addr my_addr; - int mount_timeout; - int osd_idle_ttl; - int osd_keepalive_timeout; + unsigned long mount_timeout; /* jiffies */ + unsigned long osd_idle_ttl; /* jiffies */ + unsigned long osd_keepalive_timeout; /* jiffies */ + unsigned long monc_ping_timeout; /* jiffies */ /* * any type that can't be simply compared or doesn't need need @@ -63,9 +65,10 @@ struct ceph_options { /* * defaults */ -#define CEPH_MOUNT_TIMEOUT_DEFAULT 60 -#define CEPH_OSD_KEEPALIVE_DEFAULT 5 -#define CEPH_OSD_IDLE_TTL_DEFAULT 60 +#define CEPH_MOUNT_TIMEOUT_DEFAULT msecs_to_jiffies(60 * 1000) +#define CEPH_OSD_KEEPALIVE_DEFAULT msecs_to_jiffies(5 * 1000) +#define CEPH_OSD_IDLE_TTL_DEFAULT msecs_to_jiffies(60 * 1000) +#define CEPH_MONC_PING_TIMEOUT_DEFAULT msecs_to_jiffies(30 * 1000) #define CEPH_MSG_MAX_FRONT_LEN (16*1024*1024) #define CEPH_MSG_MAX_MIDDLE_LEN (16*1024*1024) @@ -93,13 +96,9 @@ enum { CEPH_MOUNT_SHUTDOWN, }; -/* - * subtract jiffies - */ -static inline unsigned long time_sub(unsigned long a, unsigned long b) +static inline unsigned long ceph_timeout_jiffies(unsigned long timeout) { - BUG_ON(time_after(b, a)); - return (long)a - (long)b; + return timeout ?: MAX_SCHEDULE_TIMEOUT; } struct ceph_mds_client; @@ -139,6 +138,7 @@ struct ceph_client { #endif }; +#define from_msgr(ms) container_of(ms, struct ceph_client, msgr) /* @@ -178,6 +178,7 @@ static inline int calc_pages_for(u64 off, u64 len) extern struct kmem_cache *ceph_inode_cachep; extern struct kmem_cache *ceph_cap_cachep; +extern struct kmem_cache *ceph_cap_flush_cachep; extern struct kmem_cache *ceph_dentry_cachep; extern struct kmem_cache *ceph_file_cachep; diff --git a/kernel/include/linux/ceph/messenger.h b/kernel/include/linux/ceph/messenger.h index e15499422..8dbd7879f 100644 --- a/kernel/include/linux/ceph/messenger.h +++ b/kernel/include/linux/ceph/messenger.h @@ -8,6 +8,7 @@ #include <linux/radix-tree.h> #include <linux/uio.h> #include <linux/workqueue.h> +#include <net/net_namespace.h> #include <linux/ceph/types.h> #include <linux/ceph/buffer.h> @@ -42,10 +43,9 @@ struct ceph_connection_operations { struct ceph_msg * (*alloc_msg) (struct ceph_connection *con, struct ceph_msg_header *hdr, int *skip); - int (*sign_message) (struct ceph_connection *con, struct ceph_msg *msg); - int (*check_message_signature) (struct ceph_connection *con, - struct ceph_msg *msg); + int (*sign_message) (struct ceph_msg *msg); + int (*check_message_signature) (struct ceph_msg *msg); }; /* use format string %s%d */ @@ -56,8 +56,7 @@ struct ceph_messenger { struct ceph_entity_addr my_enc_addr; atomic_t stopping; - bool nocrc; - bool tcp_nodelay; + possible_net_t net; /* * the global_seq counts connections i (attempt to) initiate @@ -65,9 +64,6 @@ struct ceph_messenger { */ u32 global_seq; spinlock_t global_seq_lock; - - u64 supported_features; - u64 required_features; }; enum ceph_msg_data_type { @@ -224,6 +220,7 @@ struct ceph_connection { struct ceph_entity_addr actual_peer_addr; /* message out temps */ + struct ceph_msg_header out_hdr; struct ceph_msg *out_msg; /* sending message (== tail of out_sent) */ bool out_msg_done; @@ -233,9 +230,10 @@ struct ceph_connection { int out_kvec_left; /* kvec's left in out_kvec */ int out_skip; /* skip this many bytes */ int out_kvec_bytes; /* total bytes left */ - bool out_kvec_is_msg; /* kvec refers to out_msg */ int out_more; /* there is more data after the kvecs */ __le64 out_temp_ack; /* for writing an ack */ + struct ceph_timespec out_temp_keepalive2; /* for writing keepalive2 + stamp */ /* message in temps */ struct ceph_msg_header in_hdr; @@ -246,6 +244,8 @@ struct ceph_connection { int in_base_pos; /* bytes read */ __le64 in_temp_ack; /* for reading an ack */ + struct timespec last_keepalive_ack; /* keepalive2 ack stamp */ + struct delayed_work work; /* send|recv work */ unsigned long delay; /* current delay interval */ }; @@ -262,11 +262,8 @@ extern void ceph_msgr_exit(void); extern void ceph_msgr_flush(void); extern void ceph_messenger_init(struct ceph_messenger *msgr, - struct ceph_entity_addr *myaddr, - u64 supported_features, - u64 required_features, - bool nocrc, - bool tcp_nodelay); + struct ceph_entity_addr *myaddr); +extern void ceph_messenger_fini(struct ceph_messenger *msgr); extern void ceph_con_init(struct ceph_connection *con, void *private, const struct ceph_connection_operations *ops, @@ -282,6 +279,8 @@ extern void ceph_msg_revoke(struct ceph_msg *msg); extern void ceph_msg_revoke_incoming(struct ceph_msg *msg); extern void ceph_con_keepalive(struct ceph_connection *con); +extern bool ceph_con_keepalive_expired(struct ceph_connection *con, + unsigned long interval); extern void ceph_msg_data_add_pages(struct ceph_msg *msg, struct page **pages, size_t length, size_t alignment); diff --git a/kernel/include/linux/ceph/msgr.h b/kernel/include/linux/ceph/msgr.h index 1c1887206..0fe2656ac 100644 --- a/kernel/include/linux/ceph/msgr.h +++ b/kernel/include/linux/ceph/msgr.h @@ -84,10 +84,12 @@ struct ceph_entity_inst { #define CEPH_MSGR_TAG_MSG 7 /* message */ #define CEPH_MSGR_TAG_ACK 8 /* message ack */ #define CEPH_MSGR_TAG_KEEPALIVE 9 /* just a keepalive byte! */ -#define CEPH_MSGR_TAG_BADPROTOVER 10 /* bad protocol version */ +#define CEPH_MSGR_TAG_BADPROTOVER 10 /* bad protocol version */ #define CEPH_MSGR_TAG_BADAUTHORIZER 11 /* bad authorizer */ #define CEPH_MSGR_TAG_FEATURES 12 /* insufficient features */ #define CEPH_MSGR_TAG_SEQ 13 /* 64-bit int follows with seen seq number */ +#define CEPH_MSGR_TAG_KEEPALIVE2 14 /* keepalive2 byte + ceph_timespec */ +#define CEPH_MSGR_TAG_KEEPALIVE2_ACK 15 /* keepalive2 reply */ /* diff --git a/kernel/include/linux/ceph/osd_client.h b/kernel/include/linux/ceph/osd_client.h index 61b19c46b..7506b485b 100644 --- a/kernel/include/linux/ceph/osd_client.h +++ b/kernel/include/linux/ceph/osd_client.h @@ -249,7 +249,7 @@ extern void ceph_osdc_handle_map(struct ceph_osd_client *osdc, struct ceph_msg *msg); extern void osd_req_op_init(struct ceph_osd_request *osd_req, - unsigned int which, u16 opcode); + unsigned int which, u16 opcode, u32 flags); extern void osd_req_op_raw_data_in_pages(struct ceph_osd_request *, unsigned int which, diff --git a/kernel/include/linux/cgroup-defs.h b/kernel/include/linux/cgroup-defs.h new file mode 100644 index 000000000..63f0063c0 --- /dev/null +++ b/kernel/include/linux/cgroup-defs.h @@ -0,0 +1,532 @@ +/* + * linux/cgroup-defs.h - basic definitions for cgroup + * + * This file provides basic type and interface. Include this file directly + * only if necessary to avoid cyclic dependencies. + */ +#ifndef _LINUX_CGROUP_DEFS_H +#define _LINUX_CGROUP_DEFS_H + +#include <linux/limits.h> +#include <linux/list.h> +#include <linux/idr.h> +#include <linux/wait.h> +#include <linux/mutex.h> +#include <linux/rcupdate.h> +#include <linux/percpu-refcount.h> +#include <linux/percpu-rwsem.h> +#include <linux/workqueue.h> +#include <linux/work-simple.h> + +#ifdef CONFIG_CGROUPS + +struct cgroup; +struct cgroup_root; +struct cgroup_subsys; +struct cgroup_taskset; +struct kernfs_node; +struct kernfs_ops; +struct kernfs_open_file; +struct seq_file; + +#define MAX_CGROUP_TYPE_NAMELEN 32 +#define MAX_CGROUP_ROOT_NAMELEN 64 +#define MAX_CFTYPE_NAME 64 + +/* define the enumeration of all cgroup subsystems */ +#define SUBSYS(_x) _x ## _cgrp_id, +#define SUBSYS_TAG(_t) CGROUP_ ## _t, \ + __unused_tag_ ## _t = CGROUP_ ## _t - 1, +enum cgroup_subsys_id { +#include <linux/cgroup_subsys.h> + CGROUP_SUBSYS_COUNT, +}; +#undef SUBSYS_TAG +#undef SUBSYS + +#define CGROUP_CANFORK_COUNT (CGROUP_CANFORK_END - CGROUP_CANFORK_START) + +/* bits in struct cgroup_subsys_state flags field */ +enum { + CSS_NO_REF = (1 << 0), /* no reference counting for this css */ + CSS_ONLINE = (1 << 1), /* between ->css_online() and ->css_offline() */ + CSS_RELEASED = (1 << 2), /* refcnt reached zero, released */ +}; + +/* bits in struct cgroup flags field */ +enum { + /* Control Group requires release notifications to userspace */ + CGRP_NOTIFY_ON_RELEASE, + /* + * Clone the parent's configuration when creating a new child + * cpuset cgroup. For historical reasons, this option can be + * specified at mount time and thus is implemented here. + */ + CGRP_CPUSET_CLONE_CHILDREN, +}; + +/* cgroup_root->flags */ +enum { + CGRP_ROOT_SANE_BEHAVIOR = (1 << 0), /* __DEVEL__sane_behavior specified */ + CGRP_ROOT_NOPREFIX = (1 << 1), /* mounted subsystems have no named prefix */ + CGRP_ROOT_XATTR = (1 << 2), /* supports extended attributes */ +}; + +/* cftype->flags */ +enum { + CFTYPE_ONLY_ON_ROOT = (1 << 0), /* only create on root cgrp */ + CFTYPE_NOT_ON_ROOT = (1 << 1), /* don't create on root cgrp */ + CFTYPE_NO_PREFIX = (1 << 3), /* (DON'T USE FOR NEW FILES) no subsys prefix */ + CFTYPE_WORLD_WRITABLE = (1 << 4), /* (DON'T USE FOR NEW FILES) S_IWUGO */ + + /* internal flags, do not use outside cgroup core proper */ + __CFTYPE_ONLY_ON_DFL = (1 << 16), /* only on default hierarchy */ + __CFTYPE_NOT_ON_DFL = (1 << 17), /* not on default hierarchy */ +}; + +/* + * cgroup_file is the handle for a file instance created in a cgroup which + * is used, for example, to generate file changed notifications. This can + * be obtained by setting cftype->file_offset. + */ +struct cgroup_file { + /* do not access any fields from outside cgroup core */ + struct kernfs_node *kn; +}; + +/* + * Per-subsystem/per-cgroup state maintained by the system. This is the + * fundamental structural building block that controllers deal with. + * + * Fields marked with "PI:" are public and immutable and may be accessed + * directly without synchronization. + */ +struct cgroup_subsys_state { + /* PI: the cgroup that this css is attached to */ + struct cgroup *cgroup; + + /* PI: the cgroup subsystem that this css is attached to */ + struct cgroup_subsys *ss; + + /* reference count - access via css_[try]get() and css_put() */ + struct percpu_ref refcnt; + + /* PI: the parent css */ + struct cgroup_subsys_state *parent; + + /* siblings list anchored at the parent's ->children */ + struct list_head sibling; + struct list_head children; + + /* + * PI: Subsys-unique ID. 0 is unused and root is always 1. The + * matching css can be looked up using css_from_id(). + */ + int id; + + unsigned int flags; + + /* + * Monotonically increasing unique serial number which defines a + * uniform order among all csses. It's guaranteed that all + * ->children lists are in the ascending order of ->serial_nr and + * used to allow interrupting and resuming iterations. + */ + u64 serial_nr; + + /* + * Incremented by online self and children. Used to guarantee that + * parents are not offlined before their children. + */ + atomic_t online_cnt; + + /* percpu_ref killing and RCU release */ + struct rcu_head rcu_head; + struct work_struct destroy_work; + struct swork_event destroy_swork; +}; + +/* + * A css_set is a structure holding pointers to a set of + * cgroup_subsys_state objects. This saves space in the task struct + * object and speeds up fork()/exit(), since a single inc/dec and a + * list_add()/del() can bump the reference count on the entire cgroup + * set for a task. + */ +struct css_set { + /* Reference count */ + atomic_t refcount; + + /* + * List running through all cgroup groups in the same hash + * slot. Protected by css_set_lock + */ + struct hlist_node hlist; + + /* + * Lists running through all tasks using this cgroup group. + * mg_tasks lists tasks which belong to this cset but are in the + * process of being migrated out or in. Protected by + * css_set_rwsem, but, during migration, once tasks are moved to + * mg_tasks, it can be read safely while holding cgroup_mutex. + */ + struct list_head tasks; + struct list_head mg_tasks; + + /* + * List of cgrp_cset_links pointing at cgroups referenced from this + * css_set. Protected by css_set_lock. + */ + struct list_head cgrp_links; + + /* the default cgroup associated with this css_set */ + struct cgroup *dfl_cgrp; + + /* + * Set of subsystem states, one for each subsystem. This array is + * immutable after creation apart from the init_css_set during + * subsystem registration (at boot time). + */ + struct cgroup_subsys_state *subsys[CGROUP_SUBSYS_COUNT]; + + /* + * List of csets participating in the on-going migration either as + * source or destination. Protected by cgroup_mutex. + */ + struct list_head mg_preload_node; + struct list_head mg_node; + + /* + * If this cset is acting as the source of migration the following + * two fields are set. mg_src_cgrp is the source cgroup of the + * on-going migration and mg_dst_cset is the destination cset the + * target tasks on this cset should be migrated to. Protected by + * cgroup_mutex. + */ + struct cgroup *mg_src_cgrp; + struct css_set *mg_dst_cset; + + /* + * On the default hierarhcy, ->subsys[ssid] may point to a css + * attached to an ancestor instead of the cgroup this css_set is + * associated with. The following node is anchored at + * ->subsys[ssid]->cgroup->e_csets[ssid] and provides a way to + * iterate through all css's attached to a given cgroup. + */ + struct list_head e_cset_node[CGROUP_SUBSYS_COUNT]; + + /* all css_task_iters currently walking this cset */ + struct list_head task_iters; + + /* For RCU-protected deletion */ + struct rcu_head rcu_head; +}; + +struct cgroup { + /* self css with NULL ->ss, points back to this cgroup */ + struct cgroup_subsys_state self; + + unsigned long flags; /* "unsigned long" so bitops work */ + + /* + * idr allocated in-hierarchy ID. + * + * ID 0 is not used, the ID of the root cgroup is always 1, and a + * new cgroup will be assigned with a smallest available ID. + * + * Allocating/Removing ID must be protected by cgroup_mutex. + */ + int id; + + /* + * Each non-empty css_set associated with this cgroup contributes + * one to populated_cnt. All children with non-zero popuplated_cnt + * of their own contribute one. The count is zero iff there's no + * task in this cgroup or its subtree. + */ + int populated_cnt; + + struct kernfs_node *kn; /* cgroup kernfs entry */ + struct cgroup_file procs_file; /* handle for "cgroup.procs" */ + struct cgroup_file events_file; /* handle for "cgroup.events" */ + + /* + * The bitmask of subsystems enabled on the child cgroups. + * ->subtree_control is the one configured through + * "cgroup.subtree_control" while ->child_subsys_mask is the + * effective one which may have more subsystems enabled. + * Controller knobs are made available iff it's enabled in + * ->subtree_control. + */ + unsigned int subtree_control; + unsigned int child_subsys_mask; + + /* Private pointers for each registered subsystem */ + struct cgroup_subsys_state __rcu *subsys[CGROUP_SUBSYS_COUNT]; + + struct cgroup_root *root; + + /* + * List of cgrp_cset_links pointing at css_sets with tasks in this + * cgroup. Protected by css_set_lock. + */ + struct list_head cset_links; + + /* + * On the default hierarchy, a css_set for a cgroup with some + * susbsys disabled will point to css's which are associated with + * the closest ancestor which has the subsys enabled. The + * following lists all css_sets which point to this cgroup's css + * for the given subsystem. + */ + struct list_head e_csets[CGROUP_SUBSYS_COUNT]; + + /* + * list of pidlists, up to two for each namespace (one for procs, one + * for tasks); created on demand. + */ + struct list_head pidlists; + struct mutex pidlist_mutex; + + /* used to wait for offlining of csses */ + wait_queue_head_t offline_waitq; + + /* used to schedule release agent */ + struct work_struct release_agent_work; +}; + +/* + * A cgroup_root represents the root of a cgroup hierarchy, and may be + * associated with a kernfs_root to form an active hierarchy. This is + * internal to cgroup core. Don't access directly from controllers. + */ +struct cgroup_root { + struct kernfs_root *kf_root; + + /* The bitmask of subsystems attached to this hierarchy */ + unsigned int subsys_mask; + + /* Unique id for this hierarchy. */ + int hierarchy_id; + + /* The root cgroup. Root is destroyed on its release. */ + struct cgroup cgrp; + + /* Number of cgroups in the hierarchy, used only for /proc/cgroups */ + atomic_t nr_cgrps; + + /* A list running through the active hierarchies */ + struct list_head root_list; + + /* Hierarchy-specific flags */ + unsigned int flags; + + /* IDs for cgroups in this hierarchy */ + struct idr cgroup_idr; + + /* The path to use for release notifications. */ + char release_agent_path[PATH_MAX]; + + /* The name for this hierarchy - may be empty */ + char name[MAX_CGROUP_ROOT_NAMELEN]; +}; + +/* + * struct cftype: handler definitions for cgroup control files + * + * When reading/writing to a file: + * - the cgroup to use is file->f_path.dentry->d_parent->d_fsdata + * - the 'cftype' of the file is file->f_path.dentry->d_fsdata + */ +struct cftype { + /* + * By convention, the name should begin with the name of the + * subsystem, followed by a period. Zero length string indicates + * end of cftype array. + */ + char name[MAX_CFTYPE_NAME]; + unsigned long private; + + /* + * The maximum length of string, excluding trailing nul, that can + * be passed to write. If < PAGE_SIZE-1, PAGE_SIZE-1 is assumed. + */ + size_t max_write_len; + + /* CFTYPE_* flags */ + unsigned int flags; + + /* + * If non-zero, should contain the offset from the start of css to + * a struct cgroup_file field. cgroup will record the handle of + * the created file into it. The recorded handle can be used as + * long as the containing css remains accessible. + */ + unsigned int file_offset; + + /* + * Fields used for internal bookkeeping. Initialized automatically + * during registration. + */ + struct cgroup_subsys *ss; /* NULL for cgroup core files */ + struct list_head node; /* anchored at ss->cfts */ + struct kernfs_ops *kf_ops; + + /* + * read_u64() is a shortcut for the common case of returning a + * single integer. Use it in place of read() + */ + u64 (*read_u64)(struct cgroup_subsys_state *css, struct cftype *cft); + /* + * read_s64() is a signed version of read_u64() + */ + s64 (*read_s64)(struct cgroup_subsys_state *css, struct cftype *cft); + + /* generic seq_file read interface */ + int (*seq_show)(struct seq_file *sf, void *v); + + /* optional ops, implement all or none */ + void *(*seq_start)(struct seq_file *sf, loff_t *ppos); + void *(*seq_next)(struct seq_file *sf, void *v, loff_t *ppos); + void (*seq_stop)(struct seq_file *sf, void *v); + + /* + * write_u64() is a shortcut for the common case of accepting + * a single integer (as parsed by simple_strtoull) from + * userspace. Use in place of write(); return 0 or error. + */ + int (*write_u64)(struct cgroup_subsys_state *css, struct cftype *cft, + u64 val); + /* + * write_s64() is a signed version of write_u64() + */ + int (*write_s64)(struct cgroup_subsys_state *css, struct cftype *cft, + s64 val); + + /* + * write() is the generic write callback which maps directly to + * kernfs write operation and overrides all other operations. + * Maximum write size is determined by ->max_write_len. Use + * of_css/cft() to access the associated css and cft. + */ + ssize_t (*write)(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off); + +#ifdef CONFIG_DEBUG_LOCK_ALLOC + struct lock_class_key lockdep_key; +#endif +}; + +/* + * Control Group subsystem type. + * See Documentation/cgroups/cgroups.txt for details + */ +struct cgroup_subsys { + struct cgroup_subsys_state *(*css_alloc)(struct cgroup_subsys_state *parent_css); + int (*css_online)(struct cgroup_subsys_state *css); + void (*css_offline)(struct cgroup_subsys_state *css); + void (*css_released)(struct cgroup_subsys_state *css); + void (*css_free)(struct cgroup_subsys_state *css); + void (*css_reset)(struct cgroup_subsys_state *css); + void (*css_e_css_changed)(struct cgroup_subsys_state *css); + + int (*can_attach)(struct cgroup_taskset *tset); + void (*cancel_attach)(struct cgroup_taskset *tset); + void (*attach)(struct cgroup_taskset *tset); + int (*can_fork)(struct task_struct *task, void **priv_p); + void (*cancel_fork)(struct task_struct *task, void *priv); + void (*fork)(struct task_struct *task, void *priv); + void (*exit)(struct task_struct *task); + void (*free)(struct task_struct *task); + void (*bind)(struct cgroup_subsys_state *root_css); + + int early_init; + + /* + * If %false, this subsystem is properly hierarchical - + * configuration, resource accounting and restriction on a parent + * cgroup cover those of its children. If %true, hierarchy support + * is broken in some ways - some subsystems ignore hierarchy + * completely while others are only implemented half-way. + * + * It's now disallowed to create nested cgroups if the subsystem is + * broken and cgroup core will emit a warning message on such + * cases. Eventually, all subsystems will be made properly + * hierarchical and this will go away. + */ + bool broken_hierarchy; + bool warned_broken_hierarchy; + + /* the following two fields are initialized automtically during boot */ + int id; + const char *name; + + /* optional, initialized automatically during boot if not set */ + const char *legacy_name; + + /* link to parent, protected by cgroup_lock() */ + struct cgroup_root *root; + + /* idr for css->id */ + struct idr css_idr; + + /* + * List of cftypes. Each entry is the first entry of an array + * terminated by zero length name. + */ + struct list_head cfts; + + /* + * Base cftypes which are automatically registered. The two can + * point to the same array. + */ + struct cftype *dfl_cftypes; /* for the default hierarchy */ + struct cftype *legacy_cftypes; /* for the legacy hierarchies */ + + /* + * A subsystem may depend on other subsystems. When such subsystem + * is enabled on a cgroup, the depended-upon subsystems are enabled + * together if available. Subsystems enabled due to dependency are + * not visible to userland until explicitly enabled. The following + * specifies the mask of subsystems that this one depends on. + */ + unsigned int depends_on; +}; + +extern struct percpu_rw_semaphore cgroup_threadgroup_rwsem; + +/** + * cgroup_threadgroup_change_begin - threadgroup exclusion for cgroups + * @tsk: target task + * + * Called from threadgroup_change_begin() and allows cgroup operations to + * synchronize against threadgroup changes using a percpu_rw_semaphore. + */ +static inline void cgroup_threadgroup_change_begin(struct task_struct *tsk) +{ + percpu_down_read(&cgroup_threadgroup_rwsem); +} + +/** + * cgroup_threadgroup_change_end - threadgroup exclusion for cgroups + * @tsk: target task + * + * Called from threadgroup_change_end(). Counterpart of + * cgroup_threadcgroup_change_begin(). + */ +static inline void cgroup_threadgroup_change_end(struct task_struct *tsk) +{ + percpu_up_read(&cgroup_threadgroup_rwsem); +} + +#else /* CONFIG_CGROUPS */ + +#define CGROUP_CANFORK_COUNT 0 +#define CGROUP_SUBSYS_COUNT 0 + +static inline void cgroup_threadgroup_change_begin(struct task_struct *tsk) {} +static inline void cgroup_threadgroup_change_end(struct task_struct *tsk) {} + +#endif /* CONFIG_CGROUPS */ + +#endif /* _LINUX_CGROUP_DEFS_H */ diff --git a/kernel/include/linux/cgroup.h b/kernel/include/linux/cgroup.h index 3bd502178..cb91b44f5 100644 --- a/kernel/include/linux/cgroup.h +++ b/kernel/include/linux/cgroup.h @@ -11,96 +11,273 @@ #include <linux/sched.h> #include <linux/cpumask.h> #include <linux/nodemask.h> -#include <linux/rcupdate.h> #include <linux/rculist.h> #include <linux/cgroupstats.h> -#include <linux/rwsem.h> -#include <linux/idr.h> -#include <linux/workqueue.h> #include <linux/fs.h> -#include <linux/percpu-refcount.h> #include <linux/seq_file.h> #include <linux/kernfs.h> -#include <linux/wait.h> -#include <linux/work-simple.h> +#include <linux/jump_label.h> + +#include <linux/cgroup-defs.h> #ifdef CONFIG_CGROUPS -struct cgroup_root; -struct cgroup_subsys; -struct cgroup; +/* + * All weight knobs on the default hierarhcy should use the following min, + * default and max values. The default value is the logarithmic center of + * MIN and MAX and allows 100x to be expressed in both directions. + */ +#define CGROUP_WEIGHT_MIN 1 +#define CGROUP_WEIGHT_DFL 100 +#define CGROUP_WEIGHT_MAX 10000 -extern int cgroup_init_early(void); -extern int cgroup_init(void); -extern void cgroup_fork(struct task_struct *p); -extern void cgroup_post_fork(struct task_struct *p); -extern void cgroup_exit(struct task_struct *p); -extern int cgroupstats_build(struct cgroupstats *stats, - struct dentry *dentry); +/* a css_task_iter should be treated as an opaque object */ +struct css_task_iter { + struct cgroup_subsys *ss; -extern int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns, - struct pid *pid, struct task_struct *tsk); + struct list_head *cset_pos; + struct list_head *cset_head; -/* define the enumeration of all cgroup subsystems */ -#define SUBSYS(_x) _x ## _cgrp_id, -enum cgroup_subsys_id { -#include <linux/cgroup_subsys.h> - CGROUP_SUBSYS_COUNT, + struct list_head *task_pos; + struct list_head *tasks_head; + struct list_head *mg_tasks_head; + + struct css_set *cur_cset; + struct task_struct *cur_task; + struct list_head iters_node; /* css_set->task_iters */ }; + +extern struct cgroup_root cgrp_dfl_root; +extern struct css_set init_css_set; + +#define SUBSYS(_x) extern struct cgroup_subsys _x ## _cgrp_subsys; +#include <linux/cgroup_subsys.h> +#undef SUBSYS + +#define SUBSYS(_x) \ + extern struct static_key_true _x ## _cgrp_subsys_enabled_key; \ + extern struct static_key_true _x ## _cgrp_subsys_on_dfl_key; +#include <linux/cgroup_subsys.h> #undef SUBSYS +/** + * cgroup_subsys_enabled - fast test on whether a subsys is enabled + * @ss: subsystem in question + */ +#define cgroup_subsys_enabled(ss) \ + static_branch_likely(&ss ## _enabled_key) + +/** + * cgroup_subsys_on_dfl - fast test on whether a subsys is on default hierarchy + * @ss: subsystem in question + */ +#define cgroup_subsys_on_dfl(ss) \ + static_branch_likely(&ss ## _on_dfl_key) + +bool css_has_online_children(struct cgroup_subsys_state *css); +struct cgroup_subsys_state *css_from_id(int id, struct cgroup_subsys *ss); +struct cgroup_subsys_state *cgroup_get_e_css(struct cgroup *cgroup, + struct cgroup_subsys *ss); +struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry, + struct cgroup_subsys *ss); + +bool cgroup_is_descendant(struct cgroup *cgrp, struct cgroup *ancestor); +int cgroup_attach_task_all(struct task_struct *from, struct task_struct *); +int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from); + +int cgroup_add_dfl_cftypes(struct cgroup_subsys *ss, struct cftype *cfts); +int cgroup_add_legacy_cftypes(struct cgroup_subsys *ss, struct cftype *cfts); +int cgroup_rm_cftypes(struct cftype *cfts); +void cgroup_file_notify(struct cgroup_file *cfile); + +char *task_cgroup_path(struct task_struct *task, char *buf, size_t buflen); +int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry); +int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns, + struct pid *pid, struct task_struct *tsk); + +void cgroup_fork(struct task_struct *p); +extern int cgroup_can_fork(struct task_struct *p, + void *ss_priv[CGROUP_CANFORK_COUNT]); +extern void cgroup_cancel_fork(struct task_struct *p, + void *ss_priv[CGROUP_CANFORK_COUNT]); +extern void cgroup_post_fork(struct task_struct *p, + void *old_ss_priv[CGROUP_CANFORK_COUNT]); +void cgroup_exit(struct task_struct *p); +void cgroup_free(struct task_struct *p); + +int cgroup_init_early(void); +int cgroup_init(void); + /* - * Per-subsystem/per-cgroup state maintained by the system. This is the - * fundamental structural building block that controllers deal with. + * Iteration helpers and macros. + */ + +struct cgroup_subsys_state *css_next_child(struct cgroup_subsys_state *pos, + struct cgroup_subsys_state *parent); +struct cgroup_subsys_state *css_next_descendant_pre(struct cgroup_subsys_state *pos, + struct cgroup_subsys_state *css); +struct cgroup_subsys_state *css_rightmost_descendant(struct cgroup_subsys_state *pos); +struct cgroup_subsys_state *css_next_descendant_post(struct cgroup_subsys_state *pos, + struct cgroup_subsys_state *css); + +struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset, + struct cgroup_subsys_state **dst_cssp); +struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset, + struct cgroup_subsys_state **dst_cssp); + +void css_task_iter_start(struct cgroup_subsys_state *css, + struct css_task_iter *it); +struct task_struct *css_task_iter_next(struct css_task_iter *it); +void css_task_iter_end(struct css_task_iter *it); + +/** + * css_for_each_child - iterate through children of a css + * @pos: the css * to use as the loop cursor + * @parent: css whose children to walk + * + * Walk @parent's children. Must be called under rcu_read_lock(). + * + * If a subsystem synchronizes ->css_online() and the start of iteration, a + * css which finished ->css_online() is guaranteed to be visible in the + * future iterations and will stay visible until the last reference is put. + * A css which hasn't finished ->css_online() or already finished + * ->css_offline() may show up during traversal. It's each subsystem's + * responsibility to synchronize against on/offlining. * - * Fields marked with "PI:" are public and immutable and may be accessed - * directly without synchronization. + * It is allowed to temporarily drop RCU read lock during iteration. The + * caller is responsible for ensuring that @pos remains accessible until + * the start of the next iteration by, for example, bumping the css refcnt. */ -struct cgroup_subsys_state { - /* PI: the cgroup that this css is attached to */ - struct cgroup *cgroup; - - /* PI: the cgroup subsystem that this css is attached to */ - struct cgroup_subsys *ss; - - /* reference count - access via css_[try]get() and css_put() */ - struct percpu_ref refcnt; - - /* PI: the parent css */ - struct cgroup_subsys_state *parent; - - /* siblings list anchored at the parent's ->children */ - struct list_head sibling; - struct list_head children; - - /* - * PI: Subsys-unique ID. 0 is unused and root is always 1. The - * matching css can be looked up using css_from_id(). - */ - int id; - - unsigned int flags; - - /* - * Monotonically increasing unique serial number which defines a - * uniform order among all csses. It's guaranteed that all - * ->children lists are in the ascending order of ->serial_nr and - * used to allow interrupting and resuming iterations. - */ - u64 serial_nr; - - /* percpu_ref killing and RCU release */ - struct rcu_head rcu_head; - struct work_struct destroy_work; - struct swork_event destroy_swork; -}; +#define css_for_each_child(pos, parent) \ + for ((pos) = css_next_child(NULL, (parent)); (pos); \ + (pos) = css_next_child((pos), (parent))) -/* bits in struct cgroup_subsys_state flags field */ -enum { - CSS_NO_REF = (1 << 0), /* no reference counting for this css */ - CSS_ONLINE = (1 << 1), /* between ->css_online() and ->css_offline() */ - CSS_RELEASED = (1 << 2), /* refcnt reached zero, released */ -}; +/** + * css_for_each_descendant_pre - pre-order walk of a css's descendants + * @pos: the css * to use as the loop cursor + * @root: css whose descendants to walk + * + * Walk @root's descendants. @root is included in the iteration and the + * first node to be visited. Must be called under rcu_read_lock(). + * + * If a subsystem synchronizes ->css_online() and the start of iteration, a + * css which finished ->css_online() is guaranteed to be visible in the + * future iterations and will stay visible until the last reference is put. + * A css which hasn't finished ->css_online() or already finished + * ->css_offline() may show up during traversal. It's each subsystem's + * responsibility to synchronize against on/offlining. + * + * For example, the following guarantees that a descendant can't escape + * state updates of its ancestors. + * + * my_online(@css) + * { + * Lock @css's parent and @css; + * Inherit state from the parent; + * Unlock both. + * } + * + * my_update_state(@css) + * { + * css_for_each_descendant_pre(@pos, @css) { + * Lock @pos; + * if (@pos == @css) + * Update @css's state; + * else + * Verify @pos is alive and inherit state from its parent; + * Unlock @pos; + * } + * } + * + * As long as the inheriting step, including checking the parent state, is + * enclosed inside @pos locking, double-locking the parent isn't necessary + * while inheriting. The state update to the parent is guaranteed to be + * visible by walking order and, as long as inheriting operations to the + * same @pos are atomic to each other, multiple updates racing each other + * still result in the correct state. It's guaranateed that at least one + * inheritance happens for any css after the latest update to its parent. + * + * If checking parent's state requires locking the parent, each inheriting + * iteration should lock and unlock both @pos->parent and @pos. + * + * Alternatively, a subsystem may choose to use a single global lock to + * synchronize ->css_online() and ->css_offline() against tree-walking + * operations. + * + * It is allowed to temporarily drop RCU read lock during iteration. The + * caller is responsible for ensuring that @pos remains accessible until + * the start of the next iteration by, for example, bumping the css refcnt. + */ +#define css_for_each_descendant_pre(pos, css) \ + for ((pos) = css_next_descendant_pre(NULL, (css)); (pos); \ + (pos) = css_next_descendant_pre((pos), (css))) + +/** + * css_for_each_descendant_post - post-order walk of a css's descendants + * @pos: the css * to use as the loop cursor + * @css: css whose descendants to walk + * + * Similar to css_for_each_descendant_pre() but performs post-order + * traversal instead. @root is included in the iteration and the last + * node to be visited. + * + * If a subsystem synchronizes ->css_online() and the start of iteration, a + * css which finished ->css_online() is guaranteed to be visible in the + * future iterations and will stay visible until the last reference is put. + * A css which hasn't finished ->css_online() or already finished + * ->css_offline() may show up during traversal. It's each subsystem's + * responsibility to synchronize against on/offlining. + * + * Note that the walk visibility guarantee example described in pre-order + * walk doesn't apply the same to post-order walks. + */ +#define css_for_each_descendant_post(pos, css) \ + for ((pos) = css_next_descendant_post(NULL, (css)); (pos); \ + (pos) = css_next_descendant_post((pos), (css))) + +/** + * cgroup_taskset_for_each - iterate cgroup_taskset + * @task: the loop cursor + * @dst_css: the destination css + * @tset: taskset to iterate + * + * @tset may contain multiple tasks and they may belong to multiple + * processes. + * + * On the v2 hierarchy, there may be tasks from multiple processes and they + * may not share the source or destination csses. + * + * On traditional hierarchies, when there are multiple tasks in @tset, if a + * task of a process is in @tset, all tasks of the process are in @tset. + * Also, all are guaranteed to share the same source and destination csses. + * + * Iteration is not in any specific order. + */ +#define cgroup_taskset_for_each(task, dst_css, tset) \ + for ((task) = cgroup_taskset_first((tset), &(dst_css)); \ + (task); \ + (task) = cgroup_taskset_next((tset), &(dst_css))) + +/** + * cgroup_taskset_for_each_leader - iterate group leaders in a cgroup_taskset + * @leader: the loop cursor + * @dst_css: the destination css + * @tset: takset to iterate + * + * Iterate threadgroup leaders of @tset. For single-task migrations, @tset + * may not contain any. + */ +#define cgroup_taskset_for_each_leader(leader, dst_css, tset) \ + for ((leader) = cgroup_taskset_first((tset), &(dst_css)); \ + (leader); \ + (leader) = cgroup_taskset_next((tset), &(dst_css))) \ + if ((leader) != (leader)->group_leader) \ + ; \ + else + +/* + * Inline functions. + */ /** * css_get - obtain a reference on the specified css @@ -187,532 +364,6 @@ static inline void css_put_many(struct cgroup_subsys_state *css, unsigned int n) percpu_ref_put_many(&css->refcnt, n); } -/* bits in struct cgroup flags field */ -enum { - /* Control Group requires release notifications to userspace */ - CGRP_NOTIFY_ON_RELEASE, - /* - * Clone the parent's configuration when creating a new child - * cpuset cgroup. For historical reasons, this option can be - * specified at mount time and thus is implemented here. - */ - CGRP_CPUSET_CLONE_CHILDREN, -}; - -struct cgroup { - /* self css with NULL ->ss, points back to this cgroup */ - struct cgroup_subsys_state self; - - unsigned long flags; /* "unsigned long" so bitops work */ - - /* - * idr allocated in-hierarchy ID. - * - * ID 0 is not used, the ID of the root cgroup is always 1, and a - * new cgroup will be assigned with a smallest available ID. - * - * Allocating/Removing ID must be protected by cgroup_mutex. - */ - int id; - - /* - * If this cgroup contains any tasks, it contributes one to - * populated_cnt. All children with non-zero popuplated_cnt of - * their own contribute one. The count is zero iff there's no task - * in this cgroup or its subtree. - */ - int populated_cnt; - - struct kernfs_node *kn; /* cgroup kernfs entry */ - struct kernfs_node *populated_kn; /* kn for "cgroup.subtree_populated" */ - - /* - * The bitmask of subsystems enabled on the child cgroups. - * ->subtree_control is the one configured through - * "cgroup.subtree_control" while ->child_subsys_mask is the - * effective one which may have more subsystems enabled. - * Controller knobs are made available iff it's enabled in - * ->subtree_control. - */ - unsigned int subtree_control; - unsigned int child_subsys_mask; - - /* Private pointers for each registered subsystem */ - struct cgroup_subsys_state __rcu *subsys[CGROUP_SUBSYS_COUNT]; - - struct cgroup_root *root; - - /* - * List of cgrp_cset_links pointing at css_sets with tasks in this - * cgroup. Protected by css_set_lock. - */ - struct list_head cset_links; - - /* - * On the default hierarchy, a css_set for a cgroup with some - * susbsys disabled will point to css's which are associated with - * the closest ancestor which has the subsys enabled. The - * following lists all css_sets which point to this cgroup's css - * for the given subsystem. - */ - struct list_head e_csets[CGROUP_SUBSYS_COUNT]; - - /* - * list of pidlists, up to two for each namespace (one for procs, one - * for tasks); created on demand. - */ - struct list_head pidlists; - struct mutex pidlist_mutex; - - /* used to wait for offlining of csses */ - wait_queue_head_t offline_waitq; - - /* used to schedule release agent */ - struct work_struct release_agent_work; -}; - -#define MAX_CGROUP_ROOT_NAMELEN 64 - -/* cgroup_root->flags */ -enum { - CGRP_ROOT_SANE_BEHAVIOR = (1 << 0), /* __DEVEL__sane_behavior specified */ - CGRP_ROOT_NOPREFIX = (1 << 1), /* mounted subsystems have no named prefix */ - CGRP_ROOT_XATTR = (1 << 2), /* supports extended attributes */ -}; - -/* - * A cgroup_root represents the root of a cgroup hierarchy, and may be - * associated with a kernfs_root to form an active hierarchy. This is - * internal to cgroup core. Don't access directly from controllers. - */ -struct cgroup_root { - struct kernfs_root *kf_root; - - /* The bitmask of subsystems attached to this hierarchy */ - unsigned int subsys_mask; - - /* Unique id for this hierarchy. */ - int hierarchy_id; - - /* The root cgroup. Root is destroyed on its release. */ - struct cgroup cgrp; - - /* Number of cgroups in the hierarchy, used only for /proc/cgroups */ - atomic_t nr_cgrps; - - /* A list running through the active hierarchies */ - struct list_head root_list; - - /* Hierarchy-specific flags */ - unsigned int flags; - - /* IDs for cgroups in this hierarchy */ - struct idr cgroup_idr; - - /* The path to use for release notifications. */ - char release_agent_path[PATH_MAX]; - - /* The name for this hierarchy - may be empty */ - char name[MAX_CGROUP_ROOT_NAMELEN]; -}; - -/* - * A css_set is a structure holding pointers to a set of - * cgroup_subsys_state objects. This saves space in the task struct - * object and speeds up fork()/exit(), since a single inc/dec and a - * list_add()/del() can bump the reference count on the entire cgroup - * set for a task. - */ - -struct css_set { - - /* Reference count */ - atomic_t refcount; - - /* - * List running through all cgroup groups in the same hash - * slot. Protected by css_set_lock - */ - struct hlist_node hlist; - - /* - * Lists running through all tasks using this cgroup group. - * mg_tasks lists tasks which belong to this cset but are in the - * process of being migrated out or in. Protected by - * css_set_rwsem, but, during migration, once tasks are moved to - * mg_tasks, it can be read safely while holding cgroup_mutex. - */ - struct list_head tasks; - struct list_head mg_tasks; - - /* - * List of cgrp_cset_links pointing at cgroups referenced from this - * css_set. Protected by css_set_lock. - */ - struct list_head cgrp_links; - - /* the default cgroup associated with this css_set */ - struct cgroup *dfl_cgrp; - - /* - * Set of subsystem states, one for each subsystem. This array is - * immutable after creation apart from the init_css_set during - * subsystem registration (at boot time). - */ - struct cgroup_subsys_state *subsys[CGROUP_SUBSYS_COUNT]; - - /* - * List of csets participating in the on-going migration either as - * source or destination. Protected by cgroup_mutex. - */ - struct list_head mg_preload_node; - struct list_head mg_node; - - /* - * If this cset is acting as the source of migration the following - * two fields are set. mg_src_cgrp is the source cgroup of the - * on-going migration and mg_dst_cset is the destination cset the - * target tasks on this cset should be migrated to. Protected by - * cgroup_mutex. - */ - struct cgroup *mg_src_cgrp; - struct css_set *mg_dst_cset; - - /* - * On the default hierarhcy, ->subsys[ssid] may point to a css - * attached to an ancestor instead of the cgroup this css_set is - * associated with. The following node is anchored at - * ->subsys[ssid]->cgroup->e_csets[ssid] and provides a way to - * iterate through all css's attached to a given cgroup. - */ - struct list_head e_cset_node[CGROUP_SUBSYS_COUNT]; - - /* For RCU-protected deletion */ - struct rcu_head rcu_head; -}; - -/* - * struct cftype: handler definitions for cgroup control files - * - * When reading/writing to a file: - * - the cgroup to use is file->f_path.dentry->d_parent->d_fsdata - * - the 'cftype' of the file is file->f_path.dentry->d_fsdata - */ - -/* cftype->flags */ -enum { - CFTYPE_ONLY_ON_ROOT = (1 << 0), /* only create on root cgrp */ - CFTYPE_NOT_ON_ROOT = (1 << 1), /* don't create on root cgrp */ - CFTYPE_NO_PREFIX = (1 << 3), /* (DON'T USE FOR NEW FILES) no subsys prefix */ - - /* internal flags, do not use outside cgroup core proper */ - __CFTYPE_ONLY_ON_DFL = (1 << 16), /* only on default hierarchy */ - __CFTYPE_NOT_ON_DFL = (1 << 17), /* not on default hierarchy */ -}; - -#define MAX_CFTYPE_NAME 64 - -struct cftype { - /* - * By convention, the name should begin with the name of the - * subsystem, followed by a period. Zero length string indicates - * end of cftype array. - */ - char name[MAX_CFTYPE_NAME]; - int private; - /* - * If not 0, file mode is set to this value, otherwise it will - * be figured out automatically - */ - umode_t mode; - - /* - * The maximum length of string, excluding trailing nul, that can - * be passed to write. If < PAGE_SIZE-1, PAGE_SIZE-1 is assumed. - */ - size_t max_write_len; - - /* CFTYPE_* flags */ - unsigned int flags; - - /* - * Fields used for internal bookkeeping. Initialized automatically - * during registration. - */ - struct cgroup_subsys *ss; /* NULL for cgroup core files */ - struct list_head node; /* anchored at ss->cfts */ - struct kernfs_ops *kf_ops; - - /* - * read_u64() is a shortcut for the common case of returning a - * single integer. Use it in place of read() - */ - u64 (*read_u64)(struct cgroup_subsys_state *css, struct cftype *cft); - /* - * read_s64() is a signed version of read_u64() - */ - s64 (*read_s64)(struct cgroup_subsys_state *css, struct cftype *cft); - - /* generic seq_file read interface */ - int (*seq_show)(struct seq_file *sf, void *v); - - /* optional ops, implement all or none */ - void *(*seq_start)(struct seq_file *sf, loff_t *ppos); - void *(*seq_next)(struct seq_file *sf, void *v, loff_t *ppos); - void (*seq_stop)(struct seq_file *sf, void *v); - - /* - * write_u64() is a shortcut for the common case of accepting - * a single integer (as parsed by simple_strtoull) from - * userspace. Use in place of write(); return 0 or error. - */ - int (*write_u64)(struct cgroup_subsys_state *css, struct cftype *cft, - u64 val); - /* - * write_s64() is a signed version of write_u64() - */ - int (*write_s64)(struct cgroup_subsys_state *css, struct cftype *cft, - s64 val); - - /* - * write() is the generic write callback which maps directly to - * kernfs write operation and overrides all other operations. - * Maximum write size is determined by ->max_write_len. Use - * of_css/cft() to access the associated css and cft. - */ - ssize_t (*write)(struct kernfs_open_file *of, - char *buf, size_t nbytes, loff_t off); - -#ifdef CONFIG_DEBUG_LOCK_ALLOC - struct lock_class_key lockdep_key; -#endif -}; - -extern struct cgroup_root cgrp_dfl_root; -extern struct css_set init_css_set; - -/** - * cgroup_on_dfl - test whether a cgroup is on the default hierarchy - * @cgrp: the cgroup of interest - * - * The default hierarchy is the v2 interface of cgroup and this function - * can be used to test whether a cgroup is on the default hierarchy for - * cases where a subsystem should behave differnetly depending on the - * interface version. - * - * The set of behaviors which change on the default hierarchy are still - * being determined and the mount option is prefixed with __DEVEL__. - * - * List of changed behaviors: - * - * - Mount options "noprefix", "xattr", "clone_children", "release_agent" - * and "name" are disallowed. - * - * - When mounting an existing superblock, mount options should match. - * - * - Remount is disallowed. - * - * - rename(2) is disallowed. - * - * - "tasks" is removed. Everything should be at process granularity. Use - * "cgroup.procs" instead. - * - * - "cgroup.procs" is not sorted. pids will be unique unless they got - * recycled inbetween reads. - * - * - "release_agent" and "notify_on_release" are removed. Replacement - * notification mechanism will be implemented. - * - * - "cgroup.clone_children" is removed. - * - * - "cgroup.subtree_populated" is available. Its value is 0 if the cgroup - * and its descendants contain no task; otherwise, 1. The file also - * generates kernfs notification which can be monitored through poll and - * [di]notify when the value of the file changes. - * - * - cpuset: tasks will be kept in empty cpusets when hotplug happens and - * take masks of ancestors with non-empty cpus/mems, instead of being - * moved to an ancestor. - * - * - cpuset: a task can be moved into an empty cpuset, and again it takes - * masks of ancestors. - * - * - memcg: use_hierarchy is on by default and the cgroup file for the flag - * is not created. - * - * - blkcg: blk-throttle becomes properly hierarchical. - * - * - debug: disallowed on the default hierarchy. - */ -static inline bool cgroup_on_dfl(const struct cgroup *cgrp) -{ - return cgrp->root == &cgrp_dfl_root; -} - -/* no synchronization, the result can only be used as a hint */ -static inline bool cgroup_has_tasks(struct cgroup *cgrp) -{ - return !list_empty(&cgrp->cset_links); -} - -/* returns ino associated with a cgroup */ -static inline ino_t cgroup_ino(struct cgroup *cgrp) -{ - return cgrp->kn->ino; -} - -/* cft/css accessors for cftype->write() operation */ -static inline struct cftype *of_cft(struct kernfs_open_file *of) -{ - return of->kn->priv; -} - -struct cgroup_subsys_state *of_css(struct kernfs_open_file *of); - -/* cft/css accessors for cftype->seq_*() operations */ -static inline struct cftype *seq_cft(struct seq_file *seq) -{ - return of_cft(seq->private); -} - -static inline struct cgroup_subsys_state *seq_css(struct seq_file *seq) -{ - return of_css(seq->private); -} - -/* - * Name / path handling functions. All are thin wrappers around the kernfs - * counterparts and can be called under any context. - */ - -static inline int cgroup_name(struct cgroup *cgrp, char *buf, size_t buflen) -{ - return kernfs_name(cgrp->kn, buf, buflen); -} - -static inline char * __must_check cgroup_path(struct cgroup *cgrp, char *buf, - size_t buflen) -{ - return kernfs_path(cgrp->kn, buf, buflen); -} - -static inline void pr_cont_cgroup_name(struct cgroup *cgrp) -{ - pr_cont_kernfs_name(cgrp->kn); -} - -static inline void pr_cont_cgroup_path(struct cgroup *cgrp) -{ - pr_cont_kernfs_path(cgrp->kn); -} - -char *task_cgroup_path(struct task_struct *task, char *buf, size_t buflen); - -int cgroup_add_dfl_cftypes(struct cgroup_subsys *ss, struct cftype *cfts); -int cgroup_add_legacy_cftypes(struct cgroup_subsys *ss, struct cftype *cfts); -int cgroup_rm_cftypes(struct cftype *cfts); - -bool cgroup_is_descendant(struct cgroup *cgrp, struct cgroup *ancestor); - -/* - * Control Group taskset, used to pass around set of tasks to cgroup_subsys - * methods. - */ -struct cgroup_taskset; -struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset); -struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset); - -/** - * cgroup_taskset_for_each - iterate cgroup_taskset - * @task: the loop cursor - * @tset: taskset to iterate - */ -#define cgroup_taskset_for_each(task, tset) \ - for ((task) = cgroup_taskset_first((tset)); (task); \ - (task) = cgroup_taskset_next((tset))) - -/* - * Control Group subsystem type. - * See Documentation/cgroups/cgroups.txt for details - */ - -struct cgroup_subsys { - struct cgroup_subsys_state *(*css_alloc)(struct cgroup_subsys_state *parent_css); - int (*css_online)(struct cgroup_subsys_state *css); - void (*css_offline)(struct cgroup_subsys_state *css); - void (*css_released)(struct cgroup_subsys_state *css); - void (*css_free)(struct cgroup_subsys_state *css); - void (*css_reset)(struct cgroup_subsys_state *css); - void (*css_e_css_changed)(struct cgroup_subsys_state *css); - - int (*can_attach)(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset); - void (*cancel_attach)(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset); - void (*attach)(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset); - void (*fork)(struct task_struct *task); - void (*exit)(struct cgroup_subsys_state *css, - struct cgroup_subsys_state *old_css, - struct task_struct *task); - void (*bind)(struct cgroup_subsys_state *root_css); - - int disabled; - int early_init; - - /* - * If %false, this subsystem is properly hierarchical - - * configuration, resource accounting and restriction on a parent - * cgroup cover those of its children. If %true, hierarchy support - * is broken in some ways - some subsystems ignore hierarchy - * completely while others are only implemented half-way. - * - * It's now disallowed to create nested cgroups if the subsystem is - * broken and cgroup core will emit a warning message on such - * cases. Eventually, all subsystems will be made properly - * hierarchical and this will go away. - */ - bool broken_hierarchy; - bool warned_broken_hierarchy; - - /* the following two fields are initialized automtically during boot */ - int id; -#define MAX_CGROUP_TYPE_NAMELEN 32 - const char *name; - - /* link to parent, protected by cgroup_lock() */ - struct cgroup_root *root; - - /* idr for css->id */ - struct idr css_idr; - - /* - * List of cftypes. Each entry is the first entry of an array - * terminated by zero length name. - */ - struct list_head cfts; - - /* - * Base cftypes which are automatically registered. The two can - * point to the same array. - */ - struct cftype *dfl_cftypes; /* for the default hierarchy */ - struct cftype *legacy_cftypes; /* for the legacy hierarchies */ - - /* - * A subsystem may depend on other subsystems. When such subsystem - * is enabled on a cgroup, the depended-upon subsystems are enabled - * together if available. Subsystems enabled due to dependency are - * not visible to userland until explicitly enabled. The following - * specifies the mask of subsystems that this one depends on. - */ - unsigned int depends_on; -}; - -#define SUBSYS(_x) extern struct cgroup_subsys _x ## _cgrp_subsys; -#include <linux/cgroup_subsys.h> -#undef SUBSYS - /** * task_css_set_check - obtain a task's css_set with extra access conditions * @task: the task to obtain css_set for @@ -728,11 +379,11 @@ struct cgroup_subsys { */ #ifdef CONFIG_PROVE_RCU extern struct mutex cgroup_mutex; -extern struct rw_semaphore css_set_rwsem; +extern spinlock_t css_set_lock; #define task_css_set_check(task, __c) \ rcu_dereference_check((task)->cgroups, \ lockdep_is_held(&cgroup_mutex) || \ - lockdep_is_held(&css_set_rwsem) || \ + lockdep_is_held(&css_set_lock) || \ ((task)->flags & PF_EXITING) || (__c)) #else #define task_css_set_check(task, __c) \ @@ -776,6 +427,31 @@ static inline struct cgroup_subsys_state *task_css(struct task_struct *task, } /** + * task_get_css - find and get the css for (task, subsys) + * @task: the target task + * @subsys_id: the target subsystem ID + * + * Find the css for the (@task, @subsys_id) combination, increment a + * reference on and return it. This function is guaranteed to return a + * valid css. + */ +static inline struct cgroup_subsys_state * +task_get_css(struct task_struct *task, int subsys_id) +{ + struct cgroup_subsys_state *css; + + rcu_read_lock(); + while (true) { + css = task_css(task, subsys_id); + if (likely(css_tryget_online(css))) + break; + cpu_relax(); + } + rcu_read_unlock(); + return css; +} + +/** * task_css_is_root - test whether a task belongs to the root css * @task: the target task * @subsys_id: the target subsystem ID @@ -795,178 +471,86 @@ static inline struct cgroup *task_cgroup(struct task_struct *task, return task_css(task, subsys_id)->cgroup; } -struct cgroup_subsys_state *css_next_child(struct cgroup_subsys_state *pos, - struct cgroup_subsys_state *parent); - -struct cgroup_subsys_state *css_from_id(int id, struct cgroup_subsys *ss); +/* no synchronization, the result can only be used as a hint */ +static inline bool cgroup_is_populated(struct cgroup *cgrp) +{ + return cgrp->populated_cnt; +} -/** - * css_for_each_child - iterate through children of a css - * @pos: the css * to use as the loop cursor - * @parent: css whose children to walk - * - * Walk @parent's children. Must be called under rcu_read_lock(). - * - * If a subsystem synchronizes ->css_online() and the start of iteration, a - * css which finished ->css_online() is guaranteed to be visible in the - * future iterations and will stay visible until the last reference is put. - * A css which hasn't finished ->css_online() or already finished - * ->css_offline() may show up during traversal. It's each subsystem's - * responsibility to synchronize against on/offlining. - * - * It is allowed to temporarily drop RCU read lock during iteration. The - * caller is responsible for ensuring that @pos remains accessible until - * the start of the next iteration by, for example, bumping the css refcnt. - */ -#define css_for_each_child(pos, parent) \ - for ((pos) = css_next_child(NULL, (parent)); (pos); \ - (pos) = css_next_child((pos), (parent))) +/* returns ino associated with a cgroup */ +static inline ino_t cgroup_ino(struct cgroup *cgrp) +{ + return cgrp->kn->ino; +} -struct cgroup_subsys_state * -css_next_descendant_pre(struct cgroup_subsys_state *pos, - struct cgroup_subsys_state *css); +/* cft/css accessors for cftype->write() operation */ +static inline struct cftype *of_cft(struct kernfs_open_file *of) +{ + return of->kn->priv; +} -struct cgroup_subsys_state * -css_rightmost_descendant(struct cgroup_subsys_state *pos); +struct cgroup_subsys_state *of_css(struct kernfs_open_file *of); -/** - * css_for_each_descendant_pre - pre-order walk of a css's descendants - * @pos: the css * to use as the loop cursor - * @root: css whose descendants to walk - * - * Walk @root's descendants. @root is included in the iteration and the - * first node to be visited. Must be called under rcu_read_lock(). - * - * If a subsystem synchronizes ->css_online() and the start of iteration, a - * css which finished ->css_online() is guaranteed to be visible in the - * future iterations and will stay visible until the last reference is put. - * A css which hasn't finished ->css_online() or already finished - * ->css_offline() may show up during traversal. It's each subsystem's - * responsibility to synchronize against on/offlining. - * - * For example, the following guarantees that a descendant can't escape - * state updates of its ancestors. - * - * my_online(@css) - * { - * Lock @css's parent and @css; - * Inherit state from the parent; - * Unlock both. - * } - * - * my_update_state(@css) - * { - * css_for_each_descendant_pre(@pos, @css) { - * Lock @pos; - * if (@pos == @css) - * Update @css's state; - * else - * Verify @pos is alive and inherit state from its parent; - * Unlock @pos; - * } - * } - * - * As long as the inheriting step, including checking the parent state, is - * enclosed inside @pos locking, double-locking the parent isn't necessary - * while inheriting. The state update to the parent is guaranteed to be - * visible by walking order and, as long as inheriting operations to the - * same @pos are atomic to each other, multiple updates racing each other - * still result in the correct state. It's guaranateed that at least one - * inheritance happens for any css after the latest update to its parent. - * - * If checking parent's state requires locking the parent, each inheriting - * iteration should lock and unlock both @pos->parent and @pos. - * - * Alternatively, a subsystem may choose to use a single global lock to - * synchronize ->css_online() and ->css_offline() against tree-walking - * operations. - * - * It is allowed to temporarily drop RCU read lock during iteration. The - * caller is responsible for ensuring that @pos remains accessible until - * the start of the next iteration by, for example, bumping the css refcnt. - */ -#define css_for_each_descendant_pre(pos, css) \ - for ((pos) = css_next_descendant_pre(NULL, (css)); (pos); \ - (pos) = css_next_descendant_pre((pos), (css))) +/* cft/css accessors for cftype->seq_*() operations */ +static inline struct cftype *seq_cft(struct seq_file *seq) +{ + return of_cft(seq->private); +} -struct cgroup_subsys_state * -css_next_descendant_post(struct cgroup_subsys_state *pos, - struct cgroup_subsys_state *css); +static inline struct cgroup_subsys_state *seq_css(struct seq_file *seq) +{ + return of_css(seq->private); +} -/** - * css_for_each_descendant_post - post-order walk of a css's descendants - * @pos: the css * to use as the loop cursor - * @css: css whose descendants to walk - * - * Similar to css_for_each_descendant_pre() but performs post-order - * traversal instead. @root is included in the iteration and the last - * node to be visited. - * - * If a subsystem synchronizes ->css_online() and the start of iteration, a - * css which finished ->css_online() is guaranteed to be visible in the - * future iterations and will stay visible until the last reference is put. - * A css which hasn't finished ->css_online() or already finished - * ->css_offline() may show up during traversal. It's each subsystem's - * responsibility to synchronize against on/offlining. - * - * Note that the walk visibility guarantee example described in pre-order - * walk doesn't apply the same to post-order walks. +/* + * Name / path handling functions. All are thin wrappers around the kernfs + * counterparts and can be called under any context. */ -#define css_for_each_descendant_post(pos, css) \ - for ((pos) = css_next_descendant_post(NULL, (css)); (pos); \ - (pos) = css_next_descendant_post((pos), (css))) - -bool css_has_online_children(struct cgroup_subsys_state *css); - -/* A css_task_iter should be treated as an opaque object */ -struct css_task_iter { - struct cgroup_subsys *ss; - struct list_head *cset_pos; - struct list_head *cset_head; - - struct list_head *task_pos; - struct list_head *tasks_head; - struct list_head *mg_tasks_head; -}; +static inline int cgroup_name(struct cgroup *cgrp, char *buf, size_t buflen) +{ + return kernfs_name(cgrp->kn, buf, buflen); +} -void css_task_iter_start(struct cgroup_subsys_state *css, - struct css_task_iter *it); -struct task_struct *css_task_iter_next(struct css_task_iter *it); -void css_task_iter_end(struct css_task_iter *it); +static inline char * __must_check cgroup_path(struct cgroup *cgrp, char *buf, + size_t buflen) +{ + return kernfs_path(cgrp->kn, buf, buflen); +} -int cgroup_attach_task_all(struct task_struct *from, struct task_struct *); -int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from); +static inline void pr_cont_cgroup_name(struct cgroup *cgrp) +{ + pr_cont_kernfs_name(cgrp->kn); +} -struct cgroup_subsys_state *cgroup_get_e_css(struct cgroup *cgroup, - struct cgroup_subsys *ss); -struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry, - struct cgroup_subsys *ss); +static inline void pr_cont_cgroup_path(struct cgroup *cgrp) +{ + pr_cont_kernfs_path(cgrp->kn); +} #else /* !CONFIG_CGROUPS */ struct cgroup_subsys_state; -static inline int cgroup_init_early(void) { return 0; } -static inline int cgroup_init(void) { return 0; } -static inline void cgroup_fork(struct task_struct *p) {} -static inline void cgroup_post_fork(struct task_struct *p) {} -static inline void cgroup_exit(struct task_struct *p) {} - +static inline void css_put(struct cgroup_subsys_state *css) {} +static inline int cgroup_attach_task_all(struct task_struct *from, + struct task_struct *t) { return 0; } static inline int cgroupstats_build(struct cgroupstats *stats, - struct dentry *dentry) -{ - return -EINVAL; -} + struct dentry *dentry) { return -EINVAL; } -static inline void css_put(struct cgroup_subsys_state *css) {} +static inline void cgroup_fork(struct task_struct *p) {} +static inline int cgroup_can_fork(struct task_struct *p, + void *ss_priv[CGROUP_CANFORK_COUNT]) +{ return 0; } +static inline void cgroup_cancel_fork(struct task_struct *p, + void *ss_priv[CGROUP_CANFORK_COUNT]) {} +static inline void cgroup_post_fork(struct task_struct *p, + void *ss_priv[CGROUP_CANFORK_COUNT]) {} +static inline void cgroup_exit(struct task_struct *p) {} +static inline void cgroup_free(struct task_struct *p) {} -/* No cgroups - nothing to do */ -static inline int cgroup_attach_task_all(struct task_struct *from, - struct task_struct *t) -{ - return 0; -} +static inline int cgroup_init_early(void) { return 0; } +static inline int cgroup_init(void) { return 0; } #endif /* !CONFIG_CGROUPS */ diff --git a/kernel/include/linux/cgroup_subsys.h b/kernel/include/linux/cgroup_subsys.h index e4a96fb14..1a96fdaa3 100644 --- a/kernel/include/linux/cgroup_subsys.h +++ b/kernel/include/linux/cgroup_subsys.h @@ -3,6 +3,17 @@ * * DO NOT ADD ANY SUBSYSTEM WITHOUT EXPLICIT ACKS FROM CGROUP MAINTAINERS. */ + +/* + * This file *must* be included with SUBSYS() defined. + * SUBSYS_TAG() is a noop if undefined. + */ + +#ifndef SUBSYS_TAG +#define __TMP_SUBSYS_TAG +#define SUBSYS_TAG(_x) +#endif + #if IS_ENABLED(CONFIG_CPUSETS) SUBSYS(cpuset) #endif @@ -16,7 +27,7 @@ SUBSYS(cpuacct) #endif #if IS_ENABLED(CONFIG_BLK_CGROUP) -SUBSYS(blkio) +SUBSYS(io) #endif #if IS_ENABLED(CONFIG_MEMCG) @@ -48,11 +59,28 @@ SUBSYS(hugetlb) #endif /* + * Subsystems that implement the can_fork() family of callbacks. + */ +SUBSYS_TAG(CANFORK_START) + +#if IS_ENABLED(CONFIG_CGROUP_PIDS) +SUBSYS(pids) +#endif + +SUBSYS_TAG(CANFORK_END) + +/* * The following subsystems are not supported on the default hierarchy. */ #if IS_ENABLED(CONFIG_CGROUP_DEBUG) SUBSYS(debug) #endif + +#ifdef __TMP_SUBSYS_TAG +#undef __TMP_SUBSYS_TAG +#undef SUBSYS_TAG +#endif + /* * DO NOT ADD ANY SUBSYSTEM WITHOUT EXPLICIT ACKS FROM CGROUP MAINTAINERS. */ diff --git a/kernel/include/linux/clk-provider.h b/kernel/include/linux/clk-provider.h index df695313f..c56988ac6 100644 --- a/kernel/include/linux/clk-provider.h +++ b/kernel/include/linux/clk-provider.h @@ -11,7 +11,6 @@ #ifndef __LINUX_CLK_PROVIDER_H #define __LINUX_CLK_PROVIDER_H -#include <linux/clk.h> #include <linux/io.h> #include <linux/of.h> @@ -31,12 +30,36 @@ #define CLK_GET_RATE_NOCACHE BIT(6) /* do not use the cached clk rate */ #define CLK_SET_RATE_NO_REPARENT BIT(7) /* don't re-parent on rate change */ #define CLK_GET_ACCURACY_NOCACHE BIT(8) /* do not use the cached clk accuracy */ +#define CLK_RECALC_NEW_RATES BIT(9) /* recalc rates after notifications */ +struct clk; struct clk_hw; struct clk_core; struct dentry; /** + * struct clk_rate_request - Structure encoding the clk constraints that + * a clock user might require. + * + * @rate: Requested clock rate. This field will be adjusted by + * clock drivers according to hardware capabilities. + * @min_rate: Minimum rate imposed by clk users. + * @max_rate: Maximum rate a imposed by clk users. + * @best_parent_rate: The best parent rate a parent can provide to fulfill the + * requested constraints. + * @best_parent_hw: The most appropriate parent clock that fulfills the + * requested constraints. + * + */ +struct clk_rate_request { + unsigned long rate; + unsigned long min_rate; + unsigned long max_rate; + unsigned long best_parent_rate; + struct clk_hw *best_parent_hw; +}; + +/** * struct clk_ops - Callback operations for hardware clocks; these are to * be provided by the clock implementation, and will be called by drivers * through the clk_* api. @@ -175,12 +198,8 @@ struct clk_ops { unsigned long parent_rate); long (*round_rate)(struct clk_hw *hw, unsigned long rate, unsigned long *parent_rate); - long (*determine_rate)(struct clk_hw *hw, - unsigned long rate, - unsigned long min_rate, - unsigned long max_rate, - unsigned long *best_parent_rate, - struct clk_hw **best_parent_hw); + int (*determine_rate)(struct clk_hw *hw, + struct clk_rate_request *req); int (*set_parent)(struct clk_hw *hw, u8 index); u8 (*get_parent)(struct clk_hw *hw); int (*set_rate)(struct clk_hw *hw, unsigned long rate, @@ -209,7 +228,7 @@ struct clk_ops { struct clk_init_data { const char *name; const struct clk_ops *ops; - const char **parent_names; + const char * const *parent_names; u8 num_parents; unsigned long flags; }; @@ -342,6 +361,9 @@ struct clk_div_table { * to the closest integer instead of the up one. * CLK_DIVIDER_READ_ONLY - The divider settings are preconfigured and should * not be changed by the clock framework. + * CLK_DIVIDER_MAX_AT_ZERO - For dividers which are like CLK_DIVIDER_ONE_BASED + * except when the value read from the register is zero, the divisor is + * 2^width of the field. */ struct clk_divider { struct clk_hw hw; @@ -359,6 +381,7 @@ struct clk_divider { #define CLK_DIVIDER_HIWORD_MASK BIT(3) #define CLK_DIVIDER_ROUND_CLOSEST BIT(4) #define CLK_DIVIDER_READ_ONLY BIT(5) +#define CLK_DIVIDER_MAX_AT_ZERO BIT(6) extern const struct clk_ops clk_divider_ops; @@ -426,12 +449,14 @@ extern const struct clk_ops clk_mux_ops; extern const struct clk_ops clk_mux_ro_ops; struct clk *clk_register_mux(struct device *dev, const char *name, - const char **parent_names, u8 num_parents, unsigned long flags, + const char * const *parent_names, u8 num_parents, + unsigned long flags, void __iomem *reg, u8 shift, u8 width, u8 clk_mux_flags, spinlock_t *lock); struct clk *clk_register_mux_table(struct device *dev, const char *name, - const char **parent_names, u8 num_parents, unsigned long flags, + const char * const *parent_names, u8 num_parents, + unsigned long flags, void __iomem *reg, u8 shift, u32 mask, u8 clk_mux_flags, u32 *table, spinlock_t *lock); @@ -457,7 +482,7 @@ struct clk_fixed_factor { unsigned int div; }; -extern struct clk_ops clk_fixed_factor_ops; +extern const struct clk_ops clk_fixed_factor_ops; struct clk *clk_register_fixed_factor(struct device *dev, const char *name, const char *parent_name, unsigned long flags, unsigned int mult, unsigned int div); @@ -475,13 +500,14 @@ struct clk *clk_register_fixed_factor(struct device *dev, const char *name, * * Clock with adjustable fractional divider affecting its output frequency. */ - struct clk_fractional_divider { struct clk_hw hw; void __iomem *reg; u8 mshift; + u8 mwidth; u32 mmask; u8 nshift; + u8 nwidth; u32 nmask; u8 flags; spinlock_t *lock; @@ -493,6 +519,41 @@ struct clk *clk_register_fractional_divider(struct device *dev, void __iomem *reg, u8 mshift, u8 mwidth, u8 nshift, u8 nwidth, u8 clk_divider_flags, spinlock_t *lock); +/** + * struct clk_multiplier - adjustable multiplier clock + * + * @hw: handle between common and hardware-specific interfaces + * @reg: register containing the multiplier + * @shift: shift to the multiplier bit field + * @width: width of the multiplier bit field + * @lock: register lock + * + * Clock with an adjustable multiplier affecting its output frequency. + * Implements .recalc_rate, .set_rate and .round_rate + * + * Flags: + * CLK_MULTIPLIER_ZERO_BYPASS - By default, the multiplier is the value read + * from the register, with 0 being a valid value effectively + * zeroing the output clock rate. If CLK_MULTIPLIER_ZERO_BYPASS is + * set, then a null multiplier will be considered as a bypass, + * leaving the parent rate unmodified. + * CLK_MULTIPLIER_ROUND_CLOSEST - Makes the best calculated divider to be + * rounded to the closest integer instead of the down one. + */ +struct clk_multiplier { + struct clk_hw hw; + void __iomem *reg; + u8 shift; + u8 width; + u8 flags; + spinlock_t *lock; +}; + +#define CLK_MULTIPLIER_ZERO_BYPASS BIT(0) +#define CLK_MULTIPLIER_ROUND_CLOSEST BIT(1) + +extern const struct clk_ops clk_multiplier_ops; + /*** * struct clk_composite - aggregate clock of mux, divider and gate clocks * @@ -518,7 +579,7 @@ struct clk_composite { }; struct clk *clk_register_composite(struct device *dev, const char *name, - const char **parent_names, int num_parents, + const char * const *parent_names, int num_parents, struct clk_hw *mux_hw, const struct clk_ops *mux_ops, struct clk_hw *rate_hw, const struct clk_ops *rate_ops, struct clk_hw *gate_hw, const struct clk_ops *gate_ops, @@ -547,6 +608,23 @@ struct clk *clk_register_gpio_gate(struct device *dev, const char *name, void of_gpio_clk_gate_setup(struct device_node *node); /** + * struct clk_gpio_mux - gpio controlled clock multiplexer + * + * @hw: see struct clk_gpio + * @gpiod: gpio descriptor to select the parent of this clock multiplexer + * + * Clock with a gpio control for selecting the parent clock. + * Implements .get_parent, .set_parent and .determine_rate + */ + +extern const struct clk_ops clk_gpio_mux_ops; +struct clk *clk_register_gpio_mux(struct device *dev, const char *name, + const char * const *parent_names, u8 num_parents, unsigned gpio, + bool active_low, unsigned long flags); + +void of_gpio_mux_clk_setup(struct device_node *node); + +/** * clk_register - allocate a new clock, register it and return an opaque cookie * @dev: device that is registering this clock * @hw: link to hardware-specific clock data @@ -564,31 +642,29 @@ void clk_unregister(struct clk *clk); void devm_clk_unregister(struct device *dev, struct clk *clk); /* helper functions */ -const char *__clk_get_name(struct clk *clk); +const char *__clk_get_name(const struct clk *clk); +const char *clk_hw_get_name(const struct clk_hw *hw); struct clk_hw *__clk_get_hw(struct clk *clk); -u8 __clk_get_num_parents(struct clk *clk); -struct clk *__clk_get_parent(struct clk *clk); -struct clk *clk_get_parent_by_index(struct clk *clk, u8 index); +unsigned int clk_hw_get_num_parents(const struct clk_hw *hw); +struct clk_hw *clk_hw_get_parent(const struct clk_hw *hw); +struct clk_hw *clk_hw_get_parent_by_index(const struct clk_hw *hw, + unsigned int index); unsigned int __clk_get_enable_count(struct clk *clk); -unsigned long __clk_get_rate(struct clk *clk); +unsigned long clk_hw_get_rate(const struct clk_hw *hw); unsigned long __clk_get_flags(struct clk *clk); -bool __clk_is_prepared(struct clk *clk); +unsigned long clk_hw_get_flags(const struct clk_hw *hw); +bool clk_hw_is_prepared(const struct clk_hw *hw); +bool clk_hw_is_enabled(const struct clk_hw *hw); bool __clk_is_enabled(struct clk *clk); struct clk *__clk_lookup(const char *name); -long __clk_mux_determine_rate(struct clk_hw *hw, unsigned long rate, - unsigned long min_rate, - unsigned long max_rate, - unsigned long *best_parent_rate, - struct clk_hw **best_parent_p); -unsigned long __clk_determine_rate(struct clk_hw *core, - unsigned long rate, - unsigned long min_rate, - unsigned long max_rate); -long __clk_mux_determine_rate_closest(struct clk_hw *hw, unsigned long rate, - unsigned long min_rate, - unsigned long max_rate, - unsigned long *best_parent_rate, - struct clk_hw **best_parent_p); +int __clk_mux_determine_rate(struct clk_hw *hw, + struct clk_rate_request *req); +int __clk_determine_rate(struct clk_hw *core, struct clk_rate_request *req); +int __clk_mux_determine_rate_closest(struct clk_hw *hw, + struct clk_rate_request *req); +void clk_hw_reparent(struct clk_hw *hw, struct clk_hw *new_parent); +void clk_hw_set_rate_range(struct clk_hw *hw, unsigned long min_rate, + unsigned long max_rate); static inline void __clk_hw_set_clk(struct clk_hw *dst, struct clk_hw *src) { @@ -599,7 +675,7 @@ static inline void __clk_hw_set_clk(struct clk_hw *dst, struct clk_hw *src) /* * FIXME clock api without lock protection */ -unsigned long __clk_round_rate(struct clk *clk, unsigned long rate); +unsigned long clk_hw_round_rate(struct clk_hw *hw, unsigned long rate); struct of_device_id; @@ -624,6 +700,8 @@ struct clk *of_clk_src_simple_get(struct of_phandle_args *clkspec, void *data); struct clk *of_clk_src_onecell_get(struct of_phandle_args *clkspec, void *data); int of_clk_get_parent_count(struct device_node *np); +int of_clk_parent_fill(struct device_node *np, const char **parents, + unsigned int size); const char *of_clk_get_parent_name(struct device_node *np, int index); void of_clk_init(const struct of_device_id *matches); @@ -649,6 +727,15 @@ static inline struct clk *of_clk_src_onecell_get( { return ERR_PTR(-ENOENT); } +static inline int of_clk_get_parent_count(struct device_node *np) +{ + return 0; +} +static inline int of_clk_parent_fill(struct device_node *np, + const char **parents, unsigned int size) +{ + return 0; +} static inline const char *of_clk_get_parent_name(struct device_node *np, int index) { diff --git a/kernel/include/linux/clk.h b/kernel/include/linux/clk.h index 68c16a6be..0df4a51e1 100644 --- a/kernel/include/linux/clk.h +++ b/kernel/include/linux/clk.h @@ -306,6 +306,20 @@ void devm_clk_put(struct device *dev, struct clk *clk); * @clk: clock source * @rate: desired clock rate in Hz * + * This answers the question "if I were to pass @rate to clk_set_rate(), + * what clock rate would I end up with?" without changing the hardware + * in any way. In other words: + * + * rate = clk_round_rate(clk, r); + * + * and: + * + * clk_set_rate(clk, r); + * rate = clk_get_rate(clk); + * + * are equivalent except the former does not modify the clock hardware + * in any way. + * * Returns rounded clock rate in Hz, or negative errno. */ long clk_round_rate(struct clk *clk, unsigned long rate); @@ -471,19 +485,6 @@ static inline void clk_disable_unprepare(struct clk *clk) clk_unprepare(clk); } -/** - * clk_add_alias - add a new clock alias - * @alias: name for clock alias - * @alias_dev_name: device name - * @id: platform specific clock name - * @dev: device - * - * Allows using generic clock names for drivers by adding a new alias. - * Assumes clkdev, see clkdev.h for more info. - */ -int clk_add_alias(const char *alias, const char *alias_dev_name, char *id, - struct device *dev); - struct device_node; struct of_phandle_args; diff --git a/kernel/include/linux/clk/at91_pmc.h b/kernel/include/linux/clk/at91_pmc.h index 7669f7618..17f413bbb 100644 --- a/kernel/include/linux/clk/at91_pmc.h +++ b/kernel/include/linux/clk/at91_pmc.h @@ -16,18 +16,6 @@ #ifndef AT91_PMC_H #define AT91_PMC_H -#ifndef __ASSEMBLY__ -extern void __iomem *at91_pmc_base; - -#define at91_pmc_read(field) \ - readl_relaxed(at91_pmc_base + field) - -#define at91_pmc_write(field, value) \ - writel_relaxed(value, at91_pmc_base + field) -#else -.extern at91_pmc_base -#endif - #define AT91_PMC_SCER 0x00 /* System Clock Enable Register */ #define AT91_PMC_SCDR 0x04 /* System Clock Disable Register */ @@ -164,6 +152,7 @@ extern void __iomem *at91_pmc_base; #define AT91_PMC_MOSCSELS (1 << 16) /* Main Oscillator Selection [some SAM9] */ #define AT91_PMC_MOSCRCS (1 << 17) /* Main On-Chip RC [some SAM9] */ #define AT91_PMC_CFDEV (1 << 18) /* Clock Failure Detector Event [some SAM9] */ +#define AT91_PMC_GCKRDY (1 << 24) /* Generated Clocks */ #define AT91_PMC_IMR 0x6c /* Interrupt Mask Register */ #define AT91_PMC_PLLICPR 0x80 /* PLL Charge Pump Current Register */ @@ -182,13 +171,18 @@ extern void __iomem *at91_pmc_base; #define AT91_PMC_PCSR1 0x108 /* Peripheral Clock Enable Register 1 */ #define AT91_PMC_PCR 0x10c /* Peripheral Control Register [some SAM9 and SAMA5] */ -#define AT91_PMC_PCR_PID (0x3f << 0) /* Peripheral ID */ -#define AT91_PMC_PCR_CMD (0x1 << 12) /* Command (read=0, write=1) */ -#define AT91_PMC_PCR_DIV(n) ((n) << 16) /* Divisor Value */ -#define AT91_PMC_PCR_DIV0 0x0 /* Peripheral clock is MCK */ -#define AT91_PMC_PCR_DIV2 0x1 /* Peripheral clock is MCK/2 */ -#define AT91_PMC_PCR_DIV4 0x2 /* Peripheral clock is MCK/4 */ -#define AT91_PMC_PCR_DIV8 0x3 /* Peripheral clock is MCK/8 */ -#define AT91_PMC_PCR_EN (0x1 << 28) /* Enable */ +#define AT91_PMC_PCR_PID_MASK 0x3f +#define AT91_PMC_PCR_GCKCSS_OFFSET 8 +#define AT91_PMC_PCR_GCKCSS_MASK (0x7 << AT91_PMC_PCR_GCKCSS_OFFSET) +#define AT91_PMC_PCR_GCKCSS(n) ((n) << AT91_PMC_PCR_GCKCSS_OFFSET) /* GCK Clock Source Selection */ +#define AT91_PMC_PCR_CMD (0x1 << 12) /* Command (read=0, write=1) */ +#define AT91_PMC_PCR_DIV_OFFSET 16 +#define AT91_PMC_PCR_DIV_MASK (0x3 << AT91_PMC_PCR_DIV_OFFSET) +#define AT91_PMC_PCR_DIV(n) ((n) << AT91_PMC_PCR_DIV_OFFSET) /* Divisor Value */ +#define AT91_PMC_PCR_GCKDIV_OFFSET 20 +#define AT91_PMC_PCR_GCKDIV_MASK (0xff << AT91_PMC_PCR_GCKDIV_OFFSET) +#define AT91_PMC_PCR_GCKDIV(n) ((n) << AT91_PMC_PCR_GCKDIV_OFFSET) /* Generated Clock Divisor Value */ +#define AT91_PMC_PCR_EN (0x1 << 28) /* Enable */ +#define AT91_PMC_PCR_GCKEN (0x1 << 29) /* GCK Enable */ #endif diff --git a/kernel/include/linux/clk/clk-conf.h b/kernel/include/linux/clk/clk-conf.h index f3050e15f..e0c362363 100644 --- a/kernel/include/linux/clk/clk-conf.h +++ b/kernel/include/linux/clk/clk-conf.h @@ -7,6 +7,8 @@ * published by the Free Software Foundation. */ +#include <linux/types.h> + struct device_node; #if defined(CONFIG_OF) && defined(CONFIG_COMMON_CLK) diff --git a/kernel/include/linux/clk/shmobile.h b/kernel/include/linux/clk/shmobile.h index 63a8159c4..cb19cc186 100644 --- a/kernel/include/linux/clk/shmobile.h +++ b/kernel/include/linux/clk/shmobile.h @@ -16,8 +16,20 @@ #include <linux/types.h> +struct device; +struct device_node; +struct generic_pm_domain; + void r8a7778_clocks_init(u32 mode); void r8a7779_clocks_init(u32 mode); void rcar_gen2_clocks_init(u32 mode); +#ifdef CONFIG_PM_GENERIC_DOMAINS_OF +void cpg_mstp_add_clk_domain(struct device_node *np); +int cpg_mstp_attach_dev(struct generic_pm_domain *domain, struct device *dev); +void cpg_mstp_detach_dev(struct generic_pm_domain *domain, struct device *dev); +#else +static inline void cpg_mstp_add_clk_domain(struct device_node *np) {} +#endif + #endif diff --git a/kernel/include/linux/clk/tegra.h b/kernel/include/linux/clk/tegra.h index 19c4208f4..57bf7aab4 100644 --- a/kernel/include/linux/clk/tegra.h +++ b/kernel/include/linux/clk/tegra.h @@ -17,7 +17,8 @@ #ifndef __LINUX_CLK_TEGRA_H_ #define __LINUX_CLK_TEGRA_H_ -#include <linux/clk.h> +#include <linux/types.h> +#include <linux/bug.h> /* * Tegra CPU clock and reset control ops diff --git a/kernel/include/linux/clk/ti.h b/kernel/include/linux/clk/ti.h index 79b76e13d..223be696d 100644 --- a/kernel/include/linux/clk/ti.h +++ b/kernel/include/linux/clk/ti.h @@ -188,33 +188,6 @@ struct clk_hw_omap { /* DPLL Type and DCO Selection Flags */ #define DPLL_J_TYPE 0x1 -/* Composite clock component types */ -enum { - CLK_COMPONENT_TYPE_GATE = 0, - CLK_COMPONENT_TYPE_DIVIDER, - CLK_COMPONENT_TYPE_MUX, - CLK_COMPONENT_TYPE_MAX, -}; - -/** - * struct ti_dt_clk - OMAP DT clock alias declarations - * @lk: clock lookup definition - * @node_name: clock DT node to map to - */ -struct ti_dt_clk { - struct clk_lookup lk; - char *node_name; -}; - -#define DT_CLK(dev, con, name) \ - { \ - .lk = { \ - .dev_id = dev, \ - .con_id = con, \ - }, \ - .node_name = name, \ - } - /* Static memmap indices */ enum { TI_CLKM_CM = 0, @@ -225,8 +198,6 @@ enum { CLK_MAX_MEMMAPS }; -typedef void (*ti_of_clk_init_cb_t)(struct clk_hw *, struct device_node *); - /** * struct clk_omap_reg - OMAP register declaration * @offset: offset from the master IP module base address @@ -238,98 +209,62 @@ struct clk_omap_reg { }; /** - * struct ti_clk_ll_ops - low-level register access ops for a clock + * struct ti_clk_ll_ops - low-level ops for clocks * @clk_readl: pointer to register read function * @clk_writel: pointer to register write function + * @clkdm_clk_enable: pointer to clockdomain enable function + * @clkdm_clk_disable: pointer to clockdomain disable function + * @cm_wait_module_ready: pointer to CM module wait ready function + * @cm_split_idlest_reg: pointer to CM module function to split idlest reg * - * Low-level register access ops are generally used by the basic clock types - * (clk-gate, clk-mux, clk-divider etc.) to provide support for various - * low-level hardware interfaces (direct MMIO, regmap etc.), but can also be - * used by other hardware-specific clock drivers if needed. + * Low-level ops are generally used by the basic clock types (clk-gate, + * clk-mux, clk-divider etc.) to provide support for various low-level + * hadrware interfaces (direct MMIO, regmap etc.), and is initialized + * by board code. Low-level ops also contain some other platform specific + * operations not provided directly by clock drivers. */ struct ti_clk_ll_ops { u32 (*clk_readl)(void __iomem *reg); void (*clk_writel)(u32 val, void __iomem *reg); + int (*clkdm_clk_enable)(struct clockdomain *clkdm, struct clk *clk); + int (*clkdm_clk_disable)(struct clockdomain *clkdm, + struct clk *clk); + int (*cm_wait_module_ready)(u8 part, s16 prcm_mod, u16 idlest_reg, + u8 idlest_shift); + int (*cm_split_idlest_reg)(void __iomem *idlest_reg, s16 *prcm_inst, + u8 *idlest_reg_id); }; -extern struct ti_clk_ll_ops *ti_clk_ll_ops; - -extern const struct clk_ops ti_clk_divider_ops; -extern const struct clk_ops ti_clk_mux_ops; - #define to_clk_hw_omap(_hw) container_of(_hw, struct clk_hw_omap, hw) -void omap2_init_clk_hw_omap_clocks(struct clk *clk); -int omap3_noncore_dpll_enable(struct clk_hw *hw); -void omap3_noncore_dpll_disable(struct clk_hw *hw); -int omap3_noncore_dpll_set_parent(struct clk_hw *hw, u8 index); -int omap3_noncore_dpll_set_rate(struct clk_hw *hw, unsigned long rate, - unsigned long parent_rate); -int omap3_noncore_dpll_set_rate_and_parent(struct clk_hw *hw, - unsigned long rate, - unsigned long parent_rate, - u8 index); -long omap3_noncore_dpll_determine_rate(struct clk_hw *hw, - unsigned long rate, - unsigned long min_rate, - unsigned long max_rate, - unsigned long *best_parent_rate, - struct clk_hw **best_parent_clk); -unsigned long omap4_dpll_regm4xen_recalc(struct clk_hw *hw, - unsigned long parent_rate); -long omap4_dpll_regm4xen_round_rate(struct clk_hw *hw, - unsigned long target_rate, - unsigned long *parent_rate); -long omap4_dpll_regm4xen_determine_rate(struct clk_hw *hw, - unsigned long rate, - unsigned long min_rate, - unsigned long max_rate, - unsigned long *best_parent_rate, - struct clk_hw **best_parent_clk); -u8 omap2_init_dpll_parent(struct clk_hw *hw); -unsigned long omap3_dpll_recalc(struct clk_hw *hw, unsigned long parent_rate); -long omap2_dpll_round_rate(struct clk_hw *hw, unsigned long target_rate, - unsigned long *parent_rate); void omap2_init_clk_clkdm(struct clk_hw *clk); -unsigned long omap3_clkoutx2_recalc(struct clk_hw *hw, - unsigned long parent_rate); -int omap3_clkoutx2_set_rate(struct clk_hw *hw, unsigned long rate, - unsigned long parent_rate); -long omap3_clkoutx2_round_rate(struct clk_hw *hw, unsigned long rate, - unsigned long *prate); -int omap2_clkops_enable_clkdm(struct clk_hw *hw); -void omap2_clkops_disable_clkdm(struct clk_hw *hw); int omap2_clk_disable_autoidle_all(void); -void omap2_clk_enable_init_clocks(const char **clk_names, u8 num_clocks); -int omap3_dpll4_set_rate(struct clk_hw *clk, unsigned long rate, - unsigned long parent_rate); -int omap3_dpll4_set_rate_and_parent(struct clk_hw *hw, unsigned long rate, - unsigned long parent_rate, u8 index); -int omap2_dflt_clk_enable(struct clk_hw *hw); -void omap2_dflt_clk_disable(struct clk_hw *hw); -int omap2_dflt_clk_is_enabled(struct clk_hw *hw); -void omap3_clk_lock_dpll5(void); +int omap2_clk_enable_autoidle_all(void); +int omap2_clk_allow_idle(struct clk *clk); +int omap2_clk_deny_idle(struct clk *clk); unsigned long omap2_dpllcore_recalc(struct clk_hw *hw, unsigned long parent_rate); int omap2_reprogram_dpllcore(struct clk_hw *clk, unsigned long rate, unsigned long parent_rate); void omap2xxx_clkt_dpllcore_init(struct clk_hw *hw); void omap2xxx_clkt_vps_init(void); +unsigned long omap2_get_dpll_rate(struct clk_hw_omap *clk); -void __iomem *ti_clk_get_reg_addr(struct device_node *node, int index); -void ti_dt_clocks_register(struct ti_dt_clk *oclks); -void ti_dt_clk_init_provider(struct device_node *np, int index); void ti_dt_clk_init_retry_clks(void); void ti_dt_clockdomains_setup(void); -int ti_clk_retry_init(struct device_node *node, struct clk_hw *hw, - ti_of_clk_init_cb_t func); -int of_ti_clk_autoidle_setup(struct device_node *node); -int ti_clk_add_component(struct device_node *node, struct clk_hw *hw, int type); +int ti_clk_setup_ll_ops(struct ti_clk_ll_ops *ops); + +struct regmap; + +int omap2_clk_provider_init(struct device_node *parent, int index, + struct regmap *syscon, void __iomem *mem); +void omap2_clk_legacy_provider_init(int index, void __iomem *mem); int omap3430_dt_clk_init(void); int omap3630_dt_clk_init(void); int am35xx_dt_clk_init(void); -int ti81xx_dt_clk_init(void); +int dm814x_dt_clk_init(void); +int dm816x_dt_clk_init(void); int omap4xxx_dt_clk_init(void); int omap5xxx_dt_clk_init(void); int dra7xx_dt_clk_init(void); @@ -338,27 +273,24 @@ int am43xx_dt_clk_init(void); int omap2420_dt_clk_init(void); int omap2430_dt_clk_init(void); -#ifdef CONFIG_OF -void of_ti_clk_allow_autoidle_all(void); -void of_ti_clk_deny_autoidle_all(void); -#else -static inline void of_ti_clk_allow_autoidle_all(void) { } -static inline void of_ti_clk_deny_autoidle_all(void) { } -#endif +struct ti_clk_features { + u32 flags; + long fint_min; + long fint_max; + long fint_band1_max; + long fint_band2_min; + u8 dpll_bypass_vals; + u8 cm_idlest_val; +}; + +#define TI_CLK_DPLL_HAS_FREQSEL BIT(0) +#define TI_CLK_DPLL4_DENY_REPROGRAM BIT(1) +#define TI_CLK_DISABLE_CLKDM_CONTROL BIT(2) + +void ti_clk_setup_features(struct ti_clk_features *features); +const struct ti_clk_features *ti_clk_get_features(void); extern const struct clk_hw_omap_ops clkhwops_omap2xxx_dpll; -extern const struct clk_hw_omap_ops clkhwops_omap2430_i2chs_wait; -extern const struct clk_hw_omap_ops clkhwops_omap3_dpll; -extern const struct clk_hw_omap_ops clkhwops_omap4_dpllmx; -extern const struct clk_hw_omap_ops clkhwops_wait; -extern const struct clk_hw_omap_ops clkhwops_omap3430es2_dss_usbhost_wait; -extern const struct clk_hw_omap_ops clkhwops_am35xx_ipss_module_wait; -extern const struct clk_hw_omap_ops clkhwops_am35xx_ipss_wait; -extern const struct clk_hw_omap_ops clkhwops_iclk; -extern const struct clk_hw_omap_ops clkhwops_iclk_wait; -extern const struct clk_hw_omap_ops clkhwops_omap3430es2_iclk_ssi_wait; -extern const struct clk_hw_omap_ops clkhwops_omap3430es2_iclk_dss_usbhost_wait; -extern const struct clk_hw_omap_ops clkhwops_omap3430es2_iclk_hsotgusb_wait; #ifdef CONFIG_ATAGS int omap3430_clk_legacy_init(void); diff --git a/kernel/include/linux/clkdev.h b/kernel/include/linux/clkdev.h index 94bad77ee..08bffcc46 100644 --- a/kernel/include/linux/clkdev.h +++ b/kernel/include/linux/clkdev.h @@ -22,6 +22,7 @@ struct clk_lookup { const char *dev_id; const char *con_id; struct clk *clk; + struct clk_hw *clk_hw; }; #define CLKDEV_INIT(d, n, c) \ @@ -32,15 +33,19 @@ struct clk_lookup { } struct clk_lookup *clkdev_alloc(struct clk *clk, const char *con_id, - const char *dev_fmt, ...); + const char *dev_fmt, ...) __printf(3, 4); void clkdev_add(struct clk_lookup *cl); void clkdev_drop(struct clk_lookup *cl); +struct clk_lookup *clkdev_create(struct clk *clk, const char *con_id, + const char *dev_fmt, ...) __printf(3, 4); + void clkdev_add_table(struct clk_lookup *, size_t); -int clk_add_alias(const char *, const char *, char *, struct device *); +int clk_add_alias(const char *, const char *, const char *, struct device *); -int clk_register_clkdev(struct clk *, const char *, const char *, ...); +int clk_register_clkdev(struct clk *, const char *, const char *, ...) + __printf(3, 4); int clk_register_clkdevs(struct clk *, struct clk_lookup *, size_t); #ifdef CONFIG_COMMON_CLK diff --git a/kernel/include/linux/clockchips.h b/kernel/include/linux/clockchips.h index 96c280b2c..bdcf358df 100644 --- a/kernel/include/linux/clockchips.h +++ b/kernel/include/linux/clockchips.h @@ -18,15 +18,6 @@ struct clock_event_device; struct module; -/* Clock event mode commands for legacy ->set_mode(): OBSOLETE */ -enum clock_event_mode { - CLOCK_EVT_MODE_UNUSED, - CLOCK_EVT_MODE_SHUTDOWN, - CLOCK_EVT_MODE_PERIODIC, - CLOCK_EVT_MODE_ONESHOT, - CLOCK_EVT_MODE_RESUME, -}; - /* * Possible states of a clock event device. * @@ -37,12 +28,15 @@ enum clock_event_mode { * reached from DETACHED or SHUTDOWN. * ONESHOT: Device is programmed to generate event only once. Can be reached * from DETACHED or SHUTDOWN. + * ONESHOT_STOPPED: Device was programmed in ONESHOT mode and is temporarily + * stopped. */ enum clock_event_state { CLOCK_EVT_STATE_DETACHED, CLOCK_EVT_STATE_SHUTDOWN, CLOCK_EVT_STATE_PERIODIC, CLOCK_EVT_STATE_ONESHOT, + CLOCK_EVT_STATE_ONESHOT_STOPPED, }; /* @@ -83,15 +77,14 @@ enum clock_event_state { * @min_delta_ns: minimum delta value in ns * @mult: nanosecond to cycles multiplier * @shift: nanoseconds to cycles divisor (power of two) - * @mode: operating mode, relevant only to ->set_mode(), OBSOLETE - * @state: current state of the device, assigned by the core code + * @state_use_accessors:current state of the device, assigned by the core code * @features: features * @retries: number of forced programming retries - * @set_mode: legacy set mode function, only for modes <= CLOCK_EVT_MODE_RESUME. - * @set_state_periodic: switch state to periodic, if !set_mode - * @set_state_oneshot: switch state to oneshot, if !set_mode - * @set_state_shutdown: switch state to shutdown, if !set_mode - * @tick_resume: resume clkevt device, if !set_mode + * @set_state_periodic: switch state to periodic + * @set_state_oneshot: switch state to oneshot + * @set_state_oneshot_stopped: switch state to oneshot_stopped + * @set_state_shutdown: switch state to shutdown + * @tick_resume: resume clkevt device * @broadcast: function to broadcast events * @min_delta_ticks: minimum delta value in ticks stored for reconfiguration * @max_delta_ticks: maximum delta value in ticks stored for reconfiguration @@ -112,20 +105,13 @@ struct clock_event_device { u64 min_delta_ns; u32 mult; u32 shift; - enum clock_event_mode mode; - enum clock_event_state state; + enum clock_event_state state_use_accessors; unsigned int features; unsigned long retries; - /* - * State transition callback(s): Only one of the two groups should be - * defined: - * - set_mode(), only for modes <= CLOCK_EVT_MODE_RESUME. - * - set_state_{shutdown|periodic|oneshot}(), tick_resume(). - */ - void (*set_mode)(enum clock_event_mode mode, struct clock_event_device *); int (*set_state_periodic)(struct clock_event_device *); int (*set_state_oneshot)(struct clock_event_device *); + int (*set_state_oneshot_stopped)(struct clock_event_device *); int (*set_state_shutdown)(struct clock_event_device *); int (*tick_resume)(struct clock_event_device *); @@ -144,6 +130,32 @@ struct clock_event_device { struct module *owner; } ____cacheline_aligned; +/* Helpers to verify state of a clockevent device */ +static inline bool clockevent_state_detached(struct clock_event_device *dev) +{ + return dev->state_use_accessors == CLOCK_EVT_STATE_DETACHED; +} + +static inline bool clockevent_state_shutdown(struct clock_event_device *dev) +{ + return dev->state_use_accessors == CLOCK_EVT_STATE_SHUTDOWN; +} + +static inline bool clockevent_state_periodic(struct clock_event_device *dev) +{ + return dev->state_use_accessors == CLOCK_EVT_STATE_PERIODIC; +} + +static inline bool clockevent_state_oneshot(struct clock_event_device *dev) +{ + return dev->state_use_accessors == CLOCK_EVT_STATE_ONESHOT; +} + +static inline bool clockevent_state_oneshot_stopped(struct clock_event_device *dev) +{ + return dev->state_use_accessors == CLOCK_EVT_STATE_ONESHOT_STOPPED; +} + /* * Calculate a multiplication factor for scaled math, which is used to convert * nanoseconds based values to clock ticks: @@ -203,13 +215,10 @@ static inline int tick_check_broadcast_expired(void) { return 0; } static inline void tick_setup_hrtimer_broadcast(void) { } # endif -extern int clockevents_notify(unsigned long reason, void *arg); - #else /* !CONFIG_GENERIC_CLOCKEVENTS: */ static inline void clockevents_suspend(void) { } static inline void clockevents_resume(void) { } -static inline int clockevents_notify(unsigned long reason, void *arg) { return 0; } static inline int tick_check_broadcast_expired(void) { return 0; } static inline void tick_setup_hrtimer_broadcast(void) { } diff --git a/kernel/include/linux/clocksource.h b/kernel/include/linux/clocksource.h index d27d01522..7784b597e 100644 --- a/kernel/include/linux/clocksource.h +++ b/kernel/include/linux/clocksource.h @@ -181,7 +181,6 @@ static inline s64 clocksource_cyc2ns(cycle_t cycles, u32 mult, u32 shift) extern int clocksource_unregister(struct clocksource*); extern void clocksource_touch_watchdog(void); -extern struct clocksource* clocksource_get_next(void); extern void clocksource_change_rating(struct clocksource *cs, int rating); extern void clocksource_suspend(void); extern void clocksource_resume(void); @@ -247,16 +246,13 @@ extern int clocksource_i8253_init(void); #define CLOCKSOURCE_OF_DECLARE(name, compat, fn) \ OF_DECLARE_1(clksrc, name, compat, fn) -#ifdef CONFIG_CLKSRC_OF -extern void clocksource_of_init(void); +#ifdef CONFIG_CLKSRC_PROBE +extern void clocksource_probe(void); #else -static inline void clocksource_of_init(void) {} +static inline void clocksource_probe(void) {} #endif -#ifdef CONFIG_ACPI -void acpi_generic_timer_init(void); -#else -static inline void acpi_generic_timer_init(void) { } -#endif +#define CLOCKSOURCE_ACPI_DECLARE(name, table_id, fn) \ + ACPI_DECLARE_PROBE_ENTRY(clksrc, name, table_id, 0, NULL, 0, fn) #endif /* _LINUX_CLOCKSOURCE_H */ diff --git a/kernel/include/linux/cma.h b/kernel/include/linux/cma.h index f7ef093ec..29f9e774a 100644 --- a/kernel/include/linux/cma.h +++ b/kernel/include/linux/cma.h @@ -26,6 +26,6 @@ extern int __init cma_declare_contiguous(phys_addr_t base, extern int cma_init_reserved_mem(phys_addr_t base, phys_addr_t size, unsigned int order_per_bit, struct cma **res_cma); -extern struct page *cma_alloc(struct cma *cma, unsigned int count, unsigned int align); +extern struct page *cma_alloc(struct cma *cma, size_t count, unsigned int align); extern bool cma_release(struct cma *cma, const struct page *pages, unsigned int count); #endif diff --git a/kernel/include/linux/com20020.h b/kernel/include/linux/com20020.h deleted file mode 100644 index 85898995b..000000000 --- a/kernel/include/linux/com20020.h +++ /dev/null @@ -1,145 +0,0 @@ -/* - * Linux ARCnet driver - COM20020 chipset support - function declarations - * - * Written 1997 by David Woodhouse. - * Written 1994-1999 by Avery Pennarun. - * Derived from skeleton.c by Donald Becker. - * - * Special thanks to Contemporary Controls, Inc. (www.ccontrols.com) - * for sponsoring the further development of this driver. - * - * ********************** - * - * The original copyright of skeleton.c was as follows: - * - * skeleton.c Written 1993 by Donald Becker. - * Copyright 1993 United States Government as represented by the - * Director, National Security Agency. This software may only be used - * and distributed according to the terms of the GNU General Public License as - * modified by SRC, incorporated herein by reference. - * - * ********************** - * - * For more details, see drivers/net/arcnet.c - * - * ********************** - */ -#ifndef __COM20020_H -#define __COM20020_H - -int com20020_check(struct net_device *dev); -int com20020_found(struct net_device *dev, int shared); -extern const struct net_device_ops com20020_netdev_ops; - -/* The number of low I/O ports used by the card. */ -#define ARCNET_TOTAL_SIZE 8 - -/* various register addresses */ -#ifdef CONFIG_SA1100_CT6001 -#define BUS_ALIGN 2 /* 8 bit device on a 16 bit bus - needs padding */ -#else -#define BUS_ALIGN 1 -#endif - -#define PLX_PCI_MAX_CARDS 2 - -struct com20020_pci_channel_map { - u32 bar; - u32 offset; - u32 size; /* 0x00 - auto, e.g. length of entire bar */ -}; - -struct com20020_pci_card_info { - const char *name; - int devcount; - - struct com20020_pci_channel_map chan_map_tbl[PLX_PCI_MAX_CARDS]; - - unsigned int flags; -}; - -struct com20020_priv { - struct com20020_pci_card_info *ci; - struct list_head list_dev; -}; - -struct com20020_dev { - struct list_head list; - struct net_device *dev; - - struct com20020_priv *pci_priv; - int index; -}; - -#define _INTMASK (ioaddr+BUS_ALIGN*0) /* writable */ -#define _STATUS (ioaddr+BUS_ALIGN*0) /* readable */ -#define _COMMAND (ioaddr+BUS_ALIGN*1) /* standard arcnet commands */ -#define _DIAGSTAT (ioaddr+BUS_ALIGN*1) /* diagnostic status register */ -#define _ADDR_HI (ioaddr+BUS_ALIGN*2) /* control registers for IO-mapped memory */ -#define _ADDR_LO (ioaddr+BUS_ALIGN*3) -#define _MEMDATA (ioaddr+BUS_ALIGN*4) /* data port for IO-mapped memory */ -#define _SUBADR (ioaddr+BUS_ALIGN*5) /* the extended port _XREG refers to */ -#define _CONFIG (ioaddr+BUS_ALIGN*6) /* configuration register */ -#define _XREG (ioaddr+BUS_ALIGN*7) /* extra registers (indexed by _CONFIG - or _SUBADR) */ - -/* in the ADDR_HI register */ -#define RDDATAflag 0x80 /* next access is a read (not a write) */ - -/* in the DIAGSTAT register */ -#define NEWNXTIDflag 0x02 /* ID to which token is passed has changed */ - -/* in the CONFIG register */ -#define RESETcfg 0x80 /* put card in reset state */ -#define TXENcfg 0x20 /* enable TX */ - -/* in SETUP register */ -#define PROMISCset 0x10 /* enable RCV_ALL */ -#define P1MODE 0x80 /* enable P1-MODE for Backplane */ -#define SLOWARB 0x01 /* enable Slow Arbitration for >=5Mbps */ - -/* COM2002x */ -#define SUB_TENTATIVE 0 /* tentative node ID */ -#define SUB_NODE 1 /* node ID */ -#define SUB_SETUP1 2 /* various options */ -#define SUB_TEST 3 /* test/diag register */ - -/* COM20022 only */ -#define SUB_SETUP2 4 /* sundry options */ -#define SUB_BUSCTL 5 /* bus control options */ -#define SUB_DMACOUNT 6 /* DMA count options */ - -#define SET_SUBADR(x) do { \ - if ((x) < 4) \ - { \ - lp->config = (lp->config & ~0x03) | (x); \ - SETCONF; \ - } \ - else \ - { \ - outb(x, _SUBADR); \ - } \ -} while (0) - -#undef ARCRESET -#undef ASTATUS -#undef ACOMMAND -#undef AINTMASK - -#define ARCRESET { outb(lp->config | 0x80, _CONFIG); \ - udelay(5); \ - outb(lp->config , _CONFIG); \ - } -#define ARCRESET0 { outb(0x18 | 0x80, _CONFIG); \ - udelay(5); \ - outb(0x18 , _CONFIG); \ - } - -#define ASTATUS() inb(_STATUS) -#define ADIAGSTATUS() inb(_DIAGSTAT) -#define ACOMMAND(cmd) outb((cmd),_COMMAND) -#define AINTMASK(msk) outb((msk),_INTMASK) - -#define SETCONF outb(lp->config, _CONFIG) - -#endif /* __COM20020_H */ diff --git a/kernel/include/linux/compaction.h b/kernel/include/linux/compaction.h index aa8f61cf3..4cd4ddf64 100644 --- a/kernel/include/linux/compaction.h +++ b/kernel/include/linux/compaction.h @@ -15,7 +15,8 @@ /* For more detailed tracepoint output */ #define COMPACT_NO_SUITABLE_PAGE 5 #define COMPACT_NOT_SUITABLE_ZONE 6 -/* When adding new state, please change compaction_status_string, too */ +#define COMPACT_CONTENDED 7 +/* When adding new states, please adjust include/trace/events/compaction.h */ /* Used to signal whether compaction detected need_sched() or lock contention */ /* No contention detected */ diff --git a/kernel/include/linux/compat.h b/kernel/include/linux/compat.h index ab2581469..a76c9172b 100644 --- a/kernel/include/linux/compat.h +++ b/kernel/include/linux/compat.h @@ -424,7 +424,7 @@ asmlinkage long compat_sys_settimeofday(struct compat_timeval __user *tv, asmlinkage long compat_sys_adjtimex(struct compat_timex __user *utp); -extern int compat_printk(const char *fmt, ...); +extern __printf(1, 2) int compat_printk(const char *fmt, ...); extern void sigset_from_compat(sigset_t *set, const compat_sigset_t *compat); extern void sigset_to_compat(compat_sigset_t *compat, const sigset_t *set); diff --git a/kernel/include/linux/compiler-gcc.h b/kernel/include/linux/compiler-gcc.h index 371e560d1..22ab246fe 100644 --- a/kernel/include/linux/compiler-gcc.h +++ b/kernel/include/linux/compiler-gcc.h @@ -5,9 +5,9 @@ /* * Common definitions for all gcc versions go here. */ -#define GCC_VERSION (__GNUC__ * 10000 \ - + __GNUC_MINOR__ * 100 \ - + __GNUC_PATCHLEVEL__) +#define GCC_VERSION (__GNUC__ * 10000 \ + + __GNUC_MINOR__ * 100 \ + + __GNUC_PATCHLEVEL__) /* Optimization barrier */ @@ -46,55 +46,63 @@ * the inline assembly constraint from =g to =r, in this particular * case either is valid. */ -#define RELOC_HIDE(ptr, off) \ - ({ unsigned long __ptr; \ - __asm__ ("" : "=r"(__ptr) : "0"(ptr)); \ - (typeof(ptr)) (__ptr + (off)); }) +#define RELOC_HIDE(ptr, off) \ +({ \ + unsigned long __ptr; \ + __asm__ ("" : "=r"(__ptr) : "0"(ptr)); \ + (typeof(ptr)) (__ptr + (off)); \ +}) /* Make the optimizer believe the variable can be manipulated arbitrarily. */ -#define OPTIMIZER_HIDE_VAR(var) __asm__ ("" : "=r" (var) : "0" (var)) +#define OPTIMIZER_HIDE_VAR(var) \ + __asm__ ("" : "=r" (var) : "0" (var)) #ifdef __CHECKER__ -#define __must_be_array(arr) 0 +#define __must_be_array(a) 0 #else /* &a[0] degrades to a pointer: a different type from an array */ -#define __must_be_array(a) BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0])) +#define __must_be_array(a) BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0])) #endif /* * Force always-inline if the user requests it so via the .config, * or if gcc is too old: */ -#if !defined(CONFIG_ARCH_SUPPORTS_OPTIMIZED_INLINING) || \ +#if !defined(CONFIG_ARCH_SUPPORTS_OPTIMIZED_INLINING) || \ !defined(CONFIG_OPTIMIZE_INLINING) || (__GNUC__ < 4) -# define inline inline __attribute__((always_inline)) notrace -# define __inline__ __inline__ __attribute__((always_inline)) notrace -# define __inline __inline __attribute__((always_inline)) notrace +#define inline inline __attribute__((always_inline)) notrace +#define __inline__ __inline__ __attribute__((always_inline)) notrace +#define __inline __inline __attribute__((always_inline)) notrace #else /* A lot of inline functions can cause havoc with function tracing */ -# define inline inline notrace -# define __inline__ __inline__ notrace -# define __inline __inline notrace +#define inline inline notrace +#define __inline__ __inline__ notrace +#define __inline __inline notrace #endif -#define __deprecated __attribute__((deprecated)) -#define __packed __attribute__((packed)) -#define __weak __attribute__((weak)) -#define __alias(symbol) __attribute__((alias(#symbol))) +#define __always_inline inline __attribute__((always_inline)) +#define noinline __attribute__((noinline)) + +#define __deprecated __attribute__((deprecated)) +#define __packed __attribute__((packed)) +#define __weak __attribute__((weak)) +#define __alias(symbol) __attribute__((alias(#symbol))) /* - * it doesn't make sense on ARM (currently the only user of __naked) to trace - * naked functions because then mcount is called without stack and frame pointer - * being set up and there is no chance to restore the lr register to the value - * before mcount was called. + * it doesn't make sense on ARM (currently the only user of __naked) + * to trace naked functions because then mcount is called without + * stack and frame pointer being set up and there is no chance to + * restore the lr register to the value before mcount was called. + * + * The asm() bodies of naked functions often depend on standard calling + * conventions, therefore they must be noinline and noclone. * - * The asm() bodies of naked functions often depend on standard calling conventions, - * therefore they must be noinline and noclone. GCC 4.[56] currently fail to enforce - * this, so we must do so ourselves. See GCC PR44290. + * GCC 4.[56] currently fail to enforce this, so we must do so ourselves. + * See GCC PR44290. */ -#define __naked __attribute__((naked)) noinline __noclone notrace +#define __naked __attribute__((naked)) noinline __noclone notrace -#define __noreturn __attribute__((noreturn)) +#define __noreturn __attribute__((noreturn)) /* * From the GCC manual: @@ -106,28 +114,170 @@ * would be. * [...] */ -#define __pure __attribute__((pure)) -#define __aligned(x) __attribute__((aligned(x))) -#define __printf(a, b) __attribute__((format(printf, a, b))) -#define __scanf(a, b) __attribute__((format(scanf, a, b))) -#define noinline __attribute__((noinline)) -#define __attribute_const__ __attribute__((__const__)) -#define __maybe_unused __attribute__((unused)) -#define __always_unused __attribute__((unused)) - -#define __gcc_header(x) #x -#define _gcc_header(x) __gcc_header(linux/compiler-gcc##x.h) -#define gcc_header(x) _gcc_header(x) -#include gcc_header(__GNUC__) +#define __pure __attribute__((pure)) +#define __aligned(x) __attribute__((aligned(x))) +#define __printf(a, b) __attribute__((format(printf, a, b))) +#define __scanf(a, b) __attribute__((format(scanf, a, b))) +#define __attribute_const__ __attribute__((__const__)) +#define __maybe_unused __attribute__((unused)) +#define __always_unused __attribute__((unused)) + +/* gcc version specific checks */ + +#if GCC_VERSION < 30200 +# error Sorry, your compiler is too old - please upgrade it. +#endif + +#if GCC_VERSION < 30300 +# define __used __attribute__((__unused__)) +#else +# define __used __attribute__((__used__)) +#endif + +#ifdef CONFIG_GCOV_KERNEL +# if GCC_VERSION < 30400 +# error "GCOV profiling support for gcc versions below 3.4 not included" +# endif /* __GNUC_MINOR__ */ +#endif /* CONFIG_GCOV_KERNEL */ + +#if GCC_VERSION >= 30400 +#define __must_check __attribute__((warn_unused_result)) +#endif + +#if GCC_VERSION >= 40000 + +/* GCC 4.1.[01] miscompiles __weak */ +#ifdef __KERNEL__ +# if GCC_VERSION >= 40100 && GCC_VERSION <= 40101 +# error Your version of gcc miscompiles the __weak directive +# endif +#endif + +#define __used __attribute__((__used__)) +#define __compiler_offsetof(a, b) \ + __builtin_offsetof(a, b) + +#if GCC_VERSION >= 40100 && GCC_VERSION < 40600 +# define __compiletime_object_size(obj) __builtin_object_size(obj, 0) +#endif + +#if GCC_VERSION >= 40300 +/* Mark functions as cold. gcc will assume any path leading to a call + * to them will be unlikely. This means a lot of manual unlikely()s + * are unnecessary now for any paths leading to the usual suspects + * like BUG(), printk(), panic() etc. [but let's keep them for now for + * older compilers] + * + * Early snapshots of gcc 4.3 don't support this and we can't detect this + * in the preprocessor, but we can live with this because they're unreleased. + * Maketime probing would be overkill here. + * + * gcc also has a __attribute__((__hot__)) to move hot functions into + * a special section, but I don't see any sense in this right now in + * the kernel context + */ +#define __cold __attribute__((__cold__)) + +#define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __COUNTER__) + +#ifndef __CHECKER__ +# define __compiletime_warning(message) __attribute__((warning(message))) +# define __compiletime_error(message) __attribute__((error(message))) +#endif /* __CHECKER__ */ +#endif /* GCC_VERSION >= 40300 */ + +#if GCC_VERSION >= 40500 +/* + * Mark a position in code as unreachable. This can be used to + * suppress control flow warnings after asm blocks that transfer + * control elsewhere. + * + * Early snapshots of gcc 4.5 don't support this and we can't detect + * this in the preprocessor, but we can live with this because they're + * unreleased. Really, we need to have autoconf for the kernel. + */ +#define unreachable() __builtin_unreachable() + +/* Mark a function definition as prohibited from being cloned. */ +#define __noclone __attribute__((__noclone__)) + +#endif /* GCC_VERSION >= 40500 */ + +#if GCC_VERSION >= 40600 +/* + * When used with Link Time Optimization, gcc can optimize away C functions or + * variables which are referenced only from assembly code. __visible tells the + * optimizer that something else uses this function or variable, thus preventing + * this. + */ +#define __visible __attribute__((externally_visible)) +#endif + + +#if GCC_VERSION >= 40900 && !defined(__CHECKER__) +/* + * __assume_aligned(n, k): Tell the optimizer that the returned + * pointer can be assumed to be k modulo n. The second argument is + * optional (default 0), so we use a variadic macro to make the + * shorthand. + * + * Beware: Do not apply this to functions which may return + * ERR_PTRs. Also, it is probably unwise to apply it to functions + * returning extra information in the low bits (but in that case the + * compiler should see some alignment anyway, when the return value is + * massaged by 'flags = ptr & 3; ptr &= ~3;'). + */ +#define __assume_aligned(a, ...) __attribute__((__assume_aligned__(a, ## __VA_ARGS__))) +#endif + +/* + * GCC 'asm goto' miscompiles certain code sequences: + * + * http://gcc.gnu.org/bugzilla/show_bug.cgi?id=58670 + * + * Work it around via a compiler barrier quirk suggested by Jakub Jelinek. + * + * (asm goto is automatically volatile - the naming reflects this.) + */ +#define asm_volatile_goto(x...) do { asm goto(x); asm (""); } while (0) + +#ifdef CONFIG_ARCH_USE_BUILTIN_BSWAP +#if GCC_VERSION >= 40400 +#define __HAVE_BUILTIN_BSWAP32__ +#define __HAVE_BUILTIN_BSWAP64__ +#endif +#if GCC_VERSION >= 40800 || (defined(__powerpc__) && GCC_VERSION >= 40600) +#define __HAVE_BUILTIN_BSWAP16__ +#endif +#endif /* CONFIG_ARCH_USE_BUILTIN_BSWAP */ + +#if GCC_VERSION >= 50000 +#define KASAN_ABI_VERSION 4 +#elif GCC_VERSION >= 40902 +#define KASAN_ABI_VERSION 3 +#endif + +#if GCC_VERSION >= 40902 +/* + * Tell the compiler that address safety instrumentation (KASAN) + * should not be applied to that function. + * Conflicts with inlining: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=67368 + */ +#define __no_sanitize_address __attribute__((no_sanitize_address)) +#endif + +#endif /* gcc version >= 40000 specific checks */ #if !defined(__noclone) #define __noclone /* not needed */ #endif +#if !defined(__no_sanitize_address) +#define __no_sanitize_address +#endif + /* * A trick to suppress uninitialized variable warning without generating any * code */ #define uninitialized_var(x) x = x - -#define __always_inline inline __attribute__((always_inline)) diff --git a/kernel/include/linux/compiler-gcc3.h b/kernel/include/linux/compiler-gcc3.h deleted file mode 100644 index 7d89febe4..000000000 --- a/kernel/include/linux/compiler-gcc3.h +++ /dev/null @@ -1,23 +0,0 @@ -#ifndef __LINUX_COMPILER_H -#error "Please don't include <linux/compiler-gcc3.h> directly, include <linux/compiler.h> instead." -#endif - -#if GCC_VERSION < 30200 -# error Sorry, your compiler is too old - please upgrade it. -#endif - -#if GCC_VERSION >= 30300 -# define __used __attribute__((__used__)) -#else -# define __used __attribute__((__unused__)) -#endif - -#if GCC_VERSION >= 30400 -#define __must_check __attribute__((warn_unused_result)) -#endif - -#ifdef CONFIG_GCOV_KERNEL -# if GCC_VERSION < 30400 -# error "GCOV profiling support for gcc versions below 3.4 not included" -# endif /* __GNUC_MINOR__ */ -#endif /* CONFIG_GCOV_KERNEL */ diff --git a/kernel/include/linux/compiler-gcc4.h b/kernel/include/linux/compiler-gcc4.h deleted file mode 100644 index 769e19864..000000000 --- a/kernel/include/linux/compiler-gcc4.h +++ /dev/null @@ -1,91 +0,0 @@ -#ifndef __LINUX_COMPILER_H -#error "Please don't include <linux/compiler-gcc4.h> directly, include <linux/compiler.h> instead." -#endif - -/* GCC 4.1.[01] miscompiles __weak */ -#ifdef __KERNEL__ -# if GCC_VERSION >= 40100 && GCC_VERSION <= 40101 -# error Your version of gcc miscompiles the __weak directive -# endif -#endif - -#define __used __attribute__((__used__)) -#define __must_check __attribute__((warn_unused_result)) -#define __compiler_offsetof(a,b) __builtin_offsetof(a,b) - -#if GCC_VERSION >= 40100 && GCC_VERSION < 40600 -# define __compiletime_object_size(obj) __builtin_object_size(obj, 0) -#endif - -#if GCC_VERSION >= 40300 -/* Mark functions as cold. gcc will assume any path leading to a call - to them will be unlikely. This means a lot of manual unlikely()s - are unnecessary now for any paths leading to the usual suspects - like BUG(), printk(), panic() etc. [but let's keep them for now for - older compilers] - - Early snapshots of gcc 4.3 don't support this and we can't detect this - in the preprocessor, but we can live with this because they're unreleased. - Maketime probing would be overkill here. - - gcc also has a __attribute__((__hot__)) to move hot functions into - a special section, but I don't see any sense in this right now in - the kernel context */ -#define __cold __attribute__((__cold__)) - -#define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __COUNTER__) - -#ifndef __CHECKER__ -# define __compiletime_warning(message) __attribute__((warning(message))) -# define __compiletime_error(message) __attribute__((error(message))) -#endif /* __CHECKER__ */ -#endif /* GCC_VERSION >= 40300 */ - -#if GCC_VERSION >= 40500 -/* - * Mark a position in code as unreachable. This can be used to - * suppress control flow warnings after asm blocks that transfer - * control elsewhere. - * - * Early snapshots of gcc 4.5 don't support this and we can't detect - * this in the preprocessor, but we can live with this because they're - * unreleased. Really, we need to have autoconf for the kernel. - */ -#define unreachable() __builtin_unreachable() - -/* Mark a function definition as prohibited from being cloned. */ -#define __noclone __attribute__((__noclone__)) - -#endif /* GCC_VERSION >= 40500 */ - -#if GCC_VERSION >= 40600 -/* - * Tell the optimizer that something else uses this function or variable. - */ -#define __visible __attribute__((externally_visible)) -#endif - -/* - * GCC 'asm goto' miscompiles certain code sequences: - * - * http://gcc.gnu.org/bugzilla/show_bug.cgi?id=58670 - * - * Work it around via a compiler barrier quirk suggested by Jakub Jelinek. - * - * (asm goto is automatically volatile - the naming reflects this.) - */ -#define asm_volatile_goto(x...) do { asm goto(x); asm (""); } while (0) - -#ifdef CONFIG_ARCH_USE_BUILTIN_BSWAP -#if GCC_VERSION >= 40400 -#define __HAVE_BUILTIN_BSWAP32__ -#define __HAVE_BUILTIN_BSWAP64__ -#endif -#if GCC_VERSION >= 40800 || (defined(__powerpc__) && GCC_VERSION >= 40600) -#define __HAVE_BUILTIN_BSWAP16__ -#endif -#endif /* CONFIG_ARCH_USE_BUILTIN_BSWAP */ - -#if GCC_VERSION >= 40902 -#define KASAN_ABI_VERSION 3 -#endif diff --git a/kernel/include/linux/compiler-gcc5.h b/kernel/include/linux/compiler-gcc5.h deleted file mode 100644 index efee49371..000000000 --- a/kernel/include/linux/compiler-gcc5.h +++ /dev/null @@ -1,67 +0,0 @@ -#ifndef __LINUX_COMPILER_H -#error "Please don't include <linux/compiler-gcc5.h> directly, include <linux/compiler.h> instead." -#endif - -#define __used __attribute__((__used__)) -#define __must_check __attribute__((warn_unused_result)) -#define __compiler_offsetof(a, b) __builtin_offsetof(a, b) - -/* Mark functions as cold. gcc will assume any path leading to a call - to them will be unlikely. This means a lot of manual unlikely()s - are unnecessary now for any paths leading to the usual suspects - like BUG(), printk(), panic() etc. [but let's keep them for now for - older compilers] - - Early snapshots of gcc 4.3 don't support this and we can't detect this - in the preprocessor, but we can live with this because they're unreleased. - Maketime probing would be overkill here. - - gcc also has a __attribute__((__hot__)) to move hot functions into - a special section, but I don't see any sense in this right now in - the kernel context */ -#define __cold __attribute__((__cold__)) - -#define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __COUNTER__) - -#ifndef __CHECKER__ -# define __compiletime_warning(message) __attribute__((warning(message))) -# define __compiletime_error(message) __attribute__((error(message))) -#endif /* __CHECKER__ */ - -/* - * Mark a position in code as unreachable. This can be used to - * suppress control flow warnings after asm blocks that transfer - * control elsewhere. - * - * Early snapshots of gcc 4.5 don't support this and we can't detect - * this in the preprocessor, but we can live with this because they're - * unreleased. Really, we need to have autoconf for the kernel. - */ -#define unreachable() __builtin_unreachable() - -/* Mark a function definition as prohibited from being cloned. */ -#define __noclone __attribute__((__noclone__)) - -/* - * Tell the optimizer that something else uses this function or variable. - */ -#define __visible __attribute__((externally_visible)) - -/* - * GCC 'asm goto' miscompiles certain code sequences: - * - * http://gcc.gnu.org/bugzilla/show_bug.cgi?id=58670 - * - * Work it around via a compiler barrier quirk suggested by Jakub Jelinek. - * - * (asm goto is automatically volatile - the naming reflects this.) - */ -#define asm_volatile_goto(x...) do { asm goto(x); asm (""); } while (0) - -#ifdef CONFIG_ARCH_USE_BUILTIN_BSWAP -#define __HAVE_BUILTIN_BSWAP32__ -#define __HAVE_BUILTIN_BSWAP64__ -#define __HAVE_BUILTIN_BSWAP16__ -#endif /* CONFIG_ARCH_USE_BUILTIN_BSWAP */ - -#define KASAN_ABI_VERSION 4 diff --git a/kernel/include/linux/compiler.h b/kernel/include/linux/compiler.h index 867722591..6fc9a6dd5 100644 --- a/kernel/include/linux/compiler.h +++ b/kernel/include/linux/compiler.h @@ -17,6 +17,7 @@ # define __release(x) __context__(x,-1) # define __cond_lock(x,c) ((c) ? ({ __acquire(x); 1; }) : 0) # define __percpu __attribute__((noderef, address_space(3))) +# define __pmem __attribute__((noderef, address_space(5))) #ifdef CONFIG_SPARSE_RCU_POINTER # define __rcu __attribute__((noderef, address_space(4))) #else @@ -42,6 +43,7 @@ extern void __chk_io_ptr(const volatile void __iomem *); # define __cond_lock(x,c) (c) # define __percpu # define __rcu +# define __pmem #endif /* Indirect macros required for expanded argument pasting, eg. __LINE__. */ @@ -54,7 +56,7 @@ extern void __chk_io_ptr(const volatile void __iomem *); #include <linux/compiler-gcc.h> #endif -#ifdef CC_USING_HOTPATCH +#if defined(CC_USING_HOTPATCH) && !defined(__CHECKER__) #define notrace __attribute__((hotpatch(0,0))) #else #define notrace __attribute__((no_instrument_function)) @@ -142,7 +144,7 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect); */ #define if(cond, ...) __trace_if( (cond , ## __VA_ARGS__) ) #define __trace_if(cond) \ - if (__builtin_constant_p((cond)) ? !!(cond) : \ + if (__builtin_constant_p(!!(cond)) ? !!(cond) : \ ({ \ int ______r; \ static struct ftrace_branch_data \ @@ -196,19 +198,45 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect); #include <uapi/linux/types.h> -static __always_inline void __read_once_size(const volatile void *p, void *res, int size) +#define __READ_ONCE_SIZE \ +({ \ + switch (size) { \ + case 1: *(__u8 *)res = *(volatile __u8 *)p; break; \ + case 2: *(__u16 *)res = *(volatile __u16 *)p; break; \ + case 4: *(__u32 *)res = *(volatile __u32 *)p; break; \ + case 8: *(__u64 *)res = *(volatile __u64 *)p; break; \ + default: \ + barrier(); \ + __builtin_memcpy((void *)res, (const void *)p, size); \ + barrier(); \ + } \ +}) + +static __always_inline +void __read_once_size(const volatile void *p, void *res, int size) { - switch (size) { - case 1: *(__u8 *)res = *(volatile __u8 *)p; break; - case 2: *(__u16 *)res = *(volatile __u16 *)p; break; - case 4: *(__u32 *)res = *(volatile __u32 *)p; break; - case 8: *(__u64 *)res = *(volatile __u64 *)p; break; - default: - barrier(); - __builtin_memcpy((void *)res, (const void *)p, size); - barrier(); - } + __READ_ONCE_SIZE; +} + +#ifdef CONFIG_KASAN +/* + * This function is not 'inline' because __no_sanitize_address confilcts + * with inlining. Attempt to inline it may cause a build failure. + * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=67368 + * '__maybe_unused' allows us to avoid defined-but-not-used warnings. + */ +static __no_sanitize_address __maybe_unused +void __read_once_size_nocheck(const volatile void *p, void *res, int size) +{ + __READ_ONCE_SIZE; +} +#else +static __always_inline +void __read_once_size_nocheck(const volatile void *p, void *res, int size) +{ + __READ_ONCE_SIZE; } +#endif static __always_inline void __write_once_size(volatile void *p, void *res, int size) { @@ -246,11 +274,30 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s * required ordering. */ -#define READ_ONCE(x) \ - ({ union { typeof(x) __val; char __c[1]; } __u; __read_once_size(&(x), __u.__c, sizeof(x)); __u.__val; }) +#define __READ_ONCE(x, check) \ +({ \ + union { typeof(x) __val; char __c[1]; } __u; \ + if (check) \ + __read_once_size(&(x), __u.__c, sizeof(x)); \ + else \ + __read_once_size_nocheck(&(x), __u.__c, sizeof(x)); \ + __u.__val; \ +}) +#define READ_ONCE(x) __READ_ONCE(x, 1) + +/* + * Use READ_ONCE_NOCHECK() instead of READ_ONCE() if you need + * to hide memory access from KASAN. + */ +#define READ_ONCE_NOCHECK(x) __READ_ONCE(x, 0) #define WRITE_ONCE(x, val) \ - ({ typeof(x) __val = (val); __write_once_size(&(x), &__val, sizeof(__val)); __val; }) +({ \ + union { typeof(x) __val; char __c[1]; } __u = \ + { .__val = (__force typeof(x)) (val) }; \ + __write_once_size(&(x), __u.__c, sizeof(x)); \ + __u.__val; \ +}) #endif /* __KERNEL__ */ @@ -370,6 +417,14 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s #define __visible #endif +/* + * Assume alignment of return value. + */ +#ifndef __assume_aligned +#define __assume_aligned(a, ...) +#endif + + /* Are two types/vars the same type (ignoring qualifiers)? */ #ifndef __same_type # define __same_type(a, b) __builtin_types_compatible_p(typeof(a), typeof(b)) @@ -450,13 +505,28 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s * with an explicit memory barrier or atomic instruction that provides the * required ordering. * - * If possible use READ_ONCE/ASSIGN_ONCE instead. + * If possible use READ_ONCE()/WRITE_ONCE() instead. */ #define __ACCESS_ONCE(x) ({ \ __maybe_unused typeof(x) __var = (__force typeof(x)) 0; \ (volatile typeof(x) *)&(x); }) #define ACCESS_ONCE(x) (*__ACCESS_ONCE(x)) +/** + * lockless_dereference() - safely load a pointer for later dereference + * @p: The pointer to load + * + * Similar to rcu_dereference(), but for situations where the pointed-to + * object's lifetime is managed by something other than RCU. That + * "something other" might be reference counting or simple immortality. + */ +#define lockless_dereference(p) \ +({ \ + typeof(p) _________p1 = READ_ONCE(p); \ + smp_read_barrier_depends(); /* Dependency order vs. p above. */ \ + (_________p1); \ +}) + /* Ignore/forbid kprobes attach on very low level functions marked by this attribute: */ #ifdef CONFIG_KPROBES # define __kprobes __attribute__((__section__(".kprobes.text"))) diff --git a/kernel/include/linux/completion.h b/kernel/include/linux/completion.h index 3fe8d14c9..3bca1590e 100644 --- a/kernel/include/linux/completion.h +++ b/kernel/include/linux/completion.h @@ -7,7 +7,7 @@ * Atomic wait-for-completion handler data structures. * See kernel/sched/completion.c for details. */ -#include <linux/wait-simple.h> +#include <linux/swait.h> /* * struct completion - structure used to maintain state for a "completion" @@ -23,11 +23,11 @@ */ struct completion { unsigned int done; - struct swait_head wait; + struct swait_queue_head wait; }; #define COMPLETION_INITIALIZER(work) \ - { 0, SWAIT_HEAD_INITIALIZER((work).wait) } + { 0, __SWAIT_QUEUE_HEAD_INITIALIZER((work).wait) } #define COMPLETION_INITIALIZER_ONSTACK(work) \ ({ init_completion(&work); work; }) @@ -72,7 +72,7 @@ struct completion { static inline void init_completion(struct completion *x) { x->done = 0; - init_swait_head(&x->wait); + init_swait_queue_head(&x->wait); } /** diff --git a/kernel/include/linux/configfs.h b/kernel/include/linux/configfs.h index 34025df61..758a02901 100644 --- a/kernel/include/linux/configfs.h +++ b/kernel/include/linux/configfs.h @@ -64,14 +64,14 @@ struct config_item { struct dentry *ci_dentry; }; -extern int config_item_set_name(struct config_item *, const char *, ...); +extern __printf(2, 3) +int config_item_set_name(struct config_item *, const char *, ...); static inline char *config_item_name(struct config_item * item) { return item->ci_name; } -extern void config_item_init(struct config_item *); extern void config_item_init_type_name(struct config_item *item, const char *name, struct config_item_type *type); @@ -125,86 +125,33 @@ struct configfs_attribute { const char *ca_name; struct module *ca_owner; umode_t ca_mode; + ssize_t (*show)(struct config_item *, char *); + ssize_t (*store)(struct config_item *, const char *, size_t); }; -/* - * Users often need to create attribute structures for their configurable - * attributes, containing a configfs_attribute member and function pointers - * for the show() and store() operations on that attribute. If they don't - * need anything else on the extended attribute structure, they can use - * this macro to define it The argument _item is the name of the - * config_item structure. - */ -#define CONFIGFS_ATTR_STRUCT(_item) \ -struct _item##_attribute { \ - struct configfs_attribute attr; \ - ssize_t (*show)(struct _item *, char *); \ - ssize_t (*store)(struct _item *, const char *, size_t); \ +#define CONFIGFS_ATTR(_pfx, _name) \ +static struct configfs_attribute _pfx##attr_##_name = { \ + .ca_name = __stringify(_name), \ + .ca_mode = S_IRUGO | S_IWUSR, \ + .ca_owner = THIS_MODULE, \ + .show = _pfx##_name##_show, \ + .store = _pfx##_name##_store, \ } -/* - * With the extended attribute structure, users can use this macro - * (similar to sysfs' __ATTR) to make defining attributes easier. - * An example: - * #define MYITEM_ATTR(_name, _mode, _show, _store) \ - * struct myitem_attribute childless_attr_##_name = \ - * __CONFIGFS_ATTR(_name, _mode, _show, _store) - */ -#define __CONFIGFS_ATTR(_name, _mode, _show, _store) \ -{ \ - .attr = { \ - .ca_name = __stringify(_name), \ - .ca_mode = _mode, \ - .ca_owner = THIS_MODULE, \ - }, \ - .show = _show, \ - .store = _store, \ -} -/* Here is a readonly version, only requiring a show() operation */ -#define __CONFIGFS_ATTR_RO(_name, _show) \ -{ \ - .attr = { \ - .ca_name = __stringify(_name), \ - .ca_mode = 0444, \ - .ca_owner = THIS_MODULE, \ - }, \ - .show = _show, \ +#define CONFIGFS_ATTR_RO(_pfx, _name) \ +static struct configfs_attribute _pfx##attr_##_name = { \ + .ca_name = __stringify(_name), \ + .ca_mode = S_IRUGO, \ + .ca_owner = THIS_MODULE, \ + .show = _pfx##_name##_show, \ } -/* - * With these extended attributes, the simple show_attribute() and - * store_attribute() operations need to call the show() and store() of the - * attributes. This is a common pattern, so we provide a macro to define - * them. The argument _item is the name of the config_item structure. - * This macro expects the attributes to be named "struct <name>_attribute" - * and the function to_<name>() to exist; - */ -#define CONFIGFS_ATTR_OPS(_item) \ -static ssize_t _item##_attr_show(struct config_item *item, \ - struct configfs_attribute *attr, \ - char *page) \ -{ \ - struct _item *_item = to_##_item(item); \ - struct _item##_attribute *_item##_attr = \ - container_of(attr, struct _item##_attribute, attr); \ - ssize_t ret = 0; \ - \ - if (_item##_attr->show) \ - ret = _item##_attr->show(_item, page); \ - return ret; \ -} \ -static ssize_t _item##_attr_store(struct config_item *item, \ - struct configfs_attribute *attr, \ - const char *page, size_t count) \ -{ \ - struct _item *_item = to_##_item(item); \ - struct _item##_attribute *_item##_attr = \ - container_of(attr, struct _item##_attribute, attr); \ - ssize_t ret = -EINVAL; \ - \ - if (_item##_attr->store) \ - ret = _item##_attr->store(_item, page, count); \ - return ret; \ +#define CONFIGFS_ATTR_WO(_pfx, _name) \ +static struct configfs_attribute _pfx##attr_##_name = { \ + .ca_name = __stringify(_name), \ + .ca_mode = S_IWUSR, \ + .ca_owner = THIS_MODULE, \ + .store = _pfx##_name##_store, \ } /* @@ -223,8 +170,6 @@ static ssize_t _item##_attr_store(struct config_item *item, \ */ struct configfs_item_operations { void (*release)(struct config_item *); - ssize_t (*show_attribute)(struct config_item *, struct configfs_attribute *,char *); - ssize_t (*store_attribute)(struct config_item *,struct configfs_attribute *,const char *, size_t); int (*allow_link)(struct config_item *src, struct config_item *target); int (*drop_link)(struct config_item *src, struct config_item *target); }; @@ -252,6 +197,16 @@ static inline struct configfs_subsystem *to_configfs_subsystem(struct config_gro int configfs_register_subsystem(struct configfs_subsystem *subsys); void configfs_unregister_subsystem(struct configfs_subsystem *subsys); +int configfs_register_group(struct config_group *parent_group, + struct config_group *group); +void configfs_unregister_group(struct config_group *group); + +struct config_group * +configfs_register_default_group(struct config_group *parent_group, + const char *name, + struct config_item_type *item_type); +void configfs_unregister_default_group(struct config_group *group); + /* These functions can sleep and can alloc with GFP_KERNEL */ /* WARNING: These cannot be called underneath configfs callbacks!! */ int configfs_depend_item(struct configfs_subsystem *subsys, struct config_item *target); diff --git a/kernel/include/linux/console.h b/kernel/include/linux/console.h index 9f50fb413..ea731af24 100644 --- a/kernel/include/linux/console.h +++ b/kernel/include/linux/console.h @@ -115,6 +115,7 @@ static inline int con_debug_leave(void) #define CON_BOOT (8) #define CON_ANYTIME (16) /* Safe to call when cpu is offline */ #define CON_BRL (32) /* Used for a braille device */ +#define CON_EXTENDED (64) /* Use the extended output format a la /dev/kmsg */ struct console { char name[16]; @@ -149,6 +150,7 @@ extern int console_trylock(void); extern void console_unlock(void); extern void console_conditional_schedule(void); extern void console_unblank(void); +extern void console_flush_on_panic(void); extern struct tty_driver *console_device(int *); extern void console_stop(struct console *); extern void console_start(struct console *); diff --git a/kernel/include/linux/console_struct.h b/kernel/include/linux/console_struct.h index e859c98d1..e329ee266 100644 --- a/kernel/include/linux/console_struct.h +++ b/kernel/include/linux/console_struct.h @@ -104,6 +104,7 @@ struct vc_data { unsigned int vc_resize_user; /* resize request from user */ unsigned int vc_bell_pitch; /* Console bell pitch */ unsigned int vc_bell_duration; /* Console bell duration */ + unsigned short vc_cur_blink_ms; /* Cursor blink duration */ struct vc_data **vc_display_fg; /* [!] Ptr to var holding fg console for this display */ struct uni_pagedir *vc_uni_pagedir; struct uni_pagedir **vc_uni_pagedir_loc; /* [!] Location of uni_pagedir variable for this console */ diff --git a/kernel/include/linux/context_tracking.h b/kernel/include/linux/context_tracking.h index 282183825..68b575afe 100644 --- a/kernel/include/linux/context_tracking.h +++ b/kernel/include/linux/context_tracking.h @@ -10,23 +10,25 @@ #ifdef CONFIG_CONTEXT_TRACKING extern void context_tracking_cpu_set(int cpu); +/* Called with interrupts disabled. */ +extern void __context_tracking_enter(enum ctx_state state); +extern void __context_tracking_exit(enum ctx_state state); + extern void context_tracking_enter(enum ctx_state state); extern void context_tracking_exit(enum ctx_state state); extern void context_tracking_user_enter(void); extern void context_tracking_user_exit(void); -extern void __context_tracking_task_switch(struct task_struct *prev, - struct task_struct *next); static inline void user_enter(void) { if (context_tracking_is_enabled()) - context_tracking_user_enter(); + context_tracking_enter(CONTEXT_USER); } static inline void user_exit(void) { if (context_tracking_is_enabled()) - context_tracking_user_exit(); + context_tracking_exit(CONTEXT_USER); } static inline enum ctx_state exception_enter(void) @@ -51,21 +53,28 @@ static inline void exception_exit(enum ctx_state prev_ctx) } } -static inline void context_tracking_task_switch(struct task_struct *prev, - struct task_struct *next) + +/** + * ct_state() - return the current context tracking state if known + * + * Returns the current cpu's context tracking state if context tracking + * is enabled. If context tracking is disabled, returns + * CONTEXT_DISABLED. This should be used primarily for debugging. + */ +static inline enum ctx_state ct_state(void) { - if (context_tracking_is_enabled()) - __context_tracking_task_switch(prev, next); + return context_tracking_is_enabled() ? + this_cpu_read(context_tracking.state) : CONTEXT_DISABLED; } #else static inline void user_enter(void) { } static inline void user_exit(void) { } static inline enum ctx_state exception_enter(void) { return 0; } static inline void exception_exit(enum ctx_state prev_ctx) { } -static inline void context_tracking_task_switch(struct task_struct *prev, - struct task_struct *next) { } +static inline enum ctx_state ct_state(void) { return CONTEXT_DISABLED; } #endif /* !CONFIG_CONTEXT_TRACKING */ +#define CT_WARN_ON(cond) WARN_ON(context_tracking_is_enabled() && (cond)) #ifdef CONFIG_CONTEXT_TRACKING_FORCE extern void context_tracking_init(void); @@ -83,13 +92,13 @@ static inline void guest_enter(void) current->flags |= PF_VCPU; if (context_tracking_is_enabled()) - context_tracking_enter(CONTEXT_GUEST); + __context_tracking_enter(CONTEXT_GUEST); } static inline void guest_exit(void) { if (context_tracking_is_enabled()) - context_tracking_exit(CONTEXT_GUEST); + __context_tracking_exit(CONTEXT_GUEST); if (vtime_accounting_enabled()) vtime_guest_exit(current); diff --git a/kernel/include/linux/context_tracking_state.h b/kernel/include/linux/context_tracking_state.h index 6b7b96a32..ee956c528 100644 --- a/kernel/include/linux/context_tracking_state.h +++ b/kernel/include/linux/context_tracking_state.h @@ -12,7 +12,9 @@ struct context_tracking { * may be further optimized using static keys. */ bool active; + int recursion; enum ctx_state { + CONTEXT_DISABLED = -1, /* returned by ct_state() if unknown */ CONTEXT_KERNEL = 0, CONTEXT_USER, CONTEXT_GUEST, diff --git a/kernel/include/linux/coresight.h b/kernel/include/linux/coresight.h index 3486b9082..a7cabfa23 100644 --- a/kernel/include/linux/coresight.h +++ b/kernel/include/linux/coresight.h @@ -14,6 +14,7 @@ #define _LINUX_CORESIGHT_H #include <linux/device.h> +#include <linux/sched.h> /* Peripheral id registers (0xFD0-0xFEC) */ #define CORESIGHT_PERIPHIDR4 0xfd0 @@ -206,7 +207,7 @@ struct coresight_ops_link { * Operations available for sources. * @trace_id: returns the value of the component's trace ID as known to the HW. - * @enable: enables tracing from a source. + * @enable: enables tracing for a source. * @disable: disables tracing for a source. */ struct coresight_ops_source { @@ -248,4 +249,24 @@ static inline struct coresight_platform_data *of_get_coresight_platform_data( struct device *dev, struct device_node *node) { return NULL; } #endif +#ifdef CONFIG_PID_NS +static inline unsigned long +coresight_vpid_to_pid(unsigned long vpid) +{ + struct task_struct *task = NULL; + unsigned long pid = 0; + + rcu_read_lock(); + task = find_task_by_vpid(vpid); + if (task) + pid = task_pid_nr(task); + rcu_read_unlock(); + + return pid; +} +#else +static inline unsigned long +coresight_vpid_to_pid(unsigned long vpid) { return vpid; } +#endif + #endif diff --git a/kernel/include/linux/count_zeros.h b/kernel/include/linux/count_zeros.h new file mode 100644 index 000000000..363da78c4 --- /dev/null +++ b/kernel/include/linux/count_zeros.h @@ -0,0 +1,57 @@ +/* Count leading and trailing zeros functions + * + * Copyright (C) 2012 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + */ + +#ifndef _LINUX_BITOPS_COUNT_ZEROS_H_ +#define _LINUX_BITOPS_COUNT_ZEROS_H_ + +#include <asm/bitops.h> + +/** + * count_leading_zeros - Count the number of zeros from the MSB back + * @x: The value + * + * Count the number of leading zeros from the MSB going towards the LSB in @x. + * + * If the MSB of @x is set, the result is 0. + * If only the LSB of @x is set, then the result is BITS_PER_LONG-1. + * If @x is 0 then the result is COUNT_LEADING_ZEROS_0. + */ +static inline int count_leading_zeros(unsigned long x) +{ + if (sizeof(x) == 4) + return BITS_PER_LONG - fls(x); + else + return BITS_PER_LONG - fls64(x); +} + +#define COUNT_LEADING_ZEROS_0 BITS_PER_LONG + +/** + * count_trailing_zeros - Count the number of zeros from the LSB forwards + * @x: The value + * + * Count the number of trailing zeros from the LSB going towards the MSB in @x. + * + * If the LSB of @x is set, the result is 0. + * If only the MSB of @x is set, then the result is BITS_PER_LONG-1. + * If @x is 0 then the result is COUNT_TRAILING_ZEROS_0. + */ +static inline int count_trailing_zeros(unsigned long x) +{ +#define COUNT_TRAILING_ZEROS_0 (-1) + + if (sizeof(x) == 4) + return ffs(x); + else + return (x != 0) ? __ffs(x) : COUNT_TRAILING_ZEROS_0; +} + +#endif /* _LINUX_BITOPS_COUNT_ZEROS_H_ */ diff --git a/kernel/include/linux/cpu.h b/kernel/include/linux/cpu.h index 2a22c7c72..94041d803 100644 --- a/kernel/include/linux/cpu.h +++ b/kernel/include/linux/cpu.h @@ -40,9 +40,10 @@ extern void cpu_remove_dev_attr(struct device_attribute *attr); extern int cpu_add_dev_attr_group(struct attribute_group *attrs); extern void cpu_remove_dev_attr_group(struct attribute_group *attrs); -extern struct device *cpu_device_create(struct device *parent, void *drvdata, - const struct attribute_group **groups, - const char *fmt, ...); +extern __printf(4, 5) +struct device *cpu_device_create(struct device *parent, void *drvdata, + const struct attribute_group **groups, + const char *fmt, ...); #ifdef CONFIG_HOTPLUG_CPU extern void unregister_cpu(struct cpu *cpu); extern ssize_t arch_cpu_probe(const char *, size_t); @@ -227,7 +228,6 @@ extern struct bus_type cpu_subsys; extern void cpu_hotplug_begin(void); extern void cpu_hotplug_done(void); extern void get_online_cpus(void); -extern bool try_get_online_cpus(void); extern void put_online_cpus(void); extern void cpu_hotplug_disable(void); extern void cpu_hotplug_enable(void); @@ -247,7 +247,6 @@ int cpu_down(unsigned int cpu); static inline void cpu_hotplug_begin(void) {} static inline void cpu_hotplug_done(void) {} #define get_online_cpus() do { } while (0) -#define try_get_online_cpus() true #define put_online_cpus() do { } while (0) #define cpu_hotplug_disable() do { } while (0) #define cpu_hotplug_enable() do { } while (0) diff --git a/kernel/include/linux/cpu_cooling.h b/kernel/include/linux/cpu_cooling.h index bd955270d..c156f5082 100644 --- a/kernel/include/linux/cpu_cooling.h +++ b/kernel/include/linux/cpu_cooling.h @@ -28,6 +28,9 @@ #include <linux/thermal.h> #include <linux/cpumask.h> +typedef int (*get_static_t)(cpumask_t *cpumask, int interval, + unsigned long voltage, u32 *power); + #ifdef CONFIG_CPU_THERMAL /** * cpufreq_cooling_register - function to create cpufreq cooling device. @@ -36,6 +39,10 @@ struct thermal_cooling_device * cpufreq_cooling_register(const struct cpumask *clip_cpus); +struct thermal_cooling_device * +cpufreq_power_cooling_register(const struct cpumask *clip_cpus, + u32 capacitance, get_static_t plat_static_func); + /** * of_cpufreq_cooling_register - create cpufreq cooling device based on DT. * @np: a valid struct device_node to the cooling device device tree node. @@ -45,6 +52,12 @@ cpufreq_cooling_register(const struct cpumask *clip_cpus); struct thermal_cooling_device * of_cpufreq_cooling_register(struct device_node *np, const struct cpumask *clip_cpus); + +struct thermal_cooling_device * +of_cpufreq_power_cooling_register(struct device_node *np, + const struct cpumask *clip_cpus, + u32 capacitance, + get_static_t plat_static_func); #else static inline struct thermal_cooling_device * of_cpufreq_cooling_register(struct device_node *np, @@ -52,6 +65,15 @@ of_cpufreq_cooling_register(struct device_node *np, { return ERR_PTR(-ENOSYS); } + +static inline struct thermal_cooling_device * +of_cpufreq_power_cooling_register(struct device_node *np, + const struct cpumask *clip_cpus, + u32 capacitance, + get_static_t plat_static_func) +{ + return NULL; +} #endif /** @@ -68,11 +90,28 @@ cpufreq_cooling_register(const struct cpumask *clip_cpus) return ERR_PTR(-ENOSYS); } static inline struct thermal_cooling_device * +cpufreq_power_cooling_register(const struct cpumask *clip_cpus, + u32 capacitance, get_static_t plat_static_func) +{ + return NULL; +} + +static inline struct thermal_cooling_device * of_cpufreq_cooling_register(struct device_node *np, const struct cpumask *clip_cpus) { return ERR_PTR(-ENOSYS); } + +static inline struct thermal_cooling_device * +of_cpufreq_power_cooling_register(struct device_node *np, + const struct cpumask *clip_cpus, + u32 capacitance, + get_static_t plat_static_func) +{ + return NULL; +} + static inline void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev) { diff --git a/kernel/include/linux/cpufeature.h b/kernel/include/linux/cpufeature.h index c4d4eb8ac..986c06c88 100644 --- a/kernel/include/linux/cpufeature.h +++ b/kernel/include/linux/cpufeature.h @@ -11,6 +11,7 @@ #ifdef CONFIG_GENERIC_CPU_AUTOPROBE +#include <linux/init.h> #include <linux/mod_devicetable.h> #include <asm/cpufeature.h> @@ -43,16 +44,16 @@ * For a list of legal values for 'feature', please consult the file * 'asm/cpufeature.h' of your favorite architecture. */ -#define module_cpu_feature_match(x, __init) \ +#define module_cpu_feature_match(x, __initfunc) \ static struct cpu_feature const cpu_feature_match_ ## x[] = \ { { .feature = cpu_feature(x) }, { } }; \ MODULE_DEVICE_TABLE(cpu, cpu_feature_match_ ## x); \ \ -static int cpu_feature_match_ ## x ## _init(void) \ +static int __init cpu_feature_match_ ## x ## _init(void) \ { \ if (!cpu_have_feature(cpu_feature(x))) \ return -ENODEV; \ - return __init(); \ + return __initfunc(); \ } \ module_init(cpu_feature_match_ ## x ## _init) diff --git a/kernel/include/linux/cpufreq.h b/kernel/include/linux/cpufreq.h index 2ee4888c1..177c7680c 100644 --- a/kernel/include/linux/cpufreq.h +++ b/kernel/include/linux/cpufreq.h @@ -51,21 +51,21 @@ struct cpufreq_cpuinfo { unsigned int transition_latency; }; -struct cpufreq_real_policy { +struct cpufreq_user_policy { unsigned int min; /* in kHz */ unsigned int max; /* in kHz */ - unsigned int policy; /* see above */ - struct cpufreq_governor *governor; /* see below */ }; struct cpufreq_policy { /* CPUs sharing clock, require sw coordination */ cpumask_var_t cpus; /* Online CPUs only */ cpumask_var_t related_cpus; /* Online + Offline CPUs */ + cpumask_var_t real_cpus; /* Related and present */ unsigned int shared_type; /* ACPI: ANY or ALL affected CPUs should set cpufreq */ - unsigned int cpu; /* cpu nr of CPU managing this policy */ + unsigned int cpu; /* cpu managing this policy, must be online */ + struct clk *clk; struct cpufreq_cpuinfo cpuinfo;/* see above */ @@ -77,14 +77,16 @@ struct cpufreq_policy { unsigned int suspend_freq; /* freq to set during suspend */ unsigned int policy; /* see above */ + unsigned int last_policy; /* policy before unplug */ struct cpufreq_governor *governor; /* see below */ void *governor_data; bool governor_enabled; /* governor start/stop flag */ + char last_governor[CPUFREQ_NAME_LEN]; /* last governor used */ struct work_struct update; /* if update_policy() needs to be * called, but you're in IRQ context */ - struct cpufreq_real_policy user_policy; + struct cpufreq_user_policy user_policy; struct cpufreq_frequency_table *freq_table; struct list_head policy_list; @@ -125,9 +127,14 @@ struct cpufreq_policy { #define CPUFREQ_SHARED_TYPE_ANY (3) /* Freq can be set from any dependent CPU*/ #ifdef CONFIG_CPU_FREQ +struct cpufreq_policy *cpufreq_cpu_get_raw(unsigned int cpu); struct cpufreq_policy *cpufreq_cpu_get(unsigned int cpu); void cpufreq_cpu_put(struct cpufreq_policy *policy); #else +static inline struct cpufreq_policy *cpufreq_cpu_get_raw(unsigned int cpu) +{ + return NULL; +} static inline struct cpufreq_policy *cpufreq_cpu_get(unsigned int cpu) { return NULL; @@ -142,10 +149,6 @@ static inline bool policy_is_shared(struct cpufreq_policy *policy) /* /sys/devices/system/cpu/cpufreq: entry point for global variables */ extern struct kobject *cpufreq_global_kobject; -int cpufreq_get_global_kobject(void); -void cpufreq_put_global_kobject(void); -int cpufreq_sysfs_create_file(const struct attribute *attr); -void cpufreq_sysfs_remove_file(const struct attribute *attr); #ifdef CONFIG_CPU_FREQ unsigned int cpufreq_get(unsigned int cpu); @@ -365,11 +368,10 @@ static inline void cpufreq_resume(void) {} /* Policy Notifiers */ #define CPUFREQ_ADJUST (0) -#define CPUFREQ_INCOMPATIBLE (1) -#define CPUFREQ_NOTIFY (2) -#define CPUFREQ_START (3) -#define CPUFREQ_CREATE_POLICY (4) -#define CPUFREQ_REMOVE_POLICY (5) +#define CPUFREQ_NOTIFY (1) +#define CPUFREQ_START (2) +#define CPUFREQ_CREATE_POLICY (3) +#define CPUFREQ_REMOVE_POLICY (4) #ifdef CONFIG_CPU_FREQ int cpufreq_register_notifier(struct notifier_block *nb, unsigned int list); @@ -574,6 +576,8 @@ ssize_t cpufreq_show_cpus(const struct cpumask *mask, char *buf); int cpufreq_boost_trigger_state(int state); int cpufreq_boost_supported(void); int cpufreq_boost_enabled(void); +int cpufreq_enable_boost_support(void); +bool policy_has_boost_freq(struct cpufreq_policy *policy); #else static inline int cpufreq_boost_trigger_state(int state) { @@ -587,12 +591,23 @@ static inline int cpufreq_boost_enabled(void) { return 0; } + +static inline int cpufreq_enable_boost_support(void) +{ + return -EINVAL; +} + +static inline bool policy_has_boost_freq(struct cpufreq_policy *policy) +{ + return false; +} #endif /* the following funtion is for cpufreq core use only */ struct cpufreq_frequency_table *cpufreq_frequency_get_table(unsigned int cpu); /* the following are really really optional */ extern struct freq_attr cpufreq_freq_attr_scaling_available_freqs; +extern struct freq_attr cpufreq_freq_attr_scaling_boost_freqs; extern struct freq_attr *cpufreq_generic_attr[]; int cpufreq_table_validate_and_show(struct cpufreq_policy *policy, struct cpufreq_frequency_table *table); diff --git a/kernel/include/linux/cpuidle.h b/kernel/include/linux/cpuidle.h index 9c5e89254..786ad3263 100644 --- a/kernel/include/linux/cpuidle.h +++ b/kernel/include/linux/cpuidle.h @@ -84,7 +84,6 @@ struct cpuidle_device { struct list_head device_list; #ifdef CONFIG_ARCH_NEEDS_CPU_IDLE_COUPLED - int safe_state_index; cpumask_t coupled_cpus; struct cpuidle_coupled *coupled; #endif @@ -151,10 +150,6 @@ extern void cpuidle_resume(void); extern int cpuidle_enable_device(struct cpuidle_device *dev); extern void cpuidle_disable_device(struct cpuidle_device *dev); extern int cpuidle_play_dead(void); -extern int cpuidle_find_deepest_state(struct cpuidle_driver *drv, - struct cpuidle_device *dev); -extern int cpuidle_enter_freeze(struct cpuidle_driver *drv, - struct cpuidle_device *dev); extern struct cpuidle_driver *cpuidle_get_cpu_driver(struct cpuidle_device *dev); #else @@ -190,16 +185,28 @@ static inline int cpuidle_enable_device(struct cpuidle_device *dev) {return -ENODEV; } static inline void cpuidle_disable_device(struct cpuidle_device *dev) { } static inline int cpuidle_play_dead(void) {return -ENODEV; } +static inline struct cpuidle_driver *cpuidle_get_cpu_driver( + struct cpuidle_device *dev) {return NULL; } +#endif + +#if defined(CONFIG_CPU_IDLE) && defined(CONFIG_SUSPEND) +extern int cpuidle_find_deepest_state(struct cpuidle_driver *drv, + struct cpuidle_device *dev); +extern int cpuidle_enter_freeze(struct cpuidle_driver *drv, + struct cpuidle_device *dev); +#else static inline int cpuidle_find_deepest_state(struct cpuidle_driver *drv, struct cpuidle_device *dev) {return -ENODEV; } static inline int cpuidle_enter_freeze(struct cpuidle_driver *drv, struct cpuidle_device *dev) {return -ENODEV; } -static inline struct cpuidle_driver *cpuidle_get_cpu_driver( - struct cpuidle_device *dev) {return NULL; } #endif +/* kernel/sched/idle.c */ +extern void sched_idle_set_state(struct cpuidle_state *idle_state); +extern void default_idle_call(void); + #ifdef CONFIG_ARCH_NEEDS_CPU_IDLE_COUPLED void cpuidle_coupled_parallel_barrier(struct cpuidle_device *dev, atomic_t *a); #else diff --git a/kernel/include/linux/cpuset.h b/kernel/include/linux/cpuset.h index 1b357997c..fea160ee5 100644 --- a/kernel/include/linux/cpuset.h +++ b/kernel/include/linux/cpuset.h @@ -93,7 +93,7 @@ extern int current_cpuset_is_being_rebound(void); extern void rebuild_sched_domains(void); -extern void cpuset_print_task_mems_allowed(struct task_struct *p); +extern void cpuset_print_current_mems_allowed(void); /* * read_mems_allowed_begin is required when making decisions involving @@ -104,6 +104,9 @@ extern void cpuset_print_task_mems_allowed(struct task_struct *p); */ static inline unsigned int read_mems_allowed_begin(void) { + if (!cpusets_enabled()) + return 0; + return read_seqcount_begin(¤t->mems_allowed_seq); } @@ -115,6 +118,9 @@ static inline unsigned int read_mems_allowed_begin(void) */ static inline bool read_mems_allowed_retry(unsigned int seq) { + if (!cpusets_enabled()) + return false; + return read_seqcount_retry(¤t->mems_allowed_seq, seq); } @@ -131,6 +137,8 @@ static inline void set_mems_allowed(nodemask_t nodemask) task_unlock(current); } +extern void cpuset_post_attach_flush(void); + #else /* !CONFIG_CPUSETS */ static inline bool cpusets_enabled(void) { return false; } @@ -219,7 +227,7 @@ static inline void rebuild_sched_domains(void) partition_sched_domains(1, NULL, NULL); } -static inline void cpuset_print_task_mems_allowed(struct task_struct *p) +static inline void cpuset_print_current_mems_allowed(void) { } @@ -237,6 +245,10 @@ static inline bool read_mems_allowed_retry(unsigned int seq) return false; } +static inline void cpuset_post_attach_flush(void) +{ +} + #endif /* !CONFIG_CPUSETS */ #endif /* _LINUX_CPUSET_H */ diff --git a/kernel/include/linux/crc-itu-t.h b/kernel/include/linux/crc-itu-t.h index 84920f3cc..a9953c762 100644 --- a/kernel/include/linux/crc-itu-t.h +++ b/kernel/include/linux/crc-itu-t.h @@ -3,7 +3,7 @@ * * Implements the standard CRC ITU-T V.41: * Width 16 - * Poly 0x0x1021 (x^16 + x^12 + x^15 + 1) + * Poly 0x1021 (x^16 + x^12 + x^15 + 1) * Init 0 * * This source code is licensed under the GNU General Public License, diff --git a/kernel/include/linux/crc-t10dif.h b/kernel/include/linux/crc-t10dif.h index cf53d0773..d81961e9e 100644 --- a/kernel/include/linux/crc-t10dif.h +++ b/kernel/include/linux/crc-t10dif.h @@ -9,5 +9,6 @@ extern __u16 crc_t10dif_generic(__u16 crc, const unsigned char *buffer, size_t len); extern __u16 crc_t10dif(unsigned char const *, size_t); +extern __u16 crc_t10dif_update(__u16 crc, unsigned char const *, size_t); #endif diff --git a/kernel/include/linux/cred.h b/kernel/include/linux/cred.h index 8b6c083e6..8d70e1361 100644 --- a/kernel/include/linux/cred.h +++ b/kernel/include/linux/cred.h @@ -137,6 +137,7 @@ struct cred { kernel_cap_t cap_permitted; /* caps we're permitted */ kernel_cap_t cap_effective; /* caps we can actually use */ kernel_cap_t cap_bset; /* capability bounding set */ + kernel_cap_t cap_ambient; /* Ambient capability set */ #ifdef CONFIG_KEYS unsigned char jit_keyring; /* default keyring to attach requested * keys to */ @@ -212,6 +213,13 @@ static inline void validate_process_creds(void) } #endif +static inline bool cap_ambient_invariant_ok(const struct cred *cred) +{ + return cap_issubset(cred->cap_ambient, + cap_intersect(cred->cap_permitted, + cred->cap_inheritable)); +} + /** * get_new_cred - Get a reference on a new set of credentials * @cred: The new credentials to reference diff --git a/kernel/include/linux/crush/crush.h b/kernel/include/linux/crush/crush.h index 48a1a7d10..48b493057 100644 --- a/kernel/include/linux/crush/crush.h +++ b/kernel/include/linux/crush/crush.h @@ -1,7 +1,11 @@ #ifndef CEPH_CRUSH_CRUSH_H #define CEPH_CRUSH_CRUSH_H -#include <linux/types.h> +#ifdef __KERNEL__ +# include <linux/types.h> +#else +# include "crush_compat.h" +#endif /* * CRUSH is a pseudo-random data distribution algorithm that @@ -20,7 +24,11 @@ #define CRUSH_MAGIC 0x00010000ul /* for detecting algorithm revisions */ #define CRUSH_MAX_DEPTH 10 /* max crush hierarchy depth */ +#define CRUSH_MAX_RULESET (1<<8) /* max crush ruleset number */ +#define CRUSH_MAX_RULES CRUSH_MAX_RULESET /* should be the same as max rulesets */ +#define CRUSH_MAX_DEVICE_WEIGHT (100u * 0x10000u) +#define CRUSH_MAX_BUCKET_WEIGHT (65535u * 0x10000u) #define CRUSH_ITEM_UNDEF 0x7ffffffe /* undefined result (internal use only) */ #define CRUSH_ITEM_NONE 0x7fffffff /* no result */ @@ -108,6 +116,15 @@ enum { }; extern const char *crush_bucket_alg_name(int alg); +/* + * although tree was a legacy algorithm, it has been buggy, so + * exclude it. + */ +#define CRUSH_LEGACY_ALLOWED_BUCKET_ALGS ( \ + (1 << CRUSH_BUCKET_UNIFORM) | \ + (1 << CRUSH_BUCKET_LIST) | \ + (1 << CRUSH_BUCKET_STRAW)) + struct crush_bucket { __s32 id; /* this'll be negative */ __u16 type; /* non-zero; type=0 is reserved for devices */ @@ -174,7 +191,7 @@ struct crush_map { /* choose local attempts using a fallback permutation before * re-descent */ __u32 choose_local_fallback_tries; - /* choose attempts before giving up */ + /* choose attempts before giving up */ __u32 choose_total_tries; /* attempt chooseleaf inner descent once for firstn mode; on * reject retry outer descent. Note that this does *not* @@ -187,6 +204,25 @@ struct crush_map { * that want to limit reshuffling, a value of 3 or 4 will make the * mappings line up a bit better with previous mappings. */ __u8 chooseleaf_vary_r; + +#ifndef __KERNEL__ + /* + * version 0 (original) of straw_calc has various flaws. version 1 + * fixes a few of them. + */ + __u8 straw_calc_version; + + /* + * allowed bucket algs is a bitmask, here the bit positions + * are CRUSH_BUCKET_*. note that these are *bits* and + * CRUSH_BUCKET_* values are not, so we need to or together (1 + * << CRUSH_BUCKET_WHATEVER). The 0th bit is not used to + * minimize confusion (bucket type values start at 1). + */ + __u32 allowed_bucket_algs; + + __u32 *choose_tries; +#endif }; diff --git a/kernel/include/linux/crush/hash.h b/kernel/include/linux/crush/hash.h index 91e884230..d1d902582 100644 --- a/kernel/include/linux/crush/hash.h +++ b/kernel/include/linux/crush/hash.h @@ -1,6 +1,12 @@ #ifndef CEPH_CRUSH_HASH_H #define CEPH_CRUSH_HASH_H +#ifdef __KERNEL__ +# include <linux/types.h> +#else +# include "crush_compat.h" +#endif + #define CRUSH_HASH_RJENKINS1 0 #define CRUSH_HASH_DEFAULT CRUSH_HASH_RJENKINS1 diff --git a/kernel/include/linux/crush/mapper.h b/kernel/include/linux/crush/mapper.h index eab367446..5dfd5b112 100644 --- a/kernel/include/linux/crush/mapper.h +++ b/kernel/include/linux/crush/mapper.h @@ -8,7 +8,7 @@ * LGPL2 */ -#include <linux/crush/crush.h> +#include "crush.h" extern int crush_find_rule(const struct crush_map *map, int ruleset, int type, int size); extern int crush_do_rule(const struct crush_map *map, diff --git a/kernel/include/linux/crypto.h b/kernel/include/linux/crypto.h index 10df5d2d0..e71cb70a1 100644 --- a/kernel/include/linux/crypto.h +++ b/kernel/include/linux/crypto.h @@ -53,6 +53,7 @@ #define CRYPTO_ALG_TYPE_SHASH 0x00000009 #define CRYPTO_ALG_TYPE_AHASH 0x0000000a #define CRYPTO_ALG_TYPE_RNG 0x0000000c +#define CRYPTO_ALG_TYPE_AKCIPHER 0x0000000d #define CRYPTO_ALG_TYPE_PCOMPRESS 0x0000000f #define CRYPTO_ALG_TYPE_HASH_MASK 0x0000000e @@ -135,13 +136,10 @@ struct scatterlist; struct crypto_ablkcipher; struct crypto_async_request; -struct crypto_aead; struct crypto_blkcipher; struct crypto_hash; -struct crypto_rng; struct crypto_tfm; struct crypto_type; -struct aead_givcrypt_request; struct skcipher_givcrypt_request; typedef void (*crypto_completion_t)(struct crypto_async_request *req, int err); @@ -175,32 +173,6 @@ struct ablkcipher_request { void *__ctx[] CRYPTO_MINALIGN_ATTR; }; -/** - * struct aead_request - AEAD request - * @base: Common attributes for async crypto requests - * @assoclen: Length in bytes of associated data for authentication - * @cryptlen: Length of data to be encrypted or decrypted - * @iv: Initialisation vector - * @assoc: Associated data - * @src: Source data - * @dst: Destination data - * @__ctx: Start of private context data - */ -struct aead_request { - struct crypto_async_request base; - - unsigned int assoclen; - unsigned int cryptlen; - - u8 *iv; - - struct scatterlist *assoc; - struct scatterlist *src; - struct scatterlist *dst; - - void *__ctx[] CRYPTO_MINALIGN_ATTR; -}; - struct blkcipher_desc { struct crypto_blkcipher *tfm; void *info; @@ -294,47 +266,6 @@ struct ablkcipher_alg { }; /** - * struct aead_alg - AEAD cipher definition - * @maxauthsize: Set the maximum authentication tag size supported by the - * transformation. A transformation may support smaller tag sizes. - * As the authentication tag is a message digest to ensure the - * integrity of the encrypted data, a consumer typically wants the - * largest authentication tag possible as defined by this - * variable. - * @setauthsize: Set authentication size for the AEAD transformation. This - * function is used to specify the consumer requested size of the - * authentication tag to be either generated by the transformation - * during encryption or the size of the authentication tag to be - * supplied during the decryption operation. This function is also - * responsible for checking the authentication tag size for - * validity. - * @setkey: see struct ablkcipher_alg - * @encrypt: see struct ablkcipher_alg - * @decrypt: see struct ablkcipher_alg - * @givencrypt: see struct ablkcipher_alg - * @givdecrypt: see struct ablkcipher_alg - * @geniv: see struct ablkcipher_alg - * @ivsize: see struct ablkcipher_alg - * - * All fields except @givencrypt , @givdecrypt , @geniv and @ivsize are - * mandatory and must be filled. - */ -struct aead_alg { - int (*setkey)(struct crypto_aead *tfm, const u8 *key, - unsigned int keylen); - int (*setauthsize)(struct crypto_aead *tfm, unsigned int authsize); - int (*encrypt)(struct aead_request *req); - int (*decrypt)(struct aead_request *req); - int (*givencrypt)(struct aead_givcrypt_request *req); - int (*givdecrypt)(struct aead_givcrypt_request *req); - - const char *geniv; - - unsigned int ivsize; - unsigned int maxauthsize; -}; - -/** * struct blkcipher_alg - synchronous block cipher definition * @min_keysize: see struct ablkcipher_alg * @max_keysize: see struct ablkcipher_alg @@ -426,40 +357,11 @@ struct compress_alg { unsigned int slen, u8 *dst, unsigned int *dlen); }; -/** - * struct rng_alg - random number generator definition - * @rng_make_random: The function defined by this variable obtains a random - * number. The random number generator transform must generate - * the random number out of the context provided with this - * call. - * @rng_reset: Reset of the random number generator by clearing the entire state. - * With the invocation of this function call, the random number - * generator shall completely reinitialize its state. If the random - * number generator requires a seed for setting up a new state, - * the seed must be provided by the consumer while invoking this - * function. The required size of the seed is defined with - * @seedsize . - * @seedsize: The seed size required for a random number generator - * initialization defined with this variable. Some random number - * generators like the SP800-90A DRBG does not require a seed as the - * seeding is implemented internally without the need of support by - * the consumer. In this case, the seed size is set to zero. - */ -struct rng_alg { - int (*rng_make_random)(struct crypto_rng *tfm, u8 *rdata, - unsigned int dlen); - int (*rng_reset)(struct crypto_rng *tfm, u8 *seed, unsigned int slen); - - unsigned int seedsize; -}; - #define cra_ablkcipher cra_u.ablkcipher -#define cra_aead cra_u.aead #define cra_blkcipher cra_u.blkcipher #define cra_cipher cra_u.cipher #define cra_compress cra_u.compress -#define cra_rng cra_u.rng /** * struct crypto_alg - definition of a cryptograpic cipher algorithm @@ -505,9 +407,9 @@ struct rng_alg { * transformation algorithm. * @cra_type: Type of the cryptographic transformation. This is a pointer to * struct crypto_type, which implements callbacks common for all - * trasnformation types. There are multiple options: + * transformation types. There are multiple options: * &crypto_blkcipher_type, &crypto_ablkcipher_type, - * &crypto_ahash_type, &crypto_aead_type, &crypto_rng_type. + * &crypto_ahash_type, &crypto_rng_type. * This field might be empty. In that case, there are no common * callbacks. This is the case for: cipher, compress, shash. * @cra_u: Callbacks implementing the transformation. This is a union of @@ -555,11 +457,9 @@ struct crypto_alg { union { struct ablkcipher_alg ablkcipher; - struct aead_alg aead; struct blkcipher_alg blkcipher; struct cipher_alg cipher; struct compress_alg compress; - struct rng_alg rng; } cra_u; int (*cra_init)(struct crypto_tfm *tfm); @@ -567,7 +467,7 @@ struct crypto_alg { void (*cra_destroy)(struct crypto_alg *alg); struct module *cra_module; -}; +} CRYPTO_MINALIGN_ATTR; /* * Algorithm registration interface. @@ -602,21 +502,6 @@ struct ablkcipher_tfm { unsigned int reqsize; }; -struct aead_tfm { - int (*setkey)(struct crypto_aead *tfm, const u8 *key, - unsigned int keylen); - int (*encrypt)(struct aead_request *req); - int (*decrypt)(struct aead_request *req); - int (*givencrypt)(struct aead_givcrypt_request *req); - int (*givdecrypt)(struct aead_givcrypt_request *req); - - struct crypto_aead *base; - - unsigned int ivsize; - unsigned int authsize; - unsigned int reqsize; -}; - struct blkcipher_tfm { void *iv; int (*setkey)(struct crypto_tfm *tfm, const u8 *key, @@ -655,19 +540,11 @@ struct compress_tfm { u8 *dst, unsigned int *dlen); }; -struct rng_tfm { - int (*rng_gen_random)(struct crypto_rng *tfm, u8 *rdata, - unsigned int dlen); - int (*rng_reset)(struct crypto_rng *tfm, u8 *seed, unsigned int slen); -}; - #define crt_ablkcipher crt_u.ablkcipher -#define crt_aead crt_u.aead #define crt_blkcipher crt_u.blkcipher #define crt_cipher crt_u.cipher #define crt_hash crt_u.hash #define crt_compress crt_u.compress -#define crt_rng crt_u.rng struct crypto_tfm { @@ -675,12 +552,10 @@ struct crypto_tfm { union { struct ablkcipher_tfm ablkcipher; - struct aead_tfm aead; struct blkcipher_tfm blkcipher; struct cipher_tfm cipher; struct hash_tfm hash; struct compress_tfm compress; - struct rng_tfm rng; } crt_u; void (*exit)(struct crypto_tfm *tfm); @@ -694,10 +569,6 @@ struct crypto_ablkcipher { struct crypto_tfm base; }; -struct crypto_aead { - struct crypto_tfm base; -}; - struct crypto_blkcipher { struct crypto_tfm base; }; @@ -714,10 +585,6 @@ struct crypto_hash { struct crypto_tfm base; }; -struct crypto_rng { - struct crypto_tfm base; -}; - enum { CRYPTOA_UNSPEC, CRYPTOA_ALG, @@ -1194,400 +1061,6 @@ static inline void ablkcipher_request_set_crypt( } /** - * DOC: Authenticated Encryption With Associated Data (AEAD) Cipher API - * - * The AEAD cipher API is used with the ciphers of type CRYPTO_ALG_TYPE_AEAD - * (listed as type "aead" in /proc/crypto) - * - * The most prominent examples for this type of encryption is GCM and CCM. - * However, the kernel supports other types of AEAD ciphers which are defined - * with the following cipher string: - * - * authenc(keyed message digest, block cipher) - * - * For example: authenc(hmac(sha256), cbc(aes)) - * - * The example code provided for the asynchronous block cipher operation - * applies here as well. Naturally all *ablkcipher* symbols must be exchanged - * the *aead* pendants discussed in the following. In addtion, for the AEAD - * operation, the aead_request_set_assoc function must be used to set the - * pointer to the associated data memory location before performing the - * encryption or decryption operation. In case of an encryption, the associated - * data memory is filled during the encryption operation. For decryption, the - * associated data memory must contain data that is used to verify the integrity - * of the decrypted data. Another deviation from the asynchronous block cipher - * operation is that the caller should explicitly check for -EBADMSG of the - * crypto_aead_decrypt. That error indicates an authentication error, i.e. - * a breach in the integrity of the message. In essence, that -EBADMSG error - * code is the key bonus an AEAD cipher has over "standard" block chaining - * modes. - */ - -static inline struct crypto_aead *__crypto_aead_cast(struct crypto_tfm *tfm) -{ - return (struct crypto_aead *)tfm; -} - -/** - * crypto_alloc_aead() - allocate AEAD cipher handle - * @alg_name: is the cra_name / name or cra_driver_name / driver name of the - * AEAD cipher - * @type: specifies the type of the cipher - * @mask: specifies the mask for the cipher - * - * Allocate a cipher handle for an AEAD. The returned struct - * crypto_aead is the cipher handle that is required for any subsequent - * API invocation for that AEAD. - * - * Return: allocated cipher handle in case of success; IS_ERR() is true in case - * of an error, PTR_ERR() returns the error code. - */ -struct crypto_aead *crypto_alloc_aead(const char *alg_name, u32 type, u32 mask); - -static inline struct crypto_tfm *crypto_aead_tfm(struct crypto_aead *tfm) -{ - return &tfm->base; -} - -/** - * crypto_free_aead() - zeroize and free aead handle - * @tfm: cipher handle to be freed - */ -static inline void crypto_free_aead(struct crypto_aead *tfm) -{ - crypto_free_tfm(crypto_aead_tfm(tfm)); -} - -static inline struct aead_tfm *crypto_aead_crt(struct crypto_aead *tfm) -{ - return &crypto_aead_tfm(tfm)->crt_aead; -} - -/** - * crypto_aead_ivsize() - obtain IV size - * @tfm: cipher handle - * - * The size of the IV for the aead referenced by the cipher handle is - * returned. This IV size may be zero if the cipher does not need an IV. - * - * Return: IV size in bytes - */ -static inline unsigned int crypto_aead_ivsize(struct crypto_aead *tfm) -{ - return crypto_aead_crt(tfm)->ivsize; -} - -/** - * crypto_aead_authsize() - obtain maximum authentication data size - * @tfm: cipher handle - * - * The maximum size of the authentication data for the AEAD cipher referenced - * by the AEAD cipher handle is returned. The authentication data size may be - * zero if the cipher implements a hard-coded maximum. - * - * The authentication data may also be known as "tag value". - * - * Return: authentication data size / tag size in bytes - */ -static inline unsigned int crypto_aead_authsize(struct crypto_aead *tfm) -{ - return crypto_aead_crt(tfm)->authsize; -} - -/** - * crypto_aead_blocksize() - obtain block size of cipher - * @tfm: cipher handle - * - * The block size for the AEAD referenced with the cipher handle is returned. - * The caller may use that information to allocate appropriate memory for the - * data returned by the encryption or decryption operation - * - * Return: block size of cipher - */ -static inline unsigned int crypto_aead_blocksize(struct crypto_aead *tfm) -{ - return crypto_tfm_alg_blocksize(crypto_aead_tfm(tfm)); -} - -static inline unsigned int crypto_aead_alignmask(struct crypto_aead *tfm) -{ - return crypto_tfm_alg_alignmask(crypto_aead_tfm(tfm)); -} - -static inline u32 crypto_aead_get_flags(struct crypto_aead *tfm) -{ - return crypto_tfm_get_flags(crypto_aead_tfm(tfm)); -} - -static inline void crypto_aead_set_flags(struct crypto_aead *tfm, u32 flags) -{ - crypto_tfm_set_flags(crypto_aead_tfm(tfm), flags); -} - -static inline void crypto_aead_clear_flags(struct crypto_aead *tfm, u32 flags) -{ - crypto_tfm_clear_flags(crypto_aead_tfm(tfm), flags); -} - -/** - * crypto_aead_setkey() - set key for cipher - * @tfm: cipher handle - * @key: buffer holding the key - * @keylen: length of the key in bytes - * - * The caller provided key is set for the AEAD referenced by the cipher - * handle. - * - * Note, the key length determines the cipher type. Many block ciphers implement - * different cipher modes depending on the key size, such as AES-128 vs AES-192 - * vs. AES-256. When providing a 16 byte key for an AES cipher handle, AES-128 - * is performed. - * - * Return: 0 if the setting of the key was successful; < 0 if an error occurred - */ -static inline int crypto_aead_setkey(struct crypto_aead *tfm, const u8 *key, - unsigned int keylen) -{ - struct aead_tfm *crt = crypto_aead_crt(tfm); - - return crt->setkey(crt->base, key, keylen); -} - -/** - * crypto_aead_setauthsize() - set authentication data size - * @tfm: cipher handle - * @authsize: size of the authentication data / tag in bytes - * - * Set the authentication data size / tag size. AEAD requires an authentication - * tag (or MAC) in addition to the associated data. - * - * Return: 0 if the setting of the key was successful; < 0 if an error occurred - */ -int crypto_aead_setauthsize(struct crypto_aead *tfm, unsigned int authsize); - -static inline struct crypto_aead *crypto_aead_reqtfm(struct aead_request *req) -{ - return __crypto_aead_cast(req->base.tfm); -} - -/** - * crypto_aead_encrypt() - encrypt plaintext - * @req: reference to the aead_request handle that holds all information - * needed to perform the cipher operation - * - * Encrypt plaintext data using the aead_request handle. That data structure - * and how it is filled with data is discussed with the aead_request_* - * functions. - * - * IMPORTANT NOTE The encryption operation creates the authentication data / - * tag. That data is concatenated with the created ciphertext. - * The ciphertext memory size is therefore the given number of - * block cipher blocks + the size defined by the - * crypto_aead_setauthsize invocation. The caller must ensure - * that sufficient memory is available for the ciphertext and - * the authentication tag. - * - * Return: 0 if the cipher operation was successful; < 0 if an error occurred - */ -static inline int crypto_aead_encrypt(struct aead_request *req) -{ - return crypto_aead_crt(crypto_aead_reqtfm(req))->encrypt(req); -} - -/** - * crypto_aead_decrypt() - decrypt ciphertext - * @req: reference to the ablkcipher_request handle that holds all information - * needed to perform the cipher operation - * - * Decrypt ciphertext data using the aead_request handle. That data structure - * and how it is filled with data is discussed with the aead_request_* - * functions. - * - * IMPORTANT NOTE The caller must concatenate the ciphertext followed by the - * authentication data / tag. That authentication data / tag - * must have the size defined by the crypto_aead_setauthsize - * invocation. - * - * - * Return: 0 if the cipher operation was successful; -EBADMSG: The AEAD - * cipher operation performs the authentication of the data during the - * decryption operation. Therefore, the function returns this error if - * the authentication of the ciphertext was unsuccessful (i.e. the - * integrity of the ciphertext or the associated data was violated); - * < 0 if an error occurred. - */ -static inline int crypto_aead_decrypt(struct aead_request *req) -{ - if (req->cryptlen < crypto_aead_authsize(crypto_aead_reqtfm(req))) - return -EINVAL; - - return crypto_aead_crt(crypto_aead_reqtfm(req))->decrypt(req); -} - -/** - * DOC: Asynchronous AEAD Request Handle - * - * The aead_request data structure contains all pointers to data required for - * the AEAD cipher operation. This includes the cipher handle (which can be - * used by multiple aead_request instances), pointer to plaintext and - * ciphertext, asynchronous callback function, etc. It acts as a handle to the - * aead_request_* API calls in a similar way as AEAD handle to the - * crypto_aead_* API calls. - */ - -/** - * crypto_aead_reqsize() - obtain size of the request data structure - * @tfm: cipher handle - * - * Return: number of bytes - */ -static inline unsigned int crypto_aead_reqsize(struct crypto_aead *tfm) -{ - return crypto_aead_crt(tfm)->reqsize; -} - -/** - * aead_request_set_tfm() - update cipher handle reference in request - * @req: request handle to be modified - * @tfm: cipher handle that shall be added to the request handle - * - * Allow the caller to replace the existing aead handle in the request - * data structure with a different one. - */ -static inline void aead_request_set_tfm(struct aead_request *req, - struct crypto_aead *tfm) -{ - req->base.tfm = crypto_aead_tfm(crypto_aead_crt(tfm)->base); -} - -/** - * aead_request_alloc() - allocate request data structure - * @tfm: cipher handle to be registered with the request - * @gfp: memory allocation flag that is handed to kmalloc by the API call. - * - * Allocate the request data structure that must be used with the AEAD - * encrypt and decrypt API calls. During the allocation, the provided aead - * handle is registered in the request data structure. - * - * Return: allocated request handle in case of success; IS_ERR() is true in case - * of an error, PTR_ERR() returns the error code. - */ -static inline struct aead_request *aead_request_alloc(struct crypto_aead *tfm, - gfp_t gfp) -{ - struct aead_request *req; - - req = kmalloc(sizeof(*req) + crypto_aead_reqsize(tfm), gfp); - - if (likely(req)) - aead_request_set_tfm(req, tfm); - - return req; -} - -/** - * aead_request_free() - zeroize and free request data structure - * @req: request data structure cipher handle to be freed - */ -static inline void aead_request_free(struct aead_request *req) -{ - kzfree(req); -} - -/** - * aead_request_set_callback() - set asynchronous callback function - * @req: request handle - * @flags: specify zero or an ORing of the flags - * CRYPTO_TFM_REQ_MAY_BACKLOG the request queue may back log and - * increase the wait queue beyond the initial maximum size; - * CRYPTO_TFM_REQ_MAY_SLEEP the request processing may sleep - * @compl: callback function pointer to be registered with the request handle - * @data: The data pointer refers to memory that is not used by the kernel - * crypto API, but provided to the callback function for it to use. Here, - * the caller can provide a reference to memory the callback function can - * operate on. As the callback function is invoked asynchronously to the - * related functionality, it may need to access data structures of the - * related functionality which can be referenced using this pointer. The - * callback function can access the memory via the "data" field in the - * crypto_async_request data structure provided to the callback function. - * - * Setting the callback function that is triggered once the cipher operation - * completes - * - * The callback function is registered with the aead_request handle and - * must comply with the following template - * - * void callback_function(struct crypto_async_request *req, int error) - */ -static inline void aead_request_set_callback(struct aead_request *req, - u32 flags, - crypto_completion_t compl, - void *data) -{ - req->base.complete = compl; - req->base.data = data; - req->base.flags = flags; -} - -/** - * aead_request_set_crypt - set data buffers - * @req: request handle - * @src: source scatter / gather list - * @dst: destination scatter / gather list - * @cryptlen: number of bytes to process from @src - * @iv: IV for the cipher operation which must comply with the IV size defined - * by crypto_aead_ivsize() - * - * Setting the source data and destination data scatter / gather lists. - * - * For encryption, the source is treated as the plaintext and the - * destination is the ciphertext. For a decryption operation, the use is - * reversed - the source is the ciphertext and the destination is the plaintext. - * - * IMPORTANT NOTE AEAD requires an authentication tag (MAC). For decryption, - * the caller must concatenate the ciphertext followed by the - * authentication tag and provide the entire data stream to the - * decryption operation (i.e. the data length used for the - * initialization of the scatterlist and the data length for the - * decryption operation is identical). For encryption, however, - * the authentication tag is created while encrypting the data. - * The destination buffer must hold sufficient space for the - * ciphertext and the authentication tag while the encryption - * invocation must only point to the plaintext data size. The - * following code snippet illustrates the memory usage - * buffer = kmalloc(ptbuflen + (enc ? authsize : 0)); - * sg_init_one(&sg, buffer, ptbuflen + (enc ? authsize : 0)); - * aead_request_set_crypt(req, &sg, &sg, ptbuflen, iv); - */ -static inline void aead_request_set_crypt(struct aead_request *req, - struct scatterlist *src, - struct scatterlist *dst, - unsigned int cryptlen, u8 *iv) -{ - req->src = src; - req->dst = dst; - req->cryptlen = cryptlen; - req->iv = iv; -} - -/** - * aead_request_set_assoc() - set the associated data scatter / gather list - * @req: request handle - * @assoc: associated data scatter / gather list - * @assoclen: number of bytes to process from @assoc - * - * For encryption, the memory is filled with the associated data. For - * decryption, the memory must point to the associated data. - */ -static inline void aead_request_set_assoc(struct aead_request *req, - struct scatterlist *assoc, - unsigned int assoclen) -{ - req->assoc = assoc; - req->assoclen = assoclen; -} - -/** * DOC: Synchronous Block Cipher API * * The synchronous block cipher API is used with the ciphers of type diff --git a/kernel/include/linux/cryptouser.h b/kernel/include/linux/cryptouser.h deleted file mode 100644 index 4abf2ea6a..000000000 --- a/kernel/include/linux/cryptouser.h +++ /dev/null @@ -1,105 +0,0 @@ -/* - * Crypto user configuration API. - * - * Copyright (C) 2011 secunet Security Networks AG - * Copyright (C) 2011 Steffen Klassert <steffen.klassert@secunet.com> - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, write to the Free Software Foundation, Inc., - * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - */ - -/* Netlink configuration messages. */ -enum { - CRYPTO_MSG_BASE = 0x10, - CRYPTO_MSG_NEWALG = 0x10, - CRYPTO_MSG_DELALG, - CRYPTO_MSG_UPDATEALG, - CRYPTO_MSG_GETALG, - __CRYPTO_MSG_MAX -}; -#define CRYPTO_MSG_MAX (__CRYPTO_MSG_MAX - 1) -#define CRYPTO_NR_MSGTYPES (CRYPTO_MSG_MAX + 1 - CRYPTO_MSG_BASE) - -#define CRYPTO_MAX_NAME CRYPTO_MAX_ALG_NAME - -/* Netlink message attributes. */ -enum crypto_attr_type_t { - CRYPTOCFGA_UNSPEC, - CRYPTOCFGA_PRIORITY_VAL, /* __u32 */ - CRYPTOCFGA_REPORT_LARVAL, /* struct crypto_report_larval */ - CRYPTOCFGA_REPORT_HASH, /* struct crypto_report_hash */ - CRYPTOCFGA_REPORT_BLKCIPHER, /* struct crypto_report_blkcipher */ - CRYPTOCFGA_REPORT_AEAD, /* struct crypto_report_aead */ - CRYPTOCFGA_REPORT_COMPRESS, /* struct crypto_report_comp */ - CRYPTOCFGA_REPORT_RNG, /* struct crypto_report_rng */ - CRYPTOCFGA_REPORT_CIPHER, /* struct crypto_report_cipher */ - __CRYPTOCFGA_MAX - -#define CRYPTOCFGA_MAX (__CRYPTOCFGA_MAX - 1) -}; - -struct crypto_user_alg { - char cru_name[CRYPTO_MAX_ALG_NAME]; - char cru_driver_name[CRYPTO_MAX_ALG_NAME]; - char cru_module_name[CRYPTO_MAX_ALG_NAME]; - __u32 cru_type; - __u32 cru_mask; - __u32 cru_refcnt; - __u32 cru_flags; -}; - -struct crypto_report_larval { - char type[CRYPTO_MAX_NAME]; -}; - -struct crypto_report_hash { - char type[CRYPTO_MAX_NAME]; - unsigned int blocksize; - unsigned int digestsize; -}; - -struct crypto_report_cipher { - char type[CRYPTO_MAX_ALG_NAME]; - unsigned int blocksize; - unsigned int min_keysize; - unsigned int max_keysize; -}; - -struct crypto_report_blkcipher { - char type[CRYPTO_MAX_NAME]; - char geniv[CRYPTO_MAX_NAME]; - unsigned int blocksize; - unsigned int min_keysize; - unsigned int max_keysize; - unsigned int ivsize; -}; - -struct crypto_report_aead { - char type[CRYPTO_MAX_NAME]; - char geniv[CRYPTO_MAX_NAME]; - unsigned int blocksize; - unsigned int maxauthsize; - unsigned int ivsize; -}; - -struct crypto_report_comp { - char type[CRYPTO_MAX_NAME]; -}; - -struct crypto_report_rng { - char type[CRYPTO_MAX_NAME]; - unsigned int seedsize; -}; - -#define CRYPTO_REPORT_MAXSIZE (sizeof(struct crypto_user_alg) + \ - sizeof(struct crypto_report_blkcipher)) diff --git a/kernel/include/linux/dax.h b/kernel/include/linux/dax.h new file mode 100644 index 000000000..b415e5215 --- /dev/null +++ b/kernel/include/linux/dax.h @@ -0,0 +1,39 @@ +#ifndef _LINUX_DAX_H +#define _LINUX_DAX_H + +#include <linux/fs.h> +#include <linux/mm.h> +#include <asm/pgtable.h> + +ssize_t dax_do_io(struct kiocb *, struct inode *, struct iov_iter *, loff_t, + get_block_t, dio_iodone_t, int flags); +int dax_clear_blocks(struct inode *, sector_t block, long size); +int dax_zero_page_range(struct inode *, loff_t from, unsigned len, get_block_t); +int dax_truncate_page(struct inode *, loff_t from, get_block_t); +int dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t, + dax_iodone_t); +int __dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t, + dax_iodone_t); +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +int dax_pmd_fault(struct vm_area_struct *, unsigned long addr, pmd_t *, + unsigned int flags, get_block_t, dax_iodone_t); +int __dax_pmd_fault(struct vm_area_struct *, unsigned long addr, pmd_t *, + unsigned int flags, get_block_t, dax_iodone_t); +#else +static inline int dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr, + pmd_t *pmd, unsigned int flags, get_block_t gb, + dax_iodone_t di) +{ + return VM_FAULT_FALLBACK; +} +#define __dax_pmd_fault dax_pmd_fault +#endif +int dax_pfn_mkwrite(struct vm_area_struct *, struct vm_fault *); +#define dax_mkwrite(vma, vmf, gb, iod) dax_fault(vma, vmf, gb, iod) +#define __dax_mkwrite(vma, vmf, gb, iod) __dax_fault(vma, vmf, gb, iod) + +static inline bool vma_is_dax(struct vm_area_struct *vma) +{ + return vma->vm_file && IS_DAX(vma->vm_file->f_mapping->host); +} +#endif diff --git a/kernel/include/linux/dcache.h b/kernel/include/linux/dcache.h index df334cbac..8a2e009c8 100644 --- a/kernel/include/linux/dcache.h +++ b/kernel/include/linux/dcache.h @@ -160,6 +160,7 @@ struct dentry_operations { char *(*d_dname)(struct dentry *, char *, int); struct vfsmount *(*d_automount)(struct path *); int (*d_manage)(struct dentry *, bool); + struct inode *(*d_select_inode)(struct dentry *, unsigned); } ____cacheline_aligned; /* @@ -225,6 +226,7 @@ struct dentry_operations { #define DCACHE_MAY_FREE 0x00800000 #define DCACHE_FALLTHRU 0x01000000 /* Fall through to lower layer */ +#define DCACHE_OP_SELECT_INODE 0x02000000 /* Unioned entry: dcache op selects inode */ extern seqlock_t rename_lock; @@ -325,7 +327,8 @@ static inline unsigned d_count(const struct dentry *dentry) /* * helper function for dentry_operations.d_dname() members */ -extern char *dynamic_dname(struct dentry *, char *, int, const char *, ...); +extern __printf(4, 5) +char *dynamic_dname(struct dentry *, char *, int, const char *, ...); extern char *simple_dname(struct dentry *, char *, int); extern char *__d_path(const struct path *, const struct path *, char *, int); @@ -406,9 +409,7 @@ static inline bool d_mountpoint(const struct dentry *dentry) */ static inline unsigned __d_entry_type(const struct dentry *dentry) { - unsigned type = READ_ONCE(dentry->d_flags); - smp_rmb(); - return type & DCACHE_ENTRY_TYPE; + return dentry->d_flags & DCACHE_ENTRY_TYPE; } static inline bool d_is_miss(const struct dentry *dentry) @@ -505,6 +506,11 @@ static inline bool d_really_is_positive(const struct dentry *dentry) return dentry->d_inode != NULL; } +static inline int simple_positive(struct dentry *dentry) +{ + return d_really_is_positive(dentry) && !d_unhashed(dentry); +} + extern void d_set_fallthru(struct dentry *dentry); static inline bool d_is_fallthru(const struct dentry *dentry) diff --git a/kernel/include/linux/dccp.h b/kernel/include/linux/dccp.h index 221025423..61d042bbb 100644 --- a/kernel/include/linux/dccp.h +++ b/kernel/include/linux/dccp.h @@ -202,16 +202,16 @@ struct dccp_service_list { #define DCCP_SERVICE_INVALID_VALUE htonl((__u32)-1) #define DCCP_SERVICE_CODE_IS_ABSENT 0 -static inline int dccp_list_has_service(const struct dccp_service_list *sl, +static inline bool dccp_list_has_service(const struct dccp_service_list *sl, const __be32 service) { if (likely(sl != NULL)) { u32 i = sl->dccpsl_nr; while (i--) if (sl->dccpsl_list[i] == service) - return 1; + return true; } - return 0; + return false; } struct dccp_ackvec; diff --git a/kernel/include/linux/debugfs.h b/kernel/include/linux/debugfs.h index cb25af461..19c066dce 100644 --- a/kernel/include/linux/debugfs.h +++ b/kernel/include/linux/debugfs.h @@ -45,7 +45,6 @@ extern struct dentry *arch_debugfs_dir; /* declared over in file.c */ extern const struct file_operations debugfs_file_operations; -extern const struct inode_operations debugfs_link_operations; struct dentry *debugfs_create_file(const char *name, umode_t mode, struct dentry *parent, void *data, @@ -80,6 +79,8 @@ struct dentry *debugfs_create_u32(const char *name, umode_t mode, struct dentry *parent, u32 *value); struct dentry *debugfs_create_u64(const char *name, umode_t mode, struct dentry *parent, u64 *value); +struct dentry *debugfs_create_ulong(const char *name, umode_t mode, + struct dentry *parent, unsigned long *value); struct dentry *debugfs_create_x8(const char *name, umode_t mode, struct dentry *parent, u8 *value); struct dentry *debugfs_create_x16(const char *name, umode_t mode, @@ -93,7 +94,7 @@ struct dentry *debugfs_create_size_t(const char *name, umode_t mode, struct dentry *debugfs_create_atomic_t(const char *name, umode_t mode, struct dentry *parent, atomic_t *value); struct dentry *debugfs_create_bool(const char *name, umode_t mode, - struct dentry *parent, u32 *value); + struct dentry *parent, bool *value); struct dentry *debugfs_create_blob(const char *name, umode_t mode, struct dentry *parent, @@ -117,6 +118,12 @@ struct dentry *debugfs_create_devm_seqfile(struct device *dev, const char *name, bool debugfs_initialized(void); +ssize_t debugfs_read_file_bool(struct file *file, char __user *user_buf, + size_t count, loff_t *ppos); + +ssize_t debugfs_write_file_bool(struct file *file, const char __user *user_buf, + size_t count, loff_t *ppos); + #else #include <linux/err.h> @@ -238,7 +245,7 @@ static inline struct dentry *debugfs_create_atomic_t(const char *name, umode_t m static inline struct dentry *debugfs_create_bool(const char *name, umode_t mode, struct dentry *parent, - u32 *value) + bool *value) { return ERR_PTR(-ENODEV); } @@ -283,6 +290,20 @@ static inline struct dentry *debugfs_create_devm_seqfile(struct device *dev, return ERR_PTR(-ENODEV); } +static inline ssize_t debugfs_read_file_bool(struct file *file, + char __user *user_buf, + size_t count, loff_t *ppos) +{ + return -ENODEV; +} + +static inline ssize_t debugfs_write_file_bool(struct file *file, + const char __user *user_buf, + size_t count, loff_t *ppos) +{ + return -ENODEV; +} + #endif #endif diff --git a/kernel/include/linux/devfreq.h b/kernel/include/linux/devfreq.h index ce447f0f1..68030e22a 100644 --- a/kernel/include/linux/devfreq.h +++ b/kernel/include/linux/devfreq.h @@ -65,7 +65,10 @@ struct devfreq_dev_status { * The "flags" parameter's possible values are * explained above with "DEVFREQ_FLAG_*" macros. * @get_dev_status: The device should provide the current performance - * status to devfreq, which is used by governors. + * status to devfreq. Governors are recommended not to + * use this directly. Instead, governors are recommended + * to use devfreq_update_stats() along with + * devfreq.last_status. * @get_cur_freq: The device should provide the current frequency * at which it is operating. * @exit: An optional callback that is called when devfreq @@ -161,6 +164,7 @@ struct devfreq { struct delayed_work work; unsigned long previous_freq; + struct devfreq_dev_status last_status; void *data; /* private data for governors */ @@ -204,6 +208,19 @@ extern int devm_devfreq_register_opp_notifier(struct device *dev, extern void devm_devfreq_unregister_opp_notifier(struct device *dev, struct devfreq *devfreq); +/** + * devfreq_update_stats() - update the last_status pointer in struct devfreq + * @df: the devfreq instance whose status needs updating + * + * Governors are recommended to use this function along with last_status, + * which allows other entities to reuse the last_status without affecting + * the values fetched later by governors. + */ +static inline int devfreq_update_stats(struct devfreq *df) +{ + return df->profile->get_dev_status(df->dev.parent, &df->last_status); +} + #if IS_ENABLED(CONFIG_DEVFREQ_GOV_SIMPLE_ONDEMAND) /** * struct devfreq_simple_ondemand_data - void *data fed to struct devfreq @@ -289,6 +306,11 @@ static inline void devm_devfreq_unregister_opp_notifier(struct device *dev, struct devfreq *devfreq) { } + +static inline int devfreq_update_stats(struct devfreq *df) +{ + return -EINVAL; +} #endif /* CONFIG_PM_DEVFREQ */ #endif /* __LINUX_DEVFREQ_H__ */ diff --git a/kernel/include/linux/devfreq_cooling.h b/kernel/include/linux/devfreq_cooling.h new file mode 100644 index 000000000..7adf6cc4b --- /dev/null +++ b/kernel/include/linux/devfreq_cooling.h @@ -0,0 +1,81 @@ +/* + * devfreq_cooling: Thermal cooling device implementation for devices using + * devfreq + * + * Copyright (C) 2014-2015 ARM Limited + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed "as is" WITHOUT ANY WARRANTY of any + * kind, whether express or implied; without even the implied warranty + * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef __DEVFREQ_COOLING_H__ +#define __DEVFREQ_COOLING_H__ + +#include <linux/devfreq.h> +#include <linux/thermal.h> + +#ifdef CONFIG_DEVFREQ_THERMAL + +/** + * struct devfreq_cooling_power - Devfreq cooling power ops + * @get_static_power: Take voltage, in mV, and return the static power + * in mW. If NULL, the static power is assumed + * to be 0. + * @get_dynamic_power: Take voltage, in mV, and frequency, in HZ, and + * return the dynamic power draw in mW. If NULL, + * a simple power model is used. + * @dyn_power_coeff: Coefficient for the simple dynamic power model in + * mW/(MHz mV mV). + * If get_dynamic_power() is NULL, then the + * dynamic power is calculated as + * @dyn_power_coeff * frequency * voltage^2 + */ +struct devfreq_cooling_power { + unsigned long (*get_static_power)(unsigned long voltage); + unsigned long (*get_dynamic_power)(unsigned long freq, + unsigned long voltage); + unsigned long dyn_power_coeff; +}; + +struct thermal_cooling_device * +of_devfreq_cooling_register_power(struct device_node *np, struct devfreq *df, + struct devfreq_cooling_power *dfc_power); +struct thermal_cooling_device * +of_devfreq_cooling_register(struct device_node *np, struct devfreq *df); +struct thermal_cooling_device *devfreq_cooling_register(struct devfreq *df); +void devfreq_cooling_unregister(struct thermal_cooling_device *dfc); + +#else /* !CONFIG_DEVFREQ_THERMAL */ + +struct thermal_cooling_device * +of_devfreq_cooling_register_power(struct device_node *np, struct devfreq *df, + struct devfreq_cooling_power *dfc_power) +{ + return ERR_PTR(-EINVAL); +} + +static inline struct thermal_cooling_device * +of_devfreq_cooling_register(struct device_node *np, struct devfreq *df) +{ + return ERR_PTR(-EINVAL); +} + +static inline struct thermal_cooling_device * +devfreq_cooling_register(struct devfreq *df) +{ + return ERR_PTR(-EINVAL); +} + +static inline void +devfreq_cooling_unregister(struct thermal_cooling_device *dfc) +{ +} + +#endif /* CONFIG_DEVFREQ_THERMAL */ +#endif /* __DEVFREQ_COOLING_H__ */ diff --git a/kernel/include/linux/device-mapper.h b/kernel/include/linux/device-mapper.h index 51cc1deb7..ec1c61c87 100644 --- a/kernel/include/linux/device-mapper.h +++ b/kernel/include/linux/device-mapper.h @@ -79,11 +79,8 @@ typedef void (*dm_status_fn) (struct dm_target *ti, status_type_t status_type, typedef int (*dm_message_fn) (struct dm_target *ti, unsigned argc, char **argv); -typedef int (*dm_ioctl_fn) (struct dm_target *ti, unsigned int cmd, - unsigned long arg); - -typedef int (*dm_merge_fn) (struct dm_target *ti, struct bvec_merge_data *bvm, - struct bio_vec *biovec, int max_size); +typedef int (*dm_prepare_ioctl_fn) (struct dm_target *ti, + struct block_device **bdev, fmode_t *mode); /* * These iteration functions are typically used to check (and combine) @@ -159,8 +156,7 @@ struct target_type { dm_resume_fn resume; dm_status_fn status; dm_message_fn message; - dm_ioctl_fn ioctl; - dm_merge_fn merge; + dm_prepare_ioctl_fn prepare_ioctl; dm_busy_fn busy; dm_iterate_devices_fn iterate_devices; dm_io_hints_fn io_hints; diff --git a/kernel/include/linux/device.h b/kernel/include/linux/device.h index 6558af90c..b8f411b57 100644 --- a/kernel/include/linux/device.h +++ b/kernel/include/linux/device.h @@ -196,12 +196,41 @@ extern struct kset *bus_get_kset(struct bus_type *bus); extern struct klist *bus_get_device_klist(struct bus_type *bus); /** + * enum probe_type - device driver probe type to try + * Device drivers may opt in for special handling of their + * respective probe routines. This tells the core what to + * expect and prefer. + * + * @PROBE_DEFAULT_STRATEGY: Used by drivers that work equally well + * whether probed synchronously or asynchronously. + * @PROBE_PREFER_ASYNCHRONOUS: Drivers for "slow" devices which + * probing order is not essential for booting the system may + * opt into executing their probes asynchronously. + * @PROBE_FORCE_SYNCHRONOUS: Use this to annotate drivers that need + * their probe routines to run synchronously with driver and + * device registration (with the exception of -EPROBE_DEFER + * handling - re-probing always ends up being done asynchronously). + * + * Note that the end goal is to switch the kernel to use asynchronous + * probing by default, so annotating drivers with + * %PROBE_PREFER_ASYNCHRONOUS is a temporary measure that allows us + * to speed up boot process while we are validating the rest of the + * drivers. + */ +enum probe_type { + PROBE_DEFAULT_STRATEGY, + PROBE_PREFER_ASYNCHRONOUS, + PROBE_FORCE_SYNCHRONOUS, +}; + +/** * struct device_driver - The basic device driver structure * @name: Name of the device driver. * @bus: The bus which the device of this driver belongs to. * @owner: The module owner. * @mod_name: Used for built-in modules. * @suppress_bind_attrs: Disables bind/unbind via sysfs. + * @probe_type: Type of the probe (synchronous or asynchronous) to use. * @of_match_table: The open firmware table. * @acpi_match_table: The ACPI match table. * @probe: Called to query the existence of a specific device, @@ -235,6 +264,7 @@ struct device_driver { const char *mod_name; /* used for built-in modules */ bool suppress_bind_attrs; /* disables bind/unbind via sysfs */ + enum probe_type probe_type; const struct of_device_id *of_match_table; const struct acpi_device_id *acpi_match_table; @@ -311,7 +341,7 @@ struct subsys_interface { struct bus_type *subsys; struct list_head node; int (*add_dev)(struct device *dev, struct subsys_interface *sif); - int (*remove_dev)(struct device *dev, struct subsys_interface *sif); + void (*remove_dev)(struct device *dev, struct subsys_interface *sif); }; int subsys_interface_register(struct subsys_interface *sif); @@ -574,13 +604,21 @@ typedef void (*dr_release_t)(struct device *dev, void *res); typedef int (*dr_match_t)(struct device *dev, void *res, void *match_data); #ifdef CONFIG_DEBUG_DEVRES -extern void *__devres_alloc(dr_release_t release, size_t size, gfp_t gfp, - const char *name); +extern void *__devres_alloc_node(dr_release_t release, size_t size, gfp_t gfp, + int nid, const char *name); #define devres_alloc(release, size, gfp) \ - __devres_alloc(release, size, gfp, #release) + __devres_alloc_node(release, size, gfp, NUMA_NO_NODE, #release) +#define devres_alloc_node(release, size, gfp, nid) \ + __devres_alloc_node(release, size, gfp, nid, #release) #else -extern void *devres_alloc(dr_release_t release, size_t size, gfp_t gfp); +extern void *devres_alloc_node(dr_release_t release, size_t size, gfp_t gfp, + int nid); +static inline void *devres_alloc(dr_release_t release, size_t size, gfp_t gfp) +{ + return devres_alloc_node(release, size, gfp, NUMA_NO_NODE); +} #endif + extern void devres_for_each_res(struct device *dev, dr_release_t release, dr_match_t match, void *match_data, void (*fn)(struct device *, void *, void *), @@ -607,8 +645,9 @@ extern int devres_release_group(struct device *dev, void *id); /* managed devm_k.alloc/kfree for device drivers */ extern void *devm_kmalloc(struct device *dev, size_t size, gfp_t gfp); -extern char *devm_kvasprintf(struct device *dev, gfp_t gfp, const char *fmt, - va_list ap); +extern __printf(3, 0) +char *devm_kvasprintf(struct device *dev, gfp_t gfp, const char *fmt, + va_list ap); extern __printf(3, 4) char *devm_kasprintf(struct device *dev, gfp_t gfp, const char *fmt, ...); static inline void *devm_kzalloc(struct device *dev, size_t size, gfp_t gfp) @@ -683,6 +722,8 @@ struct device_dma_parameters { * along with subsystem-level and driver-level callbacks. * @pins: For device pin management. * See Documentation/pinctrl.txt for details. + * @msi_list: Hosts MSI descriptors + * @msi_domain: The generic MSI domain this device is using. * @numa_node: NUMA node this device is close to. * @dma_mask: Dma mask (if dma'ble device). * @coherent_dma_mask: Like dma_mask, but for alloc_coherent mapping as not all @@ -743,9 +784,15 @@ struct device { struct dev_pm_info power; struct dev_pm_domain *pm_domain; +#ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN + struct irq_domain *msi_domain; +#endif #ifdef CONFIG_PINCTRL struct dev_pin_info *pins; #endif +#ifdef CONFIG_GENERIC_MSI_IRQ + struct list_head msi_list; +#endif #ifdef CONFIG_NUMA int numa_node; /* NUMA node this device is close to */ @@ -830,6 +877,22 @@ static inline void set_dev_node(struct device *dev, int node) } #endif +static inline struct irq_domain *dev_get_msi_domain(const struct device *dev) +{ +#ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN + return dev->msi_domain; +#else + return NULL; +#endif +} + +static inline void dev_set_msi_domain(struct device *dev, struct irq_domain *d) +{ +#ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN + dev->msi_domain = d; +#endif +} + static inline void *dev_get_drvdata(const struct device *dev) { return dev->driver_data; @@ -928,6 +991,8 @@ extern int __must_check device_add(struct device *dev); extern void device_del(struct device *dev); extern int device_for_each_child(struct device *dev, void *data, int (*fn)(struct device *dev, void *data)); +extern int device_for_each_child_reverse(struct device *dev, void *data, + int (*fn)(struct device *dev, void *data)); extern struct device *device_find_child(struct device *dev, void *data, int (*match)(struct device *dev, void *data)); extern int device_rename(struct device *dev, const char *new_name); @@ -975,17 +1040,16 @@ extern int __must_check device_bind_driver(struct device *dev); extern void device_release_driver(struct device *dev); extern int __must_check device_attach(struct device *dev); extern int __must_check driver_attach(struct device_driver *drv); +extern void device_initial_probe(struct device *dev); extern int __must_check device_reprobe(struct device *dev); /* * Easy functions for dynamically creating devices on the fly */ -extern struct device *device_create_vargs(struct class *cls, - struct device *parent, - dev_t devt, - void *drvdata, - const char *fmt, - va_list vargs); +extern __printf(5, 0) +struct device *device_create_vargs(struct class *cls, struct device *parent, + dev_t devt, void *drvdata, + const char *fmt, va_list vargs); extern __printf(5, 6) struct device *device_create(struct class *cls, struct device *parent, dev_t devt, void *drvdata, @@ -1269,4 +1333,26 @@ static void __exit __driver##_exit(void) \ } \ module_exit(__driver##_exit); +/** + * builtin_driver() - Helper macro for drivers that don't do anything + * special in init and have no exit. This eliminates some boilerplate. + * Each driver may only use this macro once, and calling it replaces + * device_initcall (or in some cases, the legacy __initcall). This is + * meant to be a direct parallel of module_driver() above but without + * the __exit stuff that is not used for builtin cases. + * + * @__driver: driver name + * @__register: register function for this driver type + * @...: Additional arguments to be passed to __register + * + * Use this macro to construct bus specific macros for registering + * drivers, and do not use it on its own. + */ +#define builtin_driver(__driver, __register, ...) \ +static int __init __driver##_init(void) \ +{ \ + return __register(&(__driver) , ##__VA_ARGS__); \ +} \ +device_initcall(__driver##_init); + #endif /* _DEVICE_H_ */ diff --git a/kernel/include/linux/devpts_fs.h b/kernel/include/linux/devpts_fs.h index 251a2090a..e0ee0b300 100644 --- a/kernel/include/linux/devpts_fs.h +++ b/kernel/include/linux/devpts_fs.h @@ -19,6 +19,8 @@ int devpts_new_index(struct inode *ptmx_inode); void devpts_kill_index(struct inode *ptmx_inode, int idx); +void devpts_add_ref(struct inode *ptmx_inode); +void devpts_del_ref(struct inode *ptmx_inode); /* mknod in devpts */ struct inode *devpts_pty_new(struct inode *ptmx_inode, dev_t device, int index, void *priv); @@ -32,6 +34,8 @@ void devpts_pty_kill(struct inode *inode); /* Dummy stubs in the no-pty case */ static inline int devpts_new_index(struct inode *ptmx_inode) { return -EINVAL; } static inline void devpts_kill_index(struct inode *ptmx_inode, int idx) { } +static inline void devpts_add_ref(struct inode *ptmx_inode) { } +static inline void devpts_del_ref(struct inode *ptmx_inode) { } static inline struct inode *devpts_pty_new(struct inode *ptmx_inode, dev_t device, int index, void *priv) { diff --git a/kernel/include/linux/dma-buf.h b/kernel/include/linux/dma-buf.h index 2f0b431b7..f98bd7068 100644 --- a/kernel/include/linux/dma-buf.h +++ b/kernel/include/linux/dma-buf.h @@ -115,6 +115,8 @@ struct dma_buf_ops { * @attachments: list of dma_buf_attachment that denotes all devices attached. * @ops: dma_buf_ops associated with this buffer object. * @exp_name: name of the exporter; useful for debugging. + * @owner: pointer to exporter module; used for refcounting when exporter is a + * kernel module. * @list_node: node for dma_buf accounting and debugging. * @priv: exporter specific private data for this buffer object. * @resv: reservation object linked to this dma-buf @@ -129,6 +131,7 @@ struct dma_buf { unsigned vmapping_counter; void *vmap_ptr; const char *exp_name; + struct module *owner; struct list_head list_node; void *priv; struct reservation_object *resv; @@ -164,7 +167,8 @@ struct dma_buf_attachment { /** * struct dma_buf_export_info - holds information needed to export a dma_buf - * @exp_name: name of the exporting module - useful for debugging. + * @exp_name: name of the exporter - useful for debugging. + * @owner: pointer to exporter module - used for refcounting kernel module * @ops: Attach allocator-defined dma buf ops to the new buffer * @size: Size of the buffer * @flags: mode flags for the file @@ -176,6 +180,7 @@ struct dma_buf_attachment { */ struct dma_buf_export_info { const char *exp_name; + struct module *owner; const struct dma_buf_ops *ops; size_t size; int flags; @@ -187,7 +192,8 @@ struct dma_buf_export_info { * helper macro for exporters; zeros and fills in most common values */ #define DEFINE_DMA_BUF_EXPORT_INFO(a) \ - struct dma_buf_export_info a = { .exp_name = KBUILD_MODNAME } + struct dma_buf_export_info a = { .exp_name = KBUILD_MODNAME, \ + .owner = THIS_MODULE } /** * get_dma_buf - convenience wrapper for get_file. diff --git a/kernel/include/linux/dma-contiguous.h b/kernel/include/linux/dma-contiguous.h index 569bbd039..fec734df1 100644 --- a/kernel/include/linux/dma-contiguous.h +++ b/kernel/include/linux/dma-contiguous.h @@ -111,7 +111,7 @@ static inline int dma_declare_contiguous(struct device *dev, phys_addr_t size, return ret; } -struct page *dma_alloc_from_contiguous(struct device *dev, int count, +struct page *dma_alloc_from_contiguous(struct device *dev, size_t count, unsigned int order); bool dma_release_from_contiguous(struct device *dev, struct page *pages, int count); @@ -144,7 +144,7 @@ int dma_declare_contiguous(struct device *dev, phys_addr_t size, } static inline -struct page *dma_alloc_from_contiguous(struct device *dev, int count, +struct page *dma_alloc_from_contiguous(struct device *dev, size_t count, unsigned int order) { return NULL; diff --git a/kernel/include/linux/dma-iommu.h b/kernel/include/linux/dma-iommu.h new file mode 100644 index 000000000..fc4810374 --- /dev/null +++ b/kernel/include/linux/dma-iommu.h @@ -0,0 +1,85 @@ +/* + * Copyright (C) 2014-2015 ARM Ltd. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ +#ifndef __DMA_IOMMU_H +#define __DMA_IOMMU_H + +#ifdef __KERNEL__ +#include <asm/errno.h> + +#ifdef CONFIG_IOMMU_DMA +#include <linux/iommu.h> + +int iommu_dma_init(void); + +/* Domain management interface for IOMMU drivers */ +int iommu_get_dma_cookie(struct iommu_domain *domain); +void iommu_put_dma_cookie(struct iommu_domain *domain); + +/* Setup call for arch DMA mapping code */ +int iommu_dma_init_domain(struct iommu_domain *domain, dma_addr_t base, u64 size); + +/* General helpers for DMA-API <-> IOMMU-API interaction */ +int dma_direction_to_prot(enum dma_data_direction dir, bool coherent); + +/* + * These implement the bulk of the relevant DMA mapping callbacks, but require + * the arch code to take care of attributes and cache maintenance + */ +struct page **iommu_dma_alloc(struct device *dev, size_t size, + gfp_t gfp, int prot, dma_addr_t *handle, + void (*flush_page)(struct device *, const void *, phys_addr_t)); +void iommu_dma_free(struct device *dev, struct page **pages, size_t size, + dma_addr_t *handle); + +int iommu_dma_mmap(struct page **pages, size_t size, struct vm_area_struct *vma); + +dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page, + unsigned long offset, size_t size, int prot); +int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg, + int nents, int prot); + +/* + * Arch code with no special attribute handling may use these + * directly as DMA mapping callbacks for simplicity + */ +void iommu_dma_unmap_page(struct device *dev, dma_addr_t handle, size_t size, + enum dma_data_direction dir, struct dma_attrs *attrs); +void iommu_dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nents, + enum dma_data_direction dir, struct dma_attrs *attrs); +int iommu_dma_supported(struct device *dev, u64 mask); +int iommu_dma_mapping_error(struct device *dev, dma_addr_t dma_addr); + +#else + +struct iommu_domain; + +static inline int iommu_dma_init(void) +{ + return 0; +} + +static inline int iommu_get_dma_cookie(struct iommu_domain *domain) +{ + return -ENODEV; +} + +static inline void iommu_put_dma_cookie(struct iommu_domain *domain) +{ +} + +#endif /* CONFIG_IOMMU_DMA */ +#endif /* __KERNEL__ */ +#endif /* __DMA_IOMMU_H */ diff --git a/kernel/include/linux/dma-mapping.h b/kernel/include/linux/dma-mapping.h index ac07ff090..2e551e2d2 100644 --- a/kernel/include/linux/dma-mapping.h +++ b/kernel/include/linux/dma-mapping.h @@ -1,6 +1,7 @@ #ifndef _LINUX_DMA_MAPPING_H #define _LINUX_DMA_MAPPING_H +#include <linux/sizes.h> #include <linux/string.h> #include <linux/device.h> #include <linux/err.h> @@ -145,7 +146,9 @@ static inline void arch_teardown_dma_ops(struct device *dev) { } static inline unsigned int dma_get_max_seg_size(struct device *dev) { - return dev->dma_parms ? dev->dma_parms->max_segment_size : 65536; + if (dev->dma_parms && dev->dma_parms->max_segment_size) + return dev->dma_parms->max_segment_size; + return SZ_64K; } static inline unsigned int dma_set_max_seg_size(struct device *dev, @@ -154,14 +157,15 @@ static inline unsigned int dma_set_max_seg_size(struct device *dev, if (dev->dma_parms) { dev->dma_parms->max_segment_size = size; return 0; - } else - return -EIO; + } + return -EIO; } static inline unsigned long dma_get_seg_boundary(struct device *dev) { - return dev->dma_parms ? - dev->dma_parms->segment_boundary_mask : 0xffffffff; + if (dev->dma_parms && dev->dma_parms->segment_boundary_mask) + return dev->dma_parms->segment_boundary_mask; + return DMA_BIT_MASK(32); } static inline int dma_set_seg_boundary(struct device *dev, unsigned long mask) @@ -169,8 +173,8 @@ static inline int dma_set_seg_boundary(struct device *dev, unsigned long mask) if (dev->dma_parms) { dev->dma_parms->segment_boundary_mask = mask; return 0; - } else - return -EIO; + } + return -EIO; } #ifndef dma_max_pfn diff --git a/kernel/include/linux/dma/hsu.h b/kernel/include/linux/dma/hsu.h index 234393a69..79df69dc6 100644 --- a/kernel/include/linux/dma/hsu.h +++ b/kernel/include/linux/dma/hsu.h @@ -35,14 +35,23 @@ struct hsu_dma_chip { unsigned int length; unsigned int offset; struct hsu_dma *hsu; - struct hsu_dma_platform_data *pdata; }; +#if IS_ENABLED(CONFIG_HSU_DMA) /* Export to the internal users */ irqreturn_t hsu_dma_irq(struct hsu_dma_chip *chip, unsigned short nr); /* Export to the platform drivers */ int hsu_dma_probe(struct hsu_dma_chip *chip); int hsu_dma_remove(struct hsu_dma_chip *chip); +#else +static inline irqreturn_t hsu_dma_irq(struct hsu_dma_chip *chip, + unsigned short nr) +{ + return IRQ_NONE; +} +static inline int hsu_dma_probe(struct hsu_dma_chip *chip) { return -ENODEV; } +static inline int hsu_dma_remove(struct hsu_dma_chip *chip) { return 0; } +#endif /* CONFIG_HSU_DMA */ #endif /* _DMA_HSU_H */ diff --git a/kernel/include/linux/dma/pxa-dma.h b/kernel/include/linux/dma/pxa-dma.h new file mode 100644 index 000000000..3edc99294 --- /dev/null +++ b/kernel/include/linux/dma/pxa-dma.h @@ -0,0 +1,27 @@ +#ifndef _PXA_DMA_H_ +#define _PXA_DMA_H_ + +enum pxad_chan_prio { + PXAD_PRIO_HIGHEST = 0, + PXAD_PRIO_NORMAL, + PXAD_PRIO_LOW, + PXAD_PRIO_LOWEST, +}; + +struct pxad_param { + unsigned int drcmr; + enum pxad_chan_prio prio; +}; + +struct dma_chan; + +#ifdef CONFIG_PXA_DMA +bool pxad_filter_fn(struct dma_chan *chan, void *param); +#else +static inline bool pxad_filter_fn(struct dma_chan *chan, void *param) +{ + return false; +} +#endif + +#endif /* _PXA_DMA_H_ */ diff --git a/kernel/include/linux/dma_remapping.h b/kernel/include/linux/dma_remapping.h index 7ac17f572..187c10299 100644 --- a/kernel/include/linux/dma_remapping.h +++ b/kernel/include/linux/dma_remapping.h @@ -20,6 +20,14 @@ #define CONTEXT_TT_MULTI_LEVEL 0 #define CONTEXT_TT_DEV_IOTLB 1 #define CONTEXT_TT_PASS_THROUGH 2 +/* Extended context entry types */ +#define CONTEXT_TT_PT_PASID 4 +#define CONTEXT_TT_PT_PASID_DEV_IOTLB 5 +#define CONTEXT_TT_MASK (7ULL << 2) + +#define CONTEXT_DINVE (1ULL << 8) +#define CONTEXT_PRS (1ULL << 9) +#define CONTEXT_PASIDE (1ULL << 11) struct intel_iommu; struct dmar_domain; diff --git a/kernel/include/linux/dmaengine.h b/kernel/include/linux/dmaengine.h index ad4197572..c47c68e53 100644 --- a/kernel/include/linux/dmaengine.h +++ b/kernel/include/linux/dmaengine.h @@ -65,6 +65,8 @@ enum dma_transaction_type { DMA_PQ, DMA_XOR_VAL, DMA_PQ_VAL, + DMA_MEMSET, + DMA_MEMSET_SG, DMA_INTERRUPT, DMA_SG, DMA_PRIVATE, @@ -122,10 +124,18 @@ enum dma_transfer_direction { * chunk and before first src/dst address for next chunk. * Ignored for dst(assumed 0), if dst_inc is true and dst_sgl is false. * Ignored for src(assumed 0), if src_inc is true and src_sgl is false. + * @dst_icg: Number of bytes to jump after last dst address of this + * chunk and before the first dst address for next chunk. + * Ignored if dst_inc is true and dst_sgl is false. + * @src_icg: Number of bytes to jump after last src address of this + * chunk and before the first src address for next chunk. + * Ignored if src_inc is true and src_sgl is false. */ struct data_chunk { size_t size; size_t icg; + size_t dst_icg; + size_t src_icg; }; /** @@ -174,6 +184,8 @@ struct dma_interleaved_template { * operation it continues the calculation with new sources * @DMA_PREP_FENCE - tell the driver that subsequent operations depend * on the result of this operation + * @DMA_CTRL_REUSE: client can reuse the descriptor and submit again till + * cleared or freed */ enum dma_ctrl_flags { DMA_PREP_INTERRUPT = (1 << 0), @@ -182,6 +194,7 @@ enum dma_ctrl_flags { DMA_PREP_PQ_DISABLE_Q = (1 << 3), DMA_PREP_CONTINUE = (1 << 4), DMA_PREP_FENCE = (1 << 5), + DMA_CTRL_REUSE = (1 << 6), }; /** @@ -222,6 +235,16 @@ struct dma_chan_percpu { }; /** + * struct dma_router - DMA router structure + * @dev: pointer to the DMA router device + * @route_free: function to be called when the route can be disconnected + */ +struct dma_router { + struct device *dev; + void (*route_free)(struct device *dev, void *route_data); +}; + +/** * struct dma_chan - devices supply DMA channels, clients use them * @device: ptr to the dma device who supplies this channel, always !%NULL * @cookie: last cookie value returned to client @@ -232,6 +255,8 @@ struct dma_chan_percpu { * @local: per-cpu pointer to a struct dma_chan_percpu * @client_count: how many clients are using this channel * @table_count: number of appearances in the mem-to-mem allocation table + * @router: pointer to the DMA router structure + * @route_data: channel specific data for the router * @private: private data for certain client-channel associations */ struct dma_chan { @@ -247,6 +272,11 @@ struct dma_chan { struct dma_chan_percpu __percpu *local; int client_count; int table_count; + + /* DMA router */ + struct dma_router *router; + void *route_data; + void *private; }; @@ -374,6 +404,8 @@ enum dma_residue_granularity { * @cmd_pause: true, if pause and thereby resume is supported * @cmd_terminate: true, if terminate cmd is supported * @residue_granularity: granularity of the reported transfer residue + * @descriptor_reuse: if a descriptor can be reused by client and + * resubmitted multiple times */ struct dma_slave_caps { u32 src_addr_widths; @@ -382,6 +414,7 @@ struct dma_slave_caps { bool cmd_pause; bool cmd_terminate; enum dma_residue_granularity residue_granularity; + bool descriptor_reuse; }; static inline const char *dma_chan_name(struct dma_chan *chan) @@ -441,6 +474,7 @@ struct dma_async_tx_descriptor { dma_addr_t phys; struct dma_chan *chan; dma_cookie_t (*tx_submit)(struct dma_async_tx_descriptor *tx); + int (*desc_free)(struct dma_async_tx_descriptor *tx); dma_async_tx_callback callback; void *callback_param; struct dmaengine_unmap_data *unmap; @@ -559,6 +593,20 @@ struct dma_tx_state { }; /** + * enum dmaengine_alignment - defines alignment of the DMA async tx + * buffers + */ +enum dmaengine_alignment { + DMAENGINE_ALIGN_1_BYTE = 0, + DMAENGINE_ALIGN_2_BYTES = 1, + DMAENGINE_ALIGN_4_BYTES = 2, + DMAENGINE_ALIGN_8_BYTES = 3, + DMAENGINE_ALIGN_16_BYTES = 4, + DMAENGINE_ALIGN_32_BYTES = 5, + DMAENGINE_ALIGN_64_BYTES = 6, +}; + +/** * struct dma_device - info on the entity supplying DMA services * @chancnt: how many DMA channels are supported * @privatecnt: how many DMA channels are requested by dma_request_channel @@ -570,6 +618,7 @@ struct dma_tx_state { * @copy_align: alignment shift for memcpy operations * @xor_align: alignment shift for xor operations * @pq_align: alignment shift for pq operations + * @fill_align: alignment shift for memset operations * @dev_id: unique device ID * @dev: struct device reference for dma mapping api * @src_addr_widths: bit mask of src addr widths the device supports @@ -588,12 +637,15 @@ struct dma_tx_state { * @device_prep_dma_xor_val: prepares a xor validation operation * @device_prep_dma_pq: prepares a pq operation * @device_prep_dma_pq_val: prepares a pqzero_sum operation + * @device_prep_dma_memset: prepares a memset operation + * @device_prep_dma_memset_sg: prepares a memset operation over a scatter list * @device_prep_dma_interrupt: prepares an end of chain interrupt operation * @device_prep_slave_sg: prepares a slave dma operation * @device_prep_dma_cyclic: prepare a cyclic dma operation suitable for audio. * The function takes a buffer of size buf_len. The callback function will * be called after period_len bytes have been transferred. * @device_prep_interleaved_dma: Transfer expression in a generic way. + * @device_prep_dma_imm_data: DMA's 8 byte immediate data to the dst address * @device_config: Pushes a new configuration to a channel, return 0 or an error * code * @device_pause: Pauses any transfer happening on a channel. Returns @@ -617,9 +669,10 @@ struct dma_device { dma_cap_mask_t cap_mask; unsigned short max_xor; unsigned short max_pq; - u8 copy_align; - u8 xor_align; - u8 pq_align; + enum dmaengine_alignment copy_align; + enum dmaengine_alignment xor_align; + enum dmaengine_alignment pq_align; + enum dmaengine_alignment fill_align; #define DMA_HAS_PQ_CONTINUE (1 << 15) int dev_id; @@ -650,6 +703,12 @@ struct dma_device { struct dma_chan *chan, dma_addr_t *pq, dma_addr_t *src, unsigned int src_cnt, const unsigned char *scf, size_t len, enum sum_check_flags *pqres, unsigned long flags); + struct dma_async_tx_descriptor *(*device_prep_dma_memset)( + struct dma_chan *chan, dma_addr_t dest, int value, size_t len, + unsigned long flags); + struct dma_async_tx_descriptor *(*device_prep_dma_memset_sg)( + struct dma_chan *chan, struct scatterlist *sg, + unsigned int nents, int value, unsigned long flags); struct dma_async_tx_descriptor *(*device_prep_dma_interrupt)( struct dma_chan *chan, unsigned long flags); struct dma_async_tx_descriptor *(*device_prep_dma_sg)( @@ -669,6 +728,9 @@ struct dma_device { struct dma_async_tx_descriptor *(*device_prep_interleaved_dma)( struct dma_chan *chan, struct dma_interleaved_template *xt, unsigned long flags); + struct dma_async_tx_descriptor *(*device_prep_dma_imm_data)( + struct dma_chan *chan, dma_addr_t dst, u64 data, + unsigned long flags); int (*device_config)(struct dma_chan *chan, struct dma_slave_config *config); @@ -745,6 +807,17 @@ static inline struct dma_async_tx_descriptor *dmaengine_prep_interleaved_dma( return chan->device->device_prep_interleaved_dma(chan, xt, flags); } +static inline struct dma_async_tx_descriptor *dmaengine_prep_dma_memset( + struct dma_chan *chan, dma_addr_t dest, int value, size_t len, + unsigned long flags) +{ + if (!chan || !chan->device) + return NULL; + + return chan->device->device_prep_dma_memset(chan, dest, value, + len, flags); +} + static inline struct dma_async_tx_descriptor *dmaengine_prep_dma_sg( struct dma_chan *chan, struct scatterlist *dst_sg, unsigned int dst_nents, @@ -790,7 +863,8 @@ static inline dma_cookie_t dmaengine_submit(struct dma_async_tx_descriptor *desc return desc->tx_submit(desc); } -static inline bool dmaengine_check_align(u8 align, size_t off1, size_t off2, size_t len) +static inline bool dmaengine_check_align(enum dmaengine_alignment align, + size_t off1, size_t off2, size_t len) { size_t mask; @@ -820,6 +894,12 @@ static inline bool is_dma_pq_aligned(struct dma_device *dev, size_t off1, return dmaengine_check_align(dev->pq_align, off1, off2, len); } +static inline bool is_dma_fill_aligned(struct dma_device *dev, size_t off1, + size_t off2, size_t len) +{ + return dmaengine_check_align(dev->fill_align, off1, off2, len); +} + static inline void dma_set_maxpq(struct dma_device *dma, int maxpq, int has_pq_continue) { @@ -874,6 +954,33 @@ static inline int dma_maxpq(struct dma_device *dma, enum dma_ctrl_flags flags) BUG(); } +static inline size_t dmaengine_get_icg(bool inc, bool sgl, size_t icg, + size_t dir_icg) +{ + if (inc) { + if (dir_icg) + return dir_icg; + else if (sgl) + return icg; + } + + return 0; +} + +static inline size_t dmaengine_get_dst_icg(struct dma_interleaved_template *xt, + struct data_chunk *chunk) +{ + return dmaengine_get_icg(xt->dst_inc, xt->dst_sgl, + chunk->icg, chunk->dst_icg); +} + +static inline size_t dmaengine_get_src_icg(struct dma_interleaved_template *xt, + struct data_chunk *chunk) +{ + return dmaengine_get_icg(xt->src_inc, xt->src_sgl, + chunk->icg, chunk->src_icg); +} + /* --- public DMA engine API --- */ #ifdef CONFIG_DMA_ENGINE @@ -1079,6 +1186,39 @@ static inline int dma_get_slave_caps(struct dma_chan *chan, } #endif +static inline int dmaengine_desc_set_reuse(struct dma_async_tx_descriptor *tx) +{ + struct dma_slave_caps caps; + + dma_get_slave_caps(tx->chan, &caps); + + if (caps.descriptor_reuse) { + tx->flags |= DMA_CTRL_REUSE; + return 0; + } else { + return -EPERM; + } +} + +static inline void dmaengine_desc_clear_reuse(struct dma_async_tx_descriptor *tx) +{ + tx->flags &= ~DMA_CTRL_REUSE; +} + +static inline bool dmaengine_desc_test_reuse(struct dma_async_tx_descriptor *tx) +{ + return (tx->flags & DMA_CTRL_REUSE) == DMA_CTRL_REUSE; +} + +static inline int dmaengine_desc_free(struct dma_async_tx_descriptor *desc) +{ + /* this is supported for reusable desc, so check that */ + if (dmaengine_desc_test_reuse(desc)) + return desc->desc_free(desc); + else + return -EPERM; +} + /* --- DMA device --- */ int dma_async_device_register(struct dma_device *device); @@ -1093,7 +1233,7 @@ struct dma_chan *dma_get_any_slave_channel(struct dma_device *device); static inline struct dma_chan *__dma_request_slave_channel_compat(const dma_cap_mask_t *mask, dma_filter_fn fn, void *fn_param, - struct device *dev, char *name) + struct device *dev, const char *name) { struct dma_chan *chan; @@ -1101,6 +1241,9 @@ static inline struct dma_chan if (chan) return chan; + if (!fn || !fn_param) + return NULL; + return __dma_request_channel(mask, fn, fn_param); } #endif /* DMAENGINE_H */ diff --git a/kernel/include/linux/dmapool.h b/kernel/include/linux/dmapool.h index 52456aa56..53ba73750 100644 --- a/kernel/include/linux/dmapool.h +++ b/kernel/include/linux/dmapool.h @@ -11,8 +11,8 @@ #ifndef LINUX_DMAPOOL_H #define LINUX_DMAPOOL_H +#include <linux/scatterlist.h> #include <asm/io.h> -#include <asm/scatterlist.h> struct device; @@ -24,6 +24,12 @@ void dma_pool_destroy(struct dma_pool *pool); void *dma_pool_alloc(struct dma_pool *pool, gfp_t mem_flags, dma_addr_t *handle); +static inline void *dma_pool_zalloc(struct dma_pool *pool, gfp_t mem_flags, + dma_addr_t *handle) +{ + return dma_pool_alloc(pool, mem_flags | __GFP_ZERO, handle); +} + void dma_pool_free(struct dma_pool *pool, void *vaddr, dma_addr_t addr); /* diff --git a/kernel/include/linux/dmar.h b/kernel/include/linux/dmar.h index 30624954d..e9bc9292b 100644 --- a/kernel/include/linux/dmar.h +++ b/kernel/include/linux/dmar.h @@ -185,33 +185,85 @@ static inline int dmar_device_remove(void *handle) struct irte { union { + /* Shared between remapped and posted mode*/ struct { - __u64 present : 1, - fpd : 1, - dst_mode : 1, - redir_hint : 1, - trigger_mode : 1, - dlvry_mode : 3, - avail : 4, - __reserved_1 : 4, - vector : 8, - __reserved_2 : 8, - dest_id : 32; + __u64 present : 1, /* 0 */ + fpd : 1, /* 1 */ + __res0 : 6, /* 2 - 6 */ + avail : 4, /* 8 - 11 */ + __res1 : 3, /* 12 - 14 */ + pst : 1, /* 15 */ + vector : 8, /* 16 - 23 */ + __res2 : 40; /* 24 - 63 */ + }; + + /* Remapped mode */ + struct { + __u64 r_present : 1, /* 0 */ + r_fpd : 1, /* 1 */ + dst_mode : 1, /* 2 */ + redir_hint : 1, /* 3 */ + trigger_mode : 1, /* 4 */ + dlvry_mode : 3, /* 5 - 7 */ + r_avail : 4, /* 8 - 11 */ + r_res0 : 4, /* 12 - 15 */ + r_vector : 8, /* 16 - 23 */ + r_res1 : 8, /* 24 - 31 */ + dest_id : 32; /* 32 - 63 */ + }; + + /* Posted mode */ + struct { + __u64 p_present : 1, /* 0 */ + p_fpd : 1, /* 1 */ + p_res0 : 6, /* 2 - 7 */ + p_avail : 4, /* 8 - 11 */ + p_res1 : 2, /* 12 - 13 */ + p_urgent : 1, /* 14 */ + p_pst : 1, /* 15 */ + p_vector : 8, /* 16 - 23 */ + p_res2 : 14, /* 24 - 37 */ + pda_l : 26; /* 38 - 63 */ }; __u64 low; }; union { + /* Shared between remapped and posted mode*/ struct { - __u64 sid : 16, - sq : 2, - svt : 2, - __reserved_3 : 44; + __u64 sid : 16, /* 64 - 79 */ + sq : 2, /* 80 - 81 */ + svt : 2, /* 82 - 83 */ + __res3 : 44; /* 84 - 127 */ + }; + + /* Posted mode*/ + struct { + __u64 p_sid : 16, /* 64 - 79 */ + p_sq : 2, /* 80 - 81 */ + p_svt : 2, /* 82 - 83 */ + p_res3 : 12, /* 84 - 95 */ + pda_h : 32; /* 96 - 127 */ }; __u64 high; }; }; +static inline void dmar_copy_shared_irte(struct irte *dst, struct irte *src) +{ + dst->present = src->present; + dst->fpd = src->fpd; + dst->avail = src->avail; + dst->pst = src->pst; + dst->vector = src->vector; + dst->sid = src->sid; + dst->sq = src->sq; + dst->svt = src->svt; +} + +#define PDA_LOW_BIT 26 +#define PDA_HIGH_BIT 32 + enum { IRQ_REMAP_XAPIC_MODE, IRQ_REMAP_X2APIC_MODE, @@ -227,6 +279,7 @@ extern void dmar_msi_read(int irq, struct msi_msg *msg); extern void dmar_msi_write(int irq, struct msi_msg *msg); extern int dmar_set_interrupt(struct intel_iommu *iommu); extern irqreturn_t dmar_fault(int irq, void *dev_id); -extern int arch_setup_dmar_msi(unsigned int irq); +extern int dmar_alloc_hwirq(int id, int node, void *arg); +extern void dmar_free_hwirq(int irq); #endif /* __DMAR_H__ */ diff --git a/kernel/include/linux/dmi.h b/kernel/include/linux/dmi.h index f820f0a33..5055ac341 100644 --- a/kernel/include/linux/dmi.h +++ b/kernel/include/linux/dmi.h @@ -2,6 +2,7 @@ #define __DMI_H__ #include <linux/list.h> +#include <linux/kobject.h> #include <linux/mod_devicetable.h> /* enum dmi_field is in mod_devicetable.h */ @@ -74,7 +75,7 @@ struct dmi_header { u8 type; u8 length; u16 handle; -}; +} __packed; struct dmi_device { struct list_head list; @@ -93,6 +94,7 @@ struct dmi_dev_onboard { int devfn; }; +extern struct kobject *dmi_kobj; extern int dmi_check_system(const struct dmi_system_id *list); const struct dmi_system_id *dmi_first_match(const struct dmi_system_id *list); extern const char * dmi_get_system_info(int field); diff --git a/kernel/include/linux/dns_resolver.h b/kernel/include/linux/dns_resolver.h index cc92268af..6ac3cad9a 100644 --- a/kernel/include/linux/dns_resolver.h +++ b/kernel/include/linux/dns_resolver.h @@ -27,7 +27,7 @@ #ifdef __KERNEL__ extern int dns_query(const char *type, const char *name, size_t namelen, - const char *options, char **_result, time_t *_expiry); + const char *options, char **_result, time64_t *_expiry); #endif /* KERNEL */ diff --git a/kernel/include/linux/edac.h b/kernel/include/linux/edac.h index da3b72e95..4fe67b853 100644 --- a/kernel/include/linux/edac.h +++ b/kernel/include/linux/edac.h @@ -769,12 +769,10 @@ struct mem_ctl_info { /* the internal state of this controller instance */ int op_state; -#ifdef CONFIG_EDAC_DEBUG struct dentry *debugfs; u8 fake_inject_layer[EDAC_MAX_LAYERS]; - u32 fake_inject_ue; + bool fake_inject_ue; u16 fake_inject_count; -#endif }; /* diff --git a/kernel/include/linux/efi.h b/kernel/include/linux/efi.h index af5be0368..47be3ad7d 100644 --- a/kernel/include/linux/efi.h +++ b/kernel/include/linux/efi.h @@ -85,7 +85,8 @@ typedef struct { #define EFI_MEMORY_MAPPED_IO 11 #define EFI_MEMORY_MAPPED_IO_PORT_SPACE 12 #define EFI_PAL_CODE 13 -#define EFI_MAX_MEMORY_TYPE 14 +#define EFI_PERSISTENT_MEMORY 14 +#define EFI_MAX_MEMORY_TYPE 15 /* Attribute values: */ #define EFI_MEMORY_UC ((u64)0x0000000000000001ULL) /* uncached */ @@ -96,6 +97,9 @@ typedef struct { #define EFI_MEMORY_WP ((u64)0x0000000000001000ULL) /* write-protect */ #define EFI_MEMORY_RP ((u64)0x0000000000002000ULL) /* read-protect */ #define EFI_MEMORY_XP ((u64)0x0000000000004000ULL) /* execute-protect */ +#define EFI_MEMORY_MORE_RELIABLE \ + ((u64)0x0000000000010000ULL) /* higher reliability */ +#define EFI_MEMORY_RO ((u64)0x0000000000020000ULL) /* read-only */ #define EFI_MEMORY_RUNTIME ((u64)0x8000000000000000ULL) /* range requires runtime mapping */ #define EFI_MEMORY_DESCRIPTOR_VERSION 1 @@ -583,12 +587,18 @@ void efi_native_runtime_setup(void); #define EFI_FILE_INFO_ID \ EFI_GUID( 0x9576e92, 0x6d3f, 0x11d2, 0x8e, 0x39, 0x00, 0xa0, 0xc9, 0x69, 0x72, 0x3b ) +#define EFI_SYSTEM_RESOURCE_TABLE_GUID \ + EFI_GUID( 0xb122a263, 0x3661, 0x4f68, 0x99, 0x29, 0x78, 0xf8, 0xb0, 0xd6, 0x21, 0x80 ) + #define EFI_FILE_SYSTEM_GUID \ EFI_GUID( 0x964e5b22, 0x6459, 0x11d2, 0x8e, 0x39, 0x00, 0xa0, 0xc9, 0x69, 0x72, 0x3b ) #define DEVICE_TREE_GUID \ EFI_GUID( 0xb1b621d5, 0xf19c, 0x41a5, 0x83, 0x0b, 0xd9, 0x15, 0x2c, 0x69, 0xaa, 0xe0 ) +#define EFI_PROPERTIES_TABLE_GUID \ + EFI_GUID( 0x880aaca3, 0x4adc, 0x4a04, 0x90, 0x79, 0xb7, 0x47, 0x34, 0x08, 0x25, 0xe5 ) + typedef struct { efi_guid_t guid; u64 table; @@ -670,7 +680,7 @@ typedef struct { } efi_system_table_t; struct efi_memory_map { - void *phys_map; + phys_addr_t phys_map; void *map; void *map_end; int nr_map; @@ -802,6 +812,15 @@ typedef struct _efi_file_io_interface { #define EFI_FILE_MODE_WRITE 0x0000000000000002 #define EFI_FILE_MODE_CREATE 0x8000000000000000 +typedef struct { + u32 version; + u32 length; + u64 memory_protection_attribute; +} efi_properties_table_t; + +#define EFI_PROPERTIES_TABLE_VERSION 0x00010000 +#define EFI_PROPERTIES_RUNTIME_MEMORY_PROTECTION_NON_EXECUTABLE_PE_DATA 0x1 + #define EFI_INVALID_TABLE_ADDR (~0UL) /* @@ -823,6 +842,8 @@ extern struct efi { unsigned long fw_vendor; /* fw_vendor */ unsigned long runtime; /* runtime table */ unsigned long config_table; /* config tables */ + unsigned long esrt; /* ESRT table */ + unsigned long properties_table; /* properties table */ efi_get_time_t *get_time; efi_set_time_t *set_time; efi_get_wakeup_time_t *get_wakeup_time; @@ -864,6 +885,7 @@ extern void efi_enter_virtual_mode (void); /* switch EFI to virtual mode, if pos extern void efi_late_init(void); extern void efi_free_boot_services(void); extern efi_status_t efi_query_variable_store(u32 attributes, unsigned long size); +extern void efi_find_mirror(void); #else static inline void efi_late_init(void) {} static inline void efi_free_boot_services(void) {} @@ -875,6 +897,11 @@ static inline efi_status_t efi_query_variable_store(u32 attributes, unsigned lon #endif extern void __iomem *efi_lookup_mapped_addr(u64 phys_addr); extern int efi_config_init(efi_config_table_type_t *arch_tables); +#ifdef CONFIG_EFI_ESRT +extern void __init efi_esrt_init(void); +#else +static inline void efi_esrt_init(void) { } +#endif extern int efi_config_parse_tables(void *config_tables, int count, int sz, efi_config_table_type_t *arch_tables); extern u64 efi_get_iobase (void); @@ -882,16 +909,25 @@ extern u32 efi_mem_type (unsigned long phys_addr); extern u64 efi_mem_attributes (unsigned long phys_addr); extern u64 efi_mem_attribute (unsigned long phys_addr, unsigned long size); extern int __init efi_uart_console_only (void); +extern u64 efi_mem_desc_end(efi_memory_desc_t *md); +extern int efi_mem_desc_lookup(u64 phys_addr, efi_memory_desc_t *out_md); extern void efi_initialize_iomem_resources(struct resource *code_resource, struct resource *data_resource, struct resource *bss_resource); extern void efi_get_time(struct timespec *now); extern void efi_reserve_boot_services(void); -extern int efi_get_fdt_params(struct efi_fdt_params *params, int verbose); +extern int efi_get_fdt_params(struct efi_fdt_params *params); extern struct efi_memory_map memmap; +extern struct kobject *efi_kobj; extern int efi_reboot_quirk_mode; extern bool efi_poweroff_required(void); +#ifdef CONFIG_EFI_FAKE_MEMMAP +extern void __init efi_fake_memmap(void); +#else +static inline void efi_fake_memmap(void) { } +#endif + /* Iterate through an efi_memory_map */ #define for_each_efi_memory_desc(m, md) \ for ((md) = (m)->map; \ @@ -943,6 +979,7 @@ extern int __init efi_setup_pcdp_console(char *); #define EFI_PARAVIRT 6 /* Access is via a paravirt interface */ #define EFI_ARCH_1 7 /* First arch-specific bit */ #define EFI_DBG 8 /* Print additional debug info at runtime */ +#define EFI_NX_PE_DATA 9 /* Can runtime data regions be mapped non-executable? */ #ifdef CONFIG_EFI /* @@ -1162,7 +1199,10 @@ int efivar_entry_iter(int (*func)(struct efivar_entry *, void *), struct efivar_entry *efivar_entry_find(efi_char16_t *name, efi_guid_t guid, struct list_head *head, bool remove); -bool efivar_validate(efi_char16_t *var_name, u8 *data, unsigned long len); +bool efivar_validate(efi_guid_t vendor, efi_char16_t *var_name, u8 *data, + unsigned long data_size); +bool efivar_variable_is_removable(efi_guid_t vendor, const char *name, + size_t len); extern struct work_struct efivar_work; void efivar_run_worker(void); diff --git a/kernel/include/linux/elevator.h b/kernel/include/linux/elevator.h index 45a914744..638b324f0 100644 --- a/kernel/include/linux/elevator.h +++ b/kernel/include/linux/elevator.h @@ -39,6 +39,7 @@ typedef void (elevator_deactivate_req_fn) (struct request_queue *, struct reques typedef int (elevator_init_fn) (struct request_queue *, struct elevator_type *e); typedef void (elevator_exit_fn) (struct elevator_queue *); +typedef void (elevator_registered_fn) (struct request_queue *); struct elevator_ops { @@ -68,6 +69,7 @@ struct elevator_ops elevator_init_fn *elevator_init_fn; elevator_exit_fn *elevator_exit_fn; + elevator_registered_fn *elevator_registered_fn; }; #define ELV_NAME_MAX (16) diff --git a/kernel/include/linux/enclosure.h b/kernel/include/linux/enclosure.h index 7be22da32..a4cf57cd0 100644 --- a/kernel/include/linux/enclosure.h +++ b/kernel/include/linux/enclosure.h @@ -29,7 +29,11 @@ /* A few generic types ... taken from ses-2 */ enum enclosure_component_type { ENCLOSURE_COMPONENT_DEVICE = 0x01, + ENCLOSURE_COMPONENT_CONTROLLER_ELECTRONICS = 0x07, + ENCLOSURE_COMPONENT_SCSI_TARGET_PORT = 0x14, + ENCLOSURE_COMPONENT_SCSI_INITIATOR_PORT = 0x15, ENCLOSURE_COMPONENT_ARRAY_DEVICE = 0x17, + ENCLOSURE_COMPONENT_SAS_EXPANDER = 0x18, }; /* ses-2 common element status */ diff --git a/kernel/include/linux/etherdevice.h b/kernel/include/linux/etherdevice.h index 606563ef8..eb049c622 100644 --- a/kernel/include/linux/etherdevice.h +++ b/kernel/include/linux/etherdevice.h @@ -76,7 +76,7 @@ static inline bool is_link_local_ether_addr(const u8 *addr) #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) return (((*(const u32 *)addr) ^ (*(const u32 *)b)) | - ((a[2] ^ b[2]) & m)) == 0; + (__force int)((a[2] ^ b[2]) & m)) == 0; #else return ((a[0] ^ b[0]) | (a[1] ^ b[1]) | ((a[2] ^ b[2]) & m)) == 0; #endif @@ -110,7 +110,29 @@ static inline bool is_zero_ether_addr(const u8 *addr) */ static inline bool is_multicast_ether_addr(const u8 *addr) { - return 0x01 & addr[0]; +#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) + u32 a = *(const u32 *)addr; +#else + u16 a = *(const u16 *)addr; +#endif +#ifdef __BIG_ENDIAN + return 0x01 & (a >> ((sizeof(a) * 8) - 8)); +#else + return 0x01 & a; +#endif +} + +static inline bool is_multicast_ether_addr_64bits(const u8 addr[6+2]) +{ +#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 +#ifdef __BIG_ENDIAN + return 0x01 & ((*(const u64 *)addr) >> 56); +#else + return 0x01 & (*(const u64 *)addr); +#endif +#else + return is_multicast_ether_addr(addr); +#endif } /** @@ -169,6 +191,24 @@ static inline bool is_valid_ether_addr(const u8 *addr) } /** + * eth_proto_is_802_3 - Determine if a given Ethertype/length is a protocol + * @proto: Ethertype/length value to be tested + * + * Check that the value from the Ethertype/length field is a valid Ethertype. + * + * Return true if the valid is an 802.3 supported Ethertype. + */ +static inline bool eth_proto_is_802_3(__be16 proto) +{ +#ifndef __BIG_ENDIAN + /* if CPU is little endian mask off bits representing LSB */ + proto &= htons(0xFF00); +#endif + /* cast both to u16 and compare since LSB can be ignored */ + return (__force u16)proto >= (__force u16)htons(ETH_P_802_3_MIN); +} + +/** * eth_random_addr - Generate software assigned random Ethernet address * @addr: Pointer to a six-byte array containing the Ethernet address * diff --git a/kernel/include/linux/extcon.h b/kernel/include/linux/extcon.h index 36f49c405..7abf674c3 100644 --- a/kernel/include/linux/extcon.h +++ b/kernel/include/linux/extcon.h @@ -1,6 +1,9 @@ /* * External connector (extcon) class driver * + * Copyright (C) 2015 Samsung Electronics + * Author: Chanwoo Choi <cw00.choi@samsung.com> + * * Copyright (C) 2012 Samsung Electronics * Author: Donggeun Kim <dg77.kim@samsung.com> * Author: MyungJoo Ham <myungjoo.ham@samsung.com> @@ -24,53 +27,46 @@ #define __LINUX_EXTCON_H__ #include <linux/device.h> -#include <linux/notifier.h> -#include <linux/sysfs.h> - -#define SUPPORTED_CABLE_MAX 32 -#define CABLE_NAME_MAX 30 /* - * The standard cable name is to help support general notifier - * and notifiee device drivers to share the common names. - * Please use standard cable names unless your notifier device has - * a very unique and abnormal cable or - * the cable type is supposed to be used with only one unique - * pair of notifier/notifiee devices. - * - * Please add any other "standard" cables used with extcon dev. - * - * You may add a dot and number to specify version or specification - * of the specific cable if it is required. (e.g., "Fast-charger.18" - * and "Fast-charger.10" for 1.8A and 1.0A chargers) - * However, the notifiee and notifier should be able to handle such - * string and if the notifiee can negotiate the protocol or identify, - * you don't need such convention. This convention is helpful when - * notifier can distinguish but notifiee cannot. + * Define the unique id of supported external connectors */ -enum extcon_cable_name { - EXTCON_USB = 0, - EXTCON_USB_HOST, - EXTCON_TA, /* Travel Adaptor */ - EXTCON_FAST_CHARGER, - EXTCON_SLOW_CHARGER, - EXTCON_CHARGE_DOWNSTREAM, /* Charging an external device */ - EXTCON_HDMI, - EXTCON_MHL, - EXTCON_DVI, - EXTCON_VGA, - EXTCON_DOCK, - EXTCON_LINE_IN, - EXTCON_LINE_OUT, - EXTCON_MIC_IN, - EXTCON_HEADPHONE_OUT, - EXTCON_SPDIF_IN, - EXTCON_SPDIF_OUT, - EXTCON_VIDEO_IN, - EXTCON_VIDEO_OUT, - EXTCON_MECHANICAL, -}; -extern const char extcon_cable_name[][CABLE_NAME_MAX + 1]; +#define EXTCON_NONE 0 + +/* USB external connector */ +#define EXTCON_USB 1 +#define EXTCON_USB_HOST 2 + +/* Charging external connector */ +#define EXTCON_CHG_USB_SDP 5 /* Standard Downstream Port */ +#define EXTCON_CHG_USB_DCP 6 /* Dedicated Charging Port */ +#define EXTCON_CHG_USB_CDP 7 /* Charging Downstream Port */ +#define EXTCON_CHG_USB_ACA 8 /* Accessory Charger Adapter */ +#define EXTCON_CHG_USB_FAST 9 +#define EXTCON_CHG_USB_SLOW 10 + +/* Jack external connector */ +#define EXTCON_JACK_MICROPHONE 20 +#define EXTCON_JACK_HEADPHONE 21 +#define EXTCON_JACK_LINE_IN 22 +#define EXTCON_JACK_LINE_OUT 23 +#define EXTCON_JACK_VIDEO_IN 24 +#define EXTCON_JACK_VIDEO_OUT 25 +#define EXTCON_JACK_SPDIF_IN 26 /* Sony Philips Digital InterFace */ +#define EXTCON_JACK_SPDIF_OUT 27 + +/* Display external connector */ +#define EXTCON_DISP_HDMI 40 /* High-Definition Multimedia Interface */ +#define EXTCON_DISP_MHL 41 /* Mobile High-Definition Link */ +#define EXTCON_DISP_DVI 42 /* Digital Visual Interface */ +#define EXTCON_DISP_VGA 43 /* Video Graphics Array */ + +/* Miscellaneous external connector */ +#define EXTCON_DOCK 60 +#define EXTCON_JIG 61 +#define EXTCON_MECHANICAL 62 + +#define EXTCON_NUM 63 struct extcon_cable; @@ -78,7 +74,7 @@ struct extcon_cable; * struct extcon_dev - An extcon device represents one external connector. * @name: The name of this extcon device. Parent device name is * used if NULL. - * @supported_cable: Array of supported cable names ending with NULL. + * @supported_cable: Array of supported cable names ending with EXTCON_NONE. * If supported_cable is NULL, cable name related APIs * are disabled. * @mutually_exclusive: Array of mutually exclusive set of cables that cannot @@ -89,16 +85,12 @@ struct extcon_cable; * be attached simulataneously. {0x7, 0} is equivalent to * {0x3, 0x6, 0x5, 0}. If it is {0xFFFFFFFF, 0}, there * can be no simultaneous connections. - * @print_name: An optional callback to override the method to print the - * name of the extcon device. - * @print_state: An optional callback to override the method to print the - * status of the extcon device. * @dev: Device of this extcon. * @state: Attach/detach state of this extcon. Do not provide at * register-time. * @nh: Notifier for the state change events from this extcon - * @entry: To support list of extcon devices so that users can search - * for extcon devices based on the extcon name. + * @entry: To support list of extcon devices so that users can + * search for extcon devices based on the extcon name. * @lock: * @max_supported: Internal value to store the number of cables. * @extcon_dev_type: Device_type struct to provide attribute_groups @@ -113,16 +105,12 @@ struct extcon_cable; struct extcon_dev { /* Optional user initializing data */ const char *name; - const char **supported_cable; + const unsigned int *supported_cable; const u32 *mutually_exclusive; - /* Optional callbacks to override class functions */ - ssize_t (*print_name)(struct extcon_dev *edev, char *buf); - ssize_t (*print_state)(struct extcon_dev *edev, char *buf); - /* Internal data. Please do not set. */ struct device dev; - struct raw_notifier_head nh; + struct raw_notifier_head *nh; struct list_head entry; int max_supported; spinlock_t lock; /* could be called by irq handler */ @@ -161,8 +149,6 @@ struct extcon_cable { /** * struct extcon_specific_cable_nb - An internal data for * extcon_register_interest(). - * @internal_nb: A notifier block bridging extcon notifier - * and cable notifier. * @user_nb: user provided notifier block for events from * a specific cable. * @cable_index: the target cable. @@ -170,7 +156,6 @@ struct extcon_cable { * @previous_value: the saved previous event value. */ struct extcon_specific_cable_nb { - struct notifier_block internal_nb; struct notifier_block *user_nb; int cable_index; struct extcon_dev *edev; @@ -194,10 +179,10 @@ extern struct extcon_dev *extcon_get_extcon_dev(const char *extcon_name); /* * Following APIs control the memory of extcon device. */ -extern struct extcon_dev *extcon_dev_allocate(const char **cables); +extern struct extcon_dev *extcon_dev_allocate(const unsigned int *cable); extern void extcon_dev_free(struct extcon_dev *edev); extern struct extcon_dev *devm_extcon_dev_allocate(struct device *dev, - const char **cables); + const unsigned int *cable); extern void devm_extcon_dev_free(struct device *dev, struct extcon_dev *edev); /* @@ -216,13 +201,10 @@ extern int extcon_update_state(struct extcon_dev *edev, u32 mask, u32 state); /* * get/set_cable_state access each bit of the 32b encoded state value. - * They are used to access the status of each cable based on the cable_name - * or cable_index, which is retrieved by extcon_find_cable_index + * They are used to access the status of each cable based on the cable_name. */ -extern int extcon_find_cable_index(struct extcon_dev *sdev, - const char *cable_name); -extern int extcon_get_cable_state_(struct extcon_dev *edev, int cable_index); -extern int extcon_set_cable_state_(struct extcon_dev *edev, int cable_index, +extern int extcon_get_cable_state_(struct extcon_dev *edev, unsigned int id); +extern int extcon_set_cable_state_(struct extcon_dev *edev, unsigned int id, bool cable_state); extern int extcon_get_cable_state(struct extcon_dev *edev, @@ -249,16 +231,21 @@ extern int extcon_unregister_interest(struct extcon_specific_cable_nb *nb); * we do not recommend to use this for normal 'notifiee' device drivers who * want to be notified by a specific external port of the notifier. */ -extern int extcon_register_notifier(struct extcon_dev *edev, +extern int extcon_register_notifier(struct extcon_dev *edev, unsigned int id, + struct notifier_block *nb); +extern int extcon_unregister_notifier(struct extcon_dev *edev, unsigned int id, struct notifier_block *nb); -extern int extcon_unregister_notifier(struct extcon_dev *edev, - struct notifier_block *nb); /* * Following API get the extcon device from devicetree. * This function use phandle of devicetree to get extcon device directly. */ -extern struct extcon_dev *extcon_get_edev_by_phandle(struct device *dev, int index); +extern struct extcon_dev *extcon_get_edev_by_phandle(struct device *dev, + int index); + +/* Following API to get information of extcon device */ +extern const char *extcon_get_edev_name(struct extcon_dev *edev); + #else /* CONFIG_EXTCON */ static inline int extcon_dev_register(struct extcon_dev *edev) { @@ -276,7 +263,7 @@ static inline int devm_extcon_dev_register(struct device *dev, static inline void devm_extcon_dev_unregister(struct device *dev, struct extcon_dev *edev) { } -static inline struct extcon_dev *extcon_dev_allocate(const char **cables) +static inline struct extcon_dev *extcon_dev_allocate(const unsigned int *cable) { return ERR_PTR(-ENOSYS); } @@ -284,7 +271,7 @@ static inline struct extcon_dev *extcon_dev_allocate(const char **cables) static inline void extcon_dev_free(struct extcon_dev *edev) { } static inline struct extcon_dev *devm_extcon_dev_allocate(struct device *dev, - const char **cables) + const unsigned int *cable) { return ERR_PTR(-ENOSYS); } @@ -307,20 +294,14 @@ static inline int extcon_update_state(struct extcon_dev *edev, u32 mask, return 0; } -static inline int extcon_find_cable_index(struct extcon_dev *edev, - const char *cable_name) -{ - return 0; -} - static inline int extcon_get_cable_state_(struct extcon_dev *edev, - int cable_index) + unsigned int id) { return 0; } static inline int extcon_set_cable_state_(struct extcon_dev *edev, - int cable_index, bool cable_state) + unsigned int id, bool cable_state) { return 0; } @@ -343,13 +324,15 @@ static inline struct extcon_dev *extcon_get_extcon_dev(const char *extcon_name) } static inline int extcon_register_notifier(struct extcon_dev *edev, - struct notifier_block *nb) + unsigned int id, + struct notifier_block *nb) { return 0; } static inline int extcon_unregister_notifier(struct extcon_dev *edev, - struct notifier_block *nb) + unsigned int id, + struct notifier_block *nb) { return 0; } diff --git a/kernel/include/linux/extcon/extcon-adc-jack.h b/kernel/include/linux/extcon/extcon-adc-jack.h index 9ca958c4e..53c60806b 100644 --- a/kernel/include/linux/extcon/extcon-adc-jack.h +++ b/kernel/include/linux/extcon/extcon-adc-jack.h @@ -44,7 +44,7 @@ struct adc_jack_cond { * @consumer_channel: Unique name to identify the channel on the consumer * side. This typically describes the channels used within * the consumer. E.g. 'battery_voltage' - * @cable_names: array of cable names ending with null. + * @cable_names: array of extcon id for supported cables. * @adc_contitions: array of struct adc_jack_cond conditions ending * with .state = 0 entry. This describes how to decode * adc values into extcon state. @@ -58,8 +58,7 @@ struct adc_jack_pdata { const char *name; const char *consumer_channel; - /* The last entry should be NULL */ - const char **cable_names; + const enum extcon *cable_names; /* The last entry's state should be 0 */ struct adc_jack_cond *adc_conditions; diff --git a/kernel/include/linux/extcon/extcon-gpio.h b/kernel/include/linux/extcon/extcon-gpio.h index 0b17ad43f..7cacafb78 100644 --- a/kernel/include/linux/extcon/extcon-gpio.h +++ b/kernel/include/linux/extcon/extcon-gpio.h @@ -1,5 +1,5 @@ /* - * External connector (extcon) class generic GPIO driver + * Single-state GPIO extcon driver based on extcon class * * Copyright (C) 2012 Samsung Electronics * Author: MyungJoo Ham <myungjoo.ham@samsung.com> @@ -16,43 +16,31 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * -*/ + */ #ifndef __EXTCON_GPIO_H__ #define __EXTCON_GPIO_H__ __FILE__ #include <linux/extcon.h> /** - * struct gpio_extcon_platform_data - A simple GPIO-controlled extcon device. - * @name: The name of this GPIO extcon device. + * struct gpio_extcon_pdata - A simple GPIO-controlled extcon device. + * @extcon_id: The unique id of specific external connector. * @gpio: Corresponding GPIO. * @gpio_active_low: Boolean describing whether gpio active state is 1 or 0 * If true, low state of gpio means active. * If false, high state of gpio means active. * @debounce: Debounce time for GPIO IRQ in ms. * @irq_flags: IRQ Flags (e.g., IRQF_TRIGGER_LOW). - * @state_on: print_state is overriden with state_on if attached. - * If NULL, default method of extcon class is used. - * @state_off: print_state is overriden with state_off if detached. - * If NUll, default method of extcon class is used. * @check_on_resume: Boolean describing whether to check the state of gpio * while resuming from sleep. - * - * Note that in order for state_on or state_off to be valid, both state_on - * and state_off should be not NULL. If at least one of them is NULL, - * the print_state is not overriden. */ -struct gpio_extcon_platform_data { - const char *name; +struct gpio_extcon_pdata { + unsigned int extcon_id; unsigned gpio; bool gpio_active_low; unsigned long debounce; unsigned long irq_flags; - /* if NULL, "0" or "1" will be printed */ - const char *state_on; - const char *state_off; bool check_on_resume; }; diff --git a/kernel/include/linux/f2fs_fs.h b/kernel/include/linux/f2fs_fs.h index 591f8c3ef..25c6324a0 100644 --- a/kernel/include/linux/f2fs_fs.h +++ b/kernel/include/linux/f2fs_fs.h @@ -50,6 +50,8 @@ #define MAX_ACTIVE_NODE_LOGS 8 #define MAX_ACTIVE_DATA_LOGS 8 +#define VERSION_LEN 256 + /* * For superblock */ @@ -86,6 +88,12 @@ struct f2fs_super_block { __le32 extension_count; /* # of extensions below */ __u8 extension_list[F2FS_MAX_EXTENSION][8]; /* extension array */ __le32 cp_payload; + __u8 version[VERSION_LEN]; /* the kernel version */ + __u8 init_version[VERSION_LEN]; /* the initial kernel version */ + __le32 feature; /* defined features */ + __u8 encryption_level; /* versioning level for encryption */ + __u8 encrypt_pw_salt[16]; /* Salt used for string2key algorithm */ + __u8 reserved[871]; /* valid reserved region */ } __packed; /* @@ -409,15 +417,25 @@ typedef __le32 f2fs_hash_t; #define GET_DENTRY_SLOTS(x) ((x + F2FS_SLOT_LEN - 1) >> F2FS_SLOT_LEN_BITS) -/* the number of dentry in a block */ -#define NR_DENTRY_IN_BLOCK 214 - /* MAX level for dir lookup */ #define MAX_DIR_HASH_DEPTH 63 /* MAX buckets in one level of dir */ #define MAX_DIR_BUCKETS (1 << ((MAX_DIR_HASH_DEPTH / 2) - 1)) +/* + * space utilization of regular dentry and inline dentry + * regular dentry inline dentry + * bitmap 1 * 27 = 27 1 * 23 = 23 + * reserved 1 * 3 = 3 1 * 7 = 7 + * dentry 11 * 214 = 2354 11 * 182 = 2002 + * filename 8 * 214 = 1712 8 * 182 = 1456 + * total 4096 3488 + * + * Note: there are more reserved space in inline dentry than in regular + * dentry, when converting inline dentry we should handle this carefully. + */ +#define NR_DENTRY_IN_BLOCK 214 /* the number of dentry in a block */ #define SIZE_OF_DIR_ENTRY 11 /* by byte */ #define SIZE_OF_DENTRY_BITMAP ((NR_DENTRY_IN_BLOCK + BITS_PER_BYTE - 1) / \ BITS_PER_BYTE) diff --git a/kernel/include/linux/fault-inject.h b/kernel/include/linux/fault-inject.h index 798fad9e4..3159a7dba 100644 --- a/kernel/include/linux/fault-inject.h +++ b/kernel/include/linux/fault-inject.h @@ -18,7 +18,7 @@ struct fault_attr { atomic_t times; atomic_t space; unsigned long verbose; - u32 task_filter; + bool task_filter; unsigned long stacktrace_depth; unsigned long require_start; unsigned long require_end; diff --git a/kernel/include/linux/fb.h b/kernel/include/linux/fb.h index 043f3283b..3d003805a 100644 --- a/kernel/include/linux/fb.h +++ b/kernel/include/linux/fb.h @@ -156,7 +156,7 @@ struct fb_cursor_user { #define FB_EVENT_GET_REQ 0x0D /* Unbind from the console if possible */ #define FB_EVENT_FB_UNBIND 0x0E -/* CONSOLE-SPECIFIC: remap all consoles to new fb - for vga switcheroo */ +/* CONSOLE-SPECIFIC: remap all consoles to new fb - for vga_switcheroo */ #define FB_EVENT_REMAP_ALL_CONSOLE 0x0F /* A hardware display blank early change occured */ #define FB_EARLY_EVENT_BLANK 0x10 @@ -483,7 +483,10 @@ struct fb_info { #ifdef CONFIG_FB_TILEBLITTING struct fb_tile_ops *tileops; /* Tile Blitting */ #endif - char __iomem *screen_base; /* Virtual address */ + union { + char __iomem *screen_base; /* Virtual address */ + char *screen_buffer; + }; unsigned long screen_size; /* Amount of ioremapped VRAM or 0 */ void *pseudo_palette; /* Fake palette of 16 colors */ #define FBINFO_STATE_RUNNING 0 @@ -788,7 +791,7 @@ struct dmt_videomode { extern const char *fb_mode_option; extern const struct fb_videomode vesa_modes[]; -extern const struct fb_videomode cea_modes[64]; +extern const struct fb_videomode cea_modes[65]; extern const struct dmt_videomode dmt_modes[]; struct fb_modelist { diff --git a/kernel/include/linux/fdtable.h b/kernel/include/linux/fdtable.h index 230f87bdf..5295535b6 100644 --- a/kernel/include/linux/fdtable.h +++ b/kernel/include/linux/fdtable.h @@ -26,6 +26,7 @@ struct fdtable { struct file __rcu **fd; /* current fd array */ unsigned long *close_on_exec; unsigned long *open_fds; + unsigned long *full_fds_bits; struct rcu_head rcu; }; @@ -47,6 +48,9 @@ struct files_struct { * read mostly part */ atomic_t count; + bool resize_in_progress; + wait_queue_head_t resize_wait; + struct fdtable __rcu *fdt; struct fdtable fdtab; /* @@ -56,6 +60,7 @@ struct files_struct { int next_fd; unsigned long close_on_exec_init[1]; unsigned long open_fds_init[1]; + unsigned long full_fds_bits_init[1]; struct file __rcu * fd_array[NR_OPEN_DEFAULT]; }; @@ -83,8 +88,8 @@ static inline struct file *__fcheck_files(struct files_struct *files, unsigned i static inline struct file *fcheck_files(struct files_struct *files, unsigned int fd) { - rcu_lockdep_assert(rcu_read_lock_held() || - lockdep_is_held(&files->file_lock), + RCU_LOCKDEP_WARN(!rcu_read_lock_held() && + !lockdep_is_held(&files->file_lock), "suspicious rcu_dereference_check() usage"); return __fcheck_files(files, fd); } diff --git a/kernel/include/linux/fence.h b/kernel/include/linux/fence.h index 39efee130..bb5220113 100644 --- a/kernel/include/linux/fence.h +++ b/kernel/include/linux/fence.h @@ -280,6 +280,22 @@ fence_is_signaled(struct fence *fence) } /** + * fence_is_later - return if f1 is chronologically later than f2 + * @f1: [in] the first fence from the same context + * @f2: [in] the second fence from the same context + * + * Returns true if f1 is chronologically later than f2. Both fences must be + * from the same context, since a seqno is not re-used across contexts. + */ +static inline bool fence_is_later(struct fence *f1, struct fence *f2) +{ + if (WARN_ON(f1->context != f2->context)) + return false; + + return f1->seqno - f2->seqno < INT_MAX; +} + +/** * fence_later - return the chronologically later fence * @f1: [in] the first fence from the same context * @f2: [in] the second fence from the same context @@ -298,14 +314,15 @@ static inline struct fence *fence_later(struct fence *f1, struct fence *f2) * set if enable_signaling wasn't called, and enabling that here is * overkill. */ - if (f2->seqno - f1->seqno <= INT_MAX) - return fence_is_signaled(f2) ? NULL : f2; - else + if (fence_is_later(f1, f2)) return fence_is_signaled(f1) ? NULL : f1; + else + return fence_is_signaled(f2) ? NULL : f2; } signed long fence_wait_timeout(struct fence *, bool intr, signed long timeout); - +signed long fence_wait_any_timeout(struct fence **fences, uint32_t count, + bool intr, signed long timeout); /** * fence_wait - sleep until the fence gets signaled diff --git a/kernel/include/linux/filter.h b/kernel/include/linux/filter.h index fa11b3a36..5972ffe57 100644 --- a/kernel/include/linux/filter.h +++ b/kernel/include/linux/filter.h @@ -12,6 +12,8 @@ #include <linux/linkage.h> #include <linux/printk.h> #include <linux/workqueue.h> +#include <linux/sched.h> +#include <net/sch_generic.h> #include <asm/cacheflush.h> @@ -207,6 +209,16 @@ struct bpf_prog_aux; .off = OFF, \ .imm = 0 }) +/* Atomic memory add, *(uint *)(dst_reg + off16) += src_reg */ + +#define BPF_STX_XADD(SIZE, DST, SRC, OFF) \ + ((struct bpf_insn) { \ + .code = BPF_STX | BPF_SIZE(SIZE) | BPF_XADD, \ + .dst_reg = DST, \ + .src_reg = SRC, \ + .off = OFF, \ + .imm = 0 }) + /* Memory store, *(uint *) (dst_reg + off16) = imm32 */ #define BPF_ST_MEM(SIZE, DST, OFF, IMM) \ @@ -267,6 +279,14 @@ struct bpf_prog_aux; .off = 0, \ .imm = 0 }) +/* Internal classic blocks for direct assignment */ + +#define __BPF_STMT(CODE, K) \ + ((struct sock_filter) BPF_STMT(CODE, K)) + +#define __BPF_JUMP(CODE, K, JT, JF) \ + ((struct sock_filter) BPF_JUMP(CODE, K, JT, JF)) + #define bytes_to_bpf_size(bytes) \ ({ \ int bpf_size = -EINVAL; \ @@ -283,10 +303,6 @@ struct bpf_prog_aux; bpf_size; \ }) -/* Macro to invoke filter function. */ -#define SK_RUN_FILTER(filter, ctx) \ - (*filter->prog->bpf_func)(ctx, filter->prog->insnsi) - #ifdef CONFIG_COMPAT /* A struct sock_filter is architecture independent. */ struct compat_sock_fprog { @@ -307,8 +323,12 @@ struct bpf_binary_header { struct bpf_prog { u16 pages; /* Number of allocated pages */ - bool jited; /* Is our filter JIT'ed? */ - bool gpl_compatible; /* Is our filter GPL compatible? */ + kmemcheck_bitfield_begin(meta); + u16 jited:1, /* Is our filter JIT'ed? */ + gpl_compatible:1, /* Is filter GPL compatible? */ + cb_access:1, /* Is control block accessed? */ + dst_needed:1; /* Do we need dst entry? */ + kmemcheck_bitfield_end(meta); u32 len; /* Number of filter blocks */ enum bpf_prog_type type; /* Type of BPF program */ struct bpf_prog_aux *aux; /* Auxiliary fields */ @@ -330,12 +350,55 @@ struct sk_filter { #define BPF_PROG_RUN(filter, ctx) (*filter->bpf_func)(ctx, filter->insnsi) +static inline u32 bpf_prog_run_save_cb(const struct bpf_prog *prog, + struct sk_buff *skb) +{ + u8 *cb_data = qdisc_skb_cb(skb)->data; + u8 saved_cb[QDISC_CB_PRIV_LEN]; + u32 res; + + BUILD_BUG_ON(FIELD_SIZEOF(struct __sk_buff, cb) != + QDISC_CB_PRIV_LEN); + + if (unlikely(prog->cb_access)) { + memcpy(saved_cb, cb_data, sizeof(saved_cb)); + memset(cb_data, 0, sizeof(saved_cb)); + } + + res = BPF_PROG_RUN(prog, skb); + + if (unlikely(prog->cb_access)) + memcpy(cb_data, saved_cb, sizeof(saved_cb)); + + return res; +} + +static inline u32 bpf_prog_run_clear_cb(const struct bpf_prog *prog, + struct sk_buff *skb) +{ + u8 *cb_data = qdisc_skb_cb(skb)->data; + + if (unlikely(prog->cb_access)) + memset(cb_data, 0, QDISC_CB_PRIV_LEN); + return BPF_PROG_RUN(prog, skb); +} + static inline unsigned int bpf_prog_size(unsigned int proglen) { return max(sizeof(struct bpf_prog), offsetof(struct bpf_prog, insns[proglen])); } +static inline bool bpf_prog_was_classic(const struct bpf_prog *prog) +{ + /* When classic BPF programs have been loaded and the arch + * does not have a classic BPF JIT (anymore), they have been + * converted via bpf_migrate_filter() to eBPF and thus always + * have an unspec program type. + */ + return prog->type == BPF_PROG_TYPE_UNSPEC; +} + #define bpf_classic_proglen(fprog) (fprog->len * sizeof(fprog->filter[0])) #ifdef CONFIG_DEBUG_SET_MODULE_RONX @@ -360,12 +423,9 @@ static inline void bpf_prog_unlock_ro(struct bpf_prog *fp) int sk_filter(struct sock *sk, struct sk_buff *skb); -void bpf_prog_select_runtime(struct bpf_prog *fp); +int bpf_prog_select_runtime(struct bpf_prog *fp); void bpf_prog_free(struct bpf_prog *fp); -int bpf_convert_filter(struct sock_filter *prog, int len, - struct bpf_insn *new_prog, int *new_len); - struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags); struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size, gfp_t gfp_extra_flags); @@ -377,14 +437,17 @@ static inline void bpf_prog_unlock_free(struct bpf_prog *fp) __bpf_prog_free(fp); } +typedef int (*bpf_aux_classic_check_t)(struct sock_filter *filter, + unsigned int flen); + int bpf_prog_create(struct bpf_prog **pfp, struct sock_fprog_kern *fprog); +int bpf_prog_create_from_user(struct bpf_prog **pfp, struct sock_fprog *fprog, + bpf_aux_classic_check_t trans, bool save_orig); void bpf_prog_destroy(struct bpf_prog *fp); int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk); int sk_attach_bpf(u32 ufd, struct sock *sk); int sk_detach_filter(struct sock *sk); - -int bpf_check_classic(const struct sock_filter *filter, unsigned int flen); int sk_get_filter(struct sock *sk, struct sock_filter __user *filter, unsigned int len); @@ -393,6 +456,7 @@ void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp); u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); void bpf_int_jit_compile(struct bpf_prog *fp); +bool bpf_helper_changes_skb_data(void *func); #ifdef CONFIG_BPF_JIT typedef void (*bpf_jit_fill_hole_t)(void *area, unsigned int size); @@ -409,8 +473,9 @@ void bpf_jit_free(struct bpf_prog *fp); static inline void bpf_jit_dump(unsigned int flen, unsigned int proglen, u32 pass, void *image) { - pr_err("flen=%u proglen=%u pass=%u image=%pK\n", - flen, proglen, pass, image); + pr_err("flen=%u proglen=%u pass=%u image=%pK from=%s pid=%d\n", flen, + proglen, pass, image, current->comm, task_pid_nr(current)); + if (image) print_hex_dump(KERN_ERR, "JIT code: ", DUMP_PREFIX_OFFSET, 16, 1, image, proglen, false); @@ -428,6 +493,25 @@ static inline void bpf_jit_free(struct bpf_prog *fp) #define BPF_ANC BIT(15) +static inline bool bpf_needs_clear_a(const struct sock_filter *first) +{ + switch (first->code) { + case BPF_RET | BPF_K: + case BPF_LD | BPF_W | BPF_LEN: + return false; + + case BPF_LD | BPF_W | BPF_ABS: + case BPF_LD | BPF_H | BPF_ABS: + case BPF_LD | BPF_B | BPF_ABS: + if (first->k == SKF_AD_OFF + SKF_AD_ALU_XOR_X) + return true; + return false; + + default: + return true; + } +} + static inline u16 bpf_anc_helper(const struct sock_filter *ftest) { BUG_ON(ftest->code & BPF_ANC); diff --git a/kernel/include/linux/fpga/fpga-mgr.h b/kernel/include/linux/fpga/fpga-mgr.h new file mode 100644 index 000000000..0940bf45e --- /dev/null +++ b/kernel/include/linux/fpga/fpga-mgr.h @@ -0,0 +1,127 @@ +/* + * FPGA Framework + * + * Copyright (C) 2013-2015 Altera Corporation + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program. If not, see <http://www.gnu.org/licenses/>. + */ +#include <linux/mutex.h> +#include <linux/platform_device.h> + +#ifndef _LINUX_FPGA_MGR_H +#define _LINUX_FPGA_MGR_H + +struct fpga_manager; + +/** + * enum fpga_mgr_states - fpga framework states + * @FPGA_MGR_STATE_UNKNOWN: can't determine state + * @FPGA_MGR_STATE_POWER_OFF: FPGA power is off + * @FPGA_MGR_STATE_POWER_UP: FPGA reports power is up + * @FPGA_MGR_STATE_RESET: FPGA in reset state + * @FPGA_MGR_STATE_FIRMWARE_REQ: firmware request in progress + * @FPGA_MGR_STATE_FIRMWARE_REQ_ERR: firmware request failed + * @FPGA_MGR_STATE_WRITE_INIT: preparing FPGA for programming + * @FPGA_MGR_STATE_WRITE_INIT_ERR: Error during WRITE_INIT stage + * @FPGA_MGR_STATE_WRITE: writing image to FPGA + * @FPGA_MGR_STATE_WRITE_ERR: Error while writing FPGA + * @FPGA_MGR_STATE_WRITE_COMPLETE: Doing post programming steps + * @FPGA_MGR_STATE_WRITE_COMPLETE_ERR: Error during WRITE_COMPLETE + * @FPGA_MGR_STATE_OPERATING: FPGA is programmed and operating + */ +enum fpga_mgr_states { + /* default FPGA states */ + FPGA_MGR_STATE_UNKNOWN, + FPGA_MGR_STATE_POWER_OFF, + FPGA_MGR_STATE_POWER_UP, + FPGA_MGR_STATE_RESET, + + /* getting an image for loading */ + FPGA_MGR_STATE_FIRMWARE_REQ, + FPGA_MGR_STATE_FIRMWARE_REQ_ERR, + + /* write sequence: init, write, complete */ + FPGA_MGR_STATE_WRITE_INIT, + FPGA_MGR_STATE_WRITE_INIT_ERR, + FPGA_MGR_STATE_WRITE, + FPGA_MGR_STATE_WRITE_ERR, + FPGA_MGR_STATE_WRITE_COMPLETE, + FPGA_MGR_STATE_WRITE_COMPLETE_ERR, + + /* fpga is programmed and operating */ + FPGA_MGR_STATE_OPERATING, +}; + +/* + * FPGA Manager flags + * FPGA_MGR_PARTIAL_RECONFIG: do partial reconfiguration if supported + */ +#define FPGA_MGR_PARTIAL_RECONFIG BIT(0) + +/** + * struct fpga_manager_ops - ops for low level fpga manager drivers + * @state: returns an enum value of the FPGA's state + * @write_init: prepare the FPGA to receive confuration data + * @write: write count bytes of configuration data to the FPGA + * @write_complete: set FPGA to operating state after writing is done + * @fpga_remove: optional: Set FPGA into a specific state during driver remove + * + * fpga_manager_ops are the low level functions implemented by a specific + * fpga manager driver. The optional ones are tested for NULL before being + * called, so leaving them out is fine. + */ +struct fpga_manager_ops { + enum fpga_mgr_states (*state)(struct fpga_manager *mgr); + int (*write_init)(struct fpga_manager *mgr, u32 flags, + const char *buf, size_t count); + int (*write)(struct fpga_manager *mgr, const char *buf, size_t count); + int (*write_complete)(struct fpga_manager *mgr, u32 flags); + void (*fpga_remove)(struct fpga_manager *mgr); +}; + +/** + * struct fpga_manager - fpga manager structure + * @name: name of low level fpga manager + * @dev: fpga manager device + * @ref_mutex: only allows one reference to fpga manager + * @state: state of fpga manager + * @mops: pointer to struct of fpga manager ops + * @priv: low level driver private date + */ +struct fpga_manager { + const char *name; + struct device dev; + struct mutex ref_mutex; + enum fpga_mgr_states state; + const struct fpga_manager_ops *mops; + void *priv; +}; + +#define to_fpga_manager(d) container_of(d, struct fpga_manager, dev) + +int fpga_mgr_buf_load(struct fpga_manager *mgr, u32 flags, + const char *buf, size_t count); + +int fpga_mgr_firmware_load(struct fpga_manager *mgr, u32 flags, + const char *image_name); + +struct fpga_manager *of_fpga_mgr_get(struct device_node *node); + +void fpga_mgr_put(struct fpga_manager *mgr); + +int fpga_mgr_register(struct device *dev, const char *name, + const struct fpga_manager_ops *mops, void *priv); + +void fpga_mgr_unregister(struct device *dev); + +#endif /*_LINUX_FPGA_MGR_H */ diff --git a/kernel/include/linux/frontswap.h b/kernel/include/linux/frontswap.h index 829326240..e65ef9595 100644 --- a/kernel/include/linux/frontswap.h +++ b/kernel/include/linux/frontswap.h @@ -6,16 +6,16 @@ #include <linux/bitops.h> struct frontswap_ops { - void (*init)(unsigned); - int (*store)(unsigned, pgoff_t, struct page *); - int (*load)(unsigned, pgoff_t, struct page *); - void (*invalidate_page)(unsigned, pgoff_t); - void (*invalidate_area)(unsigned); + void (*init)(unsigned); /* this swap type was just swapon'ed */ + int (*store)(unsigned, pgoff_t, struct page *); /* store a page */ + int (*load)(unsigned, pgoff_t, struct page *); /* load a page */ + void (*invalidate_page)(unsigned, pgoff_t); /* page no longer needed */ + void (*invalidate_area)(unsigned); /* swap type just swapoff'ed */ + struct frontswap_ops *next; /* private pointer to next ops */ }; extern bool frontswap_enabled; -extern struct frontswap_ops * - frontswap_register_ops(struct frontswap_ops *ops); +extern void frontswap_register_ops(struct frontswap_ops *ops); extern void frontswap_shrink(unsigned long); extern unsigned long frontswap_curr_pages(void); extern void frontswap_writethrough(bool); diff --git a/kernel/include/linux/fs.h b/kernel/include/linux/fs.h index 571aab91b..3aa514254 100644 --- a/kernel/include/linux/fs.h +++ b/kernel/include/linux/fs.h @@ -1,7 +1,6 @@ #ifndef _LINUX_FS_H #define _LINUX_FS_H - #include <linux/linkage.h> #include <linux/wait.h> #include <linux/kdev_t.h> @@ -30,15 +29,17 @@ #include <linux/lockdep.h> #include <linux/percpu-rwsem.h> #include <linux/blk_types.h> +#include <linux/workqueue.h> +#include <linux/percpu-rwsem.h> #include <asm/byteorder.h> #include <uapi/linux/fs.h> struct backing_dev_info; +struct bdi_writeback; struct export_operations; struct hd_geometry; struct iovec; -struct nameidata; struct kiocb; struct kobject; struct pipe_inode_info; @@ -51,11 +52,11 @@ struct swap_info_struct; struct seq_file; struct workqueue_struct; struct iov_iter; -struct vm_fault; extern void __init inode_init(void); extern void __init inode_init_early(void); -extern void __init files_init(unsigned long); +extern void __init files_init(void); +extern void __init files_maxfiles_init(void); extern struct files_stat_struct files_stat; extern unsigned long get_max_files(void); @@ -70,6 +71,7 @@ typedef int (get_block_t)(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create); typedef void (dio_iodone_t)(struct kiocb *iocb, loff_t offset, ssize_t bytes, void *private); +typedef void (dax_iodone_t)(struct buffer_head *bh_map, int uptodate); #define MAY_EXEC 0x00000001 #define MAY_WRITE 0x00000002 @@ -634,7 +636,15 @@ struct inode { unsigned long dirtied_time_when; struct hlist_node i_hash; - struct list_head i_wb_list; /* backing dev IO list */ + struct list_head i_io_list; /* backing dev IO list */ +#ifdef CONFIG_CGROUP_WRITEBACK + struct bdi_writeback *i_wb; /* the associated cgroup wb */ + + /* foreign inode detection, see wbc_detach_inode() */ + int i_wb_frn_winner; + u16 i_wb_frn_avg_time; + u16 i_wb_frn_history; +#endif struct list_head i_lru; /* inode LRU list */ struct list_head i_sb_list; union { @@ -656,6 +666,7 @@ struct inode { struct pipe_inode_info *i_pipe; struct block_device *i_bdev; struct cdev *i_cdev; + char *i_link; }; __u32 i_generation; @@ -932,12 +943,18 @@ struct lock_manager_operations { struct lock_manager { struct list_head list; + /* + * NFSv4 and up also want opens blocked during the grace period; + * NLM doesn't care: + */ + bool block_opens; }; struct net; void locks_start_grace(struct net *, struct lock_manager *); void locks_end_grace(struct lock_manager *); int locks_in_grace(struct net *); +int opens_in_grace(struct net *); /* that will die - we need it for nfs_lock_info */ #include <linux/nfs_fs_i.h> @@ -1036,12 +1053,11 @@ extern void locks_remove_file(struct file *); extern void locks_release_private(struct file_lock *); extern void posix_test_lock(struct file *, struct file_lock *); extern int posix_lock_file(struct file *, struct file_lock *, struct file_lock *); -extern int posix_lock_file_wait(struct file *, struct file_lock *); extern int posix_unblock_lock(struct file_lock *); extern int vfs_test_lock(struct file *, struct file_lock *); extern int vfs_lock_file(struct file *, unsigned int, struct file_lock *, struct file_lock *); extern int vfs_cancel_lock(struct file *filp, struct file_lock *fl); -extern int flock_lock_file_wait(struct file *filp, struct file_lock *fl); +extern int locks_lock_inode_wait(struct inode *inode, struct file_lock *fl); extern int __break_lease(struct inode *inode, unsigned int flags, unsigned int type); extern void lease_get_mtime(struct inode *, struct timespec *time); extern int generic_setlease(struct file *, long, struct file_lock **, void **priv); @@ -1127,11 +1143,6 @@ static inline int posix_lock_file(struct file *filp, struct file_lock *fl, return -ENOLCK; } -static inline int posix_lock_file_wait(struct file *filp, struct file_lock *fl) -{ - return -ENOLCK; -} - static inline int posix_unblock_lock(struct file_lock *waiter) { return -ENOENT; @@ -1153,8 +1164,7 @@ static inline int vfs_cancel_lock(struct file *filp, struct file_lock *fl) return 0; } -static inline int flock_lock_file_wait(struct file *filp, - struct file_lock *request) +static inline int locks_lock_inode_wait(struct inode *inode, struct file_lock *fl) { return -ENOLCK; } @@ -1192,6 +1202,15 @@ static inline void show_fd_locks(struct seq_file *f, struct file *filp, struct files_struct *files) {} #endif /* !CONFIG_FILE_LOCKING */ +static inline struct inode *file_inode(const struct file *f) +{ + return f->f_inode; +} + +static inline int locks_lock_file_wait(struct file *filp, struct file_lock *fl) +{ + return locks_lock_inode_wait(file_inode(filp), fl); +} struct fasync_struct { spinlock_t fa_lock; @@ -1232,6 +1251,9 @@ struct mm_struct; #define UMOUNT_NOFOLLOW 0x00000008 /* Don't follow symlink on umount */ #define UMOUNT_UNUSED 0x80000000 /* Flag guaranteed to be unused */ +/* sb->s_iflags */ +#define SB_I_CGROUPWB 0x00000001 /* cgroup-aware writeback enabled */ +#define SB_I_NOEXEC 0x00000002 /* Ignore executables on this fs */ /* Possible states of 'frozen' field */ enum { @@ -1246,16 +1268,9 @@ enum { #define SB_FREEZE_LEVELS (SB_FREEZE_COMPLETE - 1) struct sb_writers { - /* Counters for counting writers at each level */ - struct percpu_counter counter[SB_FREEZE_LEVELS]; - wait_queue_head_t wait; /* queue for waiting for - writers / faults to finish */ - int frozen; /* Is sb frozen? */ - wait_queue_head_t wait_unfrozen; /* queue for waiting for - sb to be thawed */ -#ifdef CONFIG_DEBUG_LOCK_ALLOC - struct lockdep_map lock_map[SB_FREEZE_LEVELS]; -#endif + int frozen; /* Is sb frozen? */ + wait_queue_head_t wait_unfrozen; /* for get_super_thawed() */ + struct percpu_rw_semaphore rw_sem[SB_FREEZE_LEVELS]; }; struct super_block { @@ -1270,6 +1285,7 @@ struct super_block { const struct quotactl_ops *s_qcop; const struct export_operations *s_export_op; unsigned long s_flags; + unsigned long s_iflags; /* internal SB_I_* flags */ unsigned long s_magic; struct dentry *s_root; struct rw_semaphore s_umount; @@ -1280,7 +1296,6 @@ struct super_block { #endif const struct xattr_handler **s_xattr; - struct list_head s_inodes; /* all inodes */ struct hlist_bl_head s_anon; /* anonymous dentries for (nfs) exporting */ struct list_head s_mounts; /* list of mounts; _not_ for fs use */ struct block_device *s_bdev; @@ -1346,11 +1361,18 @@ struct super_block { struct list_lru s_dentry_lru ____cacheline_aligned_in_smp; struct list_lru s_inode_lru ____cacheline_aligned_in_smp; struct rcu_head rcu; + struct work_struct destroy_work; + + struct mutex s_sync_lock; /* sync serialisation lock */ /* * Indicates how deep in a filesystem stack this SB is */ int s_stack_depth; + + /* s_inode_list_lock protects s_inodes */ + spinlock_t s_inode_list_lock ____cacheline_aligned_in_smp; + struct list_head s_inodes; /* all inodes */ }; extern struct timespec current_fs_time(struct super_block *sb); @@ -1362,6 +1384,11 @@ extern struct timespec current_fs_time(struct super_block *sb); void __sb_end_write(struct super_block *sb, int level); int __sb_start_write(struct super_block *sb, int level, bool wait); +#define __sb_writers_acquired(sb, lev) \ + percpu_rwsem_acquire(&(sb)->s_writers.rw_sem[(lev)-1], 1, _THIS_IP_) +#define __sb_writers_release(sb, lev) \ + percpu_rwsem_release(&(sb)->s_writers.rw_sem[(lev)-1], 1, _THIS_IP_) + /** * sb_end_write - drop write access to a superblock * @sb: the super we wrote to @@ -1582,7 +1609,6 @@ struct file_operations { long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long); long (*compat_ioctl) (struct file *, unsigned int, unsigned long); int (*mmap) (struct file *, struct vm_area_struct *); - int (*mremap)(struct file *, struct vm_area_struct *); int (*open) (struct inode *, struct file *); int (*flush) (struct file *, fl_owner_t id); int (*release) (struct inode *, struct file *); @@ -1607,12 +1633,12 @@ struct file_operations { struct inode_operations { struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int); - void * (*follow_link) (struct dentry *, struct nameidata *); + const char * (*follow_link) (struct dentry *, void **); int (*permission) (struct inode *, int); struct posix_acl * (*get_acl)(struct inode *, int); int (*readlink) (struct dentry *, char __user *,int); - void (*put_link) (struct dentry *, struct nameidata *, void *); + void (*put_link) (struct inode *, void *); int (*create) (struct inode *,struct dentry *, umode_t, bool); int (*link) (struct dentry *,struct inode *,struct dentry *); @@ -1639,9 +1665,6 @@ struct inode_operations { umode_t create_mode, int *opened); int (*tmpfile) (struct inode *, struct dentry *, umode_t); int (*set_acl)(struct inode *, struct posix_acl *, int); - - /* WARNING: probably going away soon, do not use! */ - int (*dentry_open)(struct dentry *, struct file *, const struct cred *); } ____cacheline_aligned; ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector, @@ -1806,6 +1829,11 @@ struct super_operations { * * I_DIO_WAKEUP Never set. Only used as a key for wait_on_bit(). * + * I_WB_SWITCH Cgroup bdi_writeback switching in progress. Used to + * synchronize competing switching instances and to tell + * wb stat updates to grab mapping->tree_lock. See + * inode_switch_wb_work_fn() for details. + * * Q: What is the difference between I_WILL_FREE and I_FREEING? */ #define I_DIRTY_SYNC (1 << 0) @@ -1825,6 +1853,7 @@ struct super_operations { #define I_DIRTY_TIME (1 << 11) #define __I_DIRTY_TIME_EXPIRED 12 #define I_DIRTY_TIME_EXPIRED (1 << __I_DIRTY_TIME_EXPIRED) +#define I_WB_SWITCH (1 << 13) #define I_DIRTY (I_DIRTY_SYNC | I_DIRTY_DATASYNC | I_DIRTY_PAGES) #define I_DIRTY_ALL (I_DIRTY | I_DIRTY_TIME) @@ -1879,6 +1908,7 @@ enum file_time_flags { S_VERSION = 8, }; +extern bool atime_needs_update(const struct path *, struct inode *); extern void touch_atime(const struct path *); static inline void file_accessed(struct file *file) { @@ -1992,11 +2022,6 @@ extern void ihold(struct inode * inode); extern void iput(struct inode *); extern int generic_update_time(struct inode *, struct timespec *, int); -static inline struct inode *file_inode(const struct file *f) -{ - return f->f_inode; -} - /* /sys/fs */ extern struct kobject *fs_kobj; @@ -2193,7 +2218,6 @@ extern struct file *file_open_name(struct filename *, int, umode_t); extern struct file *filp_open(const char *, int, umode_t); extern struct file *file_open_root(struct dentry *, struct vfsmount *, const char *, int); -extern int vfs_open(const struct path *, struct file *, const struct cred *); extern struct file * dentry_open(const struct path *, int, const struct cred *); extern int filp_close(struct file *, fl_owner_t id); @@ -2217,7 +2241,7 @@ extern int ioctl_preallocate(struct file *filp, void __user *argp); /* fs/dcache.c */ extern void __init vfs_caches_init_early(void); -extern void __init vfs_caches_init(unsigned long); +extern void __init vfs_caches_init(void); extern struct kmem_cache *names_cachep; @@ -2240,7 +2264,13 @@ extern struct super_block *freeze_bdev(struct block_device *); extern void emergency_thaw_all(void); extern int thaw_bdev(struct block_device *bdev, struct super_block *sb); extern int fsync_bdev(struct block_device *); -extern int sb_is_blkdev_sb(struct super_block *sb); + +extern struct super_block *blockdev_superblock; + +static inline bool sb_is_blkdev_sb(struct super_block *sb) +{ + return sb == blockdev_superblock; +} #else static inline void bd_forget(struct inode *inode) {} static inline int sync_blockdev(struct block_device *bdev) { return 0; } @@ -2279,6 +2309,9 @@ extern struct block_device *blkdev_get_by_path(const char *path, fmode_t mode, extern struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder); extern void blkdev_put(struct block_device *bdev, fmode_t mode); +extern int __blkdev_reread_part(struct block_device *bdev); +extern int blkdev_reread_part(struct block_device *bdev); + #ifdef CONFIG_SYSFS extern int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk); extern void bd_unlink_disk_holder(struct block_device *bdev, @@ -2374,6 +2407,7 @@ extern int write_inode_now(struct inode *, int); extern int filemap_fdatawrite(struct address_space *); extern int filemap_flush(struct address_space *); extern int filemap_fdatawait(struct address_space *); +extern void filemap_fdatawait_keep_errors(struct address_space *); extern int filemap_fdatawait_range(struct address_space *, loff_t lstart, loff_t lend); extern int filemap_write_and_wait(struct address_space *mapping); @@ -2501,6 +2535,8 @@ extern struct file * open_exec(const char *); extern int is_subdir(struct dentry *, struct dentry *); extern int path_is_under(struct path *, struct path *); +extern char *file_path(struct file *, char *, int); + #include <linux/err.h> /* needed for stackable file system support */ @@ -2552,7 +2588,12 @@ extern struct inode *new_inode_pseudo(struct super_block *sb); extern struct inode *new_inode(struct super_block *sb); extern void free_inode_nonrcu(struct inode *inode); extern int should_remove_suid(struct dentry *); -extern int file_remove_suid(struct file *); +extern int file_remove_privs(struct file *); +extern int dentry_needs_remove_privs(struct dentry *dentry); +static inline int file_needs_remove_privs(struct file *file) +{ + return dentry_needs_remove_privs(file->f_path.dentry); +} extern void __insert_inode_hash(struct inode *, unsigned long hashval); static inline void insert_inode_hash(struct inode *inode) @@ -2563,14 +2604,14 @@ static inline void insert_inode_hash(struct inode *inode) extern void __remove_inode_hash(struct inode *); static inline void remove_inode_hash(struct inode *inode) { - if (!inode_unhashed(inode)) + if (!inode_unhashed(inode) && !hlist_fake(&inode->i_hash)) __remove_inode_hash(inode); } extern void inode_sb_list_add(struct inode *inode); #ifdef CONFIG_BLOCK -extern void submit_bio(int, struct bio *); +extern blk_qc_t submit_bio(int, struct bio *); extern int bdev_read_only(struct block_device *); #endif extern int set_blocksize(struct block_device *, int); @@ -2622,15 +2663,6 @@ extern loff_t fixed_size_llseek(struct file *file, loff_t offset, extern int generic_file_open(struct inode * inode, struct file * filp); extern int nonseekable_open(struct inode * inode, struct file * filp); -ssize_t dax_do_io(struct kiocb *, struct inode *, struct iov_iter *, loff_t, - get_block_t, dio_iodone_t, int flags); -int dax_clear_blocks(struct inode *, sector_t block, long size); -int dax_zero_page_range(struct inode *, loff_t from, unsigned len, get_block_t); -int dax_truncate_page(struct inode *, loff_t from, get_block_t); -int dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t); -int dax_pfn_mkwrite(struct vm_area_struct *, struct vm_fault *); -#define dax_mkwrite(vma, vmf, gb) dax_fault(vma, vmf, gb) - #ifdef CONFIG_BLOCK typedef void (dio_submit_t)(int rw, struct bio *bio, struct inode *inode, loff_t file_offset); @@ -2704,13 +2736,14 @@ extern const struct file_operations generic_ro_fops; extern int readlink_copy(char __user *, int, const char *); extern int page_readlink(struct dentry *, char __user *, int); -extern void *page_follow_link_light(struct dentry *, struct nameidata *); -extern void page_put_link(struct dentry *, struct nameidata *, void *); +extern const char *page_follow_link_light(struct dentry *, void **); +extern void page_put_link(struct inode *, void *); extern int __page_symlink(struct inode *inode, const char *symname, int len, int nofs); extern int page_symlink(struct inode *inode, const char *symname, int len); extern const struct inode_operations page_symlink_inode_operations; -extern void kfree_put_link(struct dentry *, struct nameidata *, void *); +extern void kfree_put_link(struct inode *, void *); +extern void free_page_put_link(struct inode *, void *); extern int generic_readlink(struct dentry *, char __user *, int); extern void generic_fillattr(struct inode *, struct kstat *); int vfs_getattr_nosec(struct path *path, struct kstat *stat); @@ -2721,6 +2754,8 @@ void __inode_sub_bytes(struct inode *inode, loff_t bytes); void inode_sub_bytes(struct inode *inode, loff_t bytes); loff_t inode_get_bytes(struct inode *inode); void inode_set_bytes(struct inode *inode, loff_t bytes); +const char *simple_follow_link(struct dentry *, void **); +extern const struct inode_operations simple_symlink_inode_operations; extern int iterate_dir(struct file *, struct dir_context *); @@ -2989,4 +3024,6 @@ static inline bool dir_relax(struct inode *inode) return !IS_DEADDIR(inode); } +extern bool path_noexec(const struct path *path); + #endif /* _LINUX_FS_H */ diff --git a/kernel/include/linux/fscache-cache.h b/kernel/include/linux/fscache-cache.h index 771484993..604e1526c 100644 --- a/kernel/include/linux/fscache-cache.h +++ b/kernel/include/linux/fscache-cache.h @@ -74,6 +74,7 @@ extern wait_queue_head_t fscache_cache_cleared_wq; */ typedef void (*fscache_operation_release_t)(struct fscache_operation *op); typedef void (*fscache_operation_processor_t)(struct fscache_operation *op); +typedef void (*fscache_operation_cancel_t)(struct fscache_operation *op); enum fscache_operation_state { FSCACHE_OP_ST_BLANK, /* Op is not yet submitted */ @@ -109,6 +110,9 @@ struct fscache_operation { * the op in a non-pool thread */ fscache_operation_processor_t processor; + /* Operation cancellation cleanup (optional) */ + fscache_operation_cancel_t cancel; + /* operation releaser */ fscache_operation_release_t release; }; @@ -119,33 +123,17 @@ extern void fscache_op_work_func(struct work_struct *work); extern void fscache_enqueue_operation(struct fscache_operation *); extern void fscache_op_complete(struct fscache_operation *, bool); extern void fscache_put_operation(struct fscache_operation *); - -/** - * fscache_operation_init - Do basic initialisation of an operation - * @op: The operation to initialise - * @release: The release function to assign - * - * Do basic initialisation of an operation. The caller must still set flags, - * object and processor if needed. - */ -static inline void fscache_operation_init(struct fscache_operation *op, - fscache_operation_processor_t processor, - fscache_operation_release_t release) -{ - INIT_WORK(&op->work, fscache_op_work_func); - atomic_set(&op->usage, 1); - op->state = FSCACHE_OP_ST_INITIALISED; - op->debug_id = atomic_inc_return(&fscache_op_debug_id); - op->processor = processor; - op->release = release; - INIT_LIST_HEAD(&op->pend_link); -} +extern void fscache_operation_init(struct fscache_operation *, + fscache_operation_processor_t, + fscache_operation_cancel_t, + fscache_operation_release_t); /* * data read operation */ struct fscache_retrieval { struct fscache_operation op; + struct fscache_cookie *cookie; /* The netfs cookie */ struct address_space *mapping; /* netfs pages */ fscache_rw_complete_t end_io_func; /* function to call on I/O completion */ void *context; /* netfs read context (pinned) */ @@ -371,6 +359,7 @@ struct fscache_object { #define FSCACHE_OBJECT_IS_LOOKED_UP 4 /* T if object has been looked up */ #define FSCACHE_OBJECT_IS_AVAILABLE 5 /* T if object has become active */ #define FSCACHE_OBJECT_RETIRED 6 /* T if object was retired on relinquishment */ +#define FSCACHE_OBJECT_KILLED_BY_CACHE 7 /* T if object was killed by the cache */ struct list_head cache_link; /* link in cache->object_list */ struct hlist_node cookie_link; /* link in cookie->backing_objects */ @@ -410,17 +399,16 @@ static inline bool fscache_object_is_available(struct fscache_object *object) return test_bit(FSCACHE_OBJECT_IS_AVAILABLE, &object->flags); } -static inline bool fscache_object_is_active(struct fscache_object *object) +static inline bool fscache_cache_is_broken(struct fscache_object *object) { - return fscache_object_is_available(object) && - fscache_object_is_live(object) && - !test_bit(FSCACHE_IOERROR, &object->cache->flags); + return test_bit(FSCACHE_IOERROR, &object->cache->flags); } -static inline bool fscache_object_is_dead(struct fscache_object *object) +static inline bool fscache_object_is_active(struct fscache_object *object) { - return fscache_object_is_dying(object) && - test_bit(FSCACHE_IOERROR, &object->cache->flags); + return fscache_object_is_available(object) && + fscache_object_is_live(object) && + !fscache_cache_is_broken(object); } /** @@ -551,4 +539,15 @@ extern enum fscache_checkaux fscache_check_aux(struct fscache_object *object, const void *data, uint16_t datalen); +extern void fscache_object_retrying_stale(struct fscache_object *object); + +enum fscache_why_object_killed { + FSCACHE_OBJECT_IS_STALE, + FSCACHE_OBJECT_NO_SPACE, + FSCACHE_OBJECT_WAS_RETIRED, + FSCACHE_OBJECT_WAS_CULLED, +}; +extern void fscache_object_mark_killed(struct fscache_object *object, + enum fscache_why_object_killed why); + #endif /* _LINUX_FSCACHE_CACHE_H */ diff --git a/kernel/include/linux/fsl/guts.h b/kernel/include/linux/fsl/guts.h new file mode 100644 index 000000000..84d971ff3 --- /dev/null +++ b/kernel/include/linux/fsl/guts.h @@ -0,0 +1,192 @@ +/** + * Freecale 85xx and 86xx Global Utilties register set + * + * Authors: Jeff Brown + * Timur Tabi <timur@freescale.com> + * + * Copyright 2004,2007,2012 Freescale Semiconductor, Inc + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + */ + +#ifndef __FSL_GUTS_H__ +#define __FSL_GUTS_H__ + +#include <linux/types.h> + +/** + * Global Utility Registers. + * + * Not all registers defined in this structure are available on all chips, so + * you are expected to know whether a given register actually exists on your + * chip before you access it. + * + * Also, some registers are similar on different chips but have slightly + * different names. In these cases, one name is chosen to avoid extraneous + * #ifdefs. + */ +struct ccsr_guts { + __be32 porpllsr; /* 0x.0000 - POR PLL Ratio Status Register */ + __be32 porbmsr; /* 0x.0004 - POR Boot Mode Status Register */ + __be32 porimpscr; /* 0x.0008 - POR I/O Impedance Status and Control Register */ + __be32 pordevsr; /* 0x.000c - POR I/O Device Status Register */ + __be32 pordbgmsr; /* 0x.0010 - POR Debug Mode Status Register */ + __be32 pordevsr2; /* 0x.0014 - POR device status register 2 */ + u8 res018[0x20 - 0x18]; + __be32 porcir; /* 0x.0020 - POR Configuration Information Register */ + u8 res024[0x30 - 0x24]; + __be32 gpiocr; /* 0x.0030 - GPIO Control Register */ + u8 res034[0x40 - 0x34]; + __be32 gpoutdr; /* 0x.0040 - General-Purpose Output Data Register */ + u8 res044[0x50 - 0x44]; + __be32 gpindr; /* 0x.0050 - General-Purpose Input Data Register */ + u8 res054[0x60 - 0x54]; + __be32 pmuxcr; /* 0x.0060 - Alternate Function Signal Multiplex Control */ + __be32 pmuxcr2; /* 0x.0064 - Alternate function signal multiplex control 2 */ + __be32 dmuxcr; /* 0x.0068 - DMA Mux Control Register */ + u8 res06c[0x70 - 0x6c]; + __be32 devdisr; /* 0x.0070 - Device Disable Control */ +#define CCSR_GUTS_DEVDISR_TB1 0x00001000 +#define CCSR_GUTS_DEVDISR_TB0 0x00004000 + __be32 devdisr2; /* 0x.0074 - Device Disable Control 2 */ + u8 res078[0x7c - 0x78]; + __be32 pmjcr; /* 0x.007c - 4 Power Management Jog Control Register */ + __be32 powmgtcsr; /* 0x.0080 - Power Management Status and Control Register */ + __be32 pmrccr; /* 0x.0084 - Power Management Reset Counter Configuration Register */ + __be32 pmpdccr; /* 0x.0088 - Power Management Power Down Counter Configuration Register */ + __be32 pmcdr; /* 0x.008c - 4Power management clock disable register */ + __be32 mcpsumr; /* 0x.0090 - Machine Check Summary Register */ + __be32 rstrscr; /* 0x.0094 - Reset Request Status and Control Register */ + __be32 ectrstcr; /* 0x.0098 - Exception reset control register */ + __be32 autorstsr; /* 0x.009c - Automatic reset status register */ + __be32 pvr; /* 0x.00a0 - Processor Version Register */ + __be32 svr; /* 0x.00a4 - System Version Register */ + u8 res0a8[0xb0 - 0xa8]; + __be32 rstcr; /* 0x.00b0 - Reset Control Register */ + u8 res0b4[0xc0 - 0xb4]; + __be32 iovselsr; /* 0x.00c0 - I/O voltage select status register + Called 'elbcvselcr' on 86xx SOCs */ + u8 res0c4[0x100 - 0xc4]; + __be32 rcwsr[16]; /* 0x.0100 - Reset Control Word Status registers + There are 16 registers */ + u8 res140[0x224 - 0x140]; + __be32 iodelay1; /* 0x.0224 - IO delay control register 1 */ + __be32 iodelay2; /* 0x.0228 - IO delay control register 2 */ + u8 res22c[0x604 - 0x22c]; + __be32 pamubypenr; /* 0x.604 - PAMU bypass enable register */ + u8 res608[0x800 - 0x608]; + __be32 clkdvdr; /* 0x.0800 - Clock Divide Register */ + u8 res804[0x900 - 0x804]; + __be32 ircr; /* 0x.0900 - Infrared Control Register */ + u8 res904[0x908 - 0x904]; + __be32 dmacr; /* 0x.0908 - DMA Control Register */ + u8 res90c[0x914 - 0x90c]; + __be32 elbccr; /* 0x.0914 - eLBC Control Register */ + u8 res918[0xb20 - 0x918]; + __be32 ddr1clkdr; /* 0x.0b20 - DDR1 Clock Disable Register */ + __be32 ddr2clkdr; /* 0x.0b24 - DDR2 Clock Disable Register */ + __be32 ddrclkdr; /* 0x.0b28 - DDR Clock Disable Register */ + u8 resb2c[0xe00 - 0xb2c]; + __be32 clkocr; /* 0x.0e00 - Clock Out Select Register */ + u8 rese04[0xe10 - 0xe04]; + __be32 ddrdllcr; /* 0x.0e10 - DDR DLL Control Register */ + u8 rese14[0xe20 - 0xe14]; + __be32 lbcdllcr; /* 0x.0e20 - LBC DLL Control Register */ + __be32 cpfor; /* 0x.0e24 - L2 charge pump fuse override register */ + u8 rese28[0xf04 - 0xe28]; + __be32 srds1cr0; /* 0x.0f04 - SerDes1 Control Register 0 */ + __be32 srds1cr1; /* 0x.0f08 - SerDes1 Control Register 0 */ + u8 resf0c[0xf2c - 0xf0c]; + __be32 itcr; /* 0x.0f2c - Internal transaction control register */ + u8 resf30[0xf40 - 0xf30]; + __be32 srds2cr0; /* 0x.0f40 - SerDes2 Control Register 0 */ + __be32 srds2cr1; /* 0x.0f44 - SerDes2 Control Register 0 */ +} __attribute__ ((packed)); + + +/* Alternate function signal multiplex control */ +#define MPC85xx_PMUXCR_QE(x) (0x8000 >> (x)) + +#ifdef CONFIG_PPC_86xx + +#define CCSR_GUTS_DMACR_DEV_SSI 0 /* DMA controller/channel set to SSI */ +#define CCSR_GUTS_DMACR_DEV_IR 1 /* DMA controller/channel set to IR */ + +/* + * Set the DMACR register in the GUTS + * + * The DMACR register determines the source of initiated transfers for each + * channel on each DMA controller. Rather than have a bunch of repetitive + * macros for the bit patterns, we just have a function that calculates + * them. + * + * guts: Pointer to GUTS structure + * co: The DMA controller (0 or 1) + * ch: The channel on the DMA controller (0, 1, 2, or 3) + * device: The device to set as the source (CCSR_GUTS_DMACR_DEV_xx) + */ +static inline void guts_set_dmacr(struct ccsr_guts __iomem *guts, + unsigned int co, unsigned int ch, unsigned int device) +{ + unsigned int shift = 16 + (8 * (1 - co) + 2 * (3 - ch)); + + clrsetbits_be32(&guts->dmacr, 3 << shift, device << shift); +} + +#define CCSR_GUTS_PMUXCR_LDPSEL 0x00010000 +#define CCSR_GUTS_PMUXCR_SSI1_MASK 0x0000C000 /* Bitmask for SSI1 */ +#define CCSR_GUTS_PMUXCR_SSI1_LA 0x00000000 /* Latched address */ +#define CCSR_GUTS_PMUXCR_SSI1_HI 0x00004000 /* High impedance */ +#define CCSR_GUTS_PMUXCR_SSI1_SSI 0x00008000 /* Used for SSI1 */ +#define CCSR_GUTS_PMUXCR_SSI2_MASK 0x00003000 /* Bitmask for SSI2 */ +#define CCSR_GUTS_PMUXCR_SSI2_LA 0x00000000 /* Latched address */ +#define CCSR_GUTS_PMUXCR_SSI2_HI 0x00001000 /* High impedance */ +#define CCSR_GUTS_PMUXCR_SSI2_SSI 0x00002000 /* Used for SSI2 */ +#define CCSR_GUTS_PMUXCR_LA_22_25_LA 0x00000000 /* Latched Address */ +#define CCSR_GUTS_PMUXCR_LA_22_25_HI 0x00000400 /* High impedance */ +#define CCSR_GUTS_PMUXCR_DBGDRV 0x00000200 /* Signals not driven */ +#define CCSR_GUTS_PMUXCR_DMA2_0 0x00000008 +#define CCSR_GUTS_PMUXCR_DMA2_3 0x00000004 +#define CCSR_GUTS_PMUXCR_DMA1_0 0x00000002 +#define CCSR_GUTS_PMUXCR_DMA1_3 0x00000001 + +/* + * Set the DMA external control bits in the GUTS + * + * The DMA external control bits in the PMUXCR are only meaningful for + * channels 0 and 3. Any other channels are ignored. + * + * guts: Pointer to GUTS structure + * co: The DMA controller (0 or 1) + * ch: The channel on the DMA controller (0, 1, 2, or 3) + * value: the new value for the bit (0 or 1) + */ +static inline void guts_set_pmuxcr_dma(struct ccsr_guts __iomem *guts, + unsigned int co, unsigned int ch, unsigned int value) +{ + if ((ch == 0) || (ch == 3)) { + unsigned int shift = 2 * (co + 1) - (ch & 1) - 1; + + clrsetbits_be32(&guts->pmuxcr, 1 << shift, value << shift); + } +} + +#define CCSR_GUTS_CLKDVDR_PXCKEN 0x80000000 +#define CCSR_GUTS_CLKDVDR_SSICKEN 0x20000000 +#define CCSR_GUTS_CLKDVDR_PXCKINV 0x10000000 +#define CCSR_GUTS_CLKDVDR_PXCKDLY_SHIFT 25 +#define CCSR_GUTS_CLKDVDR_PXCKDLY_MASK 0x06000000 +#define CCSR_GUTS_CLKDVDR_PXCKDLY(x) \ + (((x) & 3) << CCSR_GUTS_CLKDVDR_PXCKDLY_SHIFT) +#define CCSR_GUTS_CLKDVDR_PXCLK_SHIFT 16 +#define CCSR_GUTS_CLKDVDR_PXCLK_MASK 0x001F0000 +#define CCSR_GUTS_CLKDVDR_PXCLK(x) (((x) & 31) << CCSR_GUTS_CLKDVDR_PXCLK_SHIFT) +#define CCSR_GUTS_CLKDVDR_SSICLK_MASK 0x000000FF +#define CCSR_GUTS_CLKDVDR_SSICLK(x) ((x) & CCSR_GUTS_CLKDVDR_SSICLK_MASK) + +#endif + +#endif diff --git a/kernel/include/linux/fsl_devices.h b/kernel/include/linux/fsl_devices.h index a82296af4..f29129141 100644 --- a/kernel/include/linux/fsl_devices.h +++ b/kernel/include/linux/fsl_devices.h @@ -20,10 +20,6 @@ #define FSL_UTMI_PHY_DLY 10 /*As per P1010RM, delay for UTMI PHY CLK to become stable - 10ms*/ #define FSL_USB_PHY_CLK_TIMEOUT 10000 /* uSec */ -#define FSL_USB_VER_OLD 0 -#define FSL_USB_VER_1_6 1 -#define FSL_USB_VER_2_2 2 -#define FSL_USB_VER_2_4 3 #include <linux/types.h> @@ -51,6 +47,15 @@ * */ +enum fsl_usb2_controller_ver { + FSL_USB_VER_NONE = -1, + FSL_USB_VER_OLD = 0, + FSL_USB_VER_1_6 = 1, + FSL_USB_VER_2_2 = 2, + FSL_USB_VER_2_4 = 3, + FSL_USB_VER_2_5 = 4, +}; + enum fsl_usb2_operating_modes { FSL_USB2_MPH_HOST, FSL_USB2_DR_HOST, @@ -64,6 +69,7 @@ enum fsl_usb2_phy_modes { FSL_USB2_PHY_UTMI, FSL_USB2_PHY_UTMI_WIDE, FSL_USB2_PHY_SERIAL, + FSL_USB2_PHY_UTMI_DUAL, }; struct clk; @@ -71,7 +77,7 @@ struct platform_device; struct fsl_usb2_platform_data { /* board specific information */ - int controller_ver; + enum fsl_usb2_controller_ver controller_ver; enum fsl_usb2_operating_modes operating_mode; enum fsl_usb2_phy_modes phy_mode; unsigned int port_enables; @@ -92,6 +98,9 @@ struct fsl_usb2_platform_data { unsigned suspended:1; unsigned already_suspended:1; + unsigned has_fsl_erratum_a007792:1; + unsigned has_fsl_erratum_a005275:1; + unsigned check_phy_clk_valid:1; /* register save area for suspend/resume */ u32 pm_command; diff --git a/kernel/include/linux/fsl_ifc.h b/kernel/include/linux/fsl_ifc.h index bf0321eab..0023088b2 100644 --- a/kernel/include/linux/fsl_ifc.h +++ b/kernel/include/linux/fsl_ifc.h @@ -841,9 +841,59 @@ struct fsl_ifc_ctrl { u32 nand_stat; wait_queue_head_t nand_wait; + bool little_endian; }; extern struct fsl_ifc_ctrl *fsl_ifc_ctrl_dev; +static inline u32 ifc_in32(void __iomem *addr) +{ + u32 val; + + if (fsl_ifc_ctrl_dev->little_endian) + val = ioread32(addr); + else + val = ioread32be(addr); + + return val; +} + +static inline u16 ifc_in16(void __iomem *addr) +{ + u16 val; + + if (fsl_ifc_ctrl_dev->little_endian) + val = ioread16(addr); + else + val = ioread16be(addr); + + return val; +} + +static inline u8 ifc_in8(void __iomem *addr) +{ + return ioread8(addr); +} + +static inline void ifc_out32(u32 val, void __iomem *addr) +{ + if (fsl_ifc_ctrl_dev->little_endian) + iowrite32(val, addr); + else + iowrite32be(val, addr); +} + +static inline void ifc_out16(u16 val, void __iomem *addr) +{ + if (fsl_ifc_ctrl_dev->little_endian) + iowrite16(val, addr); + else + iowrite16be(val, addr); +} + +static inline void ifc_out8(u8 val, void __iomem *addr) +{ + iowrite8(val, addr); +} #endif /* __ASM_FSL_IFC_H */ diff --git a/kernel/include/linux/fsnotify_backend.h b/kernel/include/linux/fsnotify_backend.h index 0f313f93c..533c44085 100644 --- a/kernel/include/linux/fsnotify_backend.h +++ b/kernel/include/linux/fsnotify_backend.h @@ -84,8 +84,6 @@ struct fsnotify_fname; * Each group much define these ops. The fsnotify infrastructure will call * these operations for each relevant group. * - * should_send_event - given a group, inode, and mask this function determines - * if the group is interested in this event. * handle_event - main call for a group to handle an fs event * free_group_priv - called when a group refcnt hits 0 to clean up the private union * freeing_mark - called when a mark is being destroyed for some reason. The group @@ -197,40 +195,49 @@ struct fsnotify_group { #define FSNOTIFY_EVENT_INODE 2 /* - * a mark is simply an object attached to an in core inode which allows an + * A mark is simply an object attached to an in core inode which allows an * fsnotify listener to indicate they are either no longer interested in events * of a type matching mask or only interested in those events. * - * these are flushed when an inode is evicted from core and may be flushed - * when the inode is modified (as seen by fsnotify_access). Some fsnotify users - * (such as dnotify) will flush these when the open fd is closed and not at - * inode eviction or modification. + * These are flushed when an inode is evicted from core and may be flushed + * when the inode is modified (as seen by fsnotify_access). Some fsnotify + * users (such as dnotify) will flush these when the open fd is closed and not + * at inode eviction or modification. + * + * Text in brackets is showing the lock(s) protecting modifications of a + * particular entry. obj_lock means either inode->i_lock or + * mnt->mnt_root->d_lock depending on the mark type. */ struct fsnotify_mark { - __u32 mask; /* mask this mark is for */ - /* we hold ref for each i_list and g_list. also one ref for each 'thing' + /* Mask this mark is for [mark->lock, group->mark_mutex] */ + __u32 mask; + /* We hold one for presence in g_list. Also one ref for each 'thing' * in kernel that found and may be using this mark. */ - atomic_t refcnt; /* active things looking at this mark */ - struct fsnotify_group *group; /* group this mark is for */ - struct list_head g_list; /* list of marks by group->i_fsnotify_marks - * Also reused for queueing mark into - * destroy_list when it's waiting for - * the end of SRCU period before it can - * be freed */ - spinlock_t lock; /* protect group and inode */ - struct hlist_node obj_list; /* list of marks for inode / vfsmount */ - struct list_head free_list; /* tmp list used when freeing this mark */ - union { + atomic_t refcnt; + /* Group this mark is for. Set on mark creation, stable until last ref + * is dropped */ + struct fsnotify_group *group; + /* List of marks by group->i_fsnotify_marks. Also reused for queueing + * mark into destroy_list when it's waiting for the end of SRCU period + * before it can be freed. [group->mark_mutex] */ + struct list_head g_list; + /* Protects inode / mnt pointers, flags, masks */ + spinlock_t lock; + /* List of marks for inode / vfsmount [obj_lock] */ + struct hlist_node obj_list; + union { /* Object pointer [mark->lock, group->mark_mutex] */ struct inode *inode; /* inode this mark is associated with */ struct vfsmount *mnt; /* vfsmount this mark is associated with */ }; - __u32 ignored_mask; /* events types to ignore */ + /* Events types to ignore [mark->lock, group->mark_mutex] */ + __u32 ignored_mask; #define FSNOTIFY_MARK_FLAG_INODE 0x01 #define FSNOTIFY_MARK_FLAG_VFSMOUNT 0x02 #define FSNOTIFY_MARK_FLAG_OBJECT_PINNED 0x04 #define FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY 0x08 #define FSNOTIFY_MARK_FLAG_ALIVE 0x10 - unsigned int flags; /* vfsmount or inode mark? */ +#define FSNOTIFY_MARK_FLAG_ATTACHED 0x20 + unsigned int flags; /* flags [mark->lock] */ void (*free_mark)(struct fsnotify_mark *mark); /* called on final put+free */ }; @@ -347,8 +354,10 @@ extern int fsnotify_add_mark_locked(struct fsnotify_mark *mark, struct fsnotify_ /* given a group and a mark, flag mark to be freed when all references are dropped */ extern void fsnotify_destroy_mark(struct fsnotify_mark *mark, struct fsnotify_group *group); -extern void fsnotify_destroy_mark_locked(struct fsnotify_mark *mark, - struct fsnotify_group *group); +/* detach mark from inode / mount list, group list, drop inode reference */ +extern void fsnotify_detach_mark(struct fsnotify_mark *mark); +/* free mark */ +extern void fsnotify_free_mark(struct fsnotify_mark *mark); /* run all the marks in a group, and clear all of the vfsmount marks */ extern void fsnotify_clear_vfsmount_marks_by_group(struct fsnotify_group *group); /* run all the marks in a group, and clear all of the inode marks */ @@ -359,7 +368,7 @@ extern void fsnotify_clear_marks_by_group_flags(struct fsnotify_group *group, un extern void fsnotify_clear_marks_by_group(struct fsnotify_group *group); extern void fsnotify_get_mark(struct fsnotify_mark *mark); extern void fsnotify_put_mark(struct fsnotify_mark *mark); -extern void fsnotify_unmount_inodes(struct list_head *list); +extern void fsnotify_unmount_inodes(struct super_block *sb); /* put here because inotify does some weird stuff when destroying watches */ extern void fsnotify_init_event(struct fsnotify_event *event, @@ -395,7 +404,7 @@ static inline u32 fsnotify_get_cookie(void) return 0; } -static inline void fsnotify_unmount_inodes(struct list_head *list) +static inline void fsnotify_unmount_inodes(struct super_block *sb) {} #endif /* CONFIG_FSNOTIFY */ diff --git a/kernel/include/linux/ftrace.h b/kernel/include/linux/ftrace.h index 6cd8c0ee4..f2cd67624 100644 --- a/kernel/include/linux/ftrace.h +++ b/kernel/include/linux/ftrace.h @@ -263,7 +263,18 @@ static inline void ftrace_kill(void) { } #endif /* CONFIG_FUNCTION_TRACER */ #ifdef CONFIG_STACK_TRACER + +#define STACK_TRACE_ENTRIES 500 + +struct stack_trace; + +extern unsigned stack_trace_index[]; +extern struct stack_trace stack_trace_max; +extern unsigned long stack_trace_max_size; +extern arch_spinlock_t stack_trace_max_lock; + extern int stack_tracer_enabled; +void stack_trace_print(void); int stack_trace_sysctl(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, @@ -575,6 +586,7 @@ extern int ftrace_arch_read_dyn_info(char *buf, int size); extern int skip_trace(unsigned long ip); extern void ftrace_module_init(struct module *mod); +extern void ftrace_release_mod(struct module *mod); extern void ftrace_disable_daemon(void); extern void ftrace_enable_daemon(void); @@ -682,6 +694,18 @@ static inline void __ftrace_enabled_restore(int enabled) #define CALLER_ADDR5 ((unsigned long)ftrace_return_address(5)) #define CALLER_ADDR6 ((unsigned long)ftrace_return_address(6)) +static inline unsigned long get_lock_parent_ip(void) +{ + unsigned long addr = CALLER_ADDR0; + + if (!in_lock_functions(addr)) + return addr; + addr = CALLER_ADDR1; + if (!in_lock_functions(addr)) + return addr; + return CALLER_ADDR2; +} + #ifdef CONFIG_IRQSOFF_TRACER extern void time_hardirqs_on(unsigned long a0, unsigned long a1); extern void time_hardirqs_off(unsigned long a0, unsigned long a1); diff --git a/kernel/include/linux/fwnode.h b/kernel/include/linux/fwnode.h index 0408545bc..851671742 100644 --- a/kernel/include/linux/fwnode.h +++ b/kernel/include/linux/fwnode.h @@ -16,7 +16,9 @@ enum fwnode_type { FWNODE_INVALID = 0, FWNODE_OF, FWNODE_ACPI, + FWNODE_ACPI_DATA, FWNODE_PDATA, + FWNODE_IRQCHIP, }; struct fwnode_handle { diff --git a/kernel/include/linux/genalloc.h b/kernel/include/linux/genalloc.h index 1ccaab44a..7ff168d06 100644 --- a/kernel/include/linux/genalloc.h +++ b/kernel/include/linux/genalloc.h @@ -59,6 +59,8 @@ struct gen_pool { genpool_algo_t algo; /* allocation function */ void *data; + + const char *name; }; /* @@ -118,17 +120,17 @@ extern unsigned long gen_pool_best_fit(unsigned long *map, unsigned long size, unsigned long start, unsigned int nr, void *data); extern struct gen_pool *devm_gen_pool_create(struct device *dev, - int min_alloc_order, int nid); -extern struct gen_pool *dev_get_gen_pool(struct device *dev); + int min_alloc_order, int nid, const char *name); +extern struct gen_pool *gen_pool_get(struct device *dev, const char *name); bool addr_in_gen_pool(struct gen_pool *pool, unsigned long start, size_t size); #ifdef CONFIG_OF -extern struct gen_pool *of_get_named_gen_pool(struct device_node *np, +extern struct gen_pool *of_gen_pool_get(struct device_node *np, const char *propname, int index); #else -static inline struct gen_pool *of_get_named_gen_pool(struct device_node *np, +static inline struct gen_pool *of_gen_pool_get(struct device_node *np, const char *propname, int index) { return NULL; diff --git a/kernel/include/linux/genetlink.h b/kernel/include/linux/genetlink.h index 09460d6d6..a4c61cbce 100644 --- a/kernel/include/linux/genetlink.h +++ b/kernel/include/linux/genetlink.h @@ -8,7 +8,7 @@ extern void genl_lock(void); extern void genl_unlock(void); #ifdef CONFIG_LOCKDEP -extern int lockdep_genl_is_held(void); +extern bool lockdep_genl_is_held(void); #endif /* for synchronisation between af_netlink and genetlink */ diff --git a/kernel/include/linux/genhd.h b/kernel/include/linux/genhd.h index ec274e0f4..847cc1d91 100644 --- a/kernel/include/linux/genhd.h +++ b/kernel/include/linux/genhd.h @@ -13,6 +13,7 @@ #include <linux/kdev_t.h> #include <linux/rcupdate.h> #include <linux/slab.h> +#include <linux/percpu-refcount.h> #ifdef CONFIG_BLOCK @@ -124,7 +125,7 @@ struct hd_struct { #else struct disk_stats dkstats; #endif - atomic_t ref; + struct percpu_ref ref; struct rcu_head rcu_head; }; @@ -162,6 +163,18 @@ struct disk_part_tbl { struct disk_events; +#if defined(CONFIG_BLK_DEV_INTEGRITY) + +struct blk_integrity { + struct blk_integrity_profile *profile; + unsigned char flags; + unsigned char tuple_size; + unsigned char interval_exp; + unsigned char tag_size; +}; + +#endif /* CONFIG_BLK_DEV_INTEGRITY */ + struct gendisk { /* major, first_minor and minors are input parameters only, * don't use directly. Use disk_devt() and disk_max_parts(). @@ -197,8 +210,8 @@ struct gendisk { atomic_t sync_io; /* RAID */ struct disk_events *ev; #ifdef CONFIG_BLK_DEV_INTEGRITY - struct blk_integrity *integrity; -#endif + struct kobject integrity_kobj; +#endif /* CONFIG_BLK_DEV_INTEGRITY */ int node_id; }; @@ -611,7 +624,7 @@ extern struct hd_struct * __must_check add_partition(struct gendisk *disk, sector_t len, int flags, struct partition_meta_info *info); -extern void __delete_partition(struct hd_struct *); +extern void __delete_partition(struct percpu_ref *); extern void delete_partition(struct gendisk *, int); extern void printk_all_partitions(void); @@ -640,27 +653,39 @@ extern ssize_t part_fail_store(struct device *dev, const char *buf, size_t count); #endif /* CONFIG_FAIL_MAKE_REQUEST */ -static inline void hd_ref_init(struct hd_struct *part) +static inline int hd_ref_init(struct hd_struct *part) { - atomic_set(&part->ref, 1); - smp_mb(); + if (percpu_ref_init(&part->ref, __delete_partition, 0, + GFP_KERNEL)) + return -ENOMEM; + return 0; } static inline void hd_struct_get(struct hd_struct *part) { - atomic_inc(&part->ref); - smp_mb__after_atomic(); + percpu_ref_get(&part->ref); } static inline int hd_struct_try_get(struct hd_struct *part) { - return atomic_inc_not_zero(&part->ref); + return percpu_ref_tryget_live(&part->ref); } static inline void hd_struct_put(struct hd_struct *part) { - if (atomic_dec_and_test(&part->ref)) - __delete_partition(part); + percpu_ref_put(&part->ref); +} + +static inline void hd_struct_kill(struct hd_struct *part) +{ + percpu_ref_kill(&part->ref); +} + +static inline void hd_free_part(struct hd_struct *part) +{ + free_part_stats(part); + free_part_info(part); + percpu_ref_exit(&part->ref); } /* @@ -714,6 +739,16 @@ static inline void part_nr_sects_write(struct hd_struct *part, sector_t size) #endif } +#if defined(CONFIG_BLK_DEV_INTEGRITY) +extern void blk_integrity_add(struct gendisk *); +extern void blk_integrity_del(struct gendisk *); +extern void blk_integrity_revalidate(struct gendisk *); +#else /* CONFIG_BLK_DEV_INTEGRITY */ +static inline void blk_integrity_add(struct gendisk *disk) { } +static inline void blk_integrity_del(struct gendisk *disk) { } +static inline void blk_integrity_revalidate(struct gendisk *disk) { } +#endif /* CONFIG_BLK_DEV_INTEGRITY */ + #else /* CONFIG_BLOCK */ static inline void printk_all_partitions(void) { } diff --git a/kernel/include/linux/gfp.h b/kernel/include/linux/gfp.h index 15928f064..8942af081 100644 --- a/kernel/include/linux/gfp.h +++ b/kernel/include/linux/gfp.h @@ -14,7 +14,7 @@ struct vm_area_struct; #define ___GFP_HIGHMEM 0x02u #define ___GFP_DMA32 0x04u #define ___GFP_MOVABLE 0x08u -#define ___GFP_WAIT 0x10u +#define ___GFP_RECLAIMABLE 0x10u #define ___GFP_HIGH 0x20u #define ___GFP_IO 0x40u #define ___GFP_FS 0x80u @@ -29,18 +29,17 @@ struct vm_area_struct; #define ___GFP_NOMEMALLOC 0x10000u #define ___GFP_HARDWALL 0x20000u #define ___GFP_THISNODE 0x40000u -#define ___GFP_RECLAIMABLE 0x80000u +#define ___GFP_ATOMIC 0x80000u #define ___GFP_NOACCOUNT 0x100000u #define ___GFP_NOTRACK 0x200000u -#define ___GFP_NO_KSWAPD 0x400000u +#define ___GFP_DIRECT_RECLAIM 0x400000u #define ___GFP_OTHER_NODE 0x800000u #define ___GFP_WRITE 0x1000000u +#define ___GFP_KSWAPD_RECLAIM 0x2000000u /* If the above are modified, __GFP_BITS_SHIFT may need updating */ /* - * GFP bitmasks.. - * - * Zone modifiers (see linux/mmzone.h - low three bits) + * Physical address zone modifiers (see linux/mmzone.h - low four bits) * * Do not put any conditional on these. If necessary modify the definitions * without the underscores and use them consistently. The definitions here may @@ -50,113 +49,229 @@ struct vm_area_struct; #define __GFP_HIGHMEM ((__force gfp_t)___GFP_HIGHMEM) #define __GFP_DMA32 ((__force gfp_t)___GFP_DMA32) #define __GFP_MOVABLE ((__force gfp_t)___GFP_MOVABLE) /* Page is movable */ +#define __GFP_MOVABLE ((__force gfp_t)___GFP_MOVABLE) /* ZONE_MOVABLE allowed */ #define GFP_ZONEMASK (__GFP_DMA|__GFP_HIGHMEM|__GFP_DMA32|__GFP_MOVABLE) + +/* + * Page mobility and placement hints + * + * These flags provide hints about how mobile the page is. Pages with similar + * mobility are placed within the same pageblocks to minimise problems due + * to external fragmentation. + * + * __GFP_MOVABLE (also a zone modifier) indicates that the page can be + * moved by page migration during memory compaction or can be reclaimed. + * + * __GFP_RECLAIMABLE is used for slab allocations that specify + * SLAB_RECLAIM_ACCOUNT and whose pages can be freed via shrinkers. + * + * __GFP_WRITE indicates the caller intends to dirty the page. Where possible, + * these pages will be spread between local zones to avoid all the dirty + * pages being in one zone (fair zone allocation policy). + * + * __GFP_HARDWALL enforces the cpuset memory allocation policy. + * + * __GFP_THISNODE forces the allocation to be satisified from the requested + * node with no fallbacks or placement policy enforcements. + */ +#define __GFP_RECLAIMABLE ((__force gfp_t)___GFP_RECLAIMABLE) +#define __GFP_WRITE ((__force gfp_t)___GFP_WRITE) +#define __GFP_HARDWALL ((__force gfp_t)___GFP_HARDWALL) +#define __GFP_THISNODE ((__force gfp_t)___GFP_THISNODE) + +/* + * Watermark modifiers -- controls access to emergency reserves + * + * __GFP_HIGH indicates that the caller is high-priority and that granting + * the request is necessary before the system can make forward progress. + * For example, creating an IO context to clean pages. + * + * __GFP_ATOMIC indicates that the caller cannot reclaim or sleep and is + * high priority. Users are typically interrupt handlers. This may be + * used in conjunction with __GFP_HIGH + * + * __GFP_MEMALLOC allows access to all memory. This should only be used when + * the caller guarantees the allocation will allow more memory to be freed + * very shortly e.g. process exiting or swapping. Users either should + * be the MM or co-ordinating closely with the VM (e.g. swap over NFS). + * + * __GFP_NOMEMALLOC is used to explicitly forbid access to emergency reserves. + * This takes precedence over the __GFP_MEMALLOC flag if both are set. + * + * __GFP_NOACCOUNT ignores the accounting for kmemcg limit enforcement. + */ +#define __GFP_ATOMIC ((__force gfp_t)___GFP_ATOMIC) +#define __GFP_HIGH ((__force gfp_t)___GFP_HIGH) +#define __GFP_MEMALLOC ((__force gfp_t)___GFP_MEMALLOC) +#define __GFP_NOMEMALLOC ((__force gfp_t)___GFP_NOMEMALLOC) +#define __GFP_NOACCOUNT ((__force gfp_t)___GFP_NOACCOUNT) + /* - * Action modifiers - doesn't change the zoning + * Reclaim modifiers + * + * __GFP_IO can start physical IO. + * + * __GFP_FS can call down to the low-level FS. Clearing the flag avoids the + * allocator recursing into the filesystem which might already be holding + * locks. + * + * __GFP_DIRECT_RECLAIM indicates that the caller may enter direct reclaim. + * This flag can be cleared to avoid unnecessary delays when a fallback + * option is available. + * + * __GFP_KSWAPD_RECLAIM indicates that the caller wants to wake kswapd when + * the low watermark is reached and have it reclaim pages until the high + * watermark is reached. A caller may wish to clear this flag when fallback + * options are available and the reclaim is likely to disrupt the system. The + * canonical example is THP allocation where a fallback is cheap but + * reclaim/compaction may cause indirect stalls. + * + * __GFP_RECLAIM is shorthand to allow/forbid both direct and kswapd reclaim. * * __GFP_REPEAT: Try hard to allocate the memory, but the allocation attempt - * _might_ fail. This depends upon the particular VM implementation. + * _might_ fail. This depends upon the particular VM implementation. * * __GFP_NOFAIL: The VM implementation _must_ retry infinitely: the caller - * cannot handle allocation failures. New users should be evaluated carefully - * (and the flag should be used only when there is no reasonable failure policy) - * but it is definitely preferable to use the flag rather than opencode endless - * loop around allocator. + * cannot handle allocation failures. New users should be evaluated carefully + * (and the flag should be used only when there is no reasonable failure + * policy) but it is definitely preferable to use the flag rather than + * opencode endless loop around allocator. * - * __GFP_NORETRY: The VM implementation must not retry indefinitely. - * - * __GFP_MOVABLE: Flag that this page will be movable by the page migration - * mechanism or reclaimed + * __GFP_NORETRY: The VM implementation must not retry indefinitely and will + * return NULL when direct reclaim and memory compaction have failed to allow + * the allocation to succeed. The OOM killer is not called with the current + * implementation. */ -#define __GFP_WAIT ((__force gfp_t)___GFP_WAIT) /* Can wait and reschedule? */ -#define __GFP_HIGH ((__force gfp_t)___GFP_HIGH) /* Should access emergency pools? */ -#define __GFP_IO ((__force gfp_t)___GFP_IO) /* Can start physical IO? */ -#define __GFP_FS ((__force gfp_t)___GFP_FS) /* Can call down to low-level FS? */ -#define __GFP_COLD ((__force gfp_t)___GFP_COLD) /* Cache-cold page required */ -#define __GFP_NOWARN ((__force gfp_t)___GFP_NOWARN) /* Suppress page allocation failure warning */ -#define __GFP_REPEAT ((__force gfp_t)___GFP_REPEAT) /* See above */ -#define __GFP_NOFAIL ((__force gfp_t)___GFP_NOFAIL) /* See above */ -#define __GFP_NORETRY ((__force gfp_t)___GFP_NORETRY) /* See above */ -#define __GFP_MEMALLOC ((__force gfp_t)___GFP_MEMALLOC)/* Allow access to emergency reserves */ -#define __GFP_COMP ((__force gfp_t)___GFP_COMP) /* Add compound page metadata */ -#define __GFP_ZERO ((__force gfp_t)___GFP_ZERO) /* Return zeroed page on success */ -#define __GFP_NOMEMALLOC ((__force gfp_t)___GFP_NOMEMALLOC) /* Don't use emergency reserves. - * This takes precedence over the - * __GFP_MEMALLOC flag if both are - * set - */ -#define __GFP_HARDWALL ((__force gfp_t)___GFP_HARDWALL) /* Enforce hardwall cpuset memory allocs */ -#define __GFP_THISNODE ((__force gfp_t)___GFP_THISNODE)/* No fallback, no policies */ -#define __GFP_RECLAIMABLE ((__force gfp_t)___GFP_RECLAIMABLE) /* Page is reclaimable */ -#define __GFP_NOACCOUNT ((__force gfp_t)___GFP_NOACCOUNT) /* Don't account to kmemcg */ -#define __GFP_NOTRACK ((__force gfp_t)___GFP_NOTRACK) /* Don't track with kmemcheck */ - -#define __GFP_NO_KSWAPD ((__force gfp_t)___GFP_NO_KSWAPD) -#define __GFP_OTHER_NODE ((__force gfp_t)___GFP_OTHER_NODE) /* On behalf of other node */ -#define __GFP_WRITE ((__force gfp_t)___GFP_WRITE) /* Allocator intends to dirty page */ +#define __GFP_IO ((__force gfp_t)___GFP_IO) +#define __GFP_FS ((__force gfp_t)___GFP_FS) +#define __GFP_DIRECT_RECLAIM ((__force gfp_t)___GFP_DIRECT_RECLAIM) /* Caller can reclaim */ +#define __GFP_KSWAPD_RECLAIM ((__force gfp_t)___GFP_KSWAPD_RECLAIM) /* kswapd can wake */ +#define __GFP_RECLAIM ((__force gfp_t)(___GFP_DIRECT_RECLAIM|___GFP_KSWAPD_RECLAIM)) +#define __GFP_REPEAT ((__force gfp_t)___GFP_REPEAT) +#define __GFP_NOFAIL ((__force gfp_t)___GFP_NOFAIL) +#define __GFP_NORETRY ((__force gfp_t)___GFP_NORETRY) /* - * This may seem redundant, but it's a way of annotating false positives vs. - * allocations that simply cannot be supported (e.g. page tables). + * Action modifiers + * + * __GFP_COLD indicates that the caller does not expect to be used in the near + * future. Where possible, a cache-cold page will be returned. + * + * __GFP_NOWARN suppresses allocation failure reports. + * + * __GFP_COMP address compound page metadata. + * + * __GFP_ZERO returns a zeroed page on success. + * + * __GFP_NOTRACK avoids tracking with kmemcheck. + * + * __GFP_NOTRACK_FALSE_POSITIVE is an alias of __GFP_NOTRACK. It's a means of + * distinguishing in the source between false positives and allocations that + * cannot be supported (e.g. page tables). + * + * __GFP_OTHER_NODE is for allocations that are on a remote node but that + * should not be accounted for as a remote allocation in vmstat. A + * typical user would be khugepaged collapsing a huge page on a remote + * node. */ +#define __GFP_COLD ((__force gfp_t)___GFP_COLD) +#define __GFP_NOWARN ((__force gfp_t)___GFP_NOWARN) +#define __GFP_COMP ((__force gfp_t)___GFP_COMP) +#define __GFP_ZERO ((__force gfp_t)___GFP_ZERO) +#define __GFP_NOTRACK ((__force gfp_t)___GFP_NOTRACK) #define __GFP_NOTRACK_FALSE_POSITIVE (__GFP_NOTRACK) +#define __GFP_OTHER_NODE ((__force gfp_t)___GFP_OTHER_NODE) -#define __GFP_BITS_SHIFT 25 /* Room for N __GFP_FOO bits */ +/* Room for N __GFP_FOO bits */ +#define __GFP_BITS_SHIFT 26 #define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1)) -/* This equals 0, but use constants in case they ever change */ -#define GFP_NOWAIT (GFP_ATOMIC & ~__GFP_HIGH) -/* GFP_ATOMIC means both !wait (__GFP_WAIT not set) and use emergency pool */ -#define GFP_ATOMIC (__GFP_HIGH) -#define GFP_NOIO (__GFP_WAIT) -#define GFP_NOFS (__GFP_WAIT | __GFP_IO) -#define GFP_KERNEL (__GFP_WAIT | __GFP_IO | __GFP_FS) -#define GFP_TEMPORARY (__GFP_WAIT | __GFP_IO | __GFP_FS | \ +/* + * Useful GFP flag combinations that are commonly used. It is recommended + * that subsystems start with one of these combinations and then set/clear + * __GFP_FOO flags as necessary. + * + * GFP_ATOMIC users can not sleep and need the allocation to succeed. A lower + * watermark is applied to allow access to "atomic reserves" + * + * GFP_KERNEL is typical for kernel-internal allocations. The caller requires + * ZONE_NORMAL or a lower zone for direct access but can direct reclaim. + * + * GFP_NOWAIT is for kernel allocations that should not stall for direct + * reclaim, start physical IO or use any filesystem callback. + * + * GFP_NOIO will use direct reclaim to discard clean pages or slab pages + * that do not require the starting of any physical IO. + * + * GFP_NOFS will use direct reclaim but will not use any filesystem interfaces. + * + * GFP_USER is for userspace allocations that also need to be directly + * accessibly by the kernel or hardware. It is typically used by hardware + * for buffers that are mapped to userspace (e.g. graphics) that hardware + * still must DMA to. cpuset limits are enforced for these allocations. + * + * GFP_DMA exists for historical reasons and should be avoided where possible. + * The flags indicates that the caller requires that the lowest zone be + * used (ZONE_DMA or 16M on x86-64). Ideally, this would be removed but + * it would require careful auditing as some users really require it and + * others use the flag to avoid lowmem reserves in ZONE_DMA and treat the + * lowest zone as a type of emergency reserve. + * + * GFP_DMA32 is similar to GFP_DMA except that the caller requires a 32-bit + * address. + * + * GFP_HIGHUSER is for userspace allocations that may be mapped to userspace, + * do not need to be directly accessible by the kernel but that cannot + * move once in use. An example may be a hardware allocation that maps + * data directly into userspace but has no addressing limitations. + * + * GFP_HIGHUSER_MOVABLE is for userspace allocations that the kernel does not + * need direct access to but can use kmap() when access is required. They + * are expected to be movable via page reclaim or page migration. Typically, + * pages on the LRU would also be allocated with GFP_HIGHUSER_MOVABLE. + * + * GFP_TRANSHUGE is used for THP allocations. They are compound allocations + * that will fail quickly if memory is not available and will not wake + * kswapd on failure. + */ +#define GFP_ATOMIC (__GFP_HIGH|__GFP_ATOMIC|__GFP_KSWAPD_RECLAIM) +#define GFP_KERNEL (__GFP_RECLAIM | __GFP_IO | __GFP_FS) +#define GFP_NOWAIT (__GFP_KSWAPD_RECLAIM) +#define GFP_NOIO (__GFP_RECLAIM) +#define GFP_NOFS (__GFP_RECLAIM | __GFP_IO) +#define GFP_TEMPORARY (__GFP_RECLAIM | __GFP_IO | __GFP_FS | \ __GFP_RECLAIMABLE) -#define GFP_USER (__GFP_WAIT | __GFP_IO | __GFP_FS | __GFP_HARDWALL) +#define GFP_USER (__GFP_RECLAIM | __GFP_IO | __GFP_FS | __GFP_HARDWALL) +#define GFP_DMA __GFP_DMA +#define GFP_DMA32 __GFP_DMA32 #define GFP_HIGHUSER (GFP_USER | __GFP_HIGHMEM) #define GFP_HIGHUSER_MOVABLE (GFP_HIGHUSER | __GFP_MOVABLE) -#define GFP_IOFS (__GFP_IO | __GFP_FS) -#define GFP_TRANSHUGE (GFP_HIGHUSER_MOVABLE | __GFP_COMP | \ - __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN | \ - __GFP_NO_KSWAPD) +#define GFP_TRANSHUGE ((GFP_HIGHUSER_MOVABLE | __GFP_COMP | \ + __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN) & \ + ~__GFP_KSWAPD_RECLAIM) -/* This mask makes up all the page movable related flags */ +/* Convert GFP flags to their corresponding migrate type */ #define GFP_MOVABLE_MASK (__GFP_RECLAIMABLE|__GFP_MOVABLE) +#define GFP_MOVABLE_SHIFT 3 -/* Control page allocator reclaim behavior */ -#define GFP_RECLAIM_MASK (__GFP_WAIT|__GFP_HIGH|__GFP_IO|__GFP_FS|\ - __GFP_NOWARN|__GFP_REPEAT|__GFP_NOFAIL|\ - __GFP_NORETRY|__GFP_MEMALLOC|__GFP_NOMEMALLOC) - -/* Control slab gfp mask during early boot */ -#define GFP_BOOT_MASK (__GFP_BITS_MASK & ~(__GFP_WAIT|__GFP_IO|__GFP_FS)) - -/* Control allocation constraints */ -#define GFP_CONSTRAINT_MASK (__GFP_HARDWALL|__GFP_THISNODE) - -/* Do not use these with a slab allocator */ -#define GFP_SLAB_BUG_MASK (__GFP_DMA32|__GFP_HIGHMEM|~__GFP_BITS_MASK) - -/* Flag - indicates that the buffer will be suitable for DMA. Ignored on some - platforms, used as appropriate on others */ - -#define GFP_DMA __GFP_DMA - -/* 4GB DMA on some platforms */ -#define GFP_DMA32 __GFP_DMA32 - -/* Convert GFP flags to their corresponding migrate type */ static inline int gfpflags_to_migratetype(const gfp_t gfp_flags) { - WARN_ON((gfp_flags & GFP_MOVABLE_MASK) == GFP_MOVABLE_MASK); + VM_WARN_ON((gfp_flags & GFP_MOVABLE_MASK) == GFP_MOVABLE_MASK); + BUILD_BUG_ON((1UL << GFP_MOVABLE_SHIFT) != ___GFP_MOVABLE); + BUILD_BUG_ON((___GFP_MOVABLE >> GFP_MOVABLE_SHIFT) != MIGRATE_MOVABLE); if (unlikely(page_group_by_mobility_disabled)) return MIGRATE_UNMOVABLE; /* Group based on mobility */ - return (((gfp_flags & __GFP_MOVABLE) != 0) << 1) | - ((gfp_flags & __GFP_RECLAIMABLE) != 0); + return (gfp_flags & GFP_MOVABLE_MASK) >> GFP_MOVABLE_SHIFT; +} +#undef GFP_MOVABLE_MASK +#undef GFP_MOVABLE_SHIFT + +static inline bool gfpflags_allow_blocking(const gfp_t gfp_flags) +{ + return (bool __force)(gfp_flags & __GFP_DIRECT_RECLAIM); } #ifdef CONFIG_HIGHMEM @@ -300,22 +415,31 @@ __alloc_pages(gfp_t gfp_mask, unsigned int order, return __alloc_pages_nodemask(gfp_mask, order, zonelist, NULL); } -static inline struct page *alloc_pages_node(int nid, gfp_t gfp_mask, - unsigned int order) +/* + * Allocate pages, preferring the node given as nid. The node must be valid and + * online. For more general interface, see alloc_pages_node(). + */ +static inline struct page * +__alloc_pages_node(int nid, gfp_t gfp_mask, unsigned int order) { - /* Unknown node is current node */ - if (nid < 0) - nid = numa_node_id(); + VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES); + VM_WARN_ON(!node_online(nid)); return __alloc_pages(gfp_mask, order, node_zonelist(nid, gfp_mask)); } -static inline struct page *alloc_pages_exact_node(int nid, gfp_t gfp_mask, +/* + * Allocate pages, preferring the node given as nid. When nid == NUMA_NO_NODE, + * prefer the current CPU's closest node. Otherwise node must be valid and + * online. + */ +static inline struct page *alloc_pages_node(int nid, gfp_t gfp_mask, unsigned int order) { - VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES || !node_online(nid)); + if (nid == NUMA_NO_NODE) + nid = numa_mem_id(); - return __alloc_pages(gfp_mask, order, node_zonelist(nid, gfp_mask)); + return __alloc_pages_node(nid, gfp_mask, order); } #ifdef CONFIG_NUMA @@ -354,7 +478,6 @@ extern unsigned long get_zeroed_page(gfp_t gfp_mask); void *alloc_pages_exact(size_t size, gfp_t gfp_mask); void free_pages_exact(void *virt, size_t size); -/* This is different from alloc_pages_exact_node !!! */ void * __meminit alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask); #define __get_free_page(gfp_mask) \ @@ -368,6 +491,11 @@ extern void free_pages(unsigned long addr, unsigned int order); extern void free_hot_cold_page(struct page *page, bool cold); extern void free_hot_cold_page_list(struct list_head *list, bool cold); +struct page_frag_cache; +extern void *__alloc_page_frag(struct page_frag_cache *nc, + unsigned int fragsz, gfp_t gfp_mask); +extern void __free_page_frag(void *addr); + extern void __free_kmem_pages(struct page *page, unsigned int order); extern void free_kmem_pages(unsigned long addr, unsigned int order); @@ -379,6 +507,14 @@ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp); void drain_all_pages(struct zone *zone); void drain_local_pages(struct zone *zone); +#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT +void page_alloc_init_late(void); +#else +static inline void page_alloc_init_late(void) +{ +} +#endif + /* * gfp_allowed_mask is set to GFP_BOOT_MASK during early boot to restrict what * GFP flags are used before interrupts are enabled. Once interrupts are diff --git a/kernel/include/linux/goldfish.h b/kernel/include/linux/goldfish.h index 569236e6b..93e080b39 100644 --- a/kernel/include/linux/goldfish.h +++ b/kernel/include/linux/goldfish.h @@ -3,13 +3,24 @@ /* Helpers for Goldfish virtual platform */ -static inline void gf_write64(unsigned long data, - void __iomem *portl, void __iomem *porth) +static inline void gf_write_ptr(const void *ptr, void __iomem *portl, + void __iomem *porth) { - writel((u32)data, portl); + writel((u32)(unsigned long)ptr, portl); #ifdef CONFIG_64BIT - writel(data>>32, porth); + writel((unsigned long)ptr >> 32, porth); #endif } +static inline void gf_write_dma_addr(const dma_addr_t addr, + void __iomem *portl, + void __iomem *porth) +{ + writel((u32)addr, portl); +#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT + writel(addr >> 32, porth); +#endif +} + + #endif /* __LINUX_GOLDFISH_H */ diff --git a/kernel/include/linux/gpio.h b/kernel/include/linux/gpio.h index ab81339a8..d12b5d566 100644 --- a/kernel/include/linux/gpio.h +++ b/kernel/include/linux/gpio.h @@ -196,13 +196,6 @@ static inline int gpio_export_link(struct device *dev, const char *name, return -EINVAL; } -static inline int gpio_sysfs_set_active_low(unsigned gpio, int value) -{ - /* GPIO can never have been requested */ - WARN_ON(1); - return -EINVAL; -} - static inline void gpio_unexport(unsigned gpio) { /* GPIO can never have been exported */ diff --git a/kernel/include/linux/gpio/consumer.h b/kernel/include/linux/gpio/consumer.h index da042657d..fb0fde686 100644 --- a/kernel/include/linux/gpio/consumer.h +++ b/kernel/include/linux/gpio/consumer.h @@ -47,17 +47,17 @@ enum gpiod_flags { int gpiod_count(struct device *dev, const char *con_id); /* Acquire and dispose GPIOs */ -struct gpio_desc *__must_check __gpiod_get(struct device *dev, +struct gpio_desc *__must_check gpiod_get(struct device *dev, const char *con_id, enum gpiod_flags flags); -struct gpio_desc *__must_check __gpiod_get_index(struct device *dev, +struct gpio_desc *__must_check gpiod_get_index(struct device *dev, const char *con_id, unsigned int idx, enum gpiod_flags flags); -struct gpio_desc *__must_check __gpiod_get_optional(struct device *dev, +struct gpio_desc *__must_check gpiod_get_optional(struct device *dev, const char *con_id, enum gpiod_flags flags); -struct gpio_desc *__must_check __gpiod_get_index_optional(struct device *dev, +struct gpio_desc *__must_check gpiod_get_index_optional(struct device *dev, const char *con_id, unsigned int index, enum gpiod_flags flags); @@ -70,18 +70,18 @@ struct gpio_descs *__must_check gpiod_get_array_optional(struct device *dev, void gpiod_put(struct gpio_desc *desc); void gpiod_put_array(struct gpio_descs *descs); -struct gpio_desc *__must_check __devm_gpiod_get(struct device *dev, +struct gpio_desc *__must_check devm_gpiod_get(struct device *dev, const char *con_id, enum gpiod_flags flags); -struct gpio_desc *__must_check __devm_gpiod_get_index(struct device *dev, +struct gpio_desc *__must_check devm_gpiod_get_index(struct device *dev, const char *con_id, unsigned int idx, enum gpiod_flags flags); -struct gpio_desc *__must_check __devm_gpiod_get_optional(struct device *dev, +struct gpio_desc *__must_check devm_gpiod_get_optional(struct device *dev, const char *con_id, enum gpiod_flags flags); struct gpio_desc *__must_check -__devm_gpiod_get_index_optional(struct device *dev, const char *con_id, +devm_gpiod_get_index_optional(struct device *dev, const char *con_id, unsigned int index, enum gpiod_flags flags); struct gpio_descs *__must_check devm_gpiod_get_array(struct device *dev, const char *con_id, @@ -100,24 +100,25 @@ int gpiod_direction_output_raw(struct gpio_desc *desc, int value); /* Value get/set from non-sleeping context */ int gpiod_get_value(const struct gpio_desc *desc); void gpiod_set_value(struct gpio_desc *desc, int value); -void gpiod_set_array(unsigned int array_size, - struct gpio_desc **desc_array, int *value_array); +void gpiod_set_array_value(unsigned int array_size, + struct gpio_desc **desc_array, int *value_array); int gpiod_get_raw_value(const struct gpio_desc *desc); void gpiod_set_raw_value(struct gpio_desc *desc, int value); -void gpiod_set_raw_array(unsigned int array_size, - struct gpio_desc **desc_array, int *value_array); +void gpiod_set_raw_array_value(unsigned int array_size, + struct gpio_desc **desc_array, + int *value_array); /* Value get/set from sleeping context */ int gpiod_get_value_cansleep(const struct gpio_desc *desc); void gpiod_set_value_cansleep(struct gpio_desc *desc, int value); -void gpiod_set_array_cansleep(unsigned int array_size, - struct gpio_desc **desc_array, - int *value_array); +void gpiod_set_array_value_cansleep(unsigned int array_size, + struct gpio_desc **desc_array, + int *value_array); int gpiod_get_raw_value_cansleep(const struct gpio_desc *desc); void gpiod_set_raw_value_cansleep(struct gpio_desc *desc, int value); -void gpiod_set_raw_array_cansleep(unsigned int array_size, - struct gpio_desc **desc_array, - int *value_array); +void gpiod_set_raw_array_value_cansleep(unsigned int array_size, + struct gpio_desc **desc_array, + int *value_array); int gpiod_set_debounce(struct gpio_desc *desc, unsigned debounce); @@ -145,31 +146,31 @@ static inline int gpiod_count(struct device *dev, const char *con_id) return 0; } -static inline struct gpio_desc *__must_check __gpiod_get(struct device *dev, - const char *con_id, - enum gpiod_flags flags) +static inline struct gpio_desc *__must_check gpiod_get(struct device *dev, + const char *con_id, + enum gpiod_flags flags) { return ERR_PTR(-ENOSYS); } static inline struct gpio_desc *__must_check -__gpiod_get_index(struct device *dev, - const char *con_id, - unsigned int idx, - enum gpiod_flags flags) +gpiod_get_index(struct device *dev, + const char *con_id, + unsigned int idx, + enum gpiod_flags flags) { return ERR_PTR(-ENOSYS); } static inline struct gpio_desc *__must_check -__gpiod_get_optional(struct device *dev, const char *con_id, - enum gpiod_flags flags) +gpiod_get_optional(struct device *dev, const char *con_id, + enum gpiod_flags flags) { return ERR_PTR(-ENOSYS); } static inline struct gpio_desc *__must_check -__gpiod_get_index_optional(struct device *dev, const char *con_id, - unsigned int index, enum gpiod_flags flags) +gpiod_get_index_optional(struct device *dev, const char *con_id, + unsigned int index, enum gpiod_flags flags) { return ERR_PTR(-ENOSYS); } @@ -205,7 +206,7 @@ static inline void gpiod_put_array(struct gpio_descs *descs) } static inline struct gpio_desc *__must_check -__devm_gpiod_get(struct device *dev, +devm_gpiod_get(struct device *dev, const char *con_id, enum gpiod_flags flags) { @@ -213,7 +214,7 @@ __devm_gpiod_get(struct device *dev, } static inline struct gpio_desc *__must_check -__devm_gpiod_get_index(struct device *dev, +devm_gpiod_get_index(struct device *dev, const char *con_id, unsigned int idx, enum gpiod_flags flags) @@ -222,14 +223,14 @@ __devm_gpiod_get_index(struct device *dev, } static inline struct gpio_desc *__must_check -__devm_gpiod_get_optional(struct device *dev, const char *con_id, +devm_gpiod_get_optional(struct device *dev, const char *con_id, enum gpiod_flags flags) { return ERR_PTR(-ENOSYS); } static inline struct gpio_desc *__must_check -__devm_gpiod_get_index_optional(struct device *dev, const char *con_id, +devm_gpiod_get_index_optional(struct device *dev, const char *con_id, unsigned int index, enum gpiod_flags flags) { return ERR_PTR(-ENOSYS); @@ -304,9 +305,9 @@ static inline void gpiod_set_value(struct gpio_desc *desc, int value) /* GPIO can never have been requested */ WARN_ON(1); } -static inline void gpiod_set_array(unsigned int array_size, - struct gpio_desc **desc_array, - int *value_array) +static inline void gpiod_set_array_value(unsigned int array_size, + struct gpio_desc **desc_array, + int *value_array) { /* GPIO can never have been requested */ WARN_ON(1); @@ -322,9 +323,9 @@ static inline void gpiod_set_raw_value(struct gpio_desc *desc, int value) /* GPIO can never have been requested */ WARN_ON(1); } -static inline void gpiod_set_raw_array(unsigned int array_size, - struct gpio_desc **desc_array, - int *value_array) +static inline void gpiod_set_raw_array_value(unsigned int array_size, + struct gpio_desc **desc_array, + int *value_array) { /* GPIO can never have been requested */ WARN_ON(1); @@ -341,7 +342,7 @@ static inline void gpiod_set_value_cansleep(struct gpio_desc *desc, int value) /* GPIO can never have been requested */ WARN_ON(1); } -static inline void gpiod_set_array_cansleep(unsigned int array_size, +static inline void gpiod_set_array_value_cansleep(unsigned int array_size, struct gpio_desc **desc_array, int *value_array) { @@ -360,7 +361,7 @@ static inline void gpiod_set_raw_value_cansleep(struct gpio_desc *desc, /* GPIO can never have been requested */ WARN_ON(1); } -static inline void gpiod_set_raw_array_cansleep(unsigned int array_size, +static inline void gpiod_set_raw_array_value_cansleep(unsigned int array_size, struct gpio_desc **desc_array, int *value_array) { @@ -399,6 +400,7 @@ static inline struct gpio_desc *gpio_to_desc(unsigned gpio) { return ERR_PTR(-EINVAL); } + static inline int desc_to_gpio(const struct gpio_desc *desc) { /* GPIO can never have been requested */ @@ -423,48 +425,11 @@ static inline struct gpio_desc *devm_get_gpiod_from_child( #endif /* CONFIG_GPIOLIB */ -/* - * Vararg-hacks! This is done to transition the kernel to always pass - * the options flags argument to the below functions. During a transition - * phase these vararg macros make both old-and-newstyle code compile, - * but when all calls to the elder API are removed, these should go away - * and the __gpiod_get() etc functions above be renamed just gpiod_get() - * etc. - */ -#define __gpiod_get(dev, con_id, flags, ...) __gpiod_get(dev, con_id, flags) -#define gpiod_get(varargs...) __gpiod_get(varargs, GPIOD_ASIS) -#define __gpiod_get_index(dev, con_id, index, flags, ...) \ - __gpiod_get_index(dev, con_id, index, flags) -#define gpiod_get_index(varargs...) __gpiod_get_index(varargs, GPIOD_ASIS) -#define __gpiod_get_optional(dev, con_id, flags, ...) \ - __gpiod_get_optional(dev, con_id, flags) -#define gpiod_get_optional(varargs...) __gpiod_get_optional(varargs, GPIOD_ASIS) -#define __gpiod_get_index_optional(dev, con_id, index, flags, ...) \ - __gpiod_get_index_optional(dev, con_id, index, flags) -#define gpiod_get_index_optional(varargs...) \ - __gpiod_get_index_optional(varargs, GPIOD_ASIS) -#define __devm_gpiod_get(dev, con_id, flags, ...) \ - __devm_gpiod_get(dev, con_id, flags) -#define devm_gpiod_get(varargs...) __devm_gpiod_get(varargs, GPIOD_ASIS) -#define __devm_gpiod_get_index(dev, con_id, index, flags, ...) \ - __devm_gpiod_get_index(dev, con_id, index, flags) -#define devm_gpiod_get_index(varargs...) \ - __devm_gpiod_get_index(varargs, GPIOD_ASIS) -#define __devm_gpiod_get_optional(dev, con_id, flags, ...) \ - __devm_gpiod_get_optional(dev, con_id, flags) -#define devm_gpiod_get_optional(varargs...) \ - __devm_gpiod_get_optional(varargs, GPIOD_ASIS) -#define __devm_gpiod_get_index_optional(dev, con_id, index, flags, ...) \ - __devm_gpiod_get_index_optional(dev, con_id, index, flags) -#define devm_gpiod_get_index_optional(varargs...) \ - __devm_gpiod_get_index_optional(varargs, GPIOD_ASIS) - #if IS_ENABLED(CONFIG_GPIOLIB) && IS_ENABLED(CONFIG_GPIO_SYSFS) int gpiod_export(struct gpio_desc *desc, bool direction_may_change); int gpiod_export_link(struct device *dev, const char *name, struct gpio_desc *desc); -int gpiod_sysfs_set_active_low(struct gpio_desc *desc, int value); void gpiod_unexport(struct gpio_desc *desc); #else /* CONFIG_GPIOLIB && CONFIG_GPIO_SYSFS */ @@ -481,11 +446,6 @@ static inline int gpiod_export_link(struct device *dev, const char *name, return -ENOSYS; } -static inline int gpiod_sysfs_set_active_low(struct gpio_desc *desc, int value) -{ - return -ENOSYS; -} - static inline void gpiod_unexport(struct gpio_desc *desc) { } diff --git a/kernel/include/linux/gpio/driver.h b/kernel/include/linux/gpio/driver.h index f1b36593e..d1baebf35 100644 --- a/kernel/include/linux/gpio/driver.h +++ b/kernel/include/linux/gpio/driver.h @@ -6,6 +6,7 @@ #include <linux/irq.h> #include <linux/irqchip/chained_irq.h> #include <linux/irqdomain.h> +#include <linux/lockdep.h> #include <linux/pinctrl/pinctrl.h> struct device; @@ -20,6 +21,7 @@ struct seq_file; * struct gpio_chip - abstract a GPIO controller * @label: for diagnostics * @dev: optional device providing the GPIOs + * @cdev: class device used by sysfs interface (may be NULL) * @owner: helps prevent removal of modules exporting active GPIOs * @list: links gpio_chips together for traversal * @request: optional hook for chip-specific activation, such as @@ -41,8 +43,12 @@ struct seq_file; * @dbg_show: optional routine to show contents in debugfs; default code * will be used when this is omitted, but custom code can show extra * state (such as pullup/pulldown configuration). - * @base: identifies the first GPIO number handled by this chip; or, if - * negative during registration, requests dynamic ID allocation. + * @base: identifies the first GPIO number handled by this chip; + * or, if negative during registration, requests dynamic ID allocation. + * DEPRECATION: providing anything non-negative and nailing the base + * offset of GPIO chips is deprecated. Please pass -1 as base to + * let gpiolib select the chip base in all possible cases. We want to + * get rid of the static GPIO number space in the long run. * @ngpio: the number of GPIOs handled by this controller; the last GPIO * handled is (base + ngpio - 1). * @desc: array of ngpio descriptors. Private. @@ -57,9 +63,19 @@ struct seq_file; * implies that if the chip supports IRQs, these IRQs need to be threaded * as the chip access may sleep when e.g. reading out the IRQ status * registers. - * @exported: flags if the gpiochip is exported for use from sysfs. Private. * @irq_not_threaded: flag must be set if @can_sleep is set but the * IRQs don't need to be threaded + * @irqchip: GPIO IRQ chip impl, provided by GPIO driver + * @irqdomain: Interrupt translation domain; responsible for mapping + * between GPIO hwirq number and linux irq number + * @irq_base: first linux IRQ number assigned to GPIO IRQ chip (deprecated) + * @irq_handler: the irq handler to use (often a predefined irq core function) + * for GPIO IRQs, provided by GPIO driver + * @irq_default_type: default IRQ triggering type applied during GPIO driver + * initialization, provided by GPIO driver + * @irq_parent: GPIO IRQ chip parent/bank linux irq number, + * provided by GPIO driver + * @lock_key: per GPIO IRQ chip lockdep class * * A gpio_chip can help platforms abstract various sources of GPIOs so * they can all be accessed through a common programing interface. @@ -74,6 +90,7 @@ struct seq_file; struct gpio_chip { const char *label; struct device *dev; + struct device *cdev; struct module *owner; struct list_head list; @@ -109,7 +126,6 @@ struct gpio_chip { const char *const *names; bool can_sleep; bool irq_not_threaded; - bool exported; #ifdef CONFIG_GPIOLIB_IRQCHIP /* @@ -121,6 +137,8 @@ struct gpio_chip { unsigned int irq_base; irq_flow_handler_t irq_handler; unsigned int irq_default_type; + int irq_parent; + struct lock_class_key *lock_key; #endif #if defined(CONFIG_OF_GPIO) @@ -166,14 +184,31 @@ void gpiochip_set_chained_irqchip(struct gpio_chip *gpiochip, int parent_irq, irq_flow_handler_t parent_handler); -int gpiochip_irqchip_add(struct gpio_chip *gpiochip, - struct irq_chip *irqchip, - unsigned int first_irq, - irq_flow_handler_t handler, - unsigned int type); +int _gpiochip_irqchip_add(struct gpio_chip *gpiochip, + struct irq_chip *irqchip, + unsigned int first_irq, + irq_flow_handler_t handler, + unsigned int type, + struct lock_class_key *lock_key); + +#ifdef CONFIG_LOCKDEP +#define gpiochip_irqchip_add(...) \ +( \ + ({ \ + static struct lock_class_key _key; \ + _gpiochip_irqchip_add(__VA_ARGS__, &_key); \ + }) \ +) +#else +#define gpiochip_irqchip_add(...) \ + _gpiochip_irqchip_add(__VA_ARGS__, NULL) +#endif #endif /* CONFIG_GPIOLIB_IRQCHIP */ +int gpiochip_generic_request(struct gpio_chip *chip, unsigned offset); +void gpiochip_generic_free(struct gpio_chip *chip, unsigned offset); + #ifdef CONFIG_PINCTRL /** diff --git a/kernel/include/linux/gpio/machine.h b/kernel/include/linux/gpio/machine.h index e2706140e..c0d712d22 100644 --- a/kernel/include/linux/gpio/machine.h +++ b/kernel/include/linux/gpio/machine.h @@ -57,5 +57,6 @@ struct gpiod_lookup_table { } void gpiod_add_lookup_table(struct gpiod_lookup_table *table); +void gpiod_remove_lookup_table(struct gpiod_lookup_table *table); #endif /* __LINUX_GPIO_MACHINE_H */ diff --git a/kernel/include/linux/gsmmux.h b/kernel/include/linux/gsmmux.h deleted file mode 100644 index c25e9477f..000000000 --- a/kernel/include/linux/gsmmux.h +++ /dev/null @@ -1,36 +0,0 @@ -#ifndef _LINUX_GSMMUX_H -#define _LINUX_GSMMUX_H - -struct gsm_config -{ - unsigned int adaption; - unsigned int encapsulation; - unsigned int initiator; - unsigned int t1; - unsigned int t2; - unsigned int t3; - unsigned int n2; - unsigned int mru; - unsigned int mtu; - unsigned int k; - unsigned int i; - unsigned int unused[8]; /* Padding for expansion without - breaking stuff */ -}; - -#define GSMIOC_GETCONF _IOR('G', 0, struct gsm_config) -#define GSMIOC_SETCONF _IOW('G', 1, struct gsm_config) - -struct gsm_netconfig { - unsigned int adaption; /* Adaption to use in network mode */ - unsigned short protocol;/* Protocol to use - only ETH_P_IP supported */ - unsigned short unused2; - char if_name[IFNAMSIZ]; /* interface name format string */ - __u8 unused[28]; /* For future use */ -}; - -#define GSMIOC_ENABLE_NET _IOW('G', 2, struct gsm_netconfig) -#define GSMIOC_DISABLE_NET _IO('G', 3) - - -#endif diff --git a/kernel/include/linux/hardirq.h b/kernel/include/linux/hardirq.h index f4af03404..dfd59d6bc 100644 --- a/kernel/include/linux/hardirq.h +++ b/kernel/include/linux/hardirq.h @@ -1,7 +1,7 @@ #ifndef LINUX_HARDIRQ_H #define LINUX_HARDIRQ_H -#include <linux/preempt_mask.h> +#include <linux/preempt.h> #include <linux/lockdep.h> #include <linux/ftrace_irq.h> #include <linux/vtime.h> diff --git a/kernel/include/linux/hid.h b/kernel/include/linux/hid.h index 176b43670..251a1d382 100644 --- a/kernel/include/linux/hid.h +++ b/kernel/include/linux/hid.h @@ -698,8 +698,8 @@ struct hid_driver { int (*input_mapped)(struct hid_device *hdev, struct hid_input *hidinput, struct hid_field *field, struct hid_usage *usage, unsigned long **bit, int *max); - void (*input_configured)(struct hid_device *hdev, - struct hid_input *hidinput); + int (*input_configured)(struct hid_device *hdev, + struct hid_input *hidinput); void (*feature_mapping)(struct hid_device *hdev, struct hid_field *field, struct hid_usage *usage); @@ -815,6 +815,8 @@ void hid_disconnect(struct hid_device *hid); const struct hid_device_id *hid_match_id(struct hid_device *hdev, const struct hid_device_id *id); s32 hid_snto32(__u32 value, unsigned n); +__u32 hid_field_extract(const struct hid_device *hid, __u8 *report, + unsigned offset, unsigned n); /** * hid_device_io_start - enable HID input during probe, remove diff --git a/kernel/include/linux/highmem.h b/kernel/include/linux/highmem.h index 06bae5a67..a117a33ef 100644 --- a/kernel/include/linux/highmem.h +++ b/kernel/include/linux/highmem.h @@ -79,7 +79,6 @@ static inline void __kunmap_atomic(void *addr) } #define kmap_atomic_pfn(pfn) kmap_atomic(pfn_to_page(pfn)) -#define kmap_atomic_to_page(ptr) virt_to_page(ptr) #define kmap_flush_unused() do {} while(0) #endif diff --git a/kernel/include/linux/hrtimer.h b/kernel/include/linux/hrtimer.h index 64e1abb37..8fbcdfa5d 100644 --- a/kernel/include/linux/hrtimer.h +++ b/kernel/include/linux/hrtimer.h @@ -53,34 +53,25 @@ enum hrtimer_restart { * * 0x00 inactive * 0x01 enqueued into rbtree - * 0x02 callback function running - * 0x04 timer is migrated to another cpu * - * Special cases: - * 0x03 callback function running and enqueued - * (was requeued on another CPU) - * 0x05 timer was migrated on CPU hotunplug + * The callback state is not part of the timer->state because clearing it would + * mean touching the timer after the callback, this makes it impossible to free + * the timer from the callback function. * - * The "callback function running and enqueued" status is only possible on - * SMP. It happens for example when a posix timer expired and the callback + * Therefore we track the callback state in: + * + * timer->base->cpu_base->running == timer + * + * On SMP it is possible to have a "callback function running and enqueued" + * status. It happens for example when a posix timer expired and the callback * queued a signal. Between dropping the lock which protects the posix timer * and reacquiring the base lock of the hrtimer, another CPU can deliver the - * signal and rearm the timer. We have to preserve the callback running state, - * as otherwise the timer could be removed before the softirq code finishes the - * the handling of the timer. - * - * The HRTIMER_STATE_ENQUEUED bit is always or'ed to the current state - * to preserve the HRTIMER_STATE_CALLBACK in the above scenario. This - * also affects HRTIMER_STATE_MIGRATE where the preservation is not - * necessary. HRTIMER_STATE_MIGRATE is cleared after the timer is - * enqueued on the new cpu. + * signal and rearm the timer. * * All state transitions are protected by cpu_base->lock. */ #define HRTIMER_STATE_INACTIVE 0x00 #define HRTIMER_STATE_ENQUEUED 0x01 -#define HRTIMER_STATE_CALLBACK 0x02 -#define HRTIMER_STATE_MIGRATE 0x04 /** * struct hrtimer - the basic hrtimer structure @@ -96,7 +87,11 @@ enum hrtimer_restart { * @function: timer expiry callback function * @base: pointer to the timer base (per cpu and per clock) * @state: state information (See bit values above) - * @start_pid: timer statistics field to store the pid of the task which + * @cb_entry: list entry to defer timers from hardirq context + * @irqsafe: timer can run in hardirq context + * @praecox: timer expiry time if expired at the time of programming + * @is_rel: Set if the timer was armed relative + * @start_pid: timer statistics field to store the pid of the task which * started the timer * @start_site: timer statistics field to store the site where the timer * was started @@ -110,12 +105,13 @@ struct hrtimer { ktime_t _softexpires; enum hrtimer_restart (*function)(struct hrtimer *); struct hrtimer_clock_base *base; - unsigned long state; + u8 state; struct list_head cb_entry; int irqsafe; #ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST ktime_t praecox; #endif + u8 is_rel; #ifdef CONFIG_TIMER_STATS int start_pid; void *start_site; @@ -135,6 +131,8 @@ struct hrtimer_sleeper { struct task_struct *task; }; +# define HRTIMER_CLOCK_BASE_ALIGN 64 + /** * struct hrtimer_clock_base - the timer base for a specific clock * @cpu_base: per cpu clock base @@ -142,9 +140,8 @@ struct hrtimer_sleeper { * timer to a base on another cpu. * @clockid: clock id for per_cpu support * @active: red black tree root node for the active timers - * @resolution: the resolution of the clock, in nanoseconds + * @expired: list head for deferred timers. * @get_time: function to retrieve the current time of the clock - * @softirq_time: the time when running the hrtimer queue in the softirq * @offset: offset of this clock to the monotonic base */ struct hrtimer_clock_base { @@ -153,11 +150,9 @@ struct hrtimer_clock_base { clockid_t clockid; struct timerqueue_head active; struct list_head expired; - ktime_t resolution; ktime_t (*get_time)(void); - ktime_t softirq_time; ktime_t offset; -}; +} __attribute__((__aligned__(HRTIMER_CLOCK_BASE_ALIGN))); enum hrtimer_base_type { HRTIMER_BASE_MONOTONIC, @@ -171,11 +166,16 @@ enum hrtimer_base_type { * struct hrtimer_cpu_base - the per cpu clock bases * @lock: lock protecting the base and associated clock bases * and timers + * @seq: seqcount around __run_hrtimer + * @running: pointer to the currently running hrtimer * @cpu: cpu number * @active_bases: Bitfield to mark bases with active timers - * @clock_was_set: Indicates that clock was set from irq context. + * @clock_was_set_seq: Sequence counter of clock was set events + * @migration_enabled: The migration of hrtimers to other cpus is enabled + * @nohz_active: The nohz functionality is enabled * @expires_next: absolute time of the next event which was scheduled * via clock_set_next_event() + * @next_timer: Pointer to the first expiring timer * @in_hrtirq: hrtimer_interrupt() is currently executing * @hres_active: State of high resolution mode * @hang_detected: The last hrtimer interrupt detected a hang @@ -184,30 +184,42 @@ enum hrtimer_base_type { * @nr_hangs: Total number of hrtimer interrupt hangs * @max_hang_time: Maximum time spent in hrtimer_interrupt * @clock_base: array of clock bases for this cpu + * + * Note: next_timer is just an optimization for __remove_hrtimer(). + * Do not dereference the pointer because it is not reliable on + * cross cpu removals. */ struct hrtimer_cpu_base { raw_spinlock_t lock; + seqcount_t seq; + struct hrtimer *running; + struct hrtimer *running_soft; unsigned int cpu; unsigned int active_bases; - unsigned int clock_was_set; + unsigned int clock_was_set_seq; + bool migration_enabled; + bool nohz_active; #ifdef CONFIG_HIGH_RES_TIMERS + unsigned int in_hrtirq : 1, + hres_active : 1, + hang_detected : 1; ktime_t expires_next; - int in_hrtirq; - int hres_active; - int hang_detected; - unsigned long nr_events; - unsigned long nr_retries; - unsigned long nr_hangs; - ktime_t max_hang_time; + struct hrtimer *next_timer; + unsigned int nr_events; + unsigned int nr_retries; + unsigned int nr_hangs; + unsigned int max_hang_time; #endif #ifdef CONFIG_PREEMPT_RT_BASE wait_queue_head_t wait; #endif struct hrtimer_clock_base clock_base[HRTIMER_MAX_CLOCK_BASES]; -}; +} ____cacheline_aligned; static inline void hrtimer_set_expires(struct hrtimer *timer, ktime_t time) { + BUILD_BUG_ON(sizeof(struct hrtimer_clock_base) > HRTIMER_CLOCK_BASE_ALIGN); + timer->node.expires = time; timer->_softexpires = time; } @@ -271,19 +283,16 @@ static inline ktime_t hrtimer_expires_remaining(const struct hrtimer *timer) return ktime_sub(timer->node.expires, timer->base->get_time()); } -#ifdef CONFIG_HIGH_RES_TIMERS -struct clock_event_device; - -extern void hrtimer_interrupt(struct clock_event_device *dev); - -/* - * In high resolution mode the time reference must be read accurate - */ static inline ktime_t hrtimer_cb_get_time(struct hrtimer *timer) { return timer->base->get_time(); } +#ifdef CONFIG_HIGH_RES_TIMERS +struct clock_event_device; + +extern void hrtimer_interrupt(struct clock_event_device *dev); + static inline int hrtimer_is_hres_active(struct hrtimer *timer) { return timer->base->cpu_base->hres_active; @@ -304,21 +313,16 @@ extern void hrtimer_peek_ahead_timers(void); extern void clock_was_set_delayed(void); +extern unsigned int hrtimer_resolution; + #else # define MONOTONIC_RES_NSEC LOW_RES_NSEC # define KTIME_MONOTONIC_RES KTIME_LOW_RES -static inline void hrtimer_peek_ahead_timers(void) { } +#define hrtimer_resolution (unsigned int)LOW_RES_NSEC -/* - * In non high resolution mode the time reference is taken from - * the base softirq time variable. - */ -static inline ktime_t hrtimer_cb_get_time(struct hrtimer *timer) -{ - return timer->base->softirq_time; -} +static inline void hrtimer_peek_ahead_timers(void) { } static inline int hrtimer_is_hres_active(struct hrtimer *timer) { @@ -329,6 +333,27 @@ static inline void clock_was_set_delayed(void) { } #endif +static inline ktime_t +__hrtimer_expires_remaining_adjusted(const struct hrtimer *timer, ktime_t now) +{ + ktime_t rem = ktime_sub(timer->node.expires, now); + + /* + * Adjust relative timers for the extra we added in + * hrtimer_start_range_ns() to prevent short timeouts. + */ + if (IS_ENABLED(CONFIG_TIME_LOW_RES) && timer->is_rel) + rem.tv64 -= hrtimer_resolution; + return rem; +} + +static inline ktime_t +hrtimer_expires_remaining_adjusted(const struct hrtimer *timer) +{ + return __hrtimer_expires_remaining_adjusted(timer, + timer->base->get_time()); +} + extern void clock_was_set(void); #ifdef CONFIG_TIMERFD extern void timerfd_clock_was_set(void); @@ -362,32 +387,39 @@ static inline void destroy_hrtimer_on_stack(struct hrtimer *timer) { } #endif /* Basic timer operations: */ -extern int hrtimer_start(struct hrtimer *timer, ktime_t tim, - const enum hrtimer_mode mode); -extern int hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, +extern void hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, unsigned long range_ns, const enum hrtimer_mode mode); -extern int -__hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, - unsigned long delta_ns, - const enum hrtimer_mode mode, int wakeup); + +/** + * hrtimer_start - (re)start an hrtimer on the current CPU + * @timer: the timer to be added + * @tim: expiry time + * @mode: expiry mode: absolute (HRTIMER_MODE_ABS) or + * relative (HRTIMER_MODE_REL) + */ +static inline void hrtimer_start(struct hrtimer *timer, ktime_t tim, + const enum hrtimer_mode mode) +{ + hrtimer_start_range_ns(timer, tim, 0, mode); +} extern int hrtimer_cancel(struct hrtimer *timer); extern int hrtimer_try_to_cancel(struct hrtimer *timer); -static inline int hrtimer_start_expires(struct hrtimer *timer, - enum hrtimer_mode mode) +static inline void hrtimer_start_expires(struct hrtimer *timer, + enum hrtimer_mode mode) { unsigned long delta; ktime_t soft, hard; soft = hrtimer_get_softexpires(timer); hard = hrtimer_get_expires(timer); delta = ktime_to_ns(ktime_sub(hard, soft)); - return hrtimer_start_range_ns(timer, soft, delta, mode); + hrtimer_start_range_ns(timer, soft, delta, mode); } -static inline int hrtimer_restart(struct hrtimer *timer) +static inline void hrtimer_restart(struct hrtimer *timer) { - return hrtimer_start_expires(timer, HRTIMER_MODE_ABS); + hrtimer_start_expires(timer, HRTIMER_MODE_ABS); } /* Softirq preemption could deadlock timer removal */ @@ -398,21 +430,17 @@ static inline int hrtimer_restart(struct hrtimer *timer) #endif /* Query timers: */ -extern ktime_t hrtimer_get_remaining(const struct hrtimer *timer); -extern int hrtimer_get_res(const clockid_t which_clock, struct timespec *tp); - -extern ktime_t hrtimer_get_next_event(void); +extern ktime_t __hrtimer_get_remaining(const struct hrtimer *timer, bool adjust); -/* - * A timer is active, when it is enqueued into the rbtree or the - * callback function is running or it's in the state of being migrated - * to another cpu. - */ -static inline int hrtimer_active(const struct hrtimer *timer) +static inline ktime_t hrtimer_get_remaining(const struct hrtimer *timer) { - return timer->state != HRTIMER_STATE_INACTIVE; + return __hrtimer_get_remaining(timer, false); } +extern u64 hrtimer_get_next_event(void); + +extern bool hrtimer_active(const struct hrtimer *timer); + /* * Helper function to check, whether the timer is on one of the queues */ @@ -425,16 +453,31 @@ static inline int hrtimer_is_queued(struct hrtimer *timer) * Helper function to check, whether the timer is running the callback * function */ -static inline int hrtimer_callback_running(struct hrtimer *timer) +static inline int hrtimer_callback_running(const struct hrtimer *timer) { - return timer->state & HRTIMER_STATE_CALLBACK; + return timer->base->cpu_base->running == timer; } /* Forward a hrtimer so it expires after now: */ extern u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval); -/* Forward a hrtimer so it expires after the hrtimer's current now */ +/** + * hrtimer_forward_now - forward the timer expiry so it expires after now + * @timer: hrtimer to forward + * @interval: the interval to forward + * + * Forward the timer expiry so it will expire after the current time + * of the hrtimer clock base. Returns the number of overruns. + * + * Can be safely called from the callback function of @timer. If + * called from other contexts @timer must neither be enqueued nor + * running the callback and the caller needs to take care of + * serialization. + * + * Note: This only updates the timer expiry value and does not requeue + * the timer. + */ static inline u64 hrtimer_forward_now(struct hrtimer *timer, ktime_t interval) { @@ -459,7 +502,6 @@ extern int schedule_hrtimeout(ktime_t *expires, const enum hrtimer_mode mode); /* Soft interrupt function to run the hrtimer queues: */ extern void hrtimer_run_queues(void); -extern void hrtimer_run_pending(void); /* Bootup initialization: */ extern void __init hrtimers_init(void); diff --git a/kernel/include/linux/htirq.h b/kernel/include/linux/htirq.h index 70a1dbbf2..d4a527e58 100644 --- a/kernel/include/linux/htirq.h +++ b/kernel/include/linux/htirq.h @@ -1,24 +1,38 @@ #ifndef LINUX_HTIRQ_H #define LINUX_HTIRQ_H +struct pci_dev; +struct irq_data; + struct ht_irq_msg { u32 address_lo; /* low 32 bits of the ht irq message */ u32 address_hi; /* high 32 bits of the it irq message */ }; +typedef void (ht_irq_update_t)(struct pci_dev *dev, int irq, + struct ht_irq_msg *msg); + +struct ht_irq_cfg { + struct pci_dev *dev; + /* Update callback used to cope with buggy hardware */ + ht_irq_update_t *update; + unsigned pos; + unsigned idx; + struct ht_irq_msg msg; +}; + /* Helper functions.. */ void fetch_ht_irq_msg(unsigned int irq, struct ht_irq_msg *msg); void write_ht_irq_msg(unsigned int irq, struct ht_irq_msg *msg); -struct irq_data; void mask_ht_irq(struct irq_data *data); void unmask_ht_irq(struct irq_data *data); /* The arch hook for getting things started */ -int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev); +int arch_setup_ht_irq(int idx, int pos, struct pci_dev *dev, + ht_irq_update_t *update); +void arch_teardown_ht_irq(unsigned int irq); /* For drivers of buggy hardware */ -typedef void (ht_irq_update_t)(struct pci_dev *dev, int irq, - struct ht_irq_msg *msg); int __ht_create_irq(struct pci_dev *dev, int idx, ht_irq_update_t *update); #endif /* LINUX_HTIRQ_H */ diff --git a/kernel/include/linux/huge_mm.h b/kernel/include/linux/huge_mm.h index f10b20f05..ecb080d6f 100644 --- a/kernel/include/linux/huge_mm.h +++ b/kernel/include/linux/huge_mm.h @@ -33,6 +33,8 @@ extern int move_huge_pmd(struct vm_area_struct *vma, extern int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, pgprot_t newprot, int prot_numa); +int vmf_insert_pfn_pmd(struct vm_area_struct *, unsigned long addr, pmd_t *, + unsigned long pfn, bool write); enum transparent_hugepage_flag { TRANSPARENT_HUGEPAGE_FLAG, @@ -122,7 +124,7 @@ extern void split_huge_page_pmd_mm(struct mm_struct *mm, unsigned long address, #endif extern int hugepage_madvise(struct vm_area_struct *vma, unsigned long *vm_flags, int advice); -extern void __vma_adjust_trans_huge(struct vm_area_struct *vma, +extern void vma_adjust_trans_huge(struct vm_area_struct *vma, unsigned long start, unsigned long end, long adjust_next); @@ -138,15 +140,6 @@ static inline int pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma, else return 0; } -static inline void vma_adjust_trans_huge(struct vm_area_struct *vma, - unsigned long start, - unsigned long end, - long adjust_next) -{ - if (!vma->anon_vma || vma->vm_ops) - return; - __vma_adjust_trans_huge(vma, start, end, adjust_next); -} static inline int hpage_nr_pages(struct page *page) { if (unlikely(PageTransHuge(page))) @@ -164,6 +157,13 @@ static inline bool is_huge_zero_page(struct page *page) return ACCESS_ONCE(huge_zero_page) == page; } +static inline bool is_huge_zero_pmd(pmd_t pmd) +{ + return is_huge_zero_page(pmd_page(pmd)); +} + +struct page *get_huge_zero_page(void); + #else /* CONFIG_TRANSPARENT_HUGEPAGE */ #define HPAGE_PMD_SHIFT ({ BUILD_BUG(); 0; }) #define HPAGE_PMD_MASK ({ BUILD_BUG(); 0; }) diff --git a/kernel/include/linux/hugetlb.h b/kernel/include/linux/hugetlb.h index 205026175..685c262e0 100644 --- a/kernel/include/linux/hugetlb.h +++ b/kernel/include/linux/hugetlb.h @@ -35,6 +35,9 @@ struct resv_map { struct kref refs; spinlock_t lock; struct list_head regions; + long adds_in_progress; + struct list_head region_cache; + long region_cache_count; }; extern struct resv_map *resv_map_alloc(void); void resv_map_release(struct kref *ref); @@ -80,11 +83,18 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, int hugetlb_reserve_pages(struct inode *inode, long from, long to, struct vm_area_struct *vma, vm_flags_t vm_flags); -void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed); +long hugetlb_unreserve_pages(struct inode *inode, long start, long end, + long freed); int dequeue_hwpoisoned_huge_page(struct page *page); bool isolate_huge_page(struct page *page, struct list_head *list); void putback_active_hugepage(struct page *page); void free_huge_page(struct page *page); +void hugetlb_fix_reserve_counts(struct inode *inode, bool restore_reserve); +extern struct mutex *hugetlb_fault_mutex_table; +u32 hugetlb_fault_mutex_hash(struct hstate *h, struct mm_struct *mm, + struct vm_area_struct *vma, + struct address_space *mapping, + pgoff_t idx, unsigned long address); #ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud); @@ -320,9 +330,13 @@ struct huge_bootmem_page { #endif }; +struct page *alloc_huge_page(struct vm_area_struct *vma, + unsigned long addr, int avoid_reserve); struct page *alloc_huge_page_node(struct hstate *h, int nid); struct page *alloc_huge_page_noerr(struct vm_area_struct *vma, unsigned long addr, int avoid_reserve); +int huge_add_to_page_cache(struct page *page, struct address_space *mapping, + pgoff_t idx); /* arch callback */ int __init alloc_bootmem_huge_page(struct hstate *h); @@ -460,18 +474,29 @@ static inline spinlock_t *huge_pte_lockptr(struct hstate *h, return &mm->page_table_lock; } -static inline bool hugepages_supported(void) +#ifndef hugepages_supported +/* + * Some platform decide whether they support huge pages at boot + * time. Some of them, such as powerpc, set HPAGE_SHIFT to 0 + * when there is no such support + */ +#define hugepages_supported() (HPAGE_SHIFT != 0) +#endif + +void hugetlb_report_usage(struct seq_file *m, struct mm_struct *mm); + +static inline void hugetlb_count_add(long l, struct mm_struct *mm) { - /* - * Some platform decide whether they support huge pages at boot - * time. On these, such as powerpc, HPAGE_SHIFT is set to 0 when - * there is no such support - */ - return HPAGE_SHIFT != 0; + atomic_long_add(l, &mm->hugetlb_usage); } +static inline void hugetlb_count_sub(long l, struct mm_struct *mm) +{ + atomic_long_sub(l, &mm->hugetlb_usage); +} #else /* CONFIG_HUGETLB_PAGE */ struct hstate {}; +#define alloc_huge_page(v, a, r) NULL #define alloc_huge_page_node(h, nid) NULL #define alloc_huge_page_noerr(v, a, r) NULL #define alloc_bootmem_huge_page(h) NULL @@ -505,6 +530,14 @@ static inline spinlock_t *huge_pte_lockptr(struct hstate *h, { return &mm->page_table_lock; } + +static inline void hugetlb_report_usage(struct seq_file *f, struct mm_struct *m) +{ +} + +static inline void hugetlb_count_sub(long l, struct mm_struct *mm) +{ +} #endif /* CONFIG_HUGETLB_PAGE */ static inline spinlock_t *huge_pte_lock(struct hstate *h, diff --git a/kernel/include/linux/hugetlb_cgroup.h b/kernel/include/linux/hugetlb_cgroup.h index bcc853ecc..24154c26d 100644 --- a/kernel/include/linux/hugetlb_cgroup.h +++ b/kernel/include/linux/hugetlb_cgroup.h @@ -32,7 +32,7 @@ static inline struct hugetlb_cgroup *hugetlb_cgroup_from_page(struct page *page) if (compound_order(page) < HUGETLB_CGROUP_MIN_ORDER) return NULL; - return (struct hugetlb_cgroup *)page[2].lru.next; + return (struct hugetlb_cgroup *)page[2].private; } static inline @@ -42,15 +42,13 @@ int set_hugetlb_cgroup(struct page *page, struct hugetlb_cgroup *h_cg) if (compound_order(page) < HUGETLB_CGROUP_MIN_ORDER) return -1; - page[2].lru.next = (void *)h_cg; + page[2].private = (unsigned long)h_cg; return 0; } static inline bool hugetlb_cgroup_disabled(void) { - if (hugetlb_cgrp_subsys.disabled) - return true; - return false; + return !cgroup_subsys_enabled(hugetlb_cgrp_subsys); } extern int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages, diff --git a/kernel/include/linux/hwspinlock.h b/kernel/include/linux/hwspinlock.h index 3343298e4..859d673d9 100644 --- a/kernel/include/linux/hwspinlock.h +++ b/kernel/include/linux/hwspinlock.h @@ -26,6 +26,7 @@ #define HWLOCK_IRQ 0x02 /* Disable interrupts, don't save state */ struct device; +struct device_node; struct hwspinlock; struct hwspinlock_device; struct hwspinlock_ops; @@ -66,6 +67,7 @@ int hwspin_lock_unregister(struct hwspinlock_device *bank); struct hwspinlock *hwspin_lock_request(void); struct hwspinlock *hwspin_lock_request_specific(unsigned int id); int hwspin_lock_free(struct hwspinlock *hwlock); +int of_hwspin_lock_get_id(struct device_node *np, int index); int hwspin_lock_get_id(struct hwspinlock *hwlock); int __hwspin_lock_timeout(struct hwspinlock *, unsigned int, int, unsigned long *); @@ -120,6 +122,11 @@ void __hwspin_unlock(struct hwspinlock *hwlock, int mode, unsigned long *flags) { } +static inline int of_hwspin_lock_get_id(struct device_node *np, int index) +{ + return 0; +} + static inline int hwspin_lock_get_id(struct hwspinlock *hwlock) { return 0; diff --git a/kernel/include/linux/hyperv.h b/kernel/include/linux/hyperv.h index 902c37aef..ae6a711dc 100644 --- a/kernel/include/linux/hyperv.h +++ b/kernel/include/linux/hyperv.h @@ -26,6 +26,7 @@ #define _HYPERV_H #include <uapi/linux/hyperv.h> +#include <uapi/asm/hyperv.h> #include <linux/types.h> #include <linux/scatterlist.h> @@ -160,16 +161,18 @@ hv_get_ringbuffer_availbytes(struct hv_ring_buffer_info *rbi, * 1 . 1 (Windows 7) * 2 . 4 (Windows 8) * 3 . 0 (Windows 8 R2) + * 4 . 0 (Windows 10) */ #define VERSION_WS2008 ((0 << 16) | (13)) #define VERSION_WIN7 ((1 << 16) | (1)) #define VERSION_WIN8 ((2 << 16) | (4)) #define VERSION_WIN8_1 ((3 << 16) | (0)) +#define VERSION_WIN10 ((4 << 16) | (0)) #define VERSION_INVAL -1 -#define VERSION_CURRENT VERSION_WIN8_1 +#define VERSION_CURRENT VERSION_WIN10 /* Make maximum size of pipe payload of 16K */ #define MAX_PIPE_DATA_PAYLOAD (sizeof(u8) * 16384) @@ -389,10 +392,7 @@ enum vmbus_channel_message_type { CHANNELMSG_INITIATE_CONTACT = 14, CHANNELMSG_VERSION_RESPONSE = 15, CHANNELMSG_UNLOAD = 16, -#ifdef VMBUS_FEATURE_PARENT_OR_PEER_MEMORY_MAPPED_INTO_A_CHILD - CHANNELMSG_VIEWRANGE_ADD = 17, - CHANNELMSG_VIEWRANGE_REMOVE = 18, -#endif + CHANNELMSG_UNLOAD_RESPONSE = 17, CHANNELMSG_COUNT }; @@ -549,21 +549,6 @@ struct vmbus_channel_gpadl_torndown { u32 gpadl; } __packed; -#ifdef VMBUS_FEATURE_PARENT_OR_PEER_MEMORY_MAPPED_INTO_A_CHILD -struct vmbus_channel_view_range_add { - struct vmbus_channel_message_header header; - PHYSICAL_ADDRESS viewrange_base; - u64 viewrange_length; - u32 child_relid; -} __packed; - -struct vmbus_channel_view_range_remove { - struct vmbus_channel_message_header header; - PHYSICAL_ADDRESS viewrange_base; - u32 child_relid; -} __packed; -#endif - struct vmbus_channel_relid_released { struct vmbus_channel_message_header header; u32 child_relid; @@ -645,6 +630,11 @@ struct hv_input_signal_event_buffer { struct hv_input_signal_event event; }; +enum hv_signal_policy { + HV_SIGNAL_POLICY_DEFAULT = 0, + HV_SIGNAL_POLICY_EXPLICIT, +}; + struct vmbus_channel { /* Unique channel id */ int id; @@ -713,6 +703,11 @@ struct vmbus_channel { /* The corresponding CPUID in the guest */ u32 target_cpu; /* + * State to manage the CPU affiliation of channels. + */ + struct cpumask alloced_cpus_in_node; + int numa_node; + /* * Support for sub-channels. For high performance devices, * it will be useful to have multiple sub-channels to support * a scalable communication infrastructure with the host. @@ -745,6 +740,15 @@ struct vmbus_channel { */ struct list_head sc_list; /* + * Current number of sub-channels. + */ + int num_sc; + /* + * Number of a sub-channel (position within sc_list) which is supposed + * to be used as the next outgoing channel. + */ + int next_oc; + /* * The primary channel this sub-channel belongs to. * This will be NULL for the primary channel. */ @@ -758,11 +762,21 @@ struct vmbus_channel { * link up channels based on their CPU affinity. */ struct list_head percpu_list; - - int num_sc; - int next_oc; + /* + * Host signaling policy: The default policy will be + * based on the ring buffer state. We will also support + * a policy where the client driver can have explicit + * signaling control. + */ + enum hv_signal_policy signal_policy; }; +static inline void set_channel_signal_state(struct vmbus_channel *c, + enum hv_signal_policy policy) +{ + c->signal_policy = policy; +} + static inline void set_channel_read_state(struct vmbus_channel *c, bool state) { c->batched_reading = state; @@ -982,6 +996,11 @@ int __must_check __vmbus_driver_register(struct hv_driver *hv_driver, const char *mod_name); void vmbus_driver_unregister(struct hv_driver *hv_driver); +int vmbus_allocate_mmio(struct resource **new, struct hv_device *device_obj, + resource_size_t min, resource_size_t max, + resource_size_t size, resource_size_t align, + bool fb_overlap_ok); + /** * VMBUS_DEVICE - macro used to describe a specific hyperv vmbus device * @@ -1236,17 +1255,8 @@ extern bool vmbus_prep_negotiate_resp(struct icmsg_hdr *, struct icmsg_negotiate *, u8 *, int, int); -int hv_kvp_init(struct hv_util_service *); -void hv_kvp_deinit(void); -void hv_kvp_onchannelcallback(void *); - -int hv_vss_init(struct hv_util_service *); -void hv_vss_deinit(void); -void hv_vss_onchannelcallback(void *); void hv_process_channel_removal(struct vmbus_channel *channel, u32 relid); -extern struct resource hyperv_mmio; - /* * Negotiated version with the Host. */ diff --git a/kernel/include/linux/i2c-ocores.h b/kernel/include/linux/i2c-ocores.h index 1c06b5c7c..01edd96fe 100644 --- a/kernel/include/linux/i2c-ocores.h +++ b/kernel/include/linux/i2c-ocores.h @@ -15,6 +15,7 @@ struct ocores_i2c_platform_data { u32 reg_shift; /* register offset shift value */ u32 reg_io_width; /* register io read/write width */ u32 clock_khz; /* input clock in kHz */ + bool big_endian; /* registers are big endian */ u8 num_devices; /* number of devices in the devices list */ struct i2c_board_info const *devices; /* devices connected to the bus */ }; diff --git a/kernel/include/linux/i2c.h b/kernel/include/linux/i2c.h index e83a738a3..768063baa 100644 --- a/kernel/include/linux/i2c.h +++ b/kernel/include/linux/i2c.h @@ -121,6 +121,9 @@ extern s32 i2c_smbus_read_i2c_block_data(const struct i2c_client *client, extern s32 i2c_smbus_write_i2c_block_data(const struct i2c_client *client, u8 command, u8 length, const u8 *values); +extern s32 +i2c_smbus_read_i2c_block_data_or_emulated(const struct i2c_client *client, + u8 command, u8 length, u8 *values); #endif /* I2C */ /** @@ -550,11 +553,12 @@ void i2c_lock_adapter(struct i2c_adapter *); void i2c_unlock_adapter(struct i2c_adapter *); /*flags for the client struct: */ -#define I2C_CLIENT_PEC 0x04 /* Use Packet Error Checking */ -#define I2C_CLIENT_TEN 0x10 /* we have a ten bit chip address */ +#define I2C_CLIENT_PEC 0x04 /* Use Packet Error Checking */ +#define I2C_CLIENT_TEN 0x10 /* we have a ten bit chip address */ /* Must equal I2C_M_TEN below */ -#define I2C_CLIENT_WAKE 0x80 /* for board_info; true iff can wake */ -#define I2C_CLIENT_SCCB 0x9000 /* Use Omnivision SCCB protocol */ +#define I2C_CLIENT_SLAVE 0x20 /* we are the slave */ +#define I2C_CLIENT_WAKE 0x80 /* for board_info; true iff can wake */ +#define I2C_CLIENT_SCCB 0x9000 /* Use Omnivision SCCB protocol */ /* Must match I2C_M_STOP|IGNORE_NAK */ /* i2c adapter classes (bitmask) */ @@ -638,6 +642,8 @@ extern struct i2c_client *of_find_i2c_device_by_node(struct device_node *node); /* must call put_device() when done with returned i2c_adapter device */ extern struct i2c_adapter *of_find_i2c_adapter_by_node(struct device_node *node); +/* must call i2c_put_adapter() when done with returned i2c_adapter device */ +struct i2c_adapter *of_get_i2c_adapter_by_node(struct device_node *node); #else static inline struct i2c_client *of_find_i2c_device_by_node(struct device_node *node) @@ -649,6 +655,11 @@ static inline struct i2c_adapter *of_find_i2c_adapter_by_node(struct device_node { return NULL; } + +static inline struct i2c_adapter *of_get_i2c_adapter_by_node(struct device_node *node) +{ + return NULL; +} #endif /* CONFIG_OF */ #endif /* _LINUX_I2C_H */ diff --git a/kernel/include/linux/i2c/i2c-rcar.h b/kernel/include/linux/i2c/i2c-rcar.h deleted file mode 100644 index 496f5c2b2..000000000 --- a/kernel/include/linux/i2c/i2c-rcar.h +++ /dev/null @@ -1,10 +0,0 @@ -#ifndef __I2C_R_CAR_H__ -#define __I2C_R_CAR_H__ - -#include <linux/platform_device.h> - -struct i2c_rcar_platform_data { - u32 bus_speed; -}; - -#endif /* __I2C_R_CAR_H__ */ diff --git a/kernel/include/linux/i2c/twl.h b/kernel/include/linux/i2c/twl.h index 0bc03f100..9ad7828d9 100644 --- a/kernel/include/linux/i2c/twl.h +++ b/kernel/include/linux/i2c/twl.h @@ -675,6 +675,7 @@ struct twl4030_power_data { struct twl4030_resconfig *board_config; #define TWL4030_RESCONFIG_UNDEF ((u8)-1) bool use_poweroff; /* Board is wired for TWL poweroff */ + bool ac_charger_quirk; /* Disable AC charger on board */ }; extern int twl4030_remove_script(u8 flags); diff --git a/kernel/include/linux/ide.h b/kernel/include/linux/ide.h index 93b5ca754..a633898f3 100644 --- a/kernel/include/linux/ide.h +++ b/kernel/include/linux/ide.h @@ -39,6 +39,19 @@ struct device; +/* IDE-specific values for req->cmd_type */ +enum ata_cmd_type_bits { + REQ_TYPE_ATA_TASKFILE = REQ_TYPE_DRV_PRIV + 1, + REQ_TYPE_ATA_PC, + REQ_TYPE_ATA_SENSE, /* sense request */ + REQ_TYPE_ATA_PM_SUSPEND,/* suspend request */ + REQ_TYPE_ATA_PM_RESUME, /* resume request */ +}; + +#define ata_pm_request(rq) \ + ((rq)->cmd_type == REQ_TYPE_ATA_PM_SUSPEND || \ + (rq)->cmd_type == REQ_TYPE_ATA_PM_RESUME) + /* Error codes returned in rq->errors to the higher part of the driver. */ enum { IDE_DRV_ERROR_GENERAL = 101, @@ -1314,6 +1327,19 @@ struct ide_port_info { u8 udma_mask; }; +/* + * State information carried for REQ_TYPE_ATA_PM_SUSPEND and REQ_TYPE_ATA_PM_RESUME + * requests. + */ +struct ide_pm_state { + /* PM state machine step value, currently driver specific */ + int pm_step; + /* requested PM state value (S1, S2, S3, S4, ...) */ + u32 pm_state; + void* data; /* for driver use */ +}; + + int ide_pci_init_one(struct pci_dev *, const struct ide_port_info *, void *); int ide_pci_init_two(struct pci_dev *, struct pci_dev *, const struct ide_port_info *, void *); @@ -1551,4 +1577,5 @@ static inline void ide_set_drivedata(ide_drive_t *drive, void *data) #define ide_host_for_each_port(i, port, host) \ for ((i) = 0; ((port) = (host)->ports[i]) || (i) < MAX_HOST_PORTS; (i)++) + #endif /* _IDE_H */ diff --git a/kernel/include/linux/ieee80211.h b/kernel/include/linux/ieee80211.h index b9c7897dc..452c0b0d2 100644 --- a/kernel/include/linux/ieee80211.h +++ b/kernel/include/linux/ieee80211.h @@ -121,7 +121,7 @@ #define IEEE80211_MAX_SN IEEE80211_SN_MASK #define IEEE80211_SN_MODULO (IEEE80211_MAX_SN + 1) -static inline int ieee80211_sn_less(u16 sn1, u16 sn2) +static inline bool ieee80211_sn_less(u16 sn1, u16 sn2) { return ((sn1 - sn2) & IEEE80211_SN_MASK) > (IEEE80211_SN_MODULO >> 1); } @@ -250,7 +250,7 @@ struct ieee80211_qos_hdr { * ieee80211_has_tods - check if IEEE80211_FCTL_TODS is set * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_has_tods(__le16 fc) +static inline bool ieee80211_has_tods(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_TODS)) != 0; } @@ -259,7 +259,7 @@ static inline int ieee80211_has_tods(__le16 fc) * ieee80211_has_fromds - check if IEEE80211_FCTL_FROMDS is set * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_has_fromds(__le16 fc) +static inline bool ieee80211_has_fromds(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FROMDS)) != 0; } @@ -268,7 +268,7 @@ static inline int ieee80211_has_fromds(__le16 fc) * ieee80211_has_a4 - check if IEEE80211_FCTL_TODS and IEEE80211_FCTL_FROMDS are set * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_has_a4(__le16 fc) +static inline bool ieee80211_has_a4(__le16 fc) { __le16 tmp = cpu_to_le16(IEEE80211_FCTL_TODS | IEEE80211_FCTL_FROMDS); return (fc & tmp) == tmp; @@ -278,7 +278,7 @@ static inline int ieee80211_has_a4(__le16 fc) * ieee80211_has_morefrags - check if IEEE80211_FCTL_MOREFRAGS is set * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_has_morefrags(__le16 fc) +static inline bool ieee80211_has_morefrags(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_MOREFRAGS)) != 0; } @@ -287,7 +287,7 @@ static inline int ieee80211_has_morefrags(__le16 fc) * ieee80211_has_retry - check if IEEE80211_FCTL_RETRY is set * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_has_retry(__le16 fc) +static inline bool ieee80211_has_retry(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_RETRY)) != 0; } @@ -296,7 +296,7 @@ static inline int ieee80211_has_retry(__le16 fc) * ieee80211_has_pm - check if IEEE80211_FCTL_PM is set * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_has_pm(__le16 fc) +static inline bool ieee80211_has_pm(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_PM)) != 0; } @@ -305,7 +305,7 @@ static inline int ieee80211_has_pm(__le16 fc) * ieee80211_has_moredata - check if IEEE80211_FCTL_MOREDATA is set * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_has_moredata(__le16 fc) +static inline bool ieee80211_has_moredata(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_MOREDATA)) != 0; } @@ -314,7 +314,7 @@ static inline int ieee80211_has_moredata(__le16 fc) * ieee80211_has_protected - check if IEEE80211_FCTL_PROTECTED is set * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_has_protected(__le16 fc) +static inline bool ieee80211_has_protected(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_PROTECTED)) != 0; } @@ -323,7 +323,7 @@ static inline int ieee80211_has_protected(__le16 fc) * ieee80211_has_order - check if IEEE80211_FCTL_ORDER is set * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_has_order(__le16 fc) +static inline bool ieee80211_has_order(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_ORDER)) != 0; } @@ -332,7 +332,7 @@ static inline int ieee80211_has_order(__le16 fc) * ieee80211_is_mgmt - check if type is IEEE80211_FTYPE_MGMT * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_mgmt(__le16 fc) +static inline bool ieee80211_is_mgmt(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE)) == cpu_to_le16(IEEE80211_FTYPE_MGMT); @@ -342,7 +342,7 @@ static inline int ieee80211_is_mgmt(__le16 fc) * ieee80211_is_ctl - check if type is IEEE80211_FTYPE_CTL * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_ctl(__le16 fc) +static inline bool ieee80211_is_ctl(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE)) == cpu_to_le16(IEEE80211_FTYPE_CTL); @@ -352,7 +352,7 @@ static inline int ieee80211_is_ctl(__le16 fc) * ieee80211_is_data - check if type is IEEE80211_FTYPE_DATA * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_data(__le16 fc) +static inline bool ieee80211_is_data(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE)) == cpu_to_le16(IEEE80211_FTYPE_DATA); @@ -362,7 +362,7 @@ static inline int ieee80211_is_data(__le16 fc) * ieee80211_is_data_qos - check if type is IEEE80211_FTYPE_DATA and IEEE80211_STYPE_QOS_DATA is set * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_data_qos(__le16 fc) +static inline bool ieee80211_is_data_qos(__le16 fc) { /* * mask with QOS_DATA rather than IEEE80211_FCTL_STYPE as we just need @@ -376,7 +376,7 @@ static inline int ieee80211_is_data_qos(__le16 fc) * ieee80211_is_data_present - check if type is IEEE80211_FTYPE_DATA and has data * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_data_present(__le16 fc) +static inline bool ieee80211_is_data_present(__le16 fc) { /* * mask with 0x40 and test that that bit is clear to only return true @@ -390,7 +390,7 @@ static inline int ieee80211_is_data_present(__le16 fc) * ieee80211_is_assoc_req - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_ASSOC_REQ * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_assoc_req(__le16 fc) +static inline bool ieee80211_is_assoc_req(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_ASSOC_REQ); @@ -400,7 +400,7 @@ static inline int ieee80211_is_assoc_req(__le16 fc) * ieee80211_is_assoc_resp - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_ASSOC_RESP * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_assoc_resp(__le16 fc) +static inline bool ieee80211_is_assoc_resp(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_ASSOC_RESP); @@ -410,7 +410,7 @@ static inline int ieee80211_is_assoc_resp(__le16 fc) * ieee80211_is_reassoc_req - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_REASSOC_REQ * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_reassoc_req(__le16 fc) +static inline bool ieee80211_is_reassoc_req(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_REASSOC_REQ); @@ -420,7 +420,7 @@ static inline int ieee80211_is_reassoc_req(__le16 fc) * ieee80211_is_reassoc_resp - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_REASSOC_RESP * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_reassoc_resp(__le16 fc) +static inline bool ieee80211_is_reassoc_resp(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_REASSOC_RESP); @@ -430,7 +430,7 @@ static inline int ieee80211_is_reassoc_resp(__le16 fc) * ieee80211_is_probe_req - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_PROBE_REQ * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_probe_req(__le16 fc) +static inline bool ieee80211_is_probe_req(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_PROBE_REQ); @@ -440,7 +440,7 @@ static inline int ieee80211_is_probe_req(__le16 fc) * ieee80211_is_probe_resp - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_PROBE_RESP * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_probe_resp(__le16 fc) +static inline bool ieee80211_is_probe_resp(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_PROBE_RESP); @@ -450,7 +450,7 @@ static inline int ieee80211_is_probe_resp(__le16 fc) * ieee80211_is_beacon - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_BEACON * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_beacon(__le16 fc) +static inline bool ieee80211_is_beacon(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_BEACON); @@ -460,7 +460,7 @@ static inline int ieee80211_is_beacon(__le16 fc) * ieee80211_is_atim - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_ATIM * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_atim(__le16 fc) +static inline bool ieee80211_is_atim(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_ATIM); @@ -470,7 +470,7 @@ static inline int ieee80211_is_atim(__le16 fc) * ieee80211_is_disassoc - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_DISASSOC * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_disassoc(__le16 fc) +static inline bool ieee80211_is_disassoc(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_DISASSOC); @@ -480,7 +480,7 @@ static inline int ieee80211_is_disassoc(__le16 fc) * ieee80211_is_auth - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_AUTH * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_auth(__le16 fc) +static inline bool ieee80211_is_auth(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_AUTH); @@ -490,7 +490,7 @@ static inline int ieee80211_is_auth(__le16 fc) * ieee80211_is_deauth - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_DEAUTH * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_deauth(__le16 fc) +static inline bool ieee80211_is_deauth(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_DEAUTH); @@ -500,7 +500,7 @@ static inline int ieee80211_is_deauth(__le16 fc) * ieee80211_is_action - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_ACTION * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_action(__le16 fc) +static inline bool ieee80211_is_action(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_ACTION); @@ -510,7 +510,7 @@ static inline int ieee80211_is_action(__le16 fc) * ieee80211_is_back_req - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_BACK_REQ * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_back_req(__le16 fc) +static inline bool ieee80211_is_back_req(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_CTL | IEEE80211_STYPE_BACK_REQ); @@ -520,7 +520,7 @@ static inline int ieee80211_is_back_req(__le16 fc) * ieee80211_is_back - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_BACK * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_back(__le16 fc) +static inline bool ieee80211_is_back(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_CTL | IEEE80211_STYPE_BACK); @@ -530,7 +530,7 @@ static inline int ieee80211_is_back(__le16 fc) * ieee80211_is_pspoll - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_PSPOLL * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_pspoll(__le16 fc) +static inline bool ieee80211_is_pspoll(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_CTL | IEEE80211_STYPE_PSPOLL); @@ -540,7 +540,7 @@ static inline int ieee80211_is_pspoll(__le16 fc) * ieee80211_is_rts - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_RTS * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_rts(__le16 fc) +static inline bool ieee80211_is_rts(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_CTL | IEEE80211_STYPE_RTS); @@ -550,7 +550,7 @@ static inline int ieee80211_is_rts(__le16 fc) * ieee80211_is_cts - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_CTS * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_cts(__le16 fc) +static inline bool ieee80211_is_cts(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_CTL | IEEE80211_STYPE_CTS); @@ -560,7 +560,7 @@ static inline int ieee80211_is_cts(__le16 fc) * ieee80211_is_ack - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_ACK * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_ack(__le16 fc) +static inline bool ieee80211_is_ack(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_CTL | IEEE80211_STYPE_ACK); @@ -570,7 +570,7 @@ static inline int ieee80211_is_ack(__le16 fc) * ieee80211_is_cfend - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_CFEND * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_cfend(__le16 fc) +static inline bool ieee80211_is_cfend(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_CTL | IEEE80211_STYPE_CFEND); @@ -580,7 +580,7 @@ static inline int ieee80211_is_cfend(__le16 fc) * ieee80211_is_cfendack - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_CFENDACK * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_cfendack(__le16 fc) +static inline bool ieee80211_is_cfendack(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_CTL | IEEE80211_STYPE_CFENDACK); @@ -590,7 +590,7 @@ static inline int ieee80211_is_cfendack(__le16 fc) * ieee80211_is_nullfunc - check if frame is a regular (non-QoS) nullfunc frame * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_nullfunc(__le16 fc) +static inline bool ieee80211_is_nullfunc(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_DATA | IEEE80211_STYPE_NULLFUNC); @@ -600,7 +600,7 @@ static inline int ieee80211_is_nullfunc(__le16 fc) * ieee80211_is_qos_nullfunc - check if frame is a QoS nullfunc frame * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_qos_nullfunc(__le16 fc) +static inline bool ieee80211_is_qos_nullfunc(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_DATA | IEEE80211_STYPE_QOS_NULLFUNC); @@ -624,7 +624,7 @@ static inline bool ieee80211_is_bufferable_mmpdu(__le16 fc) * ieee80211_is_first_frag - check if IEEE80211_SCTL_FRAG is not set * @seq_ctrl: frame sequence control bytes in little-endian byteorder */ -static inline int ieee80211_is_first_frag(__le16 seq_ctrl) +static inline bool ieee80211_is_first_frag(__le16 seq_ctrl) { return (seq_ctrl & cpu_to_le16(IEEE80211_SCTL_FRAG)) == 0; } @@ -1379,6 +1379,7 @@ struct ieee80211_ht_operation { /* block-ack parameters */ +#define IEEE80211_ADDBA_PARAM_AMSDU_MASK 0x0001 #define IEEE80211_ADDBA_PARAM_POLICY_MASK 0x0002 #define IEEE80211_ADDBA_PARAM_TID_MASK 0x003C #define IEEE80211_ADDBA_PARAM_BUF_SIZE_MASK 0xFFC0 @@ -1745,8 +1746,7 @@ enum ieee80211_eid { WLAN_EID_TIM = 5, WLAN_EID_IBSS_PARAMS = 6, WLAN_EID_COUNTRY = 7, - WLAN_EID_HP_PARAMS = 8, - WLAN_EID_HP_TABLE = 9, + /* 8, 9 reserved */ WLAN_EID_REQUEST = 10, WLAN_EID_QBSS_LOAD = 11, WLAN_EID_EDCA_PARAM_SET = 12, @@ -1932,6 +1932,8 @@ enum ieee80211_category { WLAN_CATEGORY_HT = 7, WLAN_CATEGORY_SA_QUERY = 8, WLAN_CATEGORY_PROTECTED_DUAL_OF_ACTION = 9, + WLAN_CATEGORY_WNM = 10, + WLAN_CATEGORY_WNM_UNPROTECTED = 11, WLAN_CATEGORY_TDLS = 12, WLAN_CATEGORY_MESH_ACTION = 13, WLAN_CATEGORY_MULTIHOP_ACTION = 14, @@ -2074,8 +2076,8 @@ enum ieee80211_tdls_actioncode { #define WLAN_EXT_CAPA5_TDLS_PROHIBITED BIT(6) #define WLAN_EXT_CAPA5_TDLS_CH_SW_PROHIBITED BIT(7) +#define WLAN_EXT_CAPA8_TDLS_WIDE_BW_ENABLED BIT(5) #define WLAN_EXT_CAPA8_OPMODE_NOTIF BIT(6) -#define WLAN_EXT_CAPA8_TDLS_WIDE_BW_ENABLED BIT(7) /* TDLS specific payload type in the LLC/SNAP header */ #define WLAN_TDLS_SNAP_RFTYPE 0x2 @@ -2396,7 +2398,10 @@ static inline bool _ieee80211_is_robust_mgmt_frame(struct ieee80211_hdr *hdr) category = ((u8 *) hdr) + 24; return *category != WLAN_CATEGORY_PUBLIC && *category != WLAN_CATEGORY_HT && + *category != WLAN_CATEGORY_WNM_UNPROTECTED && *category != WLAN_CATEGORY_SELF_PROTECTED && + *category != WLAN_CATEGORY_UNPROT_DMG && + *category != WLAN_CATEGORY_VHT && *category != WLAN_CATEGORY_VENDOR_SPECIFIC; } diff --git a/kernel/include/linux/ieee802154.h b/kernel/include/linux/ieee802154.h index 8872ca103..d3e415674 100644 --- a/kernel/include/linux/ieee802154.h +++ b/kernel/include/linux/ieee802154.h @@ -25,12 +25,22 @@ #include <linux/types.h> #include <linux/random.h> -#include <asm/byteorder.h> #define IEEE802154_MTU 127 #define IEEE802154_ACK_PSDU_LEN 5 #define IEEE802154_MIN_PSDU_LEN 9 #define IEEE802154_FCS_LEN 2 +#define IEEE802154_MAX_AUTH_TAG_LEN 16 + +/* General MAC frame format: + * 2 bytes: Frame Control + * 1 byte: Sequence Number + * 20 bytes: Addressing fields + * 14 bytes: Auxiliary Security Header + */ +#define IEEE802154_MAX_HEADER_LEN (2 + 1 + 20 + 14) +#define IEEE802154_MIN_HEADER_LEN (IEEE802154_ACK_PSDU_LEN - \ + IEEE802154_FCS_LEN) #define IEEE802154_PAN_ID_BROADCAST 0xffff #define IEEE802154_ADDR_SHORT_BROADCAST 0xffff @@ -205,6 +215,41 @@ enum { IEEE802154_SCAN_IN_PROGRESS = 0xfc, }; +/* frame control handling */ +#define IEEE802154_FCTL_FTYPE 0x0003 +#define IEEE802154_FCTL_ACKREQ 0x0020 +#define IEEE802154_FCTL_INTRA_PAN 0x0040 + +#define IEEE802154_FTYPE_DATA 0x0001 + +/* + * ieee802154_is_data - check if type is IEEE802154_FTYPE_DATA + * @fc: frame control bytes in little-endian byteorder + */ +static inline int ieee802154_is_data(__le16 fc) +{ + return (fc & cpu_to_le16(IEEE802154_FCTL_FTYPE)) == + cpu_to_le16(IEEE802154_FTYPE_DATA); +} + +/** + * ieee802154_is_ackreq - check if acknowledgment request bit is set + * @fc: frame control bytes in little-endian byteorder + */ +static inline bool ieee802154_is_ackreq(__le16 fc) +{ + return fc & cpu_to_le16(IEEE802154_FCTL_ACKREQ); +} + +/** + * ieee802154_is_intra_pan - check if intra pan id communication + * @fc: frame control bytes in little-endian byteorder + */ +static inline bool ieee802154_is_intra_pan(__le16 fc) +{ + return fc & cpu_to_le16(IEEE802154_FCTL_INTRA_PAN); +} + /** * ieee802154_is_valid_psdu_len - check if psdu len is valid * available lengths: @@ -225,15 +270,13 @@ static inline bool ieee802154_is_valid_psdu_len(const u8 len) * ieee802154_is_valid_psdu_len - check if extended addr is valid * @addr: extended addr to check */ -static inline bool ieee802154_is_valid_extended_addr(const __le64 addr) +static inline bool ieee802154_is_valid_extended_unicast_addr(const __le64 addr) { - /* These EUI-64 addresses are reserved by IEEE. 0xffffffffffffffff - * is used internally as extended to short address broadcast mapping. - * This is currently a workaround because neighbor discovery can't - * deal with short addresses types right now. + /* Bail out if the address is all zero, or if the group + * address bit is set. */ return ((addr != cpu_to_le64(0x0000000000000000ULL)) && - (addr != cpu_to_le64(0xffffffffffffffffULL))); + !(addr & cpu_to_le64(0x0100000000000000ULL))); } /** @@ -244,9 +287,9 @@ static inline void ieee802154_random_extended_addr(__le64 *addr) { get_random_bytes(addr, IEEE802154_EXTENDED_ADDR_LEN); - /* toggle some bit if we hit an invalid extended addr */ - if (!ieee802154_is_valid_extended_addr(*addr)) - ((u8 *)addr)[IEEE802154_EXTENDED_ADDR_LEN - 1] ^= 0x01; + /* clear the group bit, and set the locally administered bit */ + ((u8 *)addr)[IEEE802154_EXTENDED_ADDR_LEN - 1] &= ~0x01; + ((u8 *)addr)[IEEE802154_EXTENDED_ADDR_LEN - 1] |= 0x02; } #endif /* LINUX_IEEE802154_H */ diff --git a/kernel/include/linux/if_bridge.h b/kernel/include/linux/if_bridge.h index dad8b00be..a338a688e 100644 --- a/kernel/include/linux/if_bridge.h +++ b/kernel/include/linux/if_bridge.h @@ -46,6 +46,12 @@ struct br_ip_list { #define BR_LEARNING_SYNC BIT(9) #define BR_PROXYARP_WIFI BIT(10) +/* values as per ieee8021QBridgeFdbAgingTime */ +#define BR_MIN_AGEING_TIME (10 * HZ) +#define BR_MAX_AGEING_TIME (1000000 * HZ) + +#define BR_DEFAULT_AGEING_TIME (300 * HZ) + extern void brioctl_set(int (*ioctl_hook)(struct net *, unsigned int, void __user *)); typedef int br_should_route_hook_t(struct sk_buff *skb); diff --git a/kernel/include/linux/if_link.h b/kernel/include/linux/if_link.h index da4929927..f923d15b4 100644 --- a/kernel/include/linux/if_link.h +++ b/kernel/include/linux/if_link.h @@ -5,6 +5,15 @@ /* We don't want this structure exposed to user space */ +struct ifla_vf_stats { + __u64 rx_packets; + __u64 tx_packets; + __u64 rx_bytes; + __u64 tx_bytes; + __u64 broadcast; + __u64 multicast; +}; + struct ifla_vf_info { __u32 vf; __u8 mac[32]; @@ -15,5 +24,6 @@ struct ifla_vf_info { __u32 min_tx_rate; __u32 max_tx_rate; __u32 rss_query_en; + __u32 trusted; }; #endif /* _LINUX_IF_LINK_H */ diff --git a/kernel/include/linux/if_macvlan.h b/kernel/include/linux/if_macvlan.h index 6f6929ea8..a4ccc3122 100644 --- a/kernel/include/linux/if_macvlan.h +++ b/kernel/include/linux/if_macvlan.h @@ -29,7 +29,7 @@ struct macvtap_queue; * Maximum times a macvtap device can be opened. This can be used to * configure the number of receive queue, e.g. for multiqueue virtio. */ -#define MAX_MACVTAP_QUEUES 16 +#define MAX_MACVTAP_QUEUES 256 #define MACVLAN_MC_FILTER_BITS 8 #define MACVLAN_MC_FILTER_SZ (1 << MACVLAN_MC_FILTER_BITS) diff --git a/kernel/include/linux/if_pppox.h b/kernel/include/linux/if_pppox.h index 66a7d7600..b49cf923b 100644 --- a/kernel/include/linux/if_pppox.h +++ b/kernel/include/linux/if_pppox.h @@ -74,7 +74,7 @@ static inline struct sock *sk_pppox(struct pppox_sock *po) struct module; struct pppox_proto { - int (*create)(struct net *net, struct socket *sock); + int (*create)(struct net *net, struct socket *sock, int kern); int (*ioctl)(struct socket *sock, unsigned int cmd, unsigned long arg); struct module *owner; diff --git a/kernel/include/linux/if_vlan.h b/kernel/include/linux/if_vlan.h index 920e4457c..67ce5bd3b 100644 --- a/kernel/include/linux/if_vlan.h +++ b/kernel/include/linux/if_vlan.h @@ -416,7 +416,7 @@ static inline void __vlan_hwaccel_put_tag(struct sk_buff *skb, /** * __vlan_get_tag - get the VLAN ID that is part of the payload * @skb: skbuff to query - * @vlan_tci: buffer to store vlaue + * @vlan_tci: buffer to store value * * Returns error if the skb is not of VLAN type */ @@ -435,7 +435,7 @@ static inline int __vlan_get_tag(const struct sk_buff *skb, u16 *vlan_tci) /** * __vlan_hwaccel_get_tag - get the VLAN ID that is in @skb->cb[] * @skb: skbuff to query - * @vlan_tci: buffer to store vlaue + * @vlan_tci: buffer to store value * * Returns error if @skb->vlan_tci is not set correctly */ @@ -456,7 +456,7 @@ static inline int __vlan_hwaccel_get_tag(const struct sk_buff *skb, /** * vlan_get_tag - get the VLAN ID from the skb * @skb: skbuff to query - * @vlan_tci: buffer to store vlaue + * @vlan_tci: buffer to store value * * Returns error if the skb is not VLAN tagged */ @@ -539,7 +539,7 @@ static inline void vlan_set_encap_proto(struct sk_buff *skb, */ proto = vhdr->h_vlan_encapsulated_proto; - if (ntohs(proto) >= ETH_P_802_3_MIN) { + if (eth_proto_is_802_3(proto)) { skb->protocol = proto; return; } @@ -628,4 +628,24 @@ static inline netdev_features_t vlan_features_check(const struct sk_buff *skb, return features; } +/** + * compare_vlan_header - Compare two vlan headers + * @h1: Pointer to vlan header + * @h2: Pointer to vlan header + * + * Compare two vlan headers, returns 0 if equal. + * + * Please note that alignment of h1 & h2 are only guaranteed to be 16 bits. + */ +static inline unsigned long compare_vlan_header(const struct vlan_hdr *h1, + const struct vlan_hdr *h2) +{ +#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) + return *(u32 *)h1 ^ *(u32 *)h2; +#else + return ((__force u32)h1->h_vlan_TCI ^ (__force u32)h2->h_vlan_TCI) | + ((__force u32)h1->h_vlan_encapsulated_proto ^ + (__force u32)h2->h_vlan_encapsulated_proto); +#endif +} #endif /* !(_LINUX_IF_VLAN_H_) */ diff --git a/kernel/include/linux/igmp.h b/kernel/include/linux/igmp.h index 2c677afee..9c9de1154 100644 --- a/kernel/include/linux/igmp.h +++ b/kernel/include/linux/igmp.h @@ -37,6 +37,7 @@ static inline struct igmpv3_query * return (struct igmpv3_query *)skb_transport_header(skb); } +extern int sysctl_igmp_llm_reports; extern int sysctl_igmp_max_memberships; extern int sysctl_igmp_max_msf; extern int sysctl_igmp_qrv; @@ -109,7 +110,7 @@ struct ip_mc_list { #define IGMPV3_QQIC(value) IGMPV3_EXP(0x80, 4, 3, value) #define IGMPV3_MRC(value) IGMPV3_EXP(0x80, 4, 3, value) -extern int ip_check_mc_rcu(struct in_device *dev, __be32 mc_addr, __be32 src_addr, u16 proto); +extern int ip_check_mc_rcu(struct in_device *dev, __be32 mc_addr, __be32 src_addr, u8 proto); extern int igmp_rcv(struct sk_buff *); extern int ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr); extern int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr); @@ -130,5 +131,6 @@ extern void ip_mc_unmap(struct in_device *); extern void ip_mc_remap(struct in_device *); extern void ip_mc_dec_group(struct in_device *in_dev, __be32 addr); extern void ip_mc_inc_group(struct in_device *in_dev, __be32 addr); +int ip_mc_check_igmp(struct sk_buff *skb, struct sk_buff **skb_trimmed); #endif diff --git a/kernel/include/linux/iio/buffer.h b/kernel/include/linux/iio/buffer.h index eb8622b78..1600c5582 100644 --- a/kernel/include/linux/iio/buffer.h +++ b/kernel/include/linux/iio/buffer.h @@ -29,6 +29,7 @@ struct iio_buffer; * @set_length: set number of datums in buffer * @release: called when the last reference to the buffer is dropped, * should free all resources allocated by the buffer. + * @modes: Supported operating modes by this buffer type * * The purpose of this structure is to make the buffer element * modular as event for a given driver, different usecases may require @@ -51,6 +52,8 @@ struct iio_buffer_access_funcs { int (*set_length)(struct iio_buffer *buffer, int length); void (*release)(struct iio_buffer *buffer); + + unsigned int modes; }; /** diff --git a/kernel/include/linux/iio/common/st_sensors.h b/kernel/include/linux/iio/common/st_sensors.h index 2c476acb8..2fe939c73 100644 --- a/kernel/include/linux/iio/common/st_sensors.h +++ b/kernel/include/linux/iio/common/st_sensors.h @@ -166,6 +166,7 @@ struct st_sensor_transfer_function { /** * struct st_sensor_settings - ST specific sensor settings * @wai: Contents of WhoAmI register. + * @wai_addr: The address of WhoAmI register. * @sensors_supported: List of supported sensors by struct itself. * @ch: IIO channels for the sensor. * @odr: Output data rate register and ODR list available. @@ -179,6 +180,7 @@ struct st_sensor_transfer_function { */ struct st_sensor_settings { u8 wai; + u8 wai_addr; char sensors_supported[ST_SENSORS_MAX_4WAI][ST_SENSORS_MAX_NAME]; struct iio_chan_spec *ch; int num_ch; @@ -269,6 +271,10 @@ void st_sensors_power_enable(struct iio_dev *indio_dev); void st_sensors_power_disable(struct iio_dev *indio_dev); +int st_sensors_debugfs_reg_access(struct iio_dev *indio_dev, + unsigned reg, unsigned writeval, + unsigned *readval); + int st_sensors_set_odr(struct iio_dev *indio_dev, unsigned int odr); int st_sensors_set_dataready_irq(struct iio_dev *indio_dev, bool enable); diff --git a/kernel/include/linux/iio/consumer.h b/kernel/include/linux/iio/consumer.h index 26fb8f634..fad58671c 100644 --- a/kernel/include/linux/iio/consumer.h +++ b/kernel/include/linux/iio/consumer.h @@ -100,7 +100,7 @@ void iio_channel_stop_all_cb(struct iio_cb_buffer *cb_buff); /** * iio_channel_cb_get_channels() - get access to the underlying channels. - * @cb_buff: The callback buffer from whom we want the channel + * @cb_buffer: The callback buffer from whom we want the channel * information. * * This function allows one to obtain information about the channels. diff --git a/kernel/include/linux/iio/iio.h b/kernel/include/linux/iio/iio.h index 5ed7771ad..19c94c9ac 100644 --- a/kernel/include/linux/iio/iio.h +++ b/kernel/include/linux/iio/iio.h @@ -32,6 +32,7 @@ enum iio_chan_info_enum { IIO_CHAN_INFO_QUADRATURE_CORRECTION_RAW, IIO_CHAN_INFO_AVERAGE_RAW, IIO_CHAN_INFO_LOW_PASS_FILTER_3DB_FREQUENCY, + IIO_CHAN_INFO_HIGH_PASS_FILTER_3DB_FREQUENCY, IIO_CHAN_INFO_SAMP_FREQ, IIO_CHAN_INFO_FREQUENCY, IIO_CHAN_INFO_PHASE, @@ -43,6 +44,8 @@ enum iio_chan_info_enum { IIO_CHAN_INFO_CALIBWEIGHT, IIO_CHAN_INFO_DEBOUNCE_COUNT, IIO_CHAN_INFO_DEBOUNCE_TIME, + IIO_CHAN_INFO_CALIBEMISSIVITY, + IIO_CHAN_INFO_OVERSAMPLING_RATIO, }; enum iio_shared_by { @@ -291,6 +294,7 @@ static inline s64 iio_get_time_ns(void) #define INDIO_BUFFER_TRIGGERED 0x02 #define INDIO_BUFFER_SOFTWARE 0x04 #define INDIO_BUFFER_HARDWARE 0x08 +#define INDIO_EVENT_TRIGGERED 0x10 #define INDIO_ALL_BUFFER_MODES \ (INDIO_BUFFER_TRIGGERED | INDIO_BUFFER_HARDWARE | INDIO_BUFFER_SOFTWARE) @@ -454,6 +458,7 @@ struct iio_buffer_setup_ops { * @scan_index_timestamp:[INTERN] cache of the index to the timestamp * @trig: [INTERN] current device trigger (buffer modes) * @pollfunc: [DRIVER] function run on trigger being received + * @pollfunc_event: [DRIVER] function run on events trigger being received * @channels: [DRIVER] channel specification structure table * @num_channels: [DRIVER] number of channels specified in @channels. * @channel_attr_list: [INTERN] keep track of automatically created channel @@ -492,6 +497,7 @@ struct iio_dev { unsigned scan_index_timestamp; struct iio_trigger *trig; struct iio_poll_func *pollfunc; + struct iio_poll_func *pollfunc_event; struct iio_chan_spec const *channels; int num_channels; diff --git a/kernel/include/linux/iio/sysfs.h b/kernel/include/linux/iio/sysfs.h index 8a1d18640..9cd8f7472 100644 --- a/kernel/include/linux/iio/sysfs.h +++ b/kernel/include/linux/iio/sysfs.h @@ -18,7 +18,8 @@ struct iio_chan_spec; * struct iio_dev_attr - iio specific device attribute * @dev_attr: underlying device attribute * @address: associated register address - * @l: list head for maintaining list of dynamically created attrs. + * @l: list head for maintaining list of dynamically created attrs + * @c: specification for the underlying channel */ struct iio_dev_attr { struct device_attribute dev_attr; diff --git a/kernel/include/linux/iio/trigger.h b/kernel/include/linux/iio/trigger.h index fa76c79a5..1c9e028e0 100644 --- a/kernel/include/linux/iio/trigger.h +++ b/kernel/include/linux/iio/trigger.h @@ -18,6 +18,9 @@ struct iio_subirq { bool enabled; }; +struct iio_dev; +struct iio_trigger; + /** * struct iio_trigger_ops - operations structure for an iio_trigger. * @owner: used to monitor usage count of the trigger. diff --git a/kernel/include/linux/iio/triggered_buffer.h b/kernel/include/linux/iio/triggered_buffer.h index c378ebec6..f72f70d5a 100644 --- a/kernel/include/linux/iio/triggered_buffer.h +++ b/kernel/include/linux/iio/triggered_buffer.h @@ -7,8 +7,8 @@ struct iio_dev; struct iio_buffer_setup_ops; int iio_triggered_buffer_setup(struct iio_dev *indio_dev, - irqreturn_t (*pollfunc_bh)(int irq, void *p), - irqreturn_t (*pollfunc_th)(int irq, void *p), + irqreturn_t (*h)(int irq, void *p), + irqreturn_t (*thread)(int irq, void *p), const struct iio_buffer_setup_ops *setup_ops); void iio_triggered_buffer_cleanup(struct iio_dev *indio_dev); diff --git a/kernel/include/linux/iio/triggered_event.h b/kernel/include/linux/iio/triggered_event.h new file mode 100644 index 000000000..8fe853708 --- /dev/null +++ b/kernel/include/linux/iio/triggered_event.h @@ -0,0 +1,11 @@ +#ifndef _LINUX_IIO_TRIGGERED_EVENT_H_ +#define _LINUX_IIO_TRIGGERED_EVENT_H_ + +#include <linux/interrupt.h> + +int iio_triggered_event_setup(struct iio_dev *indio_dev, + irqreturn_t (*h)(int irq, void *p), + irqreturn_t (*thread)(int irq, void *p)); +void iio_triggered_event_cleanup(struct iio_dev *indio_dev); + +#endif diff --git a/kernel/include/linux/iio/types.h b/kernel/include/linux/iio/types.h index 942b6de68..32b579525 100644 --- a/kernel/include/linux/iio/types.h +++ b/kernel/include/linux/iio/types.h @@ -17,6 +17,8 @@ enum iio_event_info { IIO_EV_INFO_VALUE, IIO_EV_INFO_HYSTERESIS, IIO_EV_INFO_PERIOD, + IIO_EV_INFO_HIGH_PASS_FILTER_3DB, + IIO_EV_INFO_LOW_PASS_FILTER_3DB, }; #define IIO_VAL_INT 1 diff --git a/kernel/include/linux/inet_diag.h b/kernel/include/linux/inet_diag.h index ac48b10c9..0e707f0c1 100644 --- a/kernel/include/linux/inet_diag.h +++ b/kernel/include/linux/inet_diag.h @@ -24,6 +24,7 @@ struct inet_diag_handler { struct inet_diag_msg *r, void *info); __u16 idiag_type; + __u16 idiag_info_size; }; struct inet_connection_sock; diff --git a/kernel/include/linux/inetdevice.h b/kernel/include/linux/inetdevice.h index 0a21fbefd..ee971f335 100644 --- a/kernel/include/linux/inetdevice.h +++ b/kernel/include/linux/inetdevice.h @@ -120,6 +120,9 @@ static inline void ipv4_devconf_setall(struct in_device *in_dev) || (!IN_DEV_FORWARD(in_dev) && \ IN_DEV_ORCONF((in_dev), ACCEPT_REDIRECTS))) +#define IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) \ + IN_DEV_CONF_GET((in_dev), IGNORE_ROUTES_WITH_LINKDOWN) + #define IN_DEV_ARPFILTER(in_dev) IN_DEV_ORCONF((in_dev), ARPFILTER) #define IN_DEV_ARP_ACCEPT(in_dev) IN_DEV_ORCONF((in_dev), ARP_ACCEPT) #define IN_DEV_ARP_ANNOUNCE(in_dev) IN_DEV_MAXCONF((in_dev), ARP_ANNOUNCE) @@ -168,7 +171,7 @@ __be32 inet_confirm_addr(struct net *net, struct in_device *in_dev, __be32 dst, __be32 local, int scope); struct in_ifaddr *inet_ifa_byprefix(struct in_device *in_dev, __be32 prefix, __be32 mask); -static __inline__ int inet_ifa_match(__be32 addr, struct in_ifaddr *ifa) +static __inline__ bool inet_ifa_match(__be32 addr, struct in_ifaddr *ifa) { return !((addr^ifa->ifa_address)&ifa->ifa_mask); } @@ -177,15 +180,15 @@ static __inline__ int inet_ifa_match(__be32 addr, struct in_ifaddr *ifa) * Check if a mask is acceptable. */ -static __inline__ int bad_mask(__be32 mask, __be32 addr) +static __inline__ bool bad_mask(__be32 mask, __be32 addr) { __u32 hmask; if (addr & (mask = ~mask)) - return 1; + return true; hmask = ntohl(mask); if (hmask & (hmask+1)) - return 1; - return 0; + return true; + return false; } #define for_primary_ifa(in_dev) { struct in_ifaddr *ifa; \ diff --git a/kernel/include/linux/init.h b/kernel/include/linux/init.h index 21b6d768e..b449f378f 100644 --- a/kernel/include/linux/init.h +++ b/kernel/include/linux/init.h @@ -91,14 +91,6 @@ #define __exit __section(.exit.text) __exitused __cold notrace -/* temporary, until all users are removed */ -#define __cpuinit -#define __cpuinitdata -#define __cpuinitconst -#define __cpuexit -#define __cpuexitdata -#define __cpuexitconst - /* Used for MEMORY_HOTPLUG */ #define __meminit __section(.meminit.text) __cold notrace #define __meminitdata __section(.meminit.data) @@ -116,9 +108,6 @@ #define __INITRODATA .section ".init.rodata","a",%progbits #define __FINITDATA .previous -/* temporary, until all users are removed */ -#define __CPUINIT - #define __MEMINIT .section ".meminit.text", "ax" #define __MEMINITDATA .section ".meminit.data", "aw" #define __MEMINITRODATA .section ".meminit.rodata", "a" @@ -293,68 +282,8 @@ void __init parse_early_param(void); void __init parse_early_options(char *cmdline); #endif /* __ASSEMBLY__ */ -/** - * module_init() - driver initialization entry point - * @x: function to be run at kernel boot time or module insertion - * - * module_init() will either be called during do_initcalls() (if - * builtin) or at module insertion time (if a module). There can only - * be one per module. - */ -#define module_init(x) __initcall(x); - -/** - * module_exit() - driver exit entry point - * @x: function to be run when driver is removed - * - * module_exit() will wrap the driver clean-up code - * with cleanup_module() when used with rmmod when - * the driver is a module. If the driver is statically - * compiled into the kernel, module_exit() has no effect. - * There can only be one per module. - */ -#define module_exit(x) __exitcall(x); - #else /* MODULE */ -/* - * In most cases loadable modules do not need custom - * initcall levels. There are still some valid cases where - * a driver may be needed early if built in, and does not - * matter when built as a loadable module. Like bus - * snooping debug drivers. - */ -#define early_initcall(fn) module_init(fn) -#define core_initcall(fn) module_init(fn) -#define core_initcall_sync(fn) module_init(fn) -#define postcore_initcall(fn) module_init(fn) -#define postcore_initcall_sync(fn) module_init(fn) -#define arch_initcall(fn) module_init(fn) -#define subsys_initcall(fn) module_init(fn) -#define subsys_initcall_sync(fn) module_init(fn) -#define fs_initcall(fn) module_init(fn) -#define fs_initcall_sync(fn) module_init(fn) -#define rootfs_initcall(fn) module_init(fn) -#define device_initcall(fn) module_init(fn) -#define device_initcall_sync(fn) module_init(fn) -#define late_initcall(fn) module_init(fn) -#define late_initcall_sync(fn) module_init(fn) - -#define console_initcall(fn) module_init(fn) -#define security_initcall(fn) module_init(fn) - -/* Each module must use one module_init(). */ -#define module_init(initfn) \ - static inline initcall_t __inittest(void) \ - { return initfn; } \ - int init_module(void) __attribute__((alias(#initfn))); - -/* This is only required if you want to be unloadable. */ -#define module_exit(exitfn) \ - static inline exitcall_t __exittest(void) \ - { return exitfn; } \ - void cleanup_module(void) __attribute__((alias(#exitfn))); - #define __setup_param(str, unique_id, fn) /* nothing */ #define __setup(str, func) /* nothing */ #endif @@ -362,24 +291,6 @@ void __init parse_early_options(char *cmdline); /* Data marked not to be saved by software suspend */ #define __nosavedata __section(.data..nosave) -/* This means "can be init if no module support, otherwise module load - may call it." */ -#ifdef CONFIG_MODULES -#define __init_or_module -#define __initdata_or_module -#define __initconst_or_module -#define __INIT_OR_MODULE .text -#define __INITDATA_OR_MODULE .data -#define __INITRODATA_OR_MODULE .section ".rodata","a",%progbits -#else -#define __init_or_module __init -#define __initdata_or_module __initdata -#define __initconst_or_module __initconst -#define __INIT_OR_MODULE __INIT -#define __INITDATA_OR_MODULE __INITDATA -#define __INITRODATA_OR_MODULE __INITRODATA -#endif /*CONFIG_MODULES*/ - #ifdef MODULE #define __exit_p(x) x #else diff --git a/kernel/include/linux/init_task.h b/kernel/include/linux/init_task.h index 4a77d39ff..d8ec0f202 100644 --- a/kernel/include/linux/init_task.h +++ b/kernel/include/linux/init_task.h @@ -25,13 +25,6 @@ extern struct files_struct init_files; extern struct fs_struct init_fs; -#ifdef CONFIG_CGROUPS -#define INIT_GROUP_RWSEM(sig) \ - .group_rwsem = __RWSEM_INITIALIZER(sig.group_rwsem), -#else -#define INIT_GROUP_RWSEM(sig) -#endif - #ifdef CONFIG_CPUSETS #define INIT_CPUSET_SEQ(tsk) \ .mems_allowed_seq = SEQCNT_ZERO(tsk.mems_allowed_seq), @@ -39,6 +32,14 @@ extern struct fs_struct init_fs; #define INIT_CPUSET_SEQ(tsk) #endif +#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE +#define INIT_PREV_CPUTIME(x) .prev_cputime = { \ + .lock = __RAW_SPIN_LOCK_UNLOCKED(x.prev_cputime.lock), \ +}, +#else +#define INIT_PREV_CPUTIME(x) +#endif + #define INIT_SIGNALS(sig) { \ .nr_threads = 1, \ .thread_head = LIST_HEAD_INIT(init_task.thread_node), \ @@ -50,13 +51,13 @@ extern struct fs_struct init_fs; .cpu_timers = INIT_CPU_TIMERS(sig.cpu_timers), \ .rlim = INIT_RLIMITS, \ .cputimer = { \ - .cputime = INIT_CPUTIME, \ - .running = 0, \ - .lock = __RAW_SPIN_LOCK_UNLOCKED(sig.cputimer.lock), \ + .cputime_atomic = INIT_CPUTIME_ATOMIC, \ + .running = false, \ + .checking_timer = false, \ }, \ + INIT_PREV_CPUTIME(sig) \ .cred_guard_mutex = \ __MUTEX_INITIALIZER(sig.cred_guard_mutex), \ - INIT_GROUP_RWSEM(sig) \ } extern struct nsproxy init_nsproxy; @@ -263,6 +264,7 @@ extern struct task_group root_task_group; INIT_TASK_RCU_TASKS(tsk) \ INIT_CPUSET_SEQ(tsk) \ INIT_RT_MUTEXES(tsk) \ + INIT_PREV_CPUTIME(tsk) \ INIT_VTIME(tsk) \ INIT_NUMA_BALANCING(tsk) \ INIT_KASAN(tsk) \ diff --git a/kernel/include/linux/input.h b/kernel/include/linux/input.h index 82ce323b9..1e967694e 100644 --- a/kernel/include/linux/input.h +++ b/kernel/include/linux/input.h @@ -469,6 +469,8 @@ int input_get_keycode(struct input_dev *dev, struct input_keymap_entry *ke); int input_set_keycode(struct input_dev *dev, const struct input_keymap_entry *ke); +void input_enable_softrepeat(struct input_dev *dev, int delay, int period); + extern struct class input_class; /** diff --git a/kernel/include/linux/input/edt-ft5x06.h b/kernel/include/linux/input/edt-ft5x06.h deleted file mode 100644 index 8a1e0d1a0..000000000 --- a/kernel/include/linux/input/edt-ft5x06.h +++ /dev/null @@ -1,24 +0,0 @@ -#ifndef _EDT_FT5X06_H -#define _EDT_FT5X06_H - -/* - * Copyright (c) 2012 Simon Budig, <simon.budig@kernelconcepts.de> - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published by - * the Free Software Foundation. - */ - -struct edt_ft5x06_platform_data { - int irq_pin; - int reset_pin; - - /* startup defaults for operational parameters */ - bool use_parameters; - u8 gain; - u8 threshold; - u8 offset; - u8 report_rate; -}; - -#endif /* _EDT_FT5X06_H */ diff --git a/kernel/include/linux/input/touchscreen.h b/kernel/include/linux/input/touchscreen.h index 08a5ef6e8..c91e13761 100644 --- a/kernel/include/linux/input/touchscreen.h +++ b/kernel/include/linux/input/touchscreen.h @@ -9,14 +9,8 @@ #ifndef _TOUCHSCREEN_H #define _TOUCHSCREEN_H -#include <linux/input.h> +struct input_dev; -#ifdef CONFIG_OF -void touchscreen_parse_of_params(struct input_dev *dev); -#else -static inline void touchscreen_parse_of_params(struct input_dev *dev) -{ -} -#endif +void touchscreen_parse_properties(struct input_dev *dev, bool multitouch); #endif diff --git a/kernel/include/linux/intel-iommu.h b/kernel/include/linux/intel-iommu.h index a240e61a7..2d9b65004 100644 --- a/kernel/include/linux/intel-iommu.h +++ b/kernel/include/linux/intel-iommu.h @@ -1,5 +1,9 @@ /* - * Copyright (c) 2006, Intel Corporation. + * Copyright © 2006-2015, Intel Corporation. + * + * Authors: Ashok Raj <ashok.raj@intel.com> + * Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com> + * David Woodhouse <David.Woodhouse@intel.com> * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, @@ -13,10 +17,6 @@ * You should have received a copy of the GNU General Public License along with * this program; if not, write to the Free Software Foundation, Inc., 59 Temple * Place - Suite 330, Boston, MA 02111-1307 USA. - * - * Copyright (C) 2006-2008 Intel Corporation - * Author: Ashok Raj <ashok.raj@intel.com> - * Author: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com> */ #ifndef _INTEL_IOMMU_H_ @@ -25,7 +25,10 @@ #include <linux/types.h> #include <linux/iova.h> #include <linux/io.h> +#include <linux/idr.h> #include <linux/dma_remapping.h> +#include <linux/mmu_notifier.h> +#include <linux/list.h> #include <asm/cacheflush.h> #include <asm/iommu.h> @@ -57,16 +60,21 @@ #define DMAR_IQA_REG 0x90 /* Invalidation queue addr register */ #define DMAR_ICS_REG 0x9c /* Invalidation complete status register */ #define DMAR_IRTA_REG 0xb8 /* Interrupt remapping table addr register */ +#define DMAR_PQH_REG 0xc0 /* Page request queue head register */ +#define DMAR_PQT_REG 0xc8 /* Page request queue tail register */ +#define DMAR_PQA_REG 0xd0 /* Page request queue address register */ +#define DMAR_PRS_REG 0xdc /* Page request status register */ +#define DMAR_PECTL_REG 0xe0 /* Page request event control register */ +#define DMAR_PEDATA_REG 0xe4 /* Page request event interrupt data register */ +#define DMAR_PEADDR_REG 0xe8 /* Page request event interrupt addr register */ +#define DMAR_PEUADDR_REG 0xec /* Page request event Upper address register */ #define OFFSET_STRIDE (9) -/* -#define dmar_readl(dmar, reg) readl(dmar + reg) -#define dmar_readq(dmar, reg) ({ \ - u32 lo, hi; \ - lo = readl(dmar + reg); \ - hi = readl(dmar + reg + 4); \ - (((u64) hi) << 32) + lo; }) -*/ + +#ifdef CONFIG_64BIT +#define dmar_readq(a) readq(a) +#define dmar_writeq(a,v) writeq(v,a) +#else static inline u64 dmar_readq(void __iomem *addr) { u32 lo, hi; @@ -80,6 +88,7 @@ static inline void dmar_writeq(void __iomem *addr, u64 val) writel((u32)val, addr); writel((u32)(val >> 32), addr + 4); } +#endif #define DMAR_VER_MAJOR(v) (((v) & 0xf0) >> 4) #define DMAR_VER_MINOR(v) ((v) & 0x0f) @@ -87,6 +96,7 @@ static inline void dmar_writeq(void __iomem *addr, u64 val) /* * Decoding Capability Register */ +#define cap_pi_support(c) (((c) >> 59) & 1) #define cap_read_drain(c) (((c) >> 55) & 1) #define cap_write_drain(c) (((c) >> 54) & 1) #define cap_max_amask_val(c) (((c) >> 48) & 0x3f) @@ -122,7 +132,7 @@ static inline void dmar_writeq(void __iomem *addr, u64 val) #define ecap_srs(e) ((e >> 31) & 0x1) #define ecap_ers(e) ((e >> 30) & 0x1) #define ecap_prs(e) ((e >> 29) & 0x1) -/* PASID support used to be on bit 28 */ +#define ecap_broken_pasid(e) ((e >> 28) & 0x1) #define ecap_dis(e) ((e >> 27) & 0x1) #define ecap_nest(e) ((e >> 26) & 0x1) #define ecap_mts(e) ((e >> 25) & 0x1) @@ -225,6 +235,9 @@ static inline void dmar_writeq(void __iomem *addr, u64 val) /* low 64 bit */ #define dma_frcd_page_addr(d) (d & (((u64)-1) << PAGE_SHIFT)) +/* PRS_REG */ +#define DMA_PRS_PPR ((u32)1) + #define IOMMU_WAIT_OP(iommu, offset, op, cond, sts) \ do { \ cycles_t start_time = get_cycles(); \ @@ -252,6 +265,11 @@ enum { #define QI_DIOTLB_TYPE 0x3 #define QI_IEC_TYPE 0x4 #define QI_IWD_TYPE 0x5 +#define QI_EIOTLB_TYPE 0x6 +#define QI_PC_TYPE 0x7 +#define QI_DEIOTLB_TYPE 0x8 +#define QI_PGRP_RESP_TYPE 0x9 +#define QI_PSTRM_RESP_TYPE 0xa #define QI_IEC_SELECTIVE (((u64)1) << 4) #define QI_IEC_IIDEX(idx) (((u64)(idx & 0xffff) << 32)) @@ -279,6 +297,53 @@ enum { #define QI_DEV_IOTLB_SIZE 1 #define QI_DEV_IOTLB_MAX_INVS 32 +#define QI_PC_PASID(pasid) (((u64)pasid) << 32) +#define QI_PC_DID(did) (((u64)did) << 16) +#define QI_PC_GRAN(gran) (((u64)gran) << 4) + +#define QI_PC_ALL_PASIDS (QI_PC_TYPE | QI_PC_GRAN(0)) +#define QI_PC_PASID_SEL (QI_PC_TYPE | QI_PC_GRAN(1)) + +#define QI_EIOTLB_ADDR(addr) ((u64)(addr) & VTD_PAGE_MASK) +#define QI_EIOTLB_GL(gl) (((u64)gl) << 7) +#define QI_EIOTLB_IH(ih) (((u64)ih) << 6) +#define QI_EIOTLB_AM(am) (((u64)am)) +#define QI_EIOTLB_PASID(pasid) (((u64)pasid) << 32) +#define QI_EIOTLB_DID(did) (((u64)did) << 16) +#define QI_EIOTLB_GRAN(gran) (((u64)gran) << 4) + +#define QI_DEV_EIOTLB_ADDR(a) ((u64)(a) & VTD_PAGE_MASK) +#define QI_DEV_EIOTLB_SIZE (((u64)1) << 11) +#define QI_DEV_EIOTLB_GLOB(g) ((u64)g) +#define QI_DEV_EIOTLB_PASID(p) (((u64)p) << 32) +#define QI_DEV_EIOTLB_SID(sid) ((u64)((sid) & 0xffff) << 32) +#define QI_DEV_EIOTLB_QDEP(qd) (((qd) & 0x1f) << 16) +#define QI_DEV_EIOTLB_MAX_INVS 32 + +#define QI_PGRP_IDX(idx) (((u64)(idx)) << 55) +#define QI_PGRP_PRIV(priv) (((u64)(priv)) << 32) +#define QI_PGRP_RESP_CODE(res) ((u64)(res)) +#define QI_PGRP_PASID(pasid) (((u64)(pasid)) << 32) +#define QI_PGRP_DID(did) (((u64)(did)) << 16) +#define QI_PGRP_PASID_P(p) (((u64)(p)) << 4) + +#define QI_PSTRM_ADDR(addr) (((u64)(addr)) & VTD_PAGE_MASK) +#define QI_PSTRM_DEVFN(devfn) (((u64)(devfn)) << 4) +#define QI_PSTRM_RESP_CODE(res) ((u64)(res)) +#define QI_PSTRM_IDX(idx) (((u64)(idx)) << 55) +#define QI_PSTRM_PRIV(priv) (((u64)(priv)) << 32) +#define QI_PSTRM_BUS(bus) (((u64)(bus)) << 24) +#define QI_PSTRM_PASID(pasid) (((u64)(pasid)) << 4) + +#define QI_RESP_SUCCESS 0x0 +#define QI_RESP_INVALID 0x1 +#define QI_RESP_FAILURE 0xf + +#define QI_GRAN_ALL_ALL 0 +#define QI_GRAN_NONG_ALL 1 +#define QI_GRAN_NONG_PASID 2 +#define QI_GRAN_PSI_PASID 3 + struct qi_desc { u64 low, high; }; @@ -296,9 +361,12 @@ struct q_inval { /* 1MB - maximum possible interrupt remapping table size */ #define INTR_REMAP_PAGE_ORDER 8 #define INTR_REMAP_TABLE_REG_SIZE 0xf +#define INTR_REMAP_TABLE_REG_SIZE_MASK 0xf #define INTR_REMAP_TABLE_ENTRIES 65536 +struct irq_domain; + struct ir_table { struct irte *base; unsigned long *bitmap; @@ -320,6 +388,13 @@ enum { MAX_SR_DMAR_REGS }; +#define VTD_FLAG_TRANS_PRE_ENABLED (1 << 0) +#define VTD_FLAG_IRQ_REMAP_PRE_ENABLED (1 << 1) + +struct pasid_entry; +struct pasid_state_entry; +struct page_req_dsc; + struct intel_iommu { void __iomem *reg; /* Pointer to hardware regs, virtual addr */ u64 reg_phys; /* physical address of hw register set */ @@ -331,26 +406,41 @@ struct intel_iommu { int seq_id; /* sequence id of the iommu */ int agaw; /* agaw of this iommu */ int msagaw; /* max sagaw of this iommu */ - unsigned int irq; + unsigned int irq, pr_irq; u16 segment; /* PCI segment# */ unsigned char name[13]; /* Device Name */ #ifdef CONFIG_INTEL_IOMMU unsigned long *domain_ids; /* bitmap of domains */ - struct dmar_domain **domains; /* ptr to domains */ + struct dmar_domain ***domains; /* ptr to domains */ spinlock_t lock; /* protect context, domain ids */ struct root_entry *root_entry; /* virtual address */ struct iommu_flush flush; #endif +#ifdef CONFIG_INTEL_IOMMU_SVM + /* These are large and need to be contiguous, so we allocate just + * one for now. We'll maybe want to rethink that if we truly give + * devices away to userspace processes (e.g. for DPDK) and don't + * want to trust that userspace will use *only* the PASID it was + * told to. But while it's all driver-arbitrated, we're fine. */ + struct pasid_entry *pasid_table; + struct pasid_state_entry *pasid_state_table; + struct page_req_dsc *prq; + unsigned char prq_name[16]; /* Name for PRQ interrupt */ + struct idr pasid_idr; +#endif struct q_inval *qi; /* Queued invalidation info */ u32 *iommu_state; /* Store iommu states between suspend and resume.*/ #ifdef CONFIG_IRQ_REMAP struct ir_table *ir_table; /* Interrupt remapping info */ + struct irq_domain *ir_domain; + struct irq_domain *ir_msi_domain; #endif struct device *iommu_dev; /* IOMMU-sysfs device */ int node; + u32 flags; /* Software defined flags */ }; static inline void __iommu_flush_cache( @@ -379,6 +469,38 @@ extern int qi_submit_sync(struct qi_desc *desc, struct intel_iommu *iommu); extern int dmar_ir_support(void); +#ifdef CONFIG_INTEL_IOMMU_SVM +extern int intel_svm_alloc_pasid_tables(struct intel_iommu *iommu); +extern int intel_svm_free_pasid_tables(struct intel_iommu *iommu); +extern int intel_svm_enable_prq(struct intel_iommu *iommu); +extern int intel_svm_finish_prq(struct intel_iommu *iommu); + +struct svm_dev_ops; + +struct intel_svm_dev { + struct list_head list; + struct rcu_head rcu; + struct device *dev; + struct svm_dev_ops *ops; + int users; + u16 did; + u16 dev_iotlb:1; + u16 sid, qdep; +}; + +struct intel_svm { + struct mmu_notifier notifier; + struct mm_struct *mm; + struct intel_iommu *iommu; + int flags; + int pasid; + struct list_head devs; +}; + +extern int intel_iommu_enable_pasid(struct intel_iommu *iommu, struct intel_svm_dev *sdev); +extern struct intel_iommu *intel_svm_device_to_iommu(struct device *dev); +#endif + extern const struct attribute_group *intel_iommu_groups[]; #endif diff --git a/kernel/include/linux/intel-svm.h b/kernel/include/linux/intel-svm.h new file mode 100644 index 000000000..3c2579404 --- /dev/null +++ b/kernel/include/linux/intel-svm.h @@ -0,0 +1,121 @@ +/* + * Copyright © 2015 Intel Corporation. + * + * Authors: David Woodhouse <David.Woodhouse@intel.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ + +#ifndef __INTEL_SVM_H__ +#define __INTEL_SVM_H__ + +struct device; + +struct svm_dev_ops { + void (*fault_cb)(struct device *dev, int pasid, u64 address, + u32 private, int rwxp, int response); +}; + +/* Values for rxwp in fault_cb callback */ +#define SVM_REQ_READ (1<<3) +#define SVM_REQ_WRITE (1<<2) +#define SVM_REQ_EXEC (1<<1) +#define SVM_REQ_PRIV (1<<0) + + +/* + * The SVM_FLAG_PRIVATE_PASID flag requests a PASID which is *not* the "main" + * PASID for the current process. Even if a PASID already exists, a new one + * will be allocated. And the PASID allocated with SVM_FLAG_PRIVATE_PASID + * will not be given to subsequent callers. This facility allows a driver to + * disambiguate between multiple device contexts which access the same MM, + * if there is no other way to do so. It should be used sparingly, if at all. + */ +#define SVM_FLAG_PRIVATE_PASID (1<<0) + +/* + * The SVM_FLAG_SUPERVISOR_MODE flag requests a PASID which can be used only + * for access to kernel addresses. No IOTLB flushes are automatically done + * for kernel mappings; it is valid only for access to the kernel's static + * 1:1 mapping of physical memory — not to vmalloc or even module mappings. + * A future API addition may permit the use of such ranges, by means of an + * explicit IOTLB flush call (akin to the DMA API's unmap method). + * + * It is unlikely that we will ever hook into flush_tlb_kernel_range() to + * do such IOTLB flushes automatically. + */ +#define SVM_FLAG_SUPERVISOR_MODE (1<<1) + +#ifdef CONFIG_INTEL_IOMMU_SVM + +/** + * intel_svm_bind_mm() - Bind the current process to a PASID + * @dev: Device to be granted acccess + * @pasid: Address for allocated PASID + * @flags: Flags. Later for requesting supervisor mode, etc. + * @ops: Callbacks to device driver + * + * This function attempts to enable PASID support for the given device. + * If the @pasid argument is non-%NULL, a PASID is allocated for access + * to the MM of the current process. + * + * By using a %NULL value for the @pasid argument, this function can + * be used to simply validate that PASID support is available for the + * given device — i.e. that it is behind an IOMMU which has the + * requisite support, and is enabled. + * + * Page faults are handled transparently by the IOMMU code, and there + * should be no need for the device driver to be involved. If a page + * fault cannot be handled (i.e. is an invalid address rather than + * just needs paging in), then the page request will be completed by + * the core IOMMU code with appropriate status, and the device itself + * can then report the resulting fault to its driver via whatever + * mechanism is appropriate. + * + * Multiple calls from the same process may result in the same PASID + * being re-used. A reference count is kept. + */ +extern int intel_svm_bind_mm(struct device *dev, int *pasid, int flags, + struct svm_dev_ops *ops); + +/** + * intel_svm_unbind_mm() - Unbind a specified PASID + * @dev: Device for which PASID was allocated + * @pasid: PASID value to be unbound + * + * This function allows a PASID to be retired when the device no + * longer requires access to the address space of a given process. + * + * If the use count for the PASID in question reaches zero, the + * PASID is revoked and may no longer be used by hardware. + * + * Device drivers are required to ensure that no access (including + * page requests) is currently outstanding for the PASID in question, + * before calling this function. + */ +extern int intel_svm_unbind_mm(struct device *dev, int pasid); + +#else /* CONFIG_INTEL_IOMMU_SVM */ + +static inline int intel_svm_bind_mm(struct device *dev, int *pasid, + int flags, struct svm_dev_ops *ops) +{ + return -ENOSYS; +} + +static inline int intel_svm_unbind_mm(struct device *dev, int pasid) +{ + BUG(); +} +#endif /* CONFIG_INTEL_IOMMU_SVM */ + +#define intel_svm_available(dev) (!intel_svm_bind_mm((dev), NULL, 0, NULL)) + +#endif /* __INTEL_SVM_H__ */ diff --git a/kernel/include/linux/interrupt.h b/kernel/include/linux/interrupt.h index fe254555c..655cee096 100644 --- a/kernel/include/linux/interrupt.h +++ b/kernel/include/linux/interrupt.h @@ -208,6 +208,7 @@ extern void resume_device_irqs(void); * @irq: Interrupt to which notification applies * @kref: Reference count, for internal use * @work: Work item, for internal use + * @list: List item for deferred callbacks * @notify: Function to be called on change. This will be * called in process context. * @release: Function to be called on release. This will be @@ -422,7 +423,8 @@ enum BLOCK_IOPOLL_SOFTIRQ, TASKLET_SOFTIRQ, SCHED_SOFTIRQ, - HRTIMER_SOFTIRQ, + HRTIMER_SOFTIRQ, /* Unused, but kept as tools rely on the + numbering. Sigh! */ RCU_SOFTIRQ, /* Preferable RCU should always be the last softirq */ NR_SOFTIRQS @@ -463,6 +465,14 @@ extern void thread_do_softirq(void); extern void open_softirq(int nr, void (*action)(struct softirq_action *)); extern void softirq_init(void); extern void __raise_softirq_irqoff(unsigned int nr); +#ifdef CONFIG_PREEMPT_RT_FULL +extern void __raise_softirq_irqoff_ksoft(unsigned int nr); +#else +static inline void __raise_softirq_irqoff_ksoft(unsigned int nr) +{ + __raise_softirq_irqoff(nr); +} +#endif extern void raise_softirq_irqoff(unsigned int nr); extern void raise_softirq(unsigned int nr); @@ -611,10 +621,10 @@ tasklet_hrtimer_init(struct tasklet_hrtimer *ttimer, clockid_t which_clock, enum hrtimer_mode mode); static inline -int tasklet_hrtimer_start(struct tasklet_hrtimer *ttimer, ktime_t time, - const enum hrtimer_mode mode) +void tasklet_hrtimer_start(struct tasklet_hrtimer *ttimer, ktime_t time, + const enum hrtimer_mode mode) { - return hrtimer_start(&ttimer->timer, time, mode); + hrtimer_start(&ttimer->timer, time, mode); } static inline diff --git a/kernel/include/linux/io-64-nonatomic-hi-lo.h b/kernel/include/linux/io-64-nonatomic-hi-lo.h new file mode 100644 index 000000000..11d7e840d --- /dev/null +++ b/kernel/include/linux/io-64-nonatomic-hi-lo.h @@ -0,0 +1,32 @@ +#ifndef _LINUX_IO_64_NONATOMIC_HI_LO_H_ +#define _LINUX_IO_64_NONATOMIC_HI_LO_H_ + +#include <linux/io.h> +#include <asm-generic/int-ll64.h> + +static inline __u64 hi_lo_readq(const volatile void __iomem *addr) +{ + const volatile u32 __iomem *p = addr; + u32 low, high; + + high = readl(p + 1); + low = readl(p); + + return low + ((u64)high << 32); +} + +static inline void hi_lo_writeq(__u64 val, volatile void __iomem *addr) +{ + writel(val >> 32, addr + 4); + writel(val, addr); +} + +#ifndef readq +#define readq hi_lo_readq +#endif + +#ifndef writeq +#define writeq hi_lo_writeq +#endif + +#endif /* _LINUX_IO_64_NONATOMIC_HI_LO_H_ */ diff --git a/kernel/include/linux/io-64-nonatomic-lo-hi.h b/kernel/include/linux/io-64-nonatomic-lo-hi.h new file mode 100644 index 000000000..1a4315f97 --- /dev/null +++ b/kernel/include/linux/io-64-nonatomic-lo-hi.h @@ -0,0 +1,32 @@ +#ifndef _LINUX_IO_64_NONATOMIC_LO_HI_H_ +#define _LINUX_IO_64_NONATOMIC_LO_HI_H_ + +#include <linux/io.h> +#include <asm-generic/int-ll64.h> + +static inline __u64 lo_hi_readq(const volatile void __iomem *addr) +{ + const volatile u32 __iomem *p = addr; + u32 low, high; + + low = readl(p); + high = readl(p + 1); + + return low + ((u64)high << 32); +} + +static inline void lo_hi_writeq(__u64 val, volatile void __iomem *addr) +{ + writel(val, addr); + writel(val >> 32, addr + 4); +} + +#ifndef readq +#define readq lo_hi_readq +#endif + +#ifndef writeq +#define writeq lo_hi_writeq +#endif + +#endif /* _LINUX_IO_64_NONATOMIC_LO_HI_H_ */ diff --git a/kernel/include/linux/io-mapping.h b/kernel/include/linux/io-mapping.h index c27dde721..e399029b6 100644 --- a/kernel/include/linux/io-mapping.h +++ b/kernel/include/linux/io-mapping.h @@ -21,7 +21,7 @@ #include <linux/types.h> #include <linux/slab.h> #include <linux/bug.h> -#include <asm/io.h> +#include <linux/io.h> #include <asm/page.h> /* diff --git a/kernel/include/linux/io.h b/kernel/include/linux/io.h index 986f2bffe..de64c1e53 100644 --- a/kernel/include/linux/io.h +++ b/kernel/include/linux/io.h @@ -19,10 +19,14 @@ #define _LINUX_IO_H #include <linux/types.h> +#include <linux/init.h> +#include <linux/bug.h> +#include <linux/err.h> #include <asm/io.h> #include <asm/page.h> struct device; +struct resource; __visible void __iowrite32_copy(void __iomem *to, const void *from, size_t count); void __iowrite64_copy(void __iomem *to, const void *from, size_t count); @@ -79,6 +83,27 @@ int check_signature(const volatile void __iomem *io_addr, const unsigned char *signature, int length); void devm_ioremap_release(struct device *dev, void *res); +void *devm_memremap(struct device *dev, resource_size_t offset, + size_t size, unsigned long flags); +void devm_memunmap(struct device *dev, void *addr); + +void *__devm_memremap_pages(struct device *dev, struct resource *res); + +#ifdef CONFIG_ZONE_DEVICE +void *devm_memremap_pages(struct device *dev, struct resource *res); +#else +static inline void *devm_memremap_pages(struct device *dev, struct resource *res) +{ + /* + * Fail attempts to call devm_memremap_pages() without + * ZONE_DEVICE support enabled, this requires callers to fall + * back to plain devm_memremap() based on config + */ + WARN_ON_ONCE(1); + return ERR_PTR(-ENXIO); +} +#endif + /* * Some systems do not have legacy ISA devices. * /dev/port is not a valid interface on these systems. @@ -111,6 +136,22 @@ static inline void arch_phys_wc_del(int handle) } #define arch_phys_wc_add arch_phys_wc_add +#ifndef arch_phys_wc_index +static inline int arch_phys_wc_index(int handle) +{ + return -1; +} +#define arch_phys_wc_index arch_phys_wc_index #endif +#endif + +enum { + /* See memremap() kernel-doc for usage description... */ + MEMREMAP_WB = 1 << 0, + MEMREMAP_WT = 1 << 1, +}; + +void *memremap(resource_size_t offset, size_t size, unsigned long flags); +void memunmap(void *addr); #endif /* _LINUX_IO_H */ diff --git a/kernel/include/linux/iommu-common.h b/kernel/include/linux/iommu-common.h index bbced83b3..376a27c9c 100644 --- a/kernel/include/linux/iommu-common.h +++ b/kernel/include/linux/iommu-common.h @@ -7,6 +7,7 @@ #define IOMMU_POOL_HASHBITS 4 #define IOMMU_NR_POOLS (1 << IOMMU_POOL_HASHBITS) +#define IOMMU_ERROR_CODE (~(unsigned long) 0) struct iommu_pool { unsigned long start; diff --git a/kernel/include/linux/iommu.h b/kernel/include/linux/iommu.h index 0546b8710..f28dff313 100644 --- a/kernel/include/linux/iommu.h +++ b/kernel/include/linux/iommu.h @@ -81,6 +81,7 @@ struct iommu_domain { iommu_fault_handler_t handler; void *handler_token; struct iommu_domain_geometry geometry; + void *iova_cookie; }; enum iommu_cap { @@ -114,6 +115,20 @@ enum iommu_attr { DOMAIN_ATTR_MAX, }; +/** + * struct iommu_dm_region - descriptor for a direct mapped memory region + * @list: Linked list pointers + * @start: System physical start address of the region + * @length: Length of the region in bytes + * @prot: IOMMU Protection flags (READ/WRITE/...) + */ +struct iommu_dm_region { + struct list_head list; + phys_addr_t start; + size_t length; + int prot; +}; + #ifdef CONFIG_IOMMU_API /** @@ -153,12 +168,16 @@ struct iommu_ops { phys_addr_t (*iova_to_phys)(struct iommu_domain *domain, dma_addr_t iova); int (*add_device)(struct device *dev); void (*remove_device)(struct device *dev); - int (*device_group)(struct device *dev, unsigned int *groupid); + struct iommu_group *(*device_group)(struct device *dev); int (*domain_get_attr)(struct iommu_domain *domain, enum iommu_attr attr, void *data); int (*domain_set_attr)(struct iommu_domain *domain, enum iommu_attr attr, void *data); + /* Request/Free a list of direct mapping requirements for a device */ + void (*get_dm_regions)(struct device *dev, struct list_head *list); + void (*put_dm_regions)(struct device *dev, struct list_head *list); + /* Window handling functions */ int (*domain_window_enable)(struct iommu_domain *domain, u32 wnd_nr, phys_addr_t paddr, u64 size, int prot); @@ -193,6 +212,7 @@ extern int iommu_attach_device(struct iommu_domain *domain, struct device *dev); extern void iommu_detach_device(struct iommu_domain *domain, struct device *dev); +extern struct iommu_domain *iommu_get_domain_for_dev(struct device *dev); extern int iommu_map(struct iommu_domain *domain, unsigned long iova, phys_addr_t paddr, size_t size, int prot); extern size_t iommu_unmap(struct iommu_domain *domain, unsigned long iova, @@ -204,6 +224,10 @@ extern phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, dma_addr_t io extern void iommu_set_fault_handler(struct iommu_domain *domain, iommu_fault_handler_t handler, void *token); +extern void iommu_get_dm_regions(struct device *dev, struct list_head *list); +extern void iommu_put_dm_regions(struct device *dev, struct list_head *list); +extern int iommu_request_dm_for_dev(struct device *dev); + extern int iommu_attach_group(struct iommu_domain *domain, struct iommu_group *group); extern void iommu_detach_group(struct iommu_domain *domain, @@ -227,6 +251,7 @@ extern int iommu_group_unregister_notifier(struct iommu_group *group, struct notifier_block *nb); extern int iommu_group_id(struct iommu_group *group); extern struct iommu_group *iommu_group_get_for_dev(struct device *dev); +extern struct iommu_domain *iommu_group_default_domain(struct iommu_group *); extern int iommu_domain_get_attr(struct iommu_domain *domain, enum iommu_attr, void *data); @@ -234,7 +259,7 @@ extern int iommu_domain_set_attr(struct iommu_domain *domain, enum iommu_attr, void *data); struct device *iommu_device_create(struct device *parent, void *drvdata, const struct attribute_group **groups, - const char *fmt, ...); + const char *fmt, ...) __printf(4, 5); void iommu_device_destroy(struct device *dev); int iommu_device_link(struct device *dev, struct device *link); void iommu_device_unlink(struct device *dev, struct device *link); @@ -292,6 +317,11 @@ static inline size_t iommu_map_sg(struct iommu_domain *domain, return domain->ops->map_sg(domain, iova, sg, nents, prot); } +/* PCI device grouping function */ +extern struct iommu_group *pci_device_group(struct device *dev); +/* Generic device grouping function */ +extern struct iommu_group *generic_device_group(struct device *dev); + #else /* CONFIG_IOMMU_API */ struct iommu_ops {}; @@ -332,6 +362,11 @@ static inline void iommu_detach_device(struct iommu_domain *domain, { } +static inline struct iommu_domain *iommu_get_domain_for_dev(struct device *dev) +{ + return NULL; +} + static inline int iommu_map(struct iommu_domain *domain, unsigned long iova, phys_addr_t paddr, int gfp_order, int prot) { @@ -373,6 +408,21 @@ static inline void iommu_set_fault_handler(struct iommu_domain *domain, { } +static inline void iommu_get_dm_regions(struct device *dev, + struct list_head *list) +{ +} + +static inline void iommu_put_dm_regions(struct device *dev, + struct list_head *list) +{ +} + +static inline int iommu_request_dm_for_dev(struct device *dev) +{ + return -ENODEV; +} + static inline int iommu_attach_group(struct iommu_domain *domain, struct iommu_group *group) { diff --git a/kernel/include/linux/ioport.h b/kernel/include/linux/ioport.h index 388e3ae94..24bea087e 100644 --- a/kernel/include/linux/ioport.h +++ b/kernel/include/linux/ioport.h @@ -94,6 +94,7 @@ struct resource { /* PnP I/O specific bits (IORESOURCE_BITS) */ #define IORESOURCE_IO_16BIT_ADDR (1<<0) #define IORESOURCE_IO_FIXED (1<<1) +#define IORESOURCE_IO_SPARSE (1<<2) /* PCI ROM control bits (IORESOURCE_BITS) */ #define IORESOURCE_ROM_ENABLE (1<<0) /* ROM is enabled, same as PCI_ROM_ADDRESS_ENABLE */ diff --git a/kernel/include/linux/iova.h b/kernel/include/linux/iova.h index 3920a19d8..92f7177db 100644 --- a/kernel/include/linux/iova.h +++ b/kernel/include/linux/iova.h @@ -68,8 +68,8 @@ static inline unsigned long iova_pfn(struct iova_domain *iovad, dma_addr_t iova) return iova >> iova_shift(iovad); } -int iommu_iova_cache_init(void); -void iommu_iova_cache_destroy(void); +int iova_cache_get(void); +void iova_cache_put(void); struct iova *alloc_iova_mem(void); void free_iova_mem(struct iova *iova); diff --git a/kernel/include/linux/ipmi_smi.h b/kernel/include/linux/ipmi_smi.h index 0b1e569f5..f8cea1448 100644 --- a/kernel/include/linux/ipmi_smi.h +++ b/kernel/include/linux/ipmi_smi.h @@ -115,6 +115,11 @@ struct ipmi_smi_handlers { implement it. */ void (*set_need_watch)(void *send_info, bool enable); + /* + * Called when flushing all pending messages. + */ + void (*flush_messages)(void *send_info); + /* Called when the interface should go into "run to completion" mode. If this call sets the value to true, the interface should make sure that all messages are flushed @@ -207,7 +212,7 @@ static inline int ipmi_demangle_device_id(const unsigned char *data, upper layer until the start_processing() function in the handlers is called, and the lower layer must get the interface from that call. */ -int ipmi_register_smi(struct ipmi_smi_handlers *handlers, +int ipmi_register_smi(const struct ipmi_smi_handlers *handlers, void *send_info, struct ipmi_device_id *device_id, struct device *dev, diff --git a/kernel/include/linux/ipv6.h b/kernel/include/linux/ipv6.h index 82806c60a..402753bcc 100644 --- a/kernel/include/linux/ipv6.h +++ b/kernel/include/linux/ipv6.h @@ -29,7 +29,9 @@ struct ipv6_devconf { __s32 max_desync_factor; __s32 max_addresses; __s32 accept_ra_defrtr; + __s32 accept_ra_min_hop_limit; __s32 accept_ra_pinfo; + __s32 ignore_routes_with_linkdown; #ifdef CONFIG_IPV6_ROUTER_PREF __s32 accept_ra_rtr_pref; __s32 rtr_probe_interval; @@ -57,6 +59,7 @@ struct ipv6_devconf { bool initialized; struct in6_addr secret; } stable_secret; + __s32 use_oif_addrs_only; void *sysctl; }; @@ -94,7 +97,6 @@ static inline struct ipv6hdr *ipipv6_hdr(const struct sk_buff *skb) struct inet6_skb_parm { int iif; __be16 ra; - __u16 hop; __u16 dst0; __u16 srcrt; __u16 dst1; @@ -111,6 +113,7 @@ struct inet6_skb_parm { #define IP6SKB_REROUTED 4 #define IP6SKB_ROUTERALERT 8 #define IP6SKB_FRAGMENTED 16 +#define IP6SKB_HOPBYHOP 32 }; #define IP6CB(skb) ((struct inet6_skb_parm*)((skb)->cb)) @@ -224,7 +227,7 @@ struct ipv6_pinfo { struct ipv6_ac_socklist *ipv6_ac_list; struct ipv6_fl_socklist __rcu *ipv6_fl_list; - struct ipv6_txoptions *opt; + struct ipv6_txoptions __rcu *opt; struct sk_buff *pktoptions; struct sk_buff *rxpmtu; struct inet6_cork cork; @@ -261,9 +264,9 @@ struct tcp6_timewait_sock { }; #if IS_ENABLED(CONFIG_IPV6) -static inline struct ipv6_pinfo * inet6_sk(const struct sock *__sk) +static inline struct ipv6_pinfo *inet6_sk(const struct sock *__sk) { - return inet_sk(__sk)->pinet6; + return sk_fullsock(__sk) ? inet_sk(__sk)->pinet6 : NULL; } static inline struct raw6_sock *raw6_sk(const struct sock *sk) diff --git a/kernel/include/linux/irq.h b/kernel/include/linux/irq.h index 38ecc0c4a..311d3f061 100644 --- a/kernel/include/linux/irq.h +++ b/kernel/include/linux/irq.h @@ -67,12 +67,13 @@ enum irqchip_irq_state; * request/setup_irq() * IRQ_NO_BALANCING - Interrupt cannot be balanced (affinity set) * IRQ_MOVE_PCNTXT - Interrupt can be migrated from process context - * IRQ_NESTED_TRHEAD - Interrupt nests into another thread + * IRQ_NESTED_THREAD - Interrupt nests into another thread * IRQ_PER_CPU_DEVID - Dev_id is a per-cpu variable * IRQ_IS_POLLED - Always polled by another interrupt. Exclude * it from the spurious interrupt detection * mechanism and from core side polling. * IRQ_NO_SOFTIRQ_CALL - No softirq processing in the irq thread context (RT) + * IRQ_DISABLE_UNLAZY - Disable lazy irq disable */ enum { IRQ_TYPE_NONE = 0x00000000, @@ -98,22 +99,23 @@ enum { IRQ_NOTHREAD = (1 << 16), IRQ_PER_CPU_DEVID = (1 << 17), IRQ_IS_POLLED = (1 << 18), - IRQ_NO_SOFTIRQ_CALL = (1 << 19), + IRQ_DISABLE_UNLAZY = (1 << 19), + IRQ_NO_SOFTIRQ_CALL = (1 << 20), }; #define IRQF_MODIFY_MASK \ (IRQ_TYPE_SENSE_MASK | IRQ_NOPROBE | IRQ_NOREQUEST | \ IRQ_NOAUTOEN | IRQ_MOVE_PCNTXT | IRQ_LEVEL | IRQ_NO_BALANCING | \ IRQ_PER_CPU | IRQ_NESTED_THREAD | IRQ_NOTHREAD | IRQ_PER_CPU_DEVID | \ - IRQ_IS_POLLED | IRQ_NO_SOFTIRQ_CALL) + IRQ_IS_POLLED | IRQ_DISABLE_UNLAZY | IRQ_NO_SOFTIRQ_CALL) #define IRQ_NO_BALANCING_MASK (IRQ_PER_CPU | IRQ_NO_BALANCING) /* * Return value for chip->irq_set_affinity() * - * IRQ_SET_MASK_OK - OK, core updates irq_data.affinity - * IRQ_SET_MASK_NOCPY - OK, chip did update irq_data.affinity + * IRQ_SET_MASK_OK - OK, core updates irq_common_data.affinity + * IRQ_SET_MASK_NOCPY - OK, chip did update irq_common_data.affinity * IRQ_SET_MASK_OK_DONE - Same as IRQ_SET_MASK_OK for core. Special code to * support stacked irqchips, which indicates skipping * all descendent irqchips. @@ -128,47 +130,53 @@ struct msi_desc; struct irq_domain; /** - * struct irq_data - per irq and irq chip data passed down to chip functions + * struct irq_common_data - per irq data shared by all irqchips + * @state_use_accessors: status information for irq chip functions. + * Use accessor functions to deal with it + * @node: node index useful for balancing + * @handler_data: per-IRQ data for the irq_chip methods + * @affinity: IRQ affinity on SMP + * @msi_desc: MSI descriptor + */ +struct irq_common_data { + unsigned int state_use_accessors; +#ifdef CONFIG_NUMA + unsigned int node; +#endif + void *handler_data; + struct msi_desc *msi_desc; + cpumask_var_t affinity; +}; + +/** + * struct irq_data - per irq chip data passed down to chip functions * @mask: precomputed bitmask for accessing the chip registers * @irq: interrupt number * @hwirq: hardware interrupt number, local to the interrupt domain - * @node: node index useful for balancing - * @state_use_accessors: status information for irq chip functions. - * Use accessor functions to deal with it + * @common: point to data shared by all irqchips * @chip: low level interrupt hardware access * @domain: Interrupt translation domain; responsible for mapping * between hwirq number and linux irq number. * @parent_data: pointer to parent struct irq_data to support hierarchy * irq_domain - * @handler_data: per-IRQ data for the irq_chip methods * @chip_data: platform-specific per-chip private data for the chip * methods, to allow shared chip implementations - * @msi_desc: MSI descriptor - * @affinity: IRQ affinity on SMP - * - * The fields here need to overlay the ones in irq_desc until we - * cleaned up the direct references and switched everything over to - * irq_data. */ struct irq_data { u32 mask; unsigned int irq; unsigned long hwirq; - unsigned int node; - unsigned int state_use_accessors; + struct irq_common_data *common; struct irq_chip *chip; struct irq_domain *domain; #ifdef CONFIG_IRQ_DOMAIN_HIERARCHY struct irq_data *parent_data; #endif - void *handler_data; void *chip_data; - struct msi_desc *msi_desc; - cpumask_var_t affinity; }; /* - * Bit masks for irq_data.state + * Bit masks for irq_common_data.state_use_accessors * * IRQD_TRIGGER_MASK - Mask for the trigger type bits * IRQD_SETAFFINITY_PENDING - Affinity setting is pending @@ -184,6 +192,7 @@ struct irq_data { * IRQD_IRQ_MASKED - Masked state of the interrupt * IRQD_IRQ_INPROGRESS - In progress state of the interrupt * IRQD_WAKEUP_ARMED - Wakeup mode armed + * IRQD_FORWARDED_TO_VCPU - The interrupt is forwarded to a VCPU */ enum { IRQD_TRIGGER_MASK = 0xf, @@ -198,36 +207,39 @@ enum { IRQD_IRQ_MASKED = (1 << 17), IRQD_IRQ_INPROGRESS = (1 << 18), IRQD_WAKEUP_ARMED = (1 << 19), + IRQD_FORWARDED_TO_VCPU = (1 << 20), }; +#define __irqd_to_state(d) ((d)->common->state_use_accessors) + static inline bool irqd_is_setaffinity_pending(struct irq_data *d) { - return d->state_use_accessors & IRQD_SETAFFINITY_PENDING; + return __irqd_to_state(d) & IRQD_SETAFFINITY_PENDING; } static inline bool irqd_is_per_cpu(struct irq_data *d) { - return d->state_use_accessors & IRQD_PER_CPU; + return __irqd_to_state(d) & IRQD_PER_CPU; } static inline bool irqd_can_balance(struct irq_data *d) { - return !(d->state_use_accessors & (IRQD_PER_CPU | IRQD_NO_BALANCING)); + return !(__irqd_to_state(d) & (IRQD_PER_CPU | IRQD_NO_BALANCING)); } static inline bool irqd_affinity_was_set(struct irq_data *d) { - return d->state_use_accessors & IRQD_AFFINITY_SET; + return __irqd_to_state(d) & IRQD_AFFINITY_SET; } static inline void irqd_mark_affinity_was_set(struct irq_data *d) { - d->state_use_accessors |= IRQD_AFFINITY_SET; + __irqd_to_state(d) |= IRQD_AFFINITY_SET; } static inline u32 irqd_get_trigger_type(struct irq_data *d) { - return d->state_use_accessors & IRQD_TRIGGER_MASK; + return __irqd_to_state(d) & IRQD_TRIGGER_MASK; } /* @@ -235,59 +247,58 @@ static inline u32 irqd_get_trigger_type(struct irq_data *d) */ static inline void irqd_set_trigger_type(struct irq_data *d, u32 type) { - d->state_use_accessors &= ~IRQD_TRIGGER_MASK; - d->state_use_accessors |= type & IRQD_TRIGGER_MASK; + __irqd_to_state(d) &= ~IRQD_TRIGGER_MASK; + __irqd_to_state(d) |= type & IRQD_TRIGGER_MASK; } static inline bool irqd_is_level_type(struct irq_data *d) { - return d->state_use_accessors & IRQD_LEVEL; + return __irqd_to_state(d) & IRQD_LEVEL; } static inline bool irqd_is_wakeup_set(struct irq_data *d) { - return d->state_use_accessors & IRQD_WAKEUP_STATE; + return __irqd_to_state(d) & IRQD_WAKEUP_STATE; } static inline bool irqd_can_move_in_process_context(struct irq_data *d) { - return d->state_use_accessors & IRQD_MOVE_PCNTXT; + return __irqd_to_state(d) & IRQD_MOVE_PCNTXT; } static inline bool irqd_irq_disabled(struct irq_data *d) { - return d->state_use_accessors & IRQD_IRQ_DISABLED; + return __irqd_to_state(d) & IRQD_IRQ_DISABLED; } static inline bool irqd_irq_masked(struct irq_data *d) { - return d->state_use_accessors & IRQD_IRQ_MASKED; + return __irqd_to_state(d) & IRQD_IRQ_MASKED; } static inline bool irqd_irq_inprogress(struct irq_data *d) { - return d->state_use_accessors & IRQD_IRQ_INPROGRESS; + return __irqd_to_state(d) & IRQD_IRQ_INPROGRESS; } static inline bool irqd_is_wakeup_armed(struct irq_data *d) { - return d->state_use_accessors & IRQD_WAKEUP_ARMED; + return __irqd_to_state(d) & IRQD_WAKEUP_ARMED; } +static inline bool irqd_is_forwarded_to_vcpu(struct irq_data *d) +{ + return __irqd_to_state(d) & IRQD_FORWARDED_TO_VCPU; +} -/* - * Functions for chained handlers which can be enabled/disabled by the - * standard disable_irq/enable_irq calls. Must be called with - * irq_desc->lock held. - */ -static inline void irqd_set_chained_irq_inprogress(struct irq_data *d) +static inline void irqd_set_forwarded_to_vcpu(struct irq_data *d) { - d->state_use_accessors |= IRQD_IRQ_INPROGRESS; + __irqd_to_state(d) |= IRQD_FORWARDED_TO_VCPU; } -static inline void irqd_clr_chained_irq_inprogress(struct irq_data *d) +static inline void irqd_clr_forwarded_to_vcpu(struct irq_data *d) { - d->state_use_accessors &= ~IRQD_IRQ_INPROGRESS; + __irqd_to_state(d) &= ~IRQD_FORWARDED_TO_VCPU; } static inline irq_hw_number_t irqd_to_hwirq(struct irq_data *d) @@ -316,8 +327,10 @@ static inline irq_hw_number_t irqd_to_hwirq(struct irq_data *d) * @irq_bus_sync_unlock:function to sync and unlock slow bus (i2c) chips * @irq_cpu_online: configure an interrupt source for a secondary CPU * @irq_cpu_offline: un-configure an interrupt source for a secondary CPU - * @irq_suspend: function called from core code on suspend once per chip - * @irq_resume: function called from core code on resume once per chip + * @irq_suspend: function called from core code on suspend once per + * chip, when one or more interrupts are installed + * @irq_resume: function called from core code on resume once per chip, + * when one ore more interrupts are installed * @irq_pm_shutdown: function called from core code on shutdown once per chip * @irq_calc_mask: Optional function to set irq_data.mask for special cases * @irq_print_chip: optional to print special chip info in show_interrupts @@ -329,6 +342,7 @@ static inline irq_hw_number_t irqd_to_hwirq(struct irq_data *d) * @irq_write_msi_msg: optional to write message content for MSI * @irq_get_irqchip_state: return the internal state of an interrupt * @irq_set_irqchip_state: set the internal state of a interrupt + * @irq_set_vcpu_affinity: optional to target a vCPU in a virtual machine * @flags: chip specific flags */ struct irq_chip { @@ -371,6 +385,8 @@ struct irq_chip { int (*irq_get_irqchip_state)(struct irq_data *data, enum irqchip_irq_state which, bool *state); int (*irq_set_irqchip_state)(struct irq_data *data, enum irqchip_irq_state which, bool state); + int (*irq_set_vcpu_affinity)(struct irq_data *data, void *vcpu_info); + unsigned long flags; }; @@ -396,7 +412,6 @@ enum { IRQCHIP_EOI_THREADED = (1 << 6), }; -/* This include will go away once we isolated irq_desc usage to core code */ #include <linux/irqdesc.h> /* @@ -424,6 +439,9 @@ extern void irq_cpu_online(void); extern void irq_cpu_offline(void); extern int irq_set_affinity_locked(struct irq_data *data, const struct cpumask *cpumask, bool force); +extern int irq_set_vcpu_affinity(unsigned int irq, void *vcpu_info); + +extern void irq_migrate_all_off_this_cpu(void); #if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_PENDING_IRQ) void irq_move_irq(struct irq_data *data); @@ -448,18 +466,20 @@ static inline int irq_set_parent(int irq, int parent_irq) * Built-in IRQ handlers for various IRQ types, * callable via desc->handle_irq() */ -extern void handle_level_irq(unsigned int irq, struct irq_desc *desc); -extern void handle_fasteoi_irq(unsigned int irq, struct irq_desc *desc); -extern void handle_edge_irq(unsigned int irq, struct irq_desc *desc); -extern void handle_edge_eoi_irq(unsigned int irq, struct irq_desc *desc); -extern void handle_simple_irq(unsigned int irq, struct irq_desc *desc); -extern void handle_percpu_irq(unsigned int irq, struct irq_desc *desc); -extern void handle_percpu_devid_irq(unsigned int irq, struct irq_desc *desc); -extern void handle_bad_irq(unsigned int irq, struct irq_desc *desc); +extern void handle_level_irq(struct irq_desc *desc); +extern void handle_fasteoi_irq(struct irq_desc *desc); +extern void handle_edge_irq(struct irq_desc *desc); +extern void handle_edge_eoi_irq(struct irq_desc *desc); +extern void handle_simple_irq(struct irq_desc *desc); +extern void handle_percpu_irq(struct irq_desc *desc); +extern void handle_percpu_devid_irq(struct irq_desc *desc); +extern void handle_bad_irq(struct irq_desc *desc); extern void handle_nested_irq(unsigned int irq); extern int irq_chip_compose_msi_msg(struct irq_data *data, struct msi_msg *msg); #ifdef CONFIG_IRQ_DOMAIN_HIERARCHY +extern void irq_chip_enable_parent(struct irq_data *data); +extern void irq_chip_disable_parent(struct irq_data *data); extern void irq_chip_ack_parent(struct irq_data *data); extern int irq_chip_retrigger_hierarchy(struct irq_data *data); extern void irq_chip_mask_parent(struct irq_data *data); @@ -469,12 +489,13 @@ extern int irq_chip_set_affinity_parent(struct irq_data *data, const struct cpumask *dest, bool force); extern int irq_chip_set_wake_parent(struct irq_data *data, unsigned int on); +extern int irq_chip_set_vcpu_affinity_parent(struct irq_data *data, + void *vcpu_info); extern int irq_chip_set_type_parent(struct irq_data *data, unsigned int type); #endif /* Handling of unhandled and spurious interrupts: */ -extern void note_interrupt(unsigned int irq, struct irq_desc *desc, - irqreturn_t action_ret); +extern void note_interrupt(struct irq_desc *desc, irqreturn_t action_ret); /* Enable/disable irq debugging output: */ @@ -520,6 +541,15 @@ irq_set_chained_handler(unsigned int irq, irq_flow_handler_t handle) __irq_set_handler(irq, handle, 1, NULL); } +/* + * Set a highlevel chained flow handler and its data for a given IRQ. + * (a chained handler is automatically enabled and set to + * IRQ_NOREQUEST, IRQ_NOPROBE, and IRQ_NOTHREAD) + */ +void +irq_set_chained_handler_and_data(unsigned int irq, irq_flow_handler_t handle, + void *data); + void irq_modify_status(unsigned int irq, unsigned long clr, unsigned long set); static inline void irq_set_status_flags(unsigned int irq, unsigned long set) @@ -602,23 +632,23 @@ static inline void *irq_data_get_irq_chip_data(struct irq_data *d) static inline void *irq_get_handler_data(unsigned int irq) { struct irq_data *d = irq_get_irq_data(irq); - return d ? d->handler_data : NULL; + return d ? d->common->handler_data : NULL; } static inline void *irq_data_get_irq_handler_data(struct irq_data *d) { - return d->handler_data; + return d->common->handler_data; } static inline struct msi_desc *irq_get_msi_desc(unsigned int irq) { struct irq_data *d = irq_get_irq_data(irq); - return d ? d->msi_desc : NULL; + return d ? d->common->msi_desc : NULL; } -static inline struct msi_desc *irq_data_get_msi(struct irq_data *d) +static inline struct msi_desc *irq_data_get_msi_desc(struct irq_data *d) { - return d->msi_desc; + return d->common->msi_desc; } static inline u32 irq_get_trigger_type(unsigned int irq) @@ -627,6 +657,32 @@ static inline u32 irq_get_trigger_type(unsigned int irq) return d ? irqd_get_trigger_type(d) : 0; } +static inline int irq_common_data_get_node(struct irq_common_data *d) +{ +#ifdef CONFIG_NUMA + return d->node; +#else + return 0; +#endif +} + +static inline int irq_data_get_node(struct irq_data *d) +{ + return irq_common_data_get_node(d->common); +} + +static inline struct cpumask *irq_get_affinity_mask(int irq) +{ + struct irq_data *d = irq_get_irq_data(irq); + + return d ? d->common->affinity : NULL; +} + +static inline struct cpumask *irq_data_get_affinity_mask(struct irq_data *d) +{ + return d->common->affinity; +} + unsigned int arch_dynirq_lower_bound(unsigned int from); int __irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node, @@ -721,6 +777,12 @@ struct irq_chip_type { * @reg_base: Register base address (virtual) * @reg_readl: Alternate I/O accessor (defaults to readl if NULL) * @reg_writel: Alternate I/O accessor (defaults to writel if NULL) + * @suspend: Function called from core code on suspend once per + * chip; can be useful instead of irq_chip::suspend to + * handle chip details even when no interrupts are in use + * @resume: Function called from core code on resume once per chip; + * can be useful instead of irq_chip::suspend to handle + * chip details even when no interrupts are in use * @irq_base: Interrupt base nr for this chip * @irq_cnt: Number of interrupts handled by this chip * @mask_cache: Cached mask register shared between all chip types @@ -747,6 +809,8 @@ struct irq_chip_generic { void __iomem *reg_base; u32 (*reg_readl)(void __iomem *addr); void (*reg_writel)(u32 val, void __iomem *addr); + void (*suspend)(struct irq_chip_generic *gc); + void (*resume)(struct irq_chip_generic *gc); unsigned int irq_base; unsigned int irq_cnt; u32 mask_cache; diff --git a/kernel/include/linux/irq_work.h b/kernel/include/linux/irq_work.h index 0e427a999..2543aab05 100644 --- a/kernel/include/linux/irq_work.h +++ b/kernel/include/linux/irq_work.h @@ -52,4 +52,10 @@ static inline bool irq_work_needs_cpu(void) { return false; } static inline void irq_work_run(void) { } #endif +#if defined(CONFIG_IRQ_WORK) && defined(CONFIG_PREEMPT_RT_FULL) +void irq_work_tick_soft(void); +#else +static inline void irq_work_tick_soft(void) { } +#endif + #endif /* _LINUX_IRQ_WORK_H */ diff --git a/kernel/include/linux/irqbypass.h b/kernel/include/linux/irqbypass.h new file mode 100644 index 000000000..1551b5b2f --- /dev/null +++ b/kernel/include/linux/irqbypass.h @@ -0,0 +1,90 @@ +/* + * IRQ offload/bypass manager + * + * Copyright (C) 2015 Red Hat, Inc. + * Copyright (c) 2015 Linaro Ltd. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#ifndef IRQBYPASS_H +#define IRQBYPASS_H + +#include <linux/list.h> + +struct irq_bypass_consumer; + +/* + * Theory of operation + * + * The IRQ bypass manager is a simple set of lists and callbacks that allows + * IRQ producers (ex. physical interrupt sources) to be matched to IRQ + * consumers (ex. virtualization hardware that allows IRQ bypass or offload) + * via a shared token (ex. eventfd_ctx). Producers and consumers register + * independently. When a token match is found, the optional @stop callback + * will be called for each participant. The pair will then be connected via + * the @add_* callbacks, and finally the optional @start callback will allow + * any final coordination. When either participant is unregistered, the + * process is repeated using the @del_* callbacks in place of the @add_* + * callbacks. Match tokens must be unique per producer/consumer, 1:N pairings + * are not supported. + */ + +/** + * struct irq_bypass_producer - IRQ bypass producer definition + * @node: IRQ bypass manager private list management + * @token: opaque token to match between producer and consumer + * @irq: Linux IRQ number for the producer device + * @add_consumer: Connect the IRQ producer to an IRQ consumer (optional) + * @del_consumer: Disconnect the IRQ producer from an IRQ consumer (optional) + * @stop: Perform any quiesce operations necessary prior to add/del (optional) + * @start: Perform any startup operations necessary after add/del (optional) + * + * The IRQ bypass producer structure represents an interrupt source for + * participation in possible host bypass, for instance an interrupt vector + * for a physical device assigned to a VM. + */ +struct irq_bypass_producer { + struct list_head node; + void *token; + int irq; + int (*add_consumer)(struct irq_bypass_producer *, + struct irq_bypass_consumer *); + void (*del_consumer)(struct irq_bypass_producer *, + struct irq_bypass_consumer *); + void (*stop)(struct irq_bypass_producer *); + void (*start)(struct irq_bypass_producer *); +}; + +/** + * struct irq_bypass_consumer - IRQ bypass consumer definition + * @node: IRQ bypass manager private list management + * @token: opaque token to match between producer and consumer + * @add_producer: Connect the IRQ consumer to an IRQ producer + * @del_producer: Disconnect the IRQ consumer from an IRQ producer + * @stop: Perform any quiesce operations necessary prior to add/del (optional) + * @start: Perform any startup operations necessary after add/del (optional) + * + * The IRQ bypass consumer structure represents an interrupt sink for + * participation in possible host bypass, for instance a hypervisor may + * support offloads to allow bypassing the host entirely or offload + * portions of the interrupt handling to the VM. + */ +struct irq_bypass_consumer { + struct list_head node; + void *token; + int (*add_producer)(struct irq_bypass_consumer *, + struct irq_bypass_producer *); + void (*del_producer)(struct irq_bypass_consumer *, + struct irq_bypass_producer *); + void (*stop)(struct irq_bypass_consumer *); + void (*start)(struct irq_bypass_consumer *); +}; + +int irq_bypass_register_producer(struct irq_bypass_producer *); +void irq_bypass_unregister_producer(struct irq_bypass_producer *); +int irq_bypass_register_consumer(struct irq_bypass_consumer *); +void irq_bypass_unregister_consumer(struct irq_bypass_consumer *); + +#endif /* IRQBYPASS_H */ diff --git a/kernel/include/linux/irqchip.h b/kernel/include/linux/irqchip.h index 14d79131f..89c34b200 100644 --- a/kernel/include/linux/irqchip.h +++ b/kernel/include/linux/irqchip.h @@ -11,6 +11,37 @@ #ifndef _LINUX_IRQCHIP_H #define _LINUX_IRQCHIP_H +#include <linux/acpi.h> +#include <linux/of.h> + +/* + * This macro must be used by the different irqchip drivers to declare + * the association between their DT compatible string and their + * initialization function. + * + * @name: name that must be unique accross all IRQCHIP_DECLARE of the + * same file. + * @compstr: compatible string of the irqchip driver + * @fn: initialization function + */ +#define IRQCHIP_DECLARE(name, compat, fn) OF_DECLARE_2(irqchip, name, compat, fn) + +/* + * This macro must be used by the different irqchip drivers to declare + * the association between their version and their initialization function. + * + * @name: name that must be unique accross all IRQCHIP_ACPI_DECLARE of the + * same file. + * @subtable: Subtable to be identified in MADT + * @validate: Function to be called on that subtable to check its validity. + * Can be NULL. + * @data: data to be checked by the validate function. + * @fn: initialization function + */ +#define IRQCHIP_ACPI_DECLARE(name, subtable, validate, data, fn) \ + ACPI_DECLARE_PROBE_ENTRY(irqchip, name, ACPI_SIG_MADT, \ + subtable, validate, data, fn) + #ifdef CONFIG_IRQCHIP void irqchip_init(void); #else diff --git a/kernel/include/linux/irqchip/arm-gic-acpi.h b/kernel/include/linux/irqchip/arm-gic-acpi.h deleted file mode 100644 index de3419ed3..000000000 --- a/kernel/include/linux/irqchip/arm-gic-acpi.h +++ /dev/null @@ -1,31 +0,0 @@ -/* - * Copyright (C) 2014, Linaro Ltd. - * Author: Tomasz Nowicki <tomasz.nowicki@linaro.org> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#ifndef ARM_GIC_ACPI_H_ -#define ARM_GIC_ACPI_H_ - -#ifdef CONFIG_ACPI - -/* - * Hard code here, we can not get memory size from MADT (but FDT does), - * Actually no need to do that, because this size can be inferred - * from GIC spec. - */ -#define ACPI_GICV2_DIST_MEM_SIZE (SZ_4K) -#define ACPI_GIC_CPU_IF_MEM_SIZE (SZ_8K) - -struct acpi_table_header; - -int gic_v2_acpi_init(struct acpi_table_header *table); -void acpi_gic_init(void); -#else -static inline void acpi_gic_init(void) { } -#endif - -#endif /* ARM_GIC_ACPI_H_ */ diff --git a/kernel/include/linux/irqchip/arm-gic-v3.h b/kernel/include/linux/irqchip/arm-gic-v3.h index ffbc034c8..d5d798b35 100644 --- a/kernel/include/linux/irqchip/arm-gic-v3.h +++ b/kernel/include/linux/irqchip/arm-gic-v3.h @@ -18,8 +18,6 @@ #ifndef __LINUX_IRQCHIP_ARM_GIC_V3_H #define __LINUX_IRQCHIP_ARM_GIC_V3_H -#include <asm/sysreg.h> - /* * Distributor registers. We assume we're running non-secure, with ARE * being set. Secure-only and non-ARE registers are not described. @@ -104,6 +102,8 @@ #define GICR_SYNCR 0x00C0 #define GICR_MOVLPIR 0x0100 #define GICR_MOVALLR 0x0110 +#define GICR_ISACTIVER GICD_ISACTIVER +#define GICR_ICACTIVER GICD_ICACTIVER #define GICR_IDREGS GICD_IDREGS #define GICR_PIDR2 GICD_PIDR2 @@ -229,6 +229,7 @@ #define GITS_BASER_PAGE_SIZE_16K (1UL << GITS_BASER_PAGE_SIZE_SHIFT) #define GITS_BASER_PAGE_SIZE_64K (2UL << GITS_BASER_PAGE_SIZE_SHIFT) #define GITS_BASER_PAGE_SIZE_MASK (3UL << GITS_BASER_PAGE_SIZE_SHIFT) +#define GITS_BASER_PAGES_MAX 256 #define GITS_BASER_TYPE_NONE 0 #define GITS_BASER_TYPE_DEVICE 1 @@ -264,13 +265,16 @@ /* * Hypervisor interface registers (SRE only) */ -#define ICH_LR_VIRTUAL_ID_MASK ((1UL << 32) - 1) +#define ICH_LR_VIRTUAL_ID_MASK ((1ULL << 32) - 1) -#define ICH_LR_EOI (1UL << 41) -#define ICH_LR_GROUP (1UL << 60) -#define ICH_LR_STATE (3UL << 62) -#define ICH_LR_PENDING_BIT (1UL << 62) -#define ICH_LR_ACTIVE_BIT (1UL << 63) +#define ICH_LR_EOI (1ULL << 41) +#define ICH_LR_GROUP (1ULL << 60) +#define ICH_LR_HW (1ULL << 61) +#define ICH_LR_STATE (3ULL << 62) +#define ICH_LR_PENDING_BIT (1ULL << 62) +#define ICH_LR_ACTIVE_BIT (1ULL << 63) +#define ICH_LR_PHYS_ID_SHIFT 32 +#define ICH_LR_PHYS_ID_MASK (0x3ffULL << ICH_LR_PHYS_ID_SHIFT) #define ICH_MISR_EOI (1 << 0) #define ICH_MISR_U (1 << 1) @@ -287,18 +291,8 @@ #define ICH_VMCR_PMR_SHIFT 24 #define ICH_VMCR_PMR_MASK (0xffUL << ICH_VMCR_PMR_SHIFT) -#define ICC_EOIR1_EL1 sys_reg(3, 0, 12, 12, 1) -#define ICC_IAR1_EL1 sys_reg(3, 0, 12, 12, 0) -#define ICC_SGI1R_EL1 sys_reg(3, 0, 12, 11, 5) -#define ICC_PMR_EL1 sys_reg(3, 0, 4, 6, 0) -#define ICC_CTLR_EL1 sys_reg(3, 0, 12, 12, 4) -#define ICC_SRE_EL1 sys_reg(3, 0, 12, 12, 5) -#define ICC_GRPEN1_EL1 sys_reg(3, 0, 12, 12, 7) - #define ICC_IAR1_EL1_SPURIOUS 0x3ff -#define ICC_SRE_EL2 sys_reg(3, 4, 12, 9, 5) - #define ICC_SRE_EL2_SRE (1 << 0) #define ICC_SRE_EL2_ENABLE (1 << 3) @@ -314,53 +308,10 @@ #define ICC_SGI1R_AFFINITY_3_SHIFT 48 #define ICC_SGI1R_AFFINITY_3_MASK (0xffULL << ICC_SGI1R_AFFINITY_1_SHIFT) -/* - * System register definitions - */ -#define ICH_VSEIR_EL2 sys_reg(3, 4, 12, 9, 4) -#define ICH_HCR_EL2 sys_reg(3, 4, 12, 11, 0) -#define ICH_VTR_EL2 sys_reg(3, 4, 12, 11, 1) -#define ICH_MISR_EL2 sys_reg(3, 4, 12, 11, 2) -#define ICH_EISR_EL2 sys_reg(3, 4, 12, 11, 3) -#define ICH_ELSR_EL2 sys_reg(3, 4, 12, 11, 5) -#define ICH_VMCR_EL2 sys_reg(3, 4, 12, 11, 7) - -#define __LR0_EL2(x) sys_reg(3, 4, 12, 12, x) -#define __LR8_EL2(x) sys_reg(3, 4, 12, 13, x) - -#define ICH_LR0_EL2 __LR0_EL2(0) -#define ICH_LR1_EL2 __LR0_EL2(1) -#define ICH_LR2_EL2 __LR0_EL2(2) -#define ICH_LR3_EL2 __LR0_EL2(3) -#define ICH_LR4_EL2 __LR0_EL2(4) -#define ICH_LR5_EL2 __LR0_EL2(5) -#define ICH_LR6_EL2 __LR0_EL2(6) -#define ICH_LR7_EL2 __LR0_EL2(7) -#define ICH_LR8_EL2 __LR8_EL2(0) -#define ICH_LR9_EL2 __LR8_EL2(1) -#define ICH_LR10_EL2 __LR8_EL2(2) -#define ICH_LR11_EL2 __LR8_EL2(3) -#define ICH_LR12_EL2 __LR8_EL2(4) -#define ICH_LR13_EL2 __LR8_EL2(5) -#define ICH_LR14_EL2 __LR8_EL2(6) -#define ICH_LR15_EL2 __LR8_EL2(7) - -#define __AP0Rx_EL2(x) sys_reg(3, 4, 12, 8, x) -#define ICH_AP0R0_EL2 __AP0Rx_EL2(0) -#define ICH_AP0R1_EL2 __AP0Rx_EL2(1) -#define ICH_AP0R2_EL2 __AP0Rx_EL2(2) -#define ICH_AP0R3_EL2 __AP0Rx_EL2(3) - -#define __AP1Rx_EL2(x) sys_reg(3, 4, 12, 9, x) -#define ICH_AP1R0_EL2 __AP1Rx_EL2(0) -#define ICH_AP1R1_EL2 __AP1Rx_EL2(1) -#define ICH_AP1R2_EL2 __AP1Rx_EL2(2) -#define ICH_AP1R3_EL2 __AP1Rx_EL2(3) +#include <asm/arch_gicv3.h> #ifndef __ASSEMBLY__ -#include <linux/stringify.h> - /* * We need a value to serve as a irq-type for LPIs. Choose one that will * hopefully pique the interest of the reviewer. @@ -378,17 +329,27 @@ struct rdists { u64 flags; }; -static inline void gic_write_eoir(u64 irq) -{ - asm volatile("msr_s " __stringify(ICC_EOIR1_EL1) ", %0" : : "r" (irq)); - isb(); -} - struct irq_domain; +struct device_node; int its_cpu_init(void); int its_init(struct device_node *node, struct rdists *rdists, struct irq_domain *domain); +static inline bool gic_enable_sre(void) +{ + u32 val; + + val = gic_read_sre(); + if (val & ICC_SRE_EL1_SRE) + return true; + + val |= ICC_SRE_EL1_SRE; + gic_write_sre(val); + val = gic_read_sre(); + + return !!(val & ICC_SRE_EL1_SRE); +} + #endif #endif diff --git a/kernel/include/linux/irqchip/arm-gic.h b/kernel/include/linux/irqchip/arm-gic.h index 9de976b4f..bae69e5d6 100644 --- a/kernel/include/linux/irqchip/arm-gic.h +++ b/kernel/include/linux/irqchip/arm-gic.h @@ -20,9 +20,13 @@ #define GIC_CPU_ALIAS_BINPOINT 0x1c #define GIC_CPU_ACTIVEPRIO 0xd0 #define GIC_CPU_IDENT 0xfc +#define GIC_CPU_DEACTIVATE 0x1000 #define GICC_ENABLE 0x1 #define GICC_INT_PRI_THRESHOLD 0xf0 + +#define GIC_CPU_CTRL_EOImodeNS (1 << 9) + #define GICC_IAR_INT_ID_MASK 0x3ff #define GICC_INT_SPURIOUS 1023 #define GICC_DIS_BYPASS_MASK 0x1e0 @@ -71,11 +75,12 @@ #define GICH_LR_VIRTUALID (0x3ff << 0) #define GICH_LR_PHYSID_CPUID_SHIFT (10) -#define GICH_LR_PHYSID_CPUID (7 << GICH_LR_PHYSID_CPUID_SHIFT) +#define GICH_LR_PHYSID_CPUID (0x3ff << GICH_LR_PHYSID_CPUID_SHIFT) #define GICH_LR_STATE (3 << 28) #define GICH_LR_PENDING_BIT (1 << 28) #define GICH_LR_ACTIVE_BIT (1 << 29) #define GICH_LR_EOI (1 << 19) +#define GICH_LR_HW (1 << 31) #define GICH_VMCR_CTRL_SHIFT 0 #define GICH_VMCR_CTRL_MASK (0x21f << GICH_VMCR_CTRL_SHIFT) @@ -95,17 +100,11 @@ struct device_node; -void gic_set_irqchip_flags(unsigned long flags); -void gic_init_bases(unsigned int, int, void __iomem *, void __iomem *, - u32 offset, struct device_node *); void gic_cascade_irq(unsigned int gic_nr, unsigned int irq); -void gic_cpu_if_down(void); +int gic_cpu_if_down(unsigned int gic_nr); -static inline void gic_init(unsigned int nr, int start, - void __iomem *dist , void __iomem *cpu) -{ - gic_init_bases(nr, start, dist, cpu, 0, NULL); -} +void gic_init(unsigned int nr, int start, + void __iomem *dist , void __iomem *cpu); int gicv2m_of_init(struct device_node *node, struct irq_domain *parent); diff --git a/kernel/include/linux/irqchip/ingenic.h b/kernel/include/linux/irqchip/ingenic.h new file mode 100644 index 000000000..0ee319a40 --- /dev/null +++ b/kernel/include/linux/irqchip/ingenic.h @@ -0,0 +1,23 @@ +/* + * Copyright (C) 2010, Lars-Peter Clausen <lars@metafoo.de> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + * You should have received a copy of the GNU General Public License along + * with this program; if not, write to the Free Software Foundation, Inc., + * 675 Mass Ave, Cambridge, MA 02139, USA. + * + */ + +#ifndef __LINUX_IRQCHIP_INGENIC_H__ +#define __LINUX_IRQCHIP_INGENIC_H__ + +#include <linux/irq.h> + +extern void ingenic_intc_irq_suspend(struct irq_data *data); +extern void ingenic_intc_irq_resume(struct irq_data *data); + +#endif diff --git a/kernel/include/linux/irqchip/irq-sa11x0.h b/kernel/include/linux/irqchip/irq-sa11x0.h new file mode 100644 index 000000000..15db6829c --- /dev/null +++ b/kernel/include/linux/irqchip/irq-sa11x0.h @@ -0,0 +1,17 @@ +/* + * Generic IRQ handling for the SA11x0. + * + * Copyright (C) 2015 Dmitry Eremin-Solenikov + * Copyright (C) 1999-2001 Nicolas Pitre + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef __INCLUDE_LINUX_IRQCHIP_IRQ_SA11x0_H +#define __INCLUDE_LINUX_IRQCHIP_IRQ_SA11x0_H + +void __init sa11x0_init_irq_nodt(int irq_start, resource_size_t io_start); + +#endif diff --git a/kernel/include/linux/irqchip/mips-gic.h b/kernel/include/linux/irqchip/mips-gic.h index 9b1ad3734..ce824db48 100644 --- a/kernel/include/linux/irqchip/mips-gic.h +++ b/kernel/include/linux/irqchip/mips-gic.h @@ -9,6 +9,7 @@ #define __LINUX_IRQCHIP_MIPS_GIC_H #include <linux/clocksource.h> +#include <linux/ioport.h> #define GIC_MAX_INTRS 256 @@ -41,12 +42,20 @@ /* Shared Global Counter */ #define GIC_SH_COUNTER_31_00_OFS 0x0010 +/* 64-bit counter register for CM3 */ +#define GIC_SH_COUNTER_OFS GIC_SH_COUNTER_31_00_OFS #define GIC_SH_COUNTER_63_32_OFS 0x0014 #define GIC_SH_REVISIONID_OFS 0x0020 /* Convert an interrupt number to a byte offset/bit for multi-word registers */ -#define GIC_INTR_OFS(intr) (((intr) / 32) * 4) -#define GIC_INTR_BIT(intr) ((intr) % 32) +#define GIC_INTR_OFS(intr) ({ \ + unsigned bits = mips_cm_is64 ? 64 : 32; \ + unsigned reg_idx = (intr) / bits; \ + unsigned reg_width = bits / 8; \ + \ + reg_idx * reg_width; \ +}) +#define GIC_INTR_BIT(intr) ((intr) % (mips_cm_is64 ? 64 : 32)) /* Polarity : Reset Value is always 0 */ #define GIC_SH_SET_POLARITY_OFS 0x0100 @@ -98,6 +107,8 @@ #define GIC_VPE_WD_COUNT0_OFS 0x0094 #define GIC_VPE_WD_INITIAL0_OFS 0x0098 #define GIC_VPE_COMPARE_LO_OFS 0x00a0 +/* 64-bit Compare register on CM3 */ +#define GIC_VPE_COMPARE_OFS GIC_VPE_COMPARE_LO_OFS #define GIC_VPE_COMPARE_HI_OFS 0x00a4 #define GIC_VPE_EIC_SHADOW_SET_BASE_OFS 0x0100 @@ -235,6 +246,8 @@ #define GIC_SHARED_TO_HWIRQ(x) (GIC_SHARED_HWIRQ_BASE + (x)) #define GIC_HWIRQ_TO_SHARED(x) ((x) - GIC_SHARED_HWIRQ_BASE) +#ifdef CONFIG_MIPS_GIC + extern unsigned int gic_present; extern void gic_init(unsigned long gic_base_addr, @@ -254,4 +267,18 @@ extern unsigned int plat_ipi_resched_int_xlate(unsigned int); extern int gic_get_c0_compare_int(void); extern int gic_get_c0_perfcount_int(void); extern int gic_get_c0_fdc_int(void); +extern int gic_get_usm_range(struct resource *gic_usm_res); + +#else /* CONFIG_MIPS_GIC */ + +#define gic_present 0 + +static inline int gic_get_usm_range(struct resource *gic_usm_res) +{ + /* Shouldn't be called. */ + return -1; +} + +#endif /* CONFIG_MIPS_GIC */ + #endif /* __LINUX_IRQCHIP_MIPS_GIC_H */ diff --git a/kernel/include/linux/irqdesc.h b/kernel/include/linux/irqdesc.h index 9d97cd5bb..ad57402a2 100644 --- a/kernel/include/linux/irqdesc.h +++ b/kernel/include/linux/irqdesc.h @@ -3,9 +3,6 @@ /* * Core internal functions to deal with irq descriptors - * - * This include will move to kernel/irq once we cleaned up the tree. - * For now it's included from <linux/irq.h> */ struct irq_affinity_notify; @@ -17,7 +14,7 @@ struct pt_regs; /** * struct irq_desc - interrupt descriptor - * @irq_data: per irq and chip data passed down to chip functions + * @irq_common_data: per irq and chip data passed down to chip functions * @kstat_irqs: irq stats per cpu * @handle_irq: highlevel irq-events handler * @preflow_handler: handler called before the flow handler (currently used by sparc) @@ -47,6 +44,7 @@ struct pt_regs; * @name: flow handler name for /proc/interrupts output */ struct irq_desc { + struct irq_common_data irq_common_data; struct irq_data irq_data; unsigned int __percpu *kstat_irqs; irq_flow_handler_t handle_irq; @@ -90,10 +88,25 @@ struct irq_desc { const char *name; } ____cacheline_internodealigned_in_smp; -#ifndef CONFIG_SPARSE_IRQ +#ifdef CONFIG_SPARSE_IRQ +extern void irq_lock_sparse(void); +extern void irq_unlock_sparse(void); +#else +static inline void irq_lock_sparse(void) { } +static inline void irq_unlock_sparse(void) { } extern struct irq_desc irq_desc[NR_IRQS]; #endif +static inline struct irq_desc *irq_data_to_desc(struct irq_data *data) +{ + return container_of(data->common, struct irq_desc, irq_common_data); +} + +static inline unsigned int irq_desc_get_irq(struct irq_desc *desc) +{ + return desc->irq_data.irq; +} + static inline struct irq_data *irq_desc_get_irq_data(struct irq_desc *desc) { return &desc->irq_data; @@ -111,23 +124,21 @@ static inline void *irq_desc_get_chip_data(struct irq_desc *desc) static inline void *irq_desc_get_handler_data(struct irq_desc *desc) { - return desc->irq_data.handler_data; + return desc->irq_common_data.handler_data; } static inline struct msi_desc *irq_desc_get_msi_desc(struct irq_desc *desc) { - return desc->irq_data.msi_desc; + return desc->irq_common_data.msi_desc; } /* * Architectures call this to let the generic IRQ layer - * handle an interrupt. If the descriptor is attached to an - * irqchip-style controller then we call the ->handle_irq() handler, - * and it calls __do_IRQ() if it's attached to an irqtype-style controller. + * handle an interrupt. */ -static inline void generic_handle_irq_desc(unsigned int irq, struct irq_desc *desc) +static inline void generic_handle_irq_desc(struct irq_desc *desc) { - desc->handle_irq(irq, desc); + desc->handle_irq(desc); } int generic_handle_irq(unsigned int irq); @@ -150,33 +161,55 @@ static inline int handle_domain_irq(struct irq_domain *domain, #endif /* Test to see if a driver has successfully requested an irq */ -static inline int irq_has_action(unsigned int irq) +static inline int irq_desc_has_action(struct irq_desc *desc) { - struct irq_desc *desc = irq_to_desc(irq); return desc->action != NULL; } -/* caller has locked the irq_desc and both params are valid */ -static inline void __irq_set_handler_locked(unsigned int irq, - irq_flow_handler_t handler) +static inline int irq_has_action(unsigned int irq) { - struct irq_desc *desc; + return irq_desc_has_action(irq_to_desc(irq)); +} + +/** + * irq_set_handler_locked - Set irq handler from a locked region + * @data: Pointer to the irq_data structure which identifies the irq + * @handler: Flow control handler function for this interrupt + * + * Sets the handler in the irq descriptor associated to @data. + * + * Must be called with irq_desc locked and valid parameters. Typical + * call site is the irq_set_type() callback. + */ +static inline void irq_set_handler_locked(struct irq_data *data, + irq_flow_handler_t handler) +{ + struct irq_desc *desc = irq_data_to_desc(data); - desc = irq_to_desc(irq); desc->handle_irq = handler; } -/* caller has locked the irq_desc and both params are valid */ +/** + * irq_set_chip_handler_name_locked - Set chip, handler and name from a locked region + * @data: Pointer to the irq_data structure for which the chip is set + * @chip: Pointer to the new irq chip + * @handler: Flow control handler function for this interrupt + * @name: Name of the interrupt + * + * Replace the irq chip at the proper hierarchy level in @data and + * sets the handler and name in the associated irq descriptor. + * + * Must be called with irq_desc locked and valid parameters. + */ static inline void -__irq_set_chip_handler_name_locked(unsigned int irq, struct irq_chip *chip, - irq_flow_handler_t handler, const char *name) +irq_set_chip_handler_name_locked(struct irq_data *data, struct irq_chip *chip, + irq_flow_handler_t handler, const char *name) { - struct irq_desc *desc; + struct irq_desc *desc = irq_data_to_desc(data); - desc = irq_to_desc(irq); - irq_desc_get_irq_data(desc)->chip = chip; desc->handle_irq = handler; desc->name = name; + data->chip = chip; } static inline int irq_balancing_disabled(unsigned int irq) diff --git a/kernel/include/linux/irqdomain.h b/kernel/include/linux/irqdomain.h index 676d7306a..d5e5c5bef 100644 --- a/kernel/include/linux/irqdomain.h +++ b/kernel/include/linux/irqdomain.h @@ -5,9 +5,10 @@ * helpful for interrupt controllers to implement mapping between hardware * irq numbers and the Linux irq number space. * - * irq_domains also have a hook for translating device tree interrupt - * representation into a hardware irq number that can be mapped back to a - * Linux irq number without any extra platform support code. + * irq_domains also have hooks for translating device tree or other + * firmware interrupt representations into a hardware irq number that + * can be mapped back to a Linux irq number without any extra platform + * support code. * * Interrupt controller "domain" data structure. This could be defined as a * irq domain controller. That is, it handles the mapping between hardware @@ -17,16 +18,12 @@ * model). It's the domain callbacks that are responsible for setting the * irq_chip on a given irq_desc after it's been mapped. * - * The host code and data structures are agnostic to whether or not - * we use an open firmware device-tree. We do have references to struct - * device_node in two places: in irq_find_host() to find the host matching - * a given interrupt controller node, and of course as an argument to its - * counterpart domain->ops->match() callback. However, those are treated as - * generic pointers by the core and the fact that it's actually a device-node - * pointer is purely a convention between callers and implementation. This - * code could thus be used on other architectures by replacing those two - * by some sort of arch-specific void * "token" used to identify interrupt - * controllers. + * The host code and data structures use a fwnode_handle pointer to + * identify the domain. In some cases, and in order to preserve source + * code compatibility, this fwnode pointer is "upgraded" to a DT + * device_node. For those firmware infrastructures that do not provide + * a unique identifier for an interrupt controller, the irq_domain + * code offers a fwnode allocator. */ #ifndef _LINUX_IRQDOMAIN_H @@ -34,6 +31,7 @@ #include <linux/types.h> #include <linux/irqhandler.h> +#include <linux/of.h> #include <linux/radix-tree.h> struct device_node; @@ -45,6 +43,38 @@ struct irq_data; /* Number of irqs reserved for a legacy isa controller */ #define NUM_ISA_INTERRUPTS 16 +#define IRQ_DOMAIN_IRQ_SPEC_PARAMS 16 + +/** + * struct irq_fwspec - generic IRQ specifier structure + * + * @fwnode: Pointer to a firmware-specific descriptor + * @param_count: Number of device-specific parameters + * @param: Device-specific parameters + * + * This structure, directly modeled after of_phandle_args, is used to + * pass a device-specific description of an interrupt. + */ +struct irq_fwspec { + struct fwnode_handle *fwnode; + int param_count; + u32 param[IRQ_DOMAIN_IRQ_SPEC_PARAMS]; +}; + +/* + * Should several domains have the same device node, but serve + * different purposes (for example one domain is for PCI/MSI, and the + * other for wired IRQs), they can be distinguished using a + * bus-specific token. Most domains are expected to only carry + * DOMAIN_BUS_ANY. + */ +enum irq_domain_bus_token { + DOMAIN_BUS_ANY = 0, + DOMAIN_BUS_PCI_MSI, + DOMAIN_BUS_PLATFORM_MSI, + DOMAIN_BUS_NEXUS, +}; + /** * struct irq_domain_ops - Methods for irq_domain objects * @match: Match an interrupt controller device node to a host, returns @@ -61,7 +91,8 @@ struct irq_data; * to setup the irq_desc when returning from map(). */ struct irq_domain_ops { - int (*match)(struct irq_domain *d, struct device_node *node); + int (*match)(struct irq_domain *d, struct device_node *node, + enum irq_domain_bus_token bus_token); int (*map)(struct irq_domain *d, unsigned int virq, irq_hw_number_t hw); void (*unmap)(struct irq_domain *d, unsigned int virq); int (*xlate)(struct irq_domain *d, struct device_node *node, @@ -76,6 +107,8 @@ struct irq_domain_ops { unsigned int nr_irqs); void (*activate)(struct irq_domain *d, struct irq_data *irq_data); void (*deactivate)(struct irq_domain *d, struct irq_data *irq_data); + int (*translate)(struct irq_domain *d, struct irq_fwspec *fwspec, + unsigned long *out_hwirq, unsigned int *out_type); #endif }; @@ -115,7 +148,8 @@ struct irq_domain { unsigned int flags; /* Optional data */ - struct device_node *of_node; + struct fwnode_handle *fwnode; + enum irq_domain_bus_token bus_token; struct irq_domain_chip_generic *gc; #ifdef CONFIG_IRQ_DOMAIN_HIERARCHY struct irq_domain *parent; @@ -145,8 +179,15 @@ enum { IRQ_DOMAIN_FLAG_NONCORE = (1 << 16), }; +static inline struct device_node *irq_domain_get_of_node(struct irq_domain *d) +{ + return to_of_node(d->fwnode); +} + #ifdef CONFIG_IRQ_DOMAIN -struct irq_domain *__irq_domain_add(struct device_node *of_node, int size, +struct fwnode_handle *irq_domain_alloc_fwnode(void *data); +void irq_domain_free_fwnode(struct fwnode_handle *fwnode); +struct irq_domain *__irq_domain_add(struct fwnode_handle *fwnode, int size, irq_hw_number_t hwirq_max, int direct_max, const struct irq_domain_ops *ops, void *host_data); @@ -161,9 +202,26 @@ struct irq_domain *irq_domain_add_legacy(struct device_node *of_node, irq_hw_number_t first_hwirq, const struct irq_domain_ops *ops, void *host_data); -extern struct irq_domain *irq_find_host(struct device_node *node); +extern struct irq_domain *irq_find_matching_fwnode(struct fwnode_handle *fwnode, + enum irq_domain_bus_token bus_token); extern void irq_set_default_host(struct irq_domain *host); +static inline struct fwnode_handle *of_node_to_fwnode(struct device_node *node) +{ + return node ? &node->fwnode : NULL; +} + +static inline struct irq_domain *irq_find_matching_host(struct device_node *node, + enum irq_domain_bus_token bus_token) +{ + return irq_find_matching_fwnode(of_node_to_fwnode(node), bus_token); +} + +static inline struct irq_domain *irq_find_host(struct device_node *node) +{ + return irq_find_matching_host(node, DOMAIN_BUS_ANY); +} + /** * irq_domain_add_linear() - Allocate and register a linear revmap irq_domain. * @of_node: pointer to interrupt controller's device tree node. @@ -176,14 +234,14 @@ static inline struct irq_domain *irq_domain_add_linear(struct device_node *of_no const struct irq_domain_ops *ops, void *host_data) { - return __irq_domain_add(of_node, size, size, 0, ops, host_data); + return __irq_domain_add(of_node_to_fwnode(of_node), size, size, 0, ops, host_data); } static inline struct irq_domain *irq_domain_add_nomap(struct device_node *of_node, unsigned int max_irq, const struct irq_domain_ops *ops, void *host_data) { - return __irq_domain_add(of_node, 0, max_irq, max_irq, ops, host_data); + return __irq_domain_add(of_node_to_fwnode(of_node), 0, max_irq, max_irq, ops, host_data); } static inline struct irq_domain *irq_domain_add_legacy_isa( struct device_node *of_node, @@ -197,7 +255,22 @@ static inline struct irq_domain *irq_domain_add_tree(struct device_node *of_node const struct irq_domain_ops *ops, void *host_data) { - return __irq_domain_add(of_node, 0, ~0, 0, ops, host_data); + return __irq_domain_add(of_node_to_fwnode(of_node), 0, ~0, 0, ops, host_data); +} + +static inline struct irq_domain *irq_domain_create_linear(struct fwnode_handle *fwnode, + unsigned int size, + const struct irq_domain_ops *ops, + void *host_data) +{ + return __irq_domain_add(fwnode, size, size, 0, ops, host_data); +} + +static inline struct irq_domain *irq_domain_create_tree(struct fwnode_handle *fwnode, + const struct irq_domain_ops *ops, + void *host_data) +{ + return __irq_domain_add(fwnode, 0, ~0, 0, ops, host_data); } extern void irq_domain_remove(struct irq_domain *host); @@ -212,6 +285,7 @@ extern void irq_domain_disassociate(struct irq_domain *domain, extern unsigned int irq_create_mapping(struct irq_domain *host, irq_hw_number_t hwirq); +extern unsigned int irq_create_fwspec_mapping(struct irq_fwspec *fwspec); extern void irq_dispose_mapping(unsigned int virq); /** @@ -258,11 +332,28 @@ int irq_domain_xlate_onetwocell(struct irq_domain *d, struct device_node *ctrlr, /* V2 interfaces to support hierarchy IRQ domains. */ extern struct irq_data *irq_domain_get_irq_data(struct irq_domain *domain, unsigned int virq); +extern void irq_domain_set_info(struct irq_domain *domain, unsigned int virq, + irq_hw_number_t hwirq, struct irq_chip *chip, + void *chip_data, irq_flow_handler_t handler, + void *handler_data, const char *handler_name); #ifdef CONFIG_IRQ_DOMAIN_HIERARCHY -extern struct irq_domain *irq_domain_add_hierarchy(struct irq_domain *parent, +extern struct irq_domain *irq_domain_create_hierarchy(struct irq_domain *parent, unsigned int flags, unsigned int size, - struct device_node *node, + struct fwnode_handle *fwnode, const struct irq_domain_ops *ops, void *host_data); + +static inline struct irq_domain *irq_domain_add_hierarchy(struct irq_domain *parent, + unsigned int flags, + unsigned int size, + struct device_node *node, + const struct irq_domain_ops *ops, + void *host_data) +{ + return irq_domain_create_hierarchy(parent, flags, size, + of_node_to_fwnode(node), + ops, host_data); +} + extern int __irq_domain_alloc_irqs(struct irq_domain *domain, int irq_base, unsigned int nr_irqs, int node, void *arg, bool realloc); @@ -281,10 +372,6 @@ extern int irq_domain_set_hwirq_and_chip(struct irq_domain *domain, irq_hw_number_t hwirq, struct irq_chip *chip, void *chip_data); -extern void irq_domain_set_info(struct irq_domain *domain, unsigned int virq, - irq_hw_number_t hwirq, struct irq_chip *chip, - void *chip_data, irq_flow_handler_t handler, - void *handler_data, const char *handler_name); extern void irq_domain_reset_irq_data(struct irq_data *irq_data); extern void irq_domain_free_irqs_common(struct irq_domain *domain, unsigned int virq, diff --git a/kernel/include/linux/irqhandler.h b/kernel/include/linux/irqhandler.h index 62d543004..661bed0ed 100644 --- a/kernel/include/linux/irqhandler.h +++ b/kernel/include/linux/irqhandler.h @@ -8,7 +8,7 @@ struct irq_desc; struct irq_data; -typedef void (*irq_flow_handler_t)(unsigned int irq, struct irq_desc *desc); +typedef void (*irq_flow_handler_t)(struct irq_desc *desc); typedef void (*irq_preflow_handler_t)(struct irq_data *data); #endif diff --git a/kernel/include/linux/irqnr.h b/kernel/include/linux/irqnr.h index fdd5cc16c..9669bf9d4 100644 --- a/kernel/include/linux/irqnr.h +++ b/kernel/include/linux/irqnr.h @@ -23,12 +23,6 @@ unsigned int irq_get_next_irq(unsigned int offset); ; \ else -#ifdef CONFIG_SMP -#define irq_node(irq) (irq_get_irq_data(irq)->node) -#else -#define irq_node(irq) 0 -#endif - # define for_each_active_irq(irq) \ for (irq = irq_get_next_irq(0); irq < nr_irqs; \ irq = irq_get_next_irq(irq + 1)) diff --git a/kernel/include/linux/irqreturn.h b/kernel/include/linux/irqreturn.h index e374e369f..eb1bdcf95 100644 --- a/kernel/include/linux/irqreturn.h +++ b/kernel/include/linux/irqreturn.h @@ -3,7 +3,7 @@ /** * enum irqreturn - * @IRQ_NONE interrupt was not from this device + * @IRQ_NONE interrupt was not from this device or was not handled * @IRQ_HANDLED interrupt was handled by this device * @IRQ_WAKE_THREAD handler requests to wake the handler thread */ diff --git a/kernel/include/linux/jbd.h b/kernel/include/linux/jbd.h deleted file mode 100644 index d32615280..000000000 --- a/kernel/include/linux/jbd.h +++ /dev/null @@ -1,1047 +0,0 @@ -/* - * linux/include/linux/jbd.h - * - * Written by Stephen C. Tweedie <sct@redhat.com> - * - * Copyright 1998-2000 Red Hat, Inc --- All Rights Reserved - * - * This file is part of the Linux kernel and is made available under - * the terms of the GNU General Public License, version 2, or at your - * option, any later version, incorporated herein by reference. - * - * Definitions for transaction data structures for the buffer cache - * filesystem journaling support. - */ - -#ifndef _LINUX_JBD_H -#define _LINUX_JBD_H - -/* Allow this file to be included directly into e2fsprogs */ -#ifndef __KERNEL__ -#include "jfs_compat.h" -#define JFS_DEBUG -#define jfs_debug jbd_debug -#else - -#include <linux/types.h> -#include <linux/buffer_head.h> -#include <linux/journal-head.h> -#include <linux/stddef.h> -#include <linux/mutex.h> -#include <linux/timer.h> -#include <linux/lockdep.h> -#include <linux/slab.h> - -#define journal_oom_retry 1 - -/* - * Define JBD_PARANOID_IOFAIL to cause a kernel BUG() if ext3 finds - * certain classes of error which can occur due to failed IOs. Under - * normal use we want ext3 to continue after such errors, because - * hardware _can_ fail, but for debugging purposes when running tests on - * known-good hardware we may want to trap these errors. - */ -#undef JBD_PARANOID_IOFAIL - -/* - * The default maximum commit age, in seconds. - */ -#define JBD_DEFAULT_MAX_COMMIT_AGE 5 - -#ifdef CONFIG_JBD_DEBUG -/* - * Define JBD_EXPENSIVE_CHECKING to enable more expensive internal - * consistency checks. By default we don't do this unless - * CONFIG_JBD_DEBUG is on. - */ -#define JBD_EXPENSIVE_CHECKING -extern u8 journal_enable_debug; - -void __jbd_debug(int level, const char *file, const char *func, - unsigned int line, const char *fmt, ...); - -#define jbd_debug(n, fmt, a...) \ - __jbd_debug((n), __FILE__, __func__, __LINE__, (fmt), ##a) -#else -#define jbd_debug(n, fmt, a...) /**/ -#endif - -static inline void *jbd_alloc(size_t size, gfp_t flags) -{ - return (void *)__get_free_pages(flags, get_order(size)); -} - -static inline void jbd_free(void *ptr, size_t size) -{ - free_pages((unsigned long)ptr, get_order(size)); -} - -#define JFS_MIN_JOURNAL_BLOCKS 1024 - - -/** - * typedef handle_t - The handle_t type represents a single atomic update being performed by some process. - * - * All filesystem modifications made by the process go - * through this handle. Recursive operations (such as quota operations) - * are gathered into a single update. - * - * The buffer credits field is used to account for journaled buffers - * being modified by the running process. To ensure that there is - * enough log space for all outstanding operations, we need to limit the - * number of outstanding buffers possible at any time. When the - * operation completes, any buffer credits not used are credited back to - * the transaction, so that at all times we know how many buffers the - * outstanding updates on a transaction might possibly touch. - * - * This is an opaque datatype. - **/ -typedef struct handle_s handle_t; /* Atomic operation type */ - - -/** - * typedef journal_t - The journal_t maintains all of the journaling state information for a single filesystem. - * - * journal_t is linked to from the fs superblock structure. - * - * We use the journal_t to keep track of all outstanding transaction - * activity on the filesystem, and to manage the state of the log - * writing process. - * - * This is an opaque datatype. - **/ -typedef struct journal_s journal_t; /* Journal control structure */ -#endif - -/* - * Internal structures used by the logging mechanism: - */ - -#define JFS_MAGIC_NUMBER 0xc03b3998U /* The first 4 bytes of /dev/random! */ - -/* - * On-disk structures - */ - -/* - * Descriptor block types: - */ - -#define JFS_DESCRIPTOR_BLOCK 1 -#define JFS_COMMIT_BLOCK 2 -#define JFS_SUPERBLOCK_V1 3 -#define JFS_SUPERBLOCK_V2 4 -#define JFS_REVOKE_BLOCK 5 - -/* - * Standard header for all descriptor blocks: - */ -typedef struct journal_header_s -{ - __be32 h_magic; - __be32 h_blocktype; - __be32 h_sequence; -} journal_header_t; - - -/* - * The block tag: used to describe a single buffer in the journal - */ -typedef struct journal_block_tag_s -{ - __be32 t_blocknr; /* The on-disk block number */ - __be32 t_flags; /* See below */ -} journal_block_tag_t; - -/* - * The revoke descriptor: used on disk to describe a series of blocks to - * be revoked from the log - */ -typedef struct journal_revoke_header_s -{ - journal_header_t r_header; - __be32 r_count; /* Count of bytes used in the block */ -} journal_revoke_header_t; - - -/* Definitions for the journal tag flags word: */ -#define JFS_FLAG_ESCAPE 1 /* on-disk block is escaped */ -#define JFS_FLAG_SAME_UUID 2 /* block has same uuid as previous */ -#define JFS_FLAG_DELETED 4 /* block deleted by this transaction */ -#define JFS_FLAG_LAST_TAG 8 /* last tag in this descriptor block */ - - -/* - * The journal superblock. All fields are in big-endian byte order. - */ -typedef struct journal_superblock_s -{ -/* 0x0000 */ - journal_header_t s_header; - -/* 0x000C */ - /* Static information describing the journal */ - __be32 s_blocksize; /* journal device blocksize */ - __be32 s_maxlen; /* total blocks in journal file */ - __be32 s_first; /* first block of log information */ - -/* 0x0018 */ - /* Dynamic information describing the current state of the log */ - __be32 s_sequence; /* first commit ID expected in log */ - __be32 s_start; /* blocknr of start of log */ - -/* 0x0020 */ - /* Error value, as set by journal_abort(). */ - __be32 s_errno; - -/* 0x0024 */ - /* Remaining fields are only valid in a version-2 superblock */ - __be32 s_feature_compat; /* compatible feature set */ - __be32 s_feature_incompat; /* incompatible feature set */ - __be32 s_feature_ro_compat; /* readonly-compatible feature set */ -/* 0x0030 */ - __u8 s_uuid[16]; /* 128-bit uuid for journal */ - -/* 0x0040 */ - __be32 s_nr_users; /* Nr of filesystems sharing log */ - - __be32 s_dynsuper; /* Blocknr of dynamic superblock copy*/ - -/* 0x0048 */ - __be32 s_max_transaction; /* Limit of journal blocks per trans.*/ - __be32 s_max_trans_data; /* Limit of data blocks per trans. */ - -/* 0x0050 */ - __u32 s_padding[44]; - -/* 0x0100 */ - __u8 s_users[16*48]; /* ids of all fs'es sharing the log */ -/* 0x0400 */ -} journal_superblock_t; - -#define JFS_HAS_COMPAT_FEATURE(j,mask) \ - ((j)->j_format_version >= 2 && \ - ((j)->j_superblock->s_feature_compat & cpu_to_be32((mask)))) -#define JFS_HAS_RO_COMPAT_FEATURE(j,mask) \ - ((j)->j_format_version >= 2 && \ - ((j)->j_superblock->s_feature_ro_compat & cpu_to_be32((mask)))) -#define JFS_HAS_INCOMPAT_FEATURE(j,mask) \ - ((j)->j_format_version >= 2 && \ - ((j)->j_superblock->s_feature_incompat & cpu_to_be32((mask)))) - -#define JFS_FEATURE_INCOMPAT_REVOKE 0x00000001 - -/* Features known to this kernel version: */ -#define JFS_KNOWN_COMPAT_FEATURES 0 -#define JFS_KNOWN_ROCOMPAT_FEATURES 0 -#define JFS_KNOWN_INCOMPAT_FEATURES JFS_FEATURE_INCOMPAT_REVOKE - -#ifdef __KERNEL__ - -#include <linux/fs.h> -#include <linux/sched.h> - -enum jbd_state_bits { - BH_JBD /* Has an attached ext3 journal_head */ - = BH_PrivateStart, - BH_JWrite, /* Being written to log (@@@ DEBUGGING) */ - BH_Freed, /* Has been freed (truncated) */ - BH_Revoked, /* Has been revoked from the log */ - BH_RevokeValid, /* Revoked flag is valid */ - BH_JBDDirty, /* Is dirty but journaled */ - BH_State, /* Pins most journal_head state */ - BH_JournalHead, /* Pins bh->b_private and jh->b_bh */ - BH_Unshadow, /* Dummy bit, for BJ_Shadow wakeup filtering */ - BH_JBDPrivateStart, /* First bit available for private use by FS */ -}; - -BUFFER_FNS(JBD, jbd) -BUFFER_FNS(JWrite, jwrite) -BUFFER_FNS(JBDDirty, jbddirty) -TAS_BUFFER_FNS(JBDDirty, jbddirty) -BUFFER_FNS(Revoked, revoked) -TAS_BUFFER_FNS(Revoked, revoked) -BUFFER_FNS(RevokeValid, revokevalid) -TAS_BUFFER_FNS(RevokeValid, revokevalid) -BUFFER_FNS(Freed, freed) - -#include <linux/jbd_common.h> - -#define J_ASSERT(assert) BUG_ON(!(assert)) - -#define J_ASSERT_BH(bh, expr) J_ASSERT(expr) -#define J_ASSERT_JH(jh, expr) J_ASSERT(expr) - -#if defined(JBD_PARANOID_IOFAIL) -#define J_EXPECT(expr, why...) J_ASSERT(expr) -#define J_EXPECT_BH(bh, expr, why...) J_ASSERT_BH(bh, expr) -#define J_EXPECT_JH(jh, expr, why...) J_ASSERT_JH(jh, expr) -#else -#define __journal_expect(expr, why...) \ - ({ \ - int val = (expr); \ - if (!val) { \ - printk(KERN_ERR \ - "EXT3-fs unexpected failure: %s;\n",# expr); \ - printk(KERN_ERR why "\n"); \ - } \ - val; \ - }) -#define J_EXPECT(expr, why...) __journal_expect(expr, ## why) -#define J_EXPECT_BH(bh, expr, why...) __journal_expect(expr, ## why) -#define J_EXPECT_JH(jh, expr, why...) __journal_expect(expr, ## why) -#endif - -struct jbd_revoke_table_s; - -/** - * struct handle_s - this is the concrete type associated with handle_t. - * @h_transaction: Which compound transaction is this update a part of? - * @h_buffer_credits: Number of remaining buffers we are allowed to dirty. - * @h_ref: Reference count on this handle - * @h_err: Field for caller's use to track errors through large fs operations - * @h_sync: flag for sync-on-close - * @h_jdata: flag to force data journaling - * @h_aborted: flag indicating fatal error on handle - * @h_lockdep_map: lockdep info for debugging lock problems - */ -struct handle_s -{ - /* Which compound transaction is this update a part of? */ - transaction_t *h_transaction; - - /* Number of remaining buffers we are allowed to dirty: */ - int h_buffer_credits; - - /* Reference count on this handle */ - int h_ref; - - /* Field for caller's use to track errors through large fs */ - /* operations */ - int h_err; - - /* Flags [no locking] */ - unsigned int h_sync: 1; /* sync-on-close */ - unsigned int h_jdata: 1; /* force data journaling */ - unsigned int h_aborted: 1; /* fatal error on handle */ - -#ifdef CONFIG_DEBUG_LOCK_ALLOC - struct lockdep_map h_lockdep_map; -#endif -}; - - -/* The transaction_t type is the guts of the journaling mechanism. It - * tracks a compound transaction through its various states: - * - * RUNNING: accepting new updates - * LOCKED: Updates still running but we don't accept new ones - * RUNDOWN: Updates are tidying up but have finished requesting - * new buffers to modify (state not used for now) - * FLUSH: All updates complete, but we are still writing to disk - * COMMIT: All data on disk, writing commit record - * FINISHED: We still have to keep the transaction for checkpointing. - * - * The transaction keeps track of all of the buffers modified by a - * running transaction, and all of the buffers committed but not yet - * flushed to home for finished transactions. - */ - -/* - * Lock ranking: - * - * j_list_lock - * ->jbd_lock_bh_journal_head() (This is "innermost") - * - * j_state_lock - * ->jbd_lock_bh_state() - * - * jbd_lock_bh_state() - * ->j_list_lock - * - * j_state_lock - * ->t_handle_lock - * - * j_state_lock - * ->j_list_lock (journal_unmap_buffer) - * - */ - -struct transaction_s -{ - /* Pointer to the journal for this transaction. [no locking] */ - journal_t *t_journal; - - /* Sequence number for this transaction [no locking] */ - tid_t t_tid; - - /* - * Transaction's current state - * [no locking - only kjournald alters this] - * [j_list_lock] guards transition of a transaction into T_FINISHED - * state and subsequent call of __journal_drop_transaction() - * FIXME: needs barriers - * KLUDGE: [use j_state_lock] - */ - enum { - T_RUNNING, - T_LOCKED, - T_FLUSH, - T_COMMIT, - T_COMMIT_RECORD, - T_FINISHED - } t_state; - - /* - * Where in the log does this transaction's commit start? [no locking] - */ - unsigned int t_log_start; - - /* Number of buffers on the t_buffers list [j_list_lock] */ - int t_nr_buffers; - - /* - * Doubly-linked circular list of all buffers reserved but not yet - * modified by this transaction [j_list_lock] - */ - struct journal_head *t_reserved_list; - - /* - * Doubly-linked circular list of all buffers under writeout during - * commit [j_list_lock] - */ - struct journal_head *t_locked_list; - - /* - * Doubly-linked circular list of all metadata buffers owned by this - * transaction [j_list_lock] - */ - struct journal_head *t_buffers; - - /* - * Doubly-linked circular list of all data buffers still to be - * flushed before this transaction can be committed [j_list_lock] - */ - struct journal_head *t_sync_datalist; - - /* - * Doubly-linked circular list of all forget buffers (superseded - * buffers which we can un-checkpoint once this transaction commits) - * [j_list_lock] - */ - struct journal_head *t_forget; - - /* - * Doubly-linked circular list of all buffers still to be flushed before - * this transaction can be checkpointed. [j_list_lock] - */ - struct journal_head *t_checkpoint_list; - - /* - * Doubly-linked circular list of all buffers submitted for IO while - * checkpointing. [j_list_lock] - */ - struct journal_head *t_checkpoint_io_list; - - /* - * Doubly-linked circular list of temporary buffers currently undergoing - * IO in the log [j_list_lock] - */ - struct journal_head *t_iobuf_list; - - /* - * Doubly-linked circular list of metadata buffers being shadowed by log - * IO. The IO buffers on the iobuf list and the shadow buffers on this - * list match each other one for one at all times. [j_list_lock] - */ - struct journal_head *t_shadow_list; - - /* - * Doubly-linked circular list of control buffers being written to the - * log. [j_list_lock] - */ - struct journal_head *t_log_list; - - /* - * Protects info related to handles - */ - spinlock_t t_handle_lock; - - /* - * Number of outstanding updates running on this transaction - * [t_handle_lock] - */ - int t_updates; - - /* - * Number of buffers reserved for use by all handles in this transaction - * handle but not yet modified. [t_handle_lock] - */ - int t_outstanding_credits; - - /* - * Forward and backward links for the circular list of all transactions - * awaiting checkpoint. [j_list_lock] - */ - transaction_t *t_cpnext, *t_cpprev; - - /* - * When will the transaction expire (become due for commit), in jiffies? - * [no locking] - */ - unsigned long t_expires; - - /* - * When this transaction started, in nanoseconds [no locking] - */ - ktime_t t_start_time; - - /* - * How many handles used this transaction? [t_handle_lock] - */ - int t_handle_count; -}; - -/** - * struct journal_s - this is the concrete type associated with journal_t. - * @j_flags: General journaling state flags - * @j_errno: Is there an outstanding uncleared error on the journal (from a - * prior abort)? - * @j_sb_buffer: First part of superblock buffer - * @j_superblock: Second part of superblock buffer - * @j_format_version: Version of the superblock format - * @j_state_lock: Protect the various scalars in the journal - * @j_barrier_count: Number of processes waiting to create a barrier lock - * @j_running_transaction: The current running transaction.. - * @j_committing_transaction: the transaction we are pushing to disk - * @j_checkpoint_transactions: a linked circular list of all transactions - * waiting for checkpointing - * @j_wait_transaction_locked: Wait queue for waiting for a locked transaction - * to start committing, or for a barrier lock to be released - * @j_wait_logspace: Wait queue for waiting for checkpointing to complete - * @j_wait_done_commit: Wait queue for waiting for commit to complete - * @j_wait_checkpoint: Wait queue to trigger checkpointing - * @j_wait_commit: Wait queue to trigger commit - * @j_wait_updates: Wait queue to wait for updates to complete - * @j_checkpoint_mutex: Mutex for locking against concurrent checkpoints - * @j_head: Journal head - identifies the first unused block in the journal - * @j_tail: Journal tail - identifies the oldest still-used block in the - * journal. - * @j_free: Journal free - how many free blocks are there in the journal? - * @j_first: The block number of the first usable block - * @j_last: The block number one beyond the last usable block - * @j_dev: Device where we store the journal - * @j_blocksize: blocksize for the location where we store the journal. - * @j_blk_offset: starting block offset for into the device where we store the - * journal - * @j_fs_dev: Device which holds the client fs. For internal journal this will - * be equal to j_dev - * @j_maxlen: Total maximum capacity of the journal region on disk. - * @j_list_lock: Protects the buffer lists and internal buffer state. - * @j_inode: Optional inode where we store the journal. If present, all journal - * block numbers are mapped into this inode via bmap(). - * @j_tail_sequence: Sequence number of the oldest transaction in the log - * @j_transaction_sequence: Sequence number of the next transaction to grant - * @j_commit_sequence: Sequence number of the most recently committed - * transaction - * @j_commit_request: Sequence number of the most recent transaction wanting - * commit - * @j_commit_waited: Sequence number of the most recent transaction someone - * is waiting for to commit. - * @j_uuid: Uuid of client object. - * @j_task: Pointer to the current commit thread for this journal - * @j_max_transaction_buffers: Maximum number of metadata buffers to allow in a - * single compound commit transaction - * @j_commit_interval: What is the maximum transaction lifetime before we begin - * a commit? - * @j_commit_timer: The timer used to wakeup the commit thread - * @j_revoke_lock: Protect the revoke table - * @j_revoke: The revoke table - maintains the list of revoked blocks in the - * current transaction. - * @j_revoke_table: alternate revoke tables for j_revoke - * @j_wbuf: array of buffer_heads for journal_commit_transaction - * @j_wbufsize: maximum number of buffer_heads allowed in j_wbuf, the - * number that will fit in j_blocksize - * @j_last_sync_writer: most recent pid which did a synchronous write - * @j_average_commit_time: the average amount of time in nanoseconds it - * takes to commit a transaction to the disk. - * @j_private: An opaque pointer to fs-private information. - */ - -struct journal_s -{ - /* General journaling state flags [j_state_lock] */ - unsigned long j_flags; - - /* - * Is there an outstanding uncleared error on the journal (from a prior - * abort)? [j_state_lock] - */ - int j_errno; - - /* The superblock buffer */ - struct buffer_head *j_sb_buffer; - journal_superblock_t *j_superblock; - - /* Version of the superblock format */ - int j_format_version; - - /* - * Protect the various scalars in the journal - */ - spinlock_t j_state_lock; - - /* - * Number of processes waiting to create a barrier lock [j_state_lock] - */ - int j_barrier_count; - - /* - * Transactions: The current running transaction... - * [j_state_lock] [caller holding open handle] - */ - transaction_t *j_running_transaction; - - /* - * the transaction we are pushing to disk - * [j_state_lock] [caller holding open handle] - */ - transaction_t *j_committing_transaction; - - /* - * ... and a linked circular list of all transactions waiting for - * checkpointing. [j_list_lock] - */ - transaction_t *j_checkpoint_transactions; - - /* - * Wait queue for waiting for a locked transaction to start committing, - * or for a barrier lock to be released - */ - wait_queue_head_t j_wait_transaction_locked; - - /* Wait queue for waiting for checkpointing to complete */ - wait_queue_head_t j_wait_logspace; - - /* Wait queue for waiting for commit to complete */ - wait_queue_head_t j_wait_done_commit; - - /* Wait queue to trigger checkpointing */ - wait_queue_head_t j_wait_checkpoint; - - /* Wait queue to trigger commit */ - wait_queue_head_t j_wait_commit; - - /* Wait queue to wait for updates to complete */ - wait_queue_head_t j_wait_updates; - - /* Semaphore for locking against concurrent checkpoints */ - struct mutex j_checkpoint_mutex; - - /* - * Journal head: identifies the first unused block in the journal. - * [j_state_lock] - */ - unsigned int j_head; - - /* - * Journal tail: identifies the oldest still-used block in the journal. - * [j_state_lock] - */ - unsigned int j_tail; - - /* - * Journal free: how many free blocks are there in the journal? - * [j_state_lock] - */ - unsigned int j_free; - - /* - * Journal start and end: the block numbers of the first usable block - * and one beyond the last usable block in the journal. [j_state_lock] - */ - unsigned int j_first; - unsigned int j_last; - - /* - * Device, blocksize and starting block offset for the location where we - * store the journal. - */ - struct block_device *j_dev; - int j_blocksize; - unsigned int j_blk_offset; - - /* - * Device which holds the client fs. For internal journal this will be - * equal to j_dev. - */ - struct block_device *j_fs_dev; - - /* Total maximum capacity of the journal region on disk. */ - unsigned int j_maxlen; - - /* - * Protects the buffer lists and internal buffer state. - */ - spinlock_t j_list_lock; - - /* Optional inode where we store the journal. If present, all */ - /* journal block numbers are mapped into this inode via */ - /* bmap(). */ - struct inode *j_inode; - - /* - * Sequence number of the oldest transaction in the log [j_state_lock] - */ - tid_t j_tail_sequence; - - /* - * Sequence number of the next transaction to grant [j_state_lock] - */ - tid_t j_transaction_sequence; - - /* - * Sequence number of the most recently committed transaction - * [j_state_lock]. - */ - tid_t j_commit_sequence; - - /* - * Sequence number of the most recent transaction wanting commit - * [j_state_lock] - */ - tid_t j_commit_request; - - /* - * Sequence number of the most recent transaction someone is waiting - * for to commit. - * [j_state_lock] - */ - tid_t j_commit_waited; - - /* - * Journal uuid: identifies the object (filesystem, LVM volume etc) - * backed by this journal. This will eventually be replaced by an array - * of uuids, allowing us to index multiple devices within a single - * journal and to perform atomic updates across them. - */ - __u8 j_uuid[16]; - - /* Pointer to the current commit thread for this journal */ - struct task_struct *j_task; - - /* - * Maximum number of metadata buffers to allow in a single compound - * commit transaction - */ - int j_max_transaction_buffers; - - /* - * What is the maximum transaction lifetime before we begin a commit? - */ - unsigned long j_commit_interval; - - /* The timer used to wakeup the commit thread: */ - struct timer_list j_commit_timer; - - /* - * The revoke table: maintains the list of revoked blocks in the - * current transaction. [j_revoke_lock] - */ - spinlock_t j_revoke_lock; - struct jbd_revoke_table_s *j_revoke; - struct jbd_revoke_table_s *j_revoke_table[2]; - - /* - * array of bhs for journal_commit_transaction - */ - struct buffer_head **j_wbuf; - int j_wbufsize; - - /* - * this is the pid of the last person to run a synchronous operation - * through the journal. - */ - pid_t j_last_sync_writer; - - /* - * the average amount of time in nanoseconds it takes to commit a - * transaction to the disk. [j_state_lock] - */ - u64 j_average_commit_time; - - /* - * An opaque pointer to fs-private information. ext3 puts its - * superblock pointer here - */ - void *j_private; -}; - -/* - * Journal flag definitions - */ -#define JFS_UNMOUNT 0x001 /* Journal thread is being destroyed */ -#define JFS_ABORT 0x002 /* Journaling has been aborted for errors. */ -#define JFS_ACK_ERR 0x004 /* The errno in the sb has been acked */ -#define JFS_FLUSHED 0x008 /* The journal superblock has been flushed */ -#define JFS_LOADED 0x010 /* The journal superblock has been loaded */ -#define JFS_BARRIER 0x020 /* Use IDE barriers */ -#define JFS_ABORT_ON_SYNCDATA_ERR 0x040 /* Abort the journal on file - * data write error in ordered - * mode */ - -/* - * Function declarations for the journaling transaction and buffer - * management - */ - -/* Filing buffers */ -extern void journal_unfile_buffer(journal_t *, struct journal_head *); -extern void __journal_unfile_buffer(struct journal_head *); -extern void __journal_refile_buffer(struct journal_head *); -extern void journal_refile_buffer(journal_t *, struct journal_head *); -extern void __journal_file_buffer(struct journal_head *, transaction_t *, int); -extern void __journal_free_buffer(struct journal_head *bh); -extern void journal_file_buffer(struct journal_head *, transaction_t *, int); -extern void __journal_clean_data_list(transaction_t *transaction); - -/* Log buffer allocation */ -extern struct journal_head * journal_get_descriptor_buffer(journal_t *); -int journal_next_log_block(journal_t *, unsigned int *); - -/* Commit management */ -extern void journal_commit_transaction(journal_t *); - -/* Checkpoint list management */ -int __journal_clean_checkpoint_list(journal_t *journal); -int __journal_remove_checkpoint(struct journal_head *); -void __journal_insert_checkpoint(struct journal_head *, transaction_t *); - -/* Buffer IO */ -extern int -journal_write_metadata_buffer(transaction_t *transaction, - struct journal_head *jh_in, - struct journal_head **jh_out, - unsigned int blocknr); - -/* Transaction locking */ -extern void __wait_on_journal (journal_t *); - -/* - * Journal locking. - * - * We need to lock the journal during transaction state changes so that nobody - * ever tries to take a handle on the running transaction while we are in the - * middle of moving it to the commit phase. j_state_lock does this. - * - * Note that the locking is completely interrupt unsafe. We never touch - * journal structures from interrupts. - */ - -static inline handle_t *journal_current_handle(void) -{ - return current->journal_info; -} - -/* The journaling code user interface: - * - * Create and destroy handles - * Register buffer modifications against the current transaction. - */ - -extern handle_t *journal_start(journal_t *, int nblocks); -extern int journal_restart (handle_t *, int nblocks); -extern int journal_extend (handle_t *, int nblocks); -extern int journal_get_write_access(handle_t *, struct buffer_head *); -extern int journal_get_create_access (handle_t *, struct buffer_head *); -extern int journal_get_undo_access(handle_t *, struct buffer_head *); -extern int journal_dirty_data (handle_t *, struct buffer_head *); -extern int journal_dirty_metadata (handle_t *, struct buffer_head *); -extern void journal_release_buffer (handle_t *, struct buffer_head *); -extern int journal_forget (handle_t *, struct buffer_head *); -extern void journal_sync_buffer (struct buffer_head *); -extern void journal_invalidatepage(journal_t *, - struct page *, unsigned int, unsigned int); -extern int journal_try_to_free_buffers(journal_t *, struct page *, gfp_t); -extern int journal_stop(handle_t *); -extern int journal_flush (journal_t *); -extern void journal_lock_updates (journal_t *); -extern void journal_unlock_updates (journal_t *); - -extern journal_t * journal_init_dev(struct block_device *bdev, - struct block_device *fs_dev, - int start, int len, int bsize); -extern journal_t * journal_init_inode (struct inode *); -extern int journal_update_format (journal_t *); -extern int journal_check_used_features - (journal_t *, unsigned long, unsigned long, unsigned long); -extern int journal_check_available_features - (journal_t *, unsigned long, unsigned long, unsigned long); -extern int journal_set_features - (journal_t *, unsigned long, unsigned long, unsigned long); -extern int journal_create (journal_t *); -extern int journal_load (journal_t *journal); -extern int journal_destroy (journal_t *); -extern int journal_recover (journal_t *journal); -extern int journal_wipe (journal_t *, int); -extern int journal_skip_recovery (journal_t *); -extern void journal_update_sb_log_tail (journal_t *, tid_t, unsigned int, - int); -extern void journal_abort (journal_t *, int); -extern int journal_errno (journal_t *); -extern void journal_ack_err (journal_t *); -extern int journal_clear_err (journal_t *); -extern int journal_bmap(journal_t *, unsigned int, unsigned int *); -extern int journal_force_commit(journal_t *); - -/* - * journal_head management - */ -struct journal_head *journal_add_journal_head(struct buffer_head *bh); -struct journal_head *journal_grab_journal_head(struct buffer_head *bh); -void journal_put_journal_head(struct journal_head *jh); - -/* - * handle management - */ -extern struct kmem_cache *jbd_handle_cache; - -static inline handle_t *jbd_alloc_handle(gfp_t gfp_flags) -{ - return kmem_cache_zalloc(jbd_handle_cache, gfp_flags); -} - -static inline void jbd_free_handle(handle_t *handle) -{ - kmem_cache_free(jbd_handle_cache, handle); -} - -/* Primary revoke support */ -#define JOURNAL_REVOKE_DEFAULT_HASH 256 -extern int journal_init_revoke(journal_t *, int); -extern void journal_destroy_revoke_caches(void); -extern int journal_init_revoke_caches(void); - -extern void journal_destroy_revoke(journal_t *); -extern int journal_revoke (handle_t *, - unsigned int, struct buffer_head *); -extern int journal_cancel_revoke(handle_t *, struct journal_head *); -extern void journal_write_revoke_records(journal_t *, - transaction_t *, int); - -/* Recovery revoke support */ -extern int journal_set_revoke(journal_t *, unsigned int, tid_t); -extern int journal_test_revoke(journal_t *, unsigned int, tid_t); -extern void journal_clear_revoke(journal_t *); -extern void journal_switch_revoke_table(journal_t *journal); -extern void journal_clear_buffer_revoked_flags(journal_t *journal); - -/* - * The log thread user interface: - * - * Request space in the current transaction, and force transaction commit - * transitions on demand. - */ - -int __log_space_left(journal_t *); /* Called with journal locked */ -int log_start_commit(journal_t *journal, tid_t tid); -int __log_start_commit(journal_t *journal, tid_t tid); -int journal_start_commit(journal_t *journal, tid_t *tid); -int journal_force_commit_nested(journal_t *journal); -int log_wait_commit(journal_t *journal, tid_t tid); -int log_do_checkpoint(journal_t *journal); -int journal_trans_will_send_data_barrier(journal_t *journal, tid_t tid); - -void __log_wait_for_space(journal_t *journal); -extern void __journal_drop_transaction(journal_t *, transaction_t *); -extern int cleanup_journal_tail(journal_t *); - -/* - * is_journal_abort - * - * Simple test wrapper function to test the JFS_ABORT state flag. This - * bit, when set, indicates that we have had a fatal error somewhere, - * either inside the journaling layer or indicated to us by the client - * (eg. ext3), and that we and should not commit any further - * transactions. - */ - -static inline int is_journal_aborted(journal_t *journal) -{ - return journal->j_flags & JFS_ABORT; -} - -static inline int is_handle_aborted(handle_t *handle) -{ - if (handle->h_aborted) - return 1; - return is_journal_aborted(handle->h_transaction->t_journal); -} - -static inline void journal_abort_handle(handle_t *handle) -{ - handle->h_aborted = 1; -} - -#endif /* __KERNEL__ */ - -/* Comparison functions for transaction IDs: perform comparisons using - * modulo arithmetic so that they work over sequence number wraps. */ - -static inline int tid_gt(tid_t x, tid_t y) -{ - int difference = (x - y); - return (difference > 0); -} - -static inline int tid_geq(tid_t x, tid_t y) -{ - int difference = (x - y); - return (difference >= 0); -} - -extern int journal_blocks_per_page(struct inode *inode); - -/* - * Return the minimum number of blocks which must be free in the journal - * before a new transaction may be started. Must be called under j_state_lock. - */ -static inline int jbd_space_needed(journal_t *journal) -{ - int nblocks = journal->j_max_transaction_buffers; - if (journal->j_committing_transaction) - nblocks += journal->j_committing_transaction-> - t_outstanding_credits; - return nblocks; -} - -/* - * Definitions which augment the buffer_head layer - */ - -/* journaling buffer types */ -#define BJ_None 0 /* Not journaled */ -#define BJ_SyncData 1 /* Normal data: flush before commit */ -#define BJ_Metadata 2 /* Normal journaled metadata */ -#define BJ_Forget 3 /* Buffer superseded by this transaction */ -#define BJ_IO 4 /* Buffer is for temporary IO use */ -#define BJ_Shadow 5 /* Buffer contents being shadowed to the log */ -#define BJ_LogCtl 6 /* Buffer contains log descriptors */ -#define BJ_Reserved 7 /* Buffer is reserved for access by journal */ -#define BJ_Locked 8 /* Locked for I/O during commit */ -#define BJ_Types 9 - -extern int jbd_blocks_per_page(struct inode *inode); - -#ifdef __KERNEL__ - -#define buffer_trace_init(bh) do {} while (0) -#define print_buffer_fields(bh) do {} while (0) -#define print_buffer_trace(bh) do {} while (0) -#define BUFFER_TRACE(bh, info) do {} while (0) -#define BUFFER_TRACE2(bh, bh2, info) do {} while (0) -#define JBUFFER_TRACE(jh, info) do {} while (0) - -#endif /* __KERNEL__ */ - -#endif /* _LINUX_JBD_H */ diff --git a/kernel/include/linux/jbd2.h b/kernel/include/linux/jbd2.h index eb1cebed3..eb5aabe4e 100644 --- a/kernel/include/linux/jbd2.h +++ b/kernel/include/linux/jbd2.h @@ -29,6 +29,7 @@ #include <linux/mutex.h> #include <linux/timer.h> #include <linux/slab.h> +#include <linux/bit_spinlock.h> #include <crypto/hash.h> #endif @@ -277,6 +278,7 @@ typedef struct journal_superblock_s /* 0x0400 */ } journal_superblock_t; +/* Use the jbd2_{has,set,clear}_feature_* helpers; these will be removed */ #define JBD2_HAS_COMPAT_FEATURE(j,mask) \ ((j)->j_format_version >= 2 && \ ((j)->j_superblock->s_feature_compat & cpu_to_be32((mask)))) @@ -287,7 +289,7 @@ typedef struct journal_superblock_s ((j)->j_format_version >= 2 && \ ((j)->j_superblock->s_feature_incompat & cpu_to_be32((mask)))) -#define JBD2_FEATURE_COMPAT_CHECKSUM 0x00000001 +#define JBD2_FEATURE_COMPAT_CHECKSUM 0x00000001 #define JBD2_FEATURE_INCOMPAT_REVOKE 0x00000001 #define JBD2_FEATURE_INCOMPAT_64BIT 0x00000002 @@ -295,6 +297,8 @@ typedef struct journal_superblock_s #define JBD2_FEATURE_INCOMPAT_CSUM_V2 0x00000008 #define JBD2_FEATURE_INCOMPAT_CSUM_V3 0x00000010 +/* See "journal feature predicate functions" below */ + /* Features known to this kernel version: */ #define JBD2_KNOWN_COMPAT_FEATURES JBD2_FEATURE_COMPAT_CHECKSUM #define JBD2_KNOWN_ROCOMPAT_FEATURES 0 @@ -336,7 +340,69 @@ BUFFER_FNS(Freed, freed) BUFFER_FNS(Shadow, shadow) BUFFER_FNS(Verified, verified) -#include <linux/jbd_common.h> +static inline struct buffer_head *jh2bh(struct journal_head *jh) +{ + return jh->b_bh; +} + +static inline struct journal_head *bh2jh(struct buffer_head *bh) +{ + return bh->b_private; +} + +static inline void jbd_lock_bh_state(struct buffer_head *bh) +{ +#ifndef CONFIG_PREEMPT_RT_BASE + bit_spin_lock(BH_State, &bh->b_state); +#else + spin_lock(&bh->b_state_lock); +#endif +} + +static inline int jbd_trylock_bh_state(struct buffer_head *bh) +{ +#ifndef CONFIG_PREEMPT_RT_BASE + return bit_spin_trylock(BH_State, &bh->b_state); +#else + return spin_trylock(&bh->b_state_lock); +#endif +} + +static inline int jbd_is_locked_bh_state(struct buffer_head *bh) +{ +#ifndef CONFIG_PREEMPT_RT_BASE + return bit_spin_is_locked(BH_State, &bh->b_state); +#else + return spin_is_locked(&bh->b_state_lock); +#endif +} + +static inline void jbd_unlock_bh_state(struct buffer_head *bh) +{ +#ifndef CONFIG_PREEMPT_RT_BASE + bit_spin_unlock(BH_State, &bh->b_state); +#else + spin_unlock(&bh->b_state_lock); +#endif +} + +static inline void jbd_lock_bh_journal_head(struct buffer_head *bh) +{ +#ifndef CONFIG_PREEMPT_RT_BASE + bit_spin_lock(BH_JournalHead, &bh->b_state); +#else + spin_lock(&bh->b_journal_head_lock); +#endif +} + +static inline void jbd_unlock_bh_journal_head(struct buffer_head *bh) +{ +#ifndef CONFIG_PREEMPT_RT_BASE + bit_spin_unlock(BH_JournalHead, &bh->b_state); +#else + spin_unlock(&bh->b_journal_head_lock); +#endif +} #define J_ASSERT(assert) BUG_ON(!(assert)) @@ -995,6 +1061,69 @@ struct journal_s __u32 j_csum_seed; }; +/* journal feature predicate functions */ +#define JBD2_FEATURE_COMPAT_FUNCS(name, flagname) \ +static inline bool jbd2_has_feature_##name(journal_t *j) \ +{ \ + return ((j)->j_format_version >= 2 && \ + ((j)->j_superblock->s_feature_compat & \ + cpu_to_be32(JBD2_FEATURE_COMPAT_##flagname)) != 0); \ +} \ +static inline void jbd2_set_feature_##name(journal_t *j) \ +{ \ + (j)->j_superblock->s_feature_compat |= \ + cpu_to_be32(JBD2_FEATURE_COMPAT_##flagname); \ +} \ +static inline void jbd2_clear_feature_##name(journal_t *j) \ +{ \ + (j)->j_superblock->s_feature_compat &= \ + ~cpu_to_be32(JBD2_FEATURE_COMPAT_##flagname); \ +} + +#define JBD2_FEATURE_RO_COMPAT_FUNCS(name, flagname) \ +static inline bool jbd2_has_feature_##name(journal_t *j) \ +{ \ + return ((j)->j_format_version >= 2 && \ + ((j)->j_superblock->s_feature_ro_compat & \ + cpu_to_be32(JBD2_FEATURE_RO_COMPAT_##flagname)) != 0); \ +} \ +static inline void jbd2_set_feature_##name(journal_t *j) \ +{ \ + (j)->j_superblock->s_feature_ro_compat |= \ + cpu_to_be32(JBD2_FEATURE_RO_COMPAT_##flagname); \ +} \ +static inline void jbd2_clear_feature_##name(journal_t *j) \ +{ \ + (j)->j_superblock->s_feature_ro_compat &= \ + ~cpu_to_be32(JBD2_FEATURE_RO_COMPAT_##flagname); \ +} + +#define JBD2_FEATURE_INCOMPAT_FUNCS(name, flagname) \ +static inline bool jbd2_has_feature_##name(journal_t *j) \ +{ \ + return ((j)->j_format_version >= 2 && \ + ((j)->j_superblock->s_feature_incompat & \ + cpu_to_be32(JBD2_FEATURE_INCOMPAT_##flagname)) != 0); \ +} \ +static inline void jbd2_set_feature_##name(journal_t *j) \ +{ \ + (j)->j_superblock->s_feature_incompat |= \ + cpu_to_be32(JBD2_FEATURE_INCOMPAT_##flagname); \ +} \ +static inline void jbd2_clear_feature_##name(journal_t *j) \ +{ \ + (j)->j_superblock->s_feature_incompat &= \ + ~cpu_to_be32(JBD2_FEATURE_INCOMPAT_##flagname); \ +} + +JBD2_FEATURE_COMPAT_FUNCS(checksum, CHECKSUM) + +JBD2_FEATURE_INCOMPAT_FUNCS(revoke, REVOKE) +JBD2_FEATURE_INCOMPAT_FUNCS(64bit, 64BIT) +JBD2_FEATURE_INCOMPAT_FUNCS(async_commit, ASYNC_COMMIT) +JBD2_FEATURE_INCOMPAT_FUNCS(csum2, CSUM_V2) +JBD2_FEATURE_INCOMPAT_FUNCS(csum3, CSUM_V3) + /* * Journal flag definitions */ @@ -1007,6 +1136,7 @@ struct journal_s #define JBD2_ABORT_ON_SYNCDATA_ERR 0x040 /* Abort the journal on file * data write error in ordered * mode */ +#define JBD2_REC_ERR 0x080 /* The errno in the sb has been recorded */ /* * Function declarations for the journaling transaction and buffer @@ -1299,13 +1429,17 @@ static inline int tid_geq(tid_t x, tid_t y) extern int jbd2_journal_blocks_per_page(struct inode *inode); extern size_t journal_tag_bytes(journal_t *journal); +static inline bool jbd2_journal_has_csum_v2or3_feature(journal_t *j) +{ + return jbd2_has_feature_csum2(j) || jbd2_has_feature_csum3(j); +} + static inline int jbd2_journal_has_csum_v2or3(journal_t *journal) { - if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2) || - JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V3)) - return 1; + WARN_ON_ONCE(jbd2_journal_has_csum_v2or3_feature(journal) && + journal->j_chksum_driver == NULL); - return 0; + return journal->j_chksum_driver != NULL; } /* @@ -1405,4 +1539,7 @@ static inline tid_t jbd2_get_latest_transaction(journal_t *journal) #endif /* __KERNEL__ */ +#define EFSBADCRC EBADMSG /* Bad CRC detected */ +#define EFSCORRUPTED EUCLEAN /* Filesystem is corrupted */ + #endif /* _LINUX_JBD2_H */ diff --git a/kernel/include/linux/jbd_common.h b/kernel/include/linux/jbd_common.h deleted file mode 100644 index a90a6f5ca..000000000 --- a/kernel/include/linux/jbd_common.h +++ /dev/null @@ -1,70 +0,0 @@ -#ifndef _LINUX_JBD_STATE_H -#define _LINUX_JBD_STATE_H - -#include <linux/bit_spinlock.h> - -static inline struct buffer_head *jh2bh(struct journal_head *jh) -{ - return jh->b_bh; -} - -static inline struct journal_head *bh2jh(struct buffer_head *bh) -{ - return bh->b_private; -} - -static inline void jbd_lock_bh_state(struct buffer_head *bh) -{ -#ifndef CONFIG_PREEMPT_RT_BASE - bit_spin_lock(BH_State, &bh->b_state); -#else - spin_lock(&bh->b_state_lock); -#endif -} - -static inline int jbd_trylock_bh_state(struct buffer_head *bh) -{ -#ifndef CONFIG_PREEMPT_RT_BASE - return bit_spin_trylock(BH_State, &bh->b_state); -#else - return spin_trylock(&bh->b_state_lock); -#endif -} - -static inline int jbd_is_locked_bh_state(struct buffer_head *bh) -{ -#ifndef CONFIG_PREEMPT_RT_BASE - return bit_spin_is_locked(BH_State, &bh->b_state); -#else - return spin_is_locked(&bh->b_state_lock); -#endif -} - -static inline void jbd_unlock_bh_state(struct buffer_head *bh) -{ -#ifndef CONFIG_PREEMPT_RT_BASE - bit_spin_unlock(BH_State, &bh->b_state); -#else - spin_unlock(&bh->b_state_lock); -#endif -} - -static inline void jbd_lock_bh_journal_head(struct buffer_head *bh) -{ -#ifndef CONFIG_PREEMPT_RT_BASE - bit_spin_lock(BH_JournalHead, &bh->b_state); -#else - spin_lock(&bh->b_journal_head_lock); -#endif -} - -static inline void jbd_unlock_bh_journal_head(struct buffer_head *bh) -{ -#ifndef CONFIG_PREEMPT_RT_BASE - bit_spin_unlock(BH_JournalHead, &bh->b_state); -#else - spin_unlock(&bh->b_journal_head_lock); -#endif -} - -#endif diff --git a/kernel/include/linux/jiffies.h b/kernel/include/linux/jiffies.h index c367cbdf7..5fdc55312 100644 --- a/kernel/include/linux/jiffies.h +++ b/kernel/include/linux/jiffies.h @@ -7,6 +7,7 @@ #include <linux/time.h> #include <linux/timex.h> #include <asm/param.h> /* for HZ */ +#include <generated/timeconst.h> /* * The following defines establish the engineering parameters of the PLL @@ -288,11 +289,145 @@ static inline u64 jiffies_to_nsecs(const unsigned long j) return (u64)jiffies_to_usecs(j) * NSEC_PER_USEC; } -extern unsigned long msecs_to_jiffies(const unsigned int m); -extern unsigned long usecs_to_jiffies(const unsigned int u); -extern unsigned long timespec_to_jiffies(const struct timespec *value); -extern void jiffies_to_timespec(const unsigned long jiffies, - struct timespec *value); +extern unsigned long __msecs_to_jiffies(const unsigned int m); +#if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ) +/* + * HZ is equal to or smaller than 1000, and 1000 is a nice round + * multiple of HZ, divide with the factor between them, but round + * upwards: + */ +static inline unsigned long _msecs_to_jiffies(const unsigned int m) +{ + return (m + (MSEC_PER_SEC / HZ) - 1) / (MSEC_PER_SEC / HZ); +} +#elif HZ > MSEC_PER_SEC && !(HZ % MSEC_PER_SEC) +/* + * HZ is larger than 1000, and HZ is a nice round multiple of 1000 - + * simply multiply with the factor between them. + * + * But first make sure the multiplication result cannot overflow: + */ +static inline unsigned long _msecs_to_jiffies(const unsigned int m) +{ + if (m > jiffies_to_msecs(MAX_JIFFY_OFFSET)) + return MAX_JIFFY_OFFSET; + return m * (HZ / MSEC_PER_SEC); +} +#else +/* + * Generic case - multiply, round and divide. But first check that if + * we are doing a net multiplication, that we wouldn't overflow: + */ +static inline unsigned long _msecs_to_jiffies(const unsigned int m) +{ + if (HZ > MSEC_PER_SEC && m > jiffies_to_msecs(MAX_JIFFY_OFFSET)) + return MAX_JIFFY_OFFSET; + + return (MSEC_TO_HZ_MUL32 * m + MSEC_TO_HZ_ADJ32) >> MSEC_TO_HZ_SHR32; +} +#endif +/** + * msecs_to_jiffies: - convert milliseconds to jiffies + * @m: time in milliseconds + * + * conversion is done as follows: + * + * - negative values mean 'infinite timeout' (MAX_JIFFY_OFFSET) + * + * - 'too large' values [that would result in larger than + * MAX_JIFFY_OFFSET values] mean 'infinite timeout' too. + * + * - all other values are converted to jiffies by either multiplying + * the input value by a factor or dividing it with a factor and + * handling any 32-bit overflows. + * for the details see __msecs_to_jiffies() + * + * msecs_to_jiffies() checks for the passed in value being a constant + * via __builtin_constant_p() allowing gcc to eliminate most of the + * code, __msecs_to_jiffies() is called if the value passed does not + * allow constant folding and the actual conversion must be done at + * runtime. + * the HZ range specific helpers _msecs_to_jiffies() are called both + * directly here and from __msecs_to_jiffies() in the case where + * constant folding is not possible. + */ +static __always_inline unsigned long msecs_to_jiffies(const unsigned int m) +{ + if (__builtin_constant_p(m)) { + if ((int)m < 0) + return MAX_JIFFY_OFFSET; + return _msecs_to_jiffies(m); + } else { + return __msecs_to_jiffies(m); + } +} + +extern unsigned long __usecs_to_jiffies(const unsigned int u); +#if !(USEC_PER_SEC % HZ) +static inline unsigned long _usecs_to_jiffies(const unsigned int u) +{ + return (u + (USEC_PER_SEC / HZ) - 1) / (USEC_PER_SEC / HZ); +} +#else +static inline unsigned long _usecs_to_jiffies(const unsigned int u) +{ + return (USEC_TO_HZ_MUL32 * u + USEC_TO_HZ_ADJ32) + >> USEC_TO_HZ_SHR32; +} +#endif + +/** + * usecs_to_jiffies: - convert microseconds to jiffies + * @u: time in microseconds + * + * conversion is done as follows: + * + * - 'too large' values [that would result in larger than + * MAX_JIFFY_OFFSET values] mean 'infinite timeout' too. + * + * - all other values are converted to jiffies by either multiplying + * the input value by a factor or dividing it with a factor and + * handling any 32-bit overflows as for msecs_to_jiffies. + * + * usecs_to_jiffies() checks for the passed in value being a constant + * via __builtin_constant_p() allowing gcc to eliminate most of the + * code, __usecs_to_jiffies() is called if the value passed does not + * allow constant folding and the actual conversion must be done at + * runtime. + * the HZ range specific helpers _usecs_to_jiffies() are called both + * directly here and from __msecs_to_jiffies() in the case where + * constant folding is not possible. + */ +static __always_inline unsigned long usecs_to_jiffies(const unsigned int u) +{ + if (__builtin_constant_p(u)) { + if (u > jiffies_to_usecs(MAX_JIFFY_OFFSET)) + return MAX_JIFFY_OFFSET; + return _usecs_to_jiffies(u); + } else { + return __usecs_to_jiffies(u); + } +} + +extern unsigned long timespec64_to_jiffies(const struct timespec64 *value); +extern void jiffies_to_timespec64(const unsigned long jiffies, + struct timespec64 *value); +static inline unsigned long timespec_to_jiffies(const struct timespec *value) +{ + struct timespec64 ts = timespec_to_timespec64(*value); + + return timespec64_to_jiffies(&ts); +} + +static inline void jiffies_to_timespec(const unsigned long jiffies, + struct timespec *value) +{ + struct timespec64 ts; + + jiffies_to_timespec64(jiffies, &ts); + *value = timespec64_to_timespec(ts); +} + extern unsigned long timeval_to_jiffies(const struct timeval *value); extern void jiffies_to_timeval(const unsigned long jiffies, struct timeval *value); diff --git a/kernel/include/linux/jump_label.h b/kernel/include/linux/jump_label.h index f4de473f2..0536524bb 100644 --- a/kernel/include/linux/jump_label.h +++ b/kernel/include/linux/jump_label.h @@ -5,19 +5,52 @@ * Jump label support * * Copyright (C) 2009-2012 Jason Baron <jbaron@redhat.com> - * Copyright (C) 2011-2012 Peter Zijlstra <pzijlstr@redhat.com> + * Copyright (C) 2011-2012 Red Hat, Inc., Peter Zijlstra + * + * DEPRECATED API: + * + * The use of 'struct static_key' directly, is now DEPRECATED. In addition + * static_key_{true,false}() is also DEPRECATED. IE DO NOT use the following: + * + * struct static_key false = STATIC_KEY_INIT_FALSE; + * struct static_key true = STATIC_KEY_INIT_TRUE; + * static_key_true() + * static_key_false() + * + * The updated API replacements are: + * + * DEFINE_STATIC_KEY_TRUE(key); + * DEFINE_STATIC_KEY_FALSE(key); + * static_branch_likely() + * static_branch_unlikely() * * Jump labels provide an interface to generate dynamic branches using - * self-modifying code. Assuming toolchain and architecture support, the result - * of a "if (static_key_false(&key))" statement is an unconditional branch (which - * defaults to false - and the true block is placed out of line). + * self-modifying code. Assuming toolchain and architecture support, if we + * define a "key" that is initially false via "DEFINE_STATIC_KEY_FALSE(key)", + * an "if (static_branch_unlikely(&key))" statement is an unconditional branch + * (which defaults to false - and the true block is placed out of line). + * Similarly, we can define an initially true key via + * "DEFINE_STATIC_KEY_TRUE(key)", and use it in the same + * "if (static_branch_unlikely(&key))", in which case we will generate an + * unconditional branch to the out-of-line true branch. Keys that are + * initially true or false can be using in both static_branch_unlikely() + * and static_branch_likely() statements. + * + * At runtime we can change the branch target by setting the key + * to true via a call to static_branch_enable(), or false using + * static_branch_disable(). If the direction of the branch is switched by + * these calls then we run-time modify the branch target via a + * no-op -> jump or jump -> no-op conversion. For example, for an + * initially false key that is used in an "if (static_branch_unlikely(&key))" + * statement, setting the key to true requires us to patch in a jump + * to the out-of-line of true branch. * - * However at runtime we can change the branch target using - * static_key_slow_{inc,dec}(). These function as a 'reference' count on the key - * object, and for as long as there are references all branches referring to - * that particular key will point to the (out of line) true block. + * In addition to static_branch_{enable,disable}, we can also reference count + * the key or branch direction via static_branch_{inc,dec}. Thus, + * static_branch_inc() can be thought of as a 'make more true' and + * static_branch_dec() as a 'make more false'. * - * Since this relies on modifying code, the static_key_slow_{inc,dec}() functions + * Since this relies on modifying code, the branch modifying functions * must be considered absolute slow paths (machine wide synchronization etc.). * OTOH, since the affected branches are unconditional, their runtime overhead * will be absolutely minimal, esp. in the default (off) case where the total @@ -29,20 +62,10 @@ * cause significant performance degradation. Struct static_key_deferred and * static_key_slow_dec_deferred() provide for this. * - * Lacking toolchain and or architecture support, jump labels fall back to a simple - * conditional branch. - * - * struct static_key my_key = STATIC_KEY_INIT_TRUE; - * - * if (static_key_true(&my_key)) { - * } + * Lacking toolchain and or architecture support, static keys fall back to a + * simple conditional branch. * - * will result in the true case being in-line and starts the key with a single - * reference. Mixing static_key_true() and static_key_false() on the same key is not - * allowed. - * - * Not initializing the key (static data is initialized to 0s anyway) is the - * same as using STATIC_KEY_INIT_FALSE. + * Additional babbling in: Documentation/static-keys.txt */ #if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_JUMP_LABEL) @@ -86,8 +109,8 @@ struct static_key { #ifndef __ASSEMBLY__ enum jump_label_type { - JUMP_LABEL_DISABLE = 0, - JUMP_LABEL_ENABLE, + JUMP_LABEL_NOP = 0, + JUMP_LABEL_JMP, }; struct module; @@ -101,33 +124,18 @@ static inline int static_key_count(struct static_key *key) #ifdef HAVE_JUMP_LABEL -#define JUMP_LABEL_TYPE_FALSE_BRANCH 0UL -#define JUMP_LABEL_TYPE_TRUE_BRANCH 1UL -#define JUMP_LABEL_TYPE_MASK 1UL - -static -inline struct jump_entry *jump_label_get_entries(struct static_key *key) -{ - return (struct jump_entry *)((unsigned long)key->entries - & ~JUMP_LABEL_TYPE_MASK); -} - -static inline bool jump_label_get_branch_default(struct static_key *key) -{ - if (((unsigned long)key->entries & JUMP_LABEL_TYPE_MASK) == - JUMP_LABEL_TYPE_TRUE_BRANCH) - return true; - return false; -} +#define JUMP_TYPE_FALSE 0UL +#define JUMP_TYPE_TRUE 1UL +#define JUMP_TYPE_MASK 1UL static __always_inline bool static_key_false(struct static_key *key) { - return arch_static_branch(key); + return arch_static_branch(key, false); } static __always_inline bool static_key_true(struct static_key *key) { - return !static_key_false(key); + return !arch_static_branch(key, true); } extern struct jump_entry __start___jump_table[]; @@ -145,12 +153,12 @@ extern void static_key_slow_inc(struct static_key *key); extern void static_key_slow_dec(struct static_key *key); extern void jump_label_apply_nops(struct module *mod); -#define STATIC_KEY_INIT_TRUE ((struct static_key) \ +#define STATIC_KEY_INIT_TRUE \ { .enabled = ATOMIC_INIT(1), \ - .entries = (void *)JUMP_LABEL_TYPE_TRUE_BRANCH }) -#define STATIC_KEY_INIT_FALSE ((struct static_key) \ + .entries = (void *)JUMP_TYPE_TRUE } +#define STATIC_KEY_INIT_FALSE \ { .enabled = ATOMIC_INIT(0), \ - .entries = (void *)JUMP_LABEL_TYPE_FALSE_BRANCH }) + .entries = (void *)JUMP_TYPE_FALSE } #else /* !HAVE_JUMP_LABEL */ @@ -198,21 +206,174 @@ static inline int jump_label_apply_nops(struct module *mod) return 0; } -#define STATIC_KEY_INIT_TRUE ((struct static_key) \ - { .enabled = ATOMIC_INIT(1) }) -#define STATIC_KEY_INIT_FALSE ((struct static_key) \ - { .enabled = ATOMIC_INIT(0) }) +#define STATIC_KEY_INIT_TRUE { .enabled = ATOMIC_INIT(1) } +#define STATIC_KEY_INIT_FALSE { .enabled = ATOMIC_INIT(0) } #endif /* HAVE_JUMP_LABEL */ #define STATIC_KEY_INIT STATIC_KEY_INIT_FALSE #define jump_label_enabled static_key_enabled -static inline bool static_key_enabled(struct static_key *key) +static inline void static_key_enable(struct static_key *key) +{ + int count = static_key_count(key); + + WARN_ON_ONCE(count < 0 || count > 1); + + if (!count) + static_key_slow_inc(key); +} + +static inline void static_key_disable(struct static_key *key) { - return static_key_count(key) > 0; + int count = static_key_count(key); + + WARN_ON_ONCE(count < 0 || count > 1); + + if (count) + static_key_slow_dec(key); } +/* -------------------------------------------------------------------------- */ + +/* + * Two type wrappers around static_key, such that we can use compile time + * type differentiation to emit the right code. + * + * All the below code is macros in order to play type games. + */ + +struct static_key_true { + struct static_key key; +}; + +struct static_key_false { + struct static_key key; +}; + +#define STATIC_KEY_TRUE_INIT (struct static_key_true) { .key = STATIC_KEY_INIT_TRUE, } +#define STATIC_KEY_FALSE_INIT (struct static_key_false){ .key = STATIC_KEY_INIT_FALSE, } + +#define DEFINE_STATIC_KEY_TRUE(name) \ + struct static_key_true name = STATIC_KEY_TRUE_INIT + +#define DEFINE_STATIC_KEY_FALSE(name) \ + struct static_key_false name = STATIC_KEY_FALSE_INIT + +extern bool ____wrong_branch_error(void); + +#define static_key_enabled(x) \ +({ \ + if (!__builtin_types_compatible_p(typeof(*x), struct static_key) && \ + !__builtin_types_compatible_p(typeof(*x), struct static_key_true) &&\ + !__builtin_types_compatible_p(typeof(*x), struct static_key_false)) \ + ____wrong_branch_error(); \ + static_key_count((struct static_key *)x) > 0; \ +}) + +#ifdef HAVE_JUMP_LABEL + +/* + * Combine the right initial value (type) with the right branch order + * to generate the desired result. + * + * + * type\branch| likely (1) | unlikely (0) + * -----------+-----------------------+------------------ + * | | + * true (1) | ... | ... + * | NOP | JMP L + * | <br-stmts> | 1: ... + * | L: ... | + * | | + * | | L: <br-stmts> + * | | jmp 1b + * | | + * -----------+-----------------------+------------------ + * | | + * false (0) | ... | ... + * | JMP L | NOP + * | <br-stmts> | 1: ... + * | L: ... | + * | | + * | | L: <br-stmts> + * | | jmp 1b + * | | + * -----------+-----------------------+------------------ + * + * The initial value is encoded in the LSB of static_key::entries, + * type: 0 = false, 1 = true. + * + * The branch type is encoded in the LSB of jump_entry::key, + * branch: 0 = unlikely, 1 = likely. + * + * This gives the following logic table: + * + * enabled type branch instuction + * -----------------------------+----------- + * 0 0 0 | NOP + * 0 0 1 | JMP + * 0 1 0 | NOP + * 0 1 1 | JMP + * + * 1 0 0 | JMP + * 1 0 1 | NOP + * 1 1 0 | JMP + * 1 1 1 | NOP + * + * Which gives the following functions: + * + * dynamic: instruction = enabled ^ branch + * static: instruction = type ^ branch + * + * See jump_label_type() / jump_label_init_type(). + */ + +#define static_branch_likely(x) \ +({ \ + bool branch; \ + if (__builtin_types_compatible_p(typeof(*x), struct static_key_true)) \ + branch = !arch_static_branch(&(x)->key, true); \ + else if (__builtin_types_compatible_p(typeof(*x), struct static_key_false)) \ + branch = !arch_static_branch_jump(&(x)->key, true); \ + else \ + branch = ____wrong_branch_error(); \ + branch; \ +}) + +#define static_branch_unlikely(x) \ +({ \ + bool branch; \ + if (__builtin_types_compatible_p(typeof(*x), struct static_key_true)) \ + branch = arch_static_branch_jump(&(x)->key, false); \ + else if (__builtin_types_compatible_p(typeof(*x), struct static_key_false)) \ + branch = arch_static_branch(&(x)->key, false); \ + else \ + branch = ____wrong_branch_error(); \ + branch; \ +}) + +#else /* !HAVE_JUMP_LABEL */ + +#define static_branch_likely(x) likely(static_key_enabled(&(x)->key)) +#define static_branch_unlikely(x) unlikely(static_key_enabled(&(x)->key)) + +#endif /* HAVE_JUMP_LABEL */ + +/* + * Advanced usage; refcount, branch is enabled when: count != 0 + */ + +#define static_branch_inc(x) static_key_slow_inc(&(x)->key) +#define static_branch_dec(x) static_key_slow_dec(&(x)->key) + +/* + * Normal usage; boolean enable/disable. + */ + +#define static_branch_enable(x) static_key_enable(&(x)->key) +#define static_branch_disable(x) static_key_disable(&(x)->key) + #endif /* _LINUX_JUMP_LABEL_H */ #endif /* __ASSEMBLY__ */ diff --git a/kernel/include/linux/kasan.h b/kernel/include/linux/kasan.h index 5486d777b..4b9f85c96 100644 --- a/kernel/include/linux/kasan.h +++ b/kernel/include/linux/kasan.h @@ -10,11 +10,19 @@ struct vm_struct; #ifdef CONFIG_KASAN #define KASAN_SHADOW_SCALE_SHIFT 3 -#define KASAN_SHADOW_OFFSET _AC(CONFIG_KASAN_SHADOW_OFFSET, UL) #include <asm/kasan.h> +#include <asm/pgtable.h> #include <linux/sched.h> +extern unsigned char kasan_zero_page[PAGE_SIZE]; +extern pte_t kasan_zero_pte[PTRS_PER_PTE]; +extern pmd_t kasan_zero_pmd[PTRS_PER_PMD]; +extern pud_t kasan_zero_pud[PTRS_PER_PUD]; + +void kasan_populate_zero_shadow(const void *shadow_start, + const void *shadow_end); + static inline void *kasan_mem_to_shadow(const void *addr) { return (void *)((unsigned long)addr >> KASAN_SHADOW_SCALE_SHIFT) diff --git a/kernel/include/linux/kdev_t.h b/kernel/include/linux/kdev_t.h index c838abe3e..052c7b32c 100644 --- a/kernel/include/linux/kdev_t.h +++ b/kernel/include/linux/kdev_t.h @@ -20,7 +20,7 @@ }) /* acceptable for old filesystems */ -static inline int old_valid_dev(dev_t dev) +static inline bool old_valid_dev(dev_t dev) { return MAJOR(dev) < 256 && MINOR(dev) < 256; } @@ -35,7 +35,7 @@ static inline dev_t old_decode_dev(u16 val) return MKDEV((val >> 8) & 255, val & 255); } -static inline int new_valid_dev(dev_t dev) +static inline bool new_valid_dev(dev_t dev) { return 1; } @@ -54,11 +54,6 @@ static inline dev_t new_decode_dev(u32 dev) return MKDEV(major, minor); } -static inline int huge_valid_dev(dev_t dev) -{ - return 1; -} - static inline u64 huge_encode_dev(dev_t dev) { return new_encode_dev(dev); diff --git a/kernel/include/linux/kernel.h b/kernel/include/linux/kernel.h index 8ecfe3c52..2370991ae 100644 --- a/kernel/include/linux/kernel.h +++ b/kernel/include/linux/kernel.h @@ -204,28 +204,28 @@ extern int _cond_resched(void); #define might_sleep_if(cond) do { if (cond) might_sleep(); } while (0) -/* - * abs() handles unsigned and signed longs, ints, shorts and chars. For all - * input types abs() returns a signed long. - * abs() should not be used for 64-bit types (s64, u64, long long) - use abs64() - * for those. +/** + * abs - return absolute value of an argument + * @x: the value. If it is unsigned type, it is converted to signed type first + * (s64, long or int depending on its size). + * + * Return: an absolute value of x. If x is 64-bit, macro's return type is s64, + * otherwise it is signed long. */ -#define abs(x) ({ \ - long ret; \ - if (sizeof(x) == sizeof(long)) { \ - long __x = (x); \ - ret = (__x < 0) ? -__x : __x; \ - } else { \ - int __x = (x); \ - ret = (__x < 0) ? -__x : __x; \ - } \ - ret; \ - }) - -#define abs64(x) ({ \ - s64 __x = (x); \ - (__x < 0) ? -__x : __x; \ - }) +#define abs(x) __builtin_choose_expr(sizeof(x) == sizeof(s64), ({ \ + s64 __x = (x); \ + (__x < 0) ? -__x : __x; \ + }), ({ \ + long ret; \ + if (sizeof(x) == sizeof(long)) { \ + long __x = (x); \ + ret = (__x < 0) ? -__x : __x; \ + } else { \ + int __x = (x); \ + ret = (__x < 0) ? -__x : __x; \ + } \ + ret; \ + })) /** * reciprocal_scale - "scale" a value into range [0, ep_ro) @@ -415,7 +415,10 @@ extern __printf(3, 0) int vscnprintf(char *buf, size_t size, const char *fmt, va_list args); extern __printf(2, 3) char *kasprintf(gfp_t gfp, const char *fmt, ...); -extern char *kvasprintf(gfp_t gfp, const char *fmt, va_list args); +extern __printf(2, 0) +char *kvasprintf(gfp_t gfp, const char *fmt, va_list args); +extern __printf(2, 0) +const char *kvasprintf_const(gfp_t gfp, const char *fmt, va_list args); extern __scanf(2, 3) int sscanf(const char *, const char *, ...); @@ -443,6 +446,9 @@ extern int panic_on_unrecovered_nmi; extern int panic_on_io_nmi; extern int panic_on_warn; extern int sysctl_panic_on_stackoverflow; + +extern bool crash_kexec_post_notifiers; + /* * Only to be used by arch init code. If the user over-wrote the default * CONFIG_PANIC_TIMEOUT, honor it. @@ -538,12 +544,6 @@ bool mac_pton(const char *s, u8 *mac); * * Most likely, you want to use tracing_on/tracing_off. */ -#ifdef CONFIG_RING_BUFFER -/* trace_off_permanent stops recording with no way to bring it back */ -void tracing_off_permanent(void); -#else -static inline void tracing_off_permanent(void) { } -#endif enum ftrace_dump_mode { DUMP_NONE, @@ -687,10 +687,10 @@ do { \ __ftrace_vprintk(_THIS_IP_, fmt, vargs); \ } while (0) -extern int +extern __printf(2, 0) int __ftrace_vbprintk(unsigned long ip, const char *fmt, va_list ap); -extern int +extern __printf(2, 0) int __ftrace_vprintk(unsigned long ip, const char *fmt, va_list ap); extern void ftrace_dump(enum ftrace_dump_mode oops_dump_mode); @@ -710,7 +710,7 @@ int trace_printk(const char *fmt, ...) { return 0; } -static inline int +static __printf(1, 0) inline int ftrace_vprintk(const char *fmt, va_list ap) { return 0; @@ -824,13 +824,15 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { } #endif /* Permissions on a sysfs file: you didn't miss the 0 prefix did you? */ -#define VERIFY_OCTAL_PERMISSIONS(perms) \ - (BUILD_BUG_ON_ZERO((perms) < 0) + \ - BUILD_BUG_ON_ZERO((perms) > 0777) + \ - /* User perms >= group perms >= other perms */ \ - BUILD_BUG_ON_ZERO(((perms) >> 6) < (((perms) >> 3) & 7)) + \ - BUILD_BUG_ON_ZERO((((perms) >> 3) & 7) < ((perms) & 7)) + \ - /* Other writable? Generally considered a bad idea. */ \ - BUILD_BUG_ON_ZERO((perms) & 2) + \ +#define VERIFY_OCTAL_PERMISSIONS(perms) \ + (BUILD_BUG_ON_ZERO((perms) < 0) + \ + BUILD_BUG_ON_ZERO((perms) > 0777) + \ + /* USER_READABLE >= GROUP_READABLE >= OTHER_READABLE */ \ + BUILD_BUG_ON_ZERO((((perms) >> 6) & 4) < (((perms) >> 3) & 4)) + \ + BUILD_BUG_ON_ZERO((((perms) >> 3) & 4) < ((perms) & 4)) + \ + /* USER_WRITABLE >= GROUP_WRITABLE */ \ + BUILD_BUG_ON_ZERO((((perms) >> 6) & 2) < (((perms) >> 3) & 2)) + \ + /* OTHER_WRITABLE? Generally considered a bad idea. */ \ + BUILD_BUG_ON_ZERO((perms) & 2) + \ (perms)) #endif diff --git a/kernel/include/linux/kernfs.h b/kernel/include/linux/kernfs.h index 29d1896c3..5d4e9c4b8 100644 --- a/kernel/include/linux/kernfs.h +++ b/kernel/include/linux/kernfs.h @@ -266,6 +266,7 @@ static inline bool kernfs_ns_enabled(struct kernfs_node *kn) } int kernfs_name(struct kernfs_node *kn, char *buf, size_t buflen); +size_t kernfs_path_len(struct kernfs_node *kn); char * __must_check kernfs_path(struct kernfs_node *kn, char *buf, size_t buflen); void pr_cont_kernfs_name(struct kernfs_node *kn); @@ -278,6 +279,7 @@ void kernfs_put(struct kernfs_node *kn); struct kernfs_node *kernfs_node_from_dentry(struct dentry *dentry); struct kernfs_root *kernfs_root_from_sb(struct super_block *sb); +struct inode *kernfs_get_inode(struct super_block *sb, struct kernfs_node *kn); struct kernfs_root *kernfs_create_root(struct kernfs_syscall_ops *scops, unsigned int flags, void *priv); @@ -331,6 +333,9 @@ static inline bool kernfs_ns_enabled(struct kernfs_node *kn) static inline int kernfs_name(struct kernfs_node *kn, char *buf, size_t buflen) { return -ENOSYS; } +static inline size_t kernfs_path_len(struct kernfs_node *kn) +{ return 0; } + static inline char * __must_check kernfs_path(struct kernfs_node *kn, char *buf, size_t buflen) { return NULL; } @@ -355,6 +360,10 @@ static inline struct kernfs_node *kernfs_node_from_dentry(struct dentry *dentry) static inline struct kernfs_root *kernfs_root_from_sb(struct super_block *sb) { return NULL; } +static inline struct inode * +kernfs_get_inode(struct super_block *sb, struct kernfs_node *kn) +{ return NULL; } + static inline struct kernfs_root * kernfs_create_root(struct kernfs_syscall_ops *scops, unsigned int flags, void *priv) diff --git a/kernel/include/linux/kexec.h b/kernel/include/linux/kexec.h index e804306ef..d140b1e9f 100644 --- a/kernel/include/linux/kexec.h +++ b/kernel/include/linux/kexec.h @@ -16,7 +16,7 @@ #include <uapi/linux/kexec.h> -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE #include <linux/list.h> #include <linux/linkage.h> #include <linux/compat.h> @@ -318,12 +318,24 @@ int crash_shrink_memory(unsigned long new_size); size_t crash_get_memory_size(void); void crash_free_reserved_phys_range(unsigned long begin, unsigned long end); -#else /* !CONFIG_KEXEC */ +int __weak arch_kexec_kernel_image_probe(struct kimage *image, void *buf, + unsigned long buf_len); +void * __weak arch_kexec_kernel_image_load(struct kimage *image); +int __weak arch_kimage_file_post_load_cleanup(struct kimage *image); +int __weak arch_kexec_kernel_verify_sig(struct kimage *image, void *buf, + unsigned long buf_len); +int __weak arch_kexec_apply_relocations_add(const Elf_Ehdr *ehdr, + Elf_Shdr *sechdrs, unsigned int relsec); +int __weak arch_kexec_apply_relocations(const Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, + unsigned int relsec); + +#else /* !CONFIG_KEXEC_CORE */ struct pt_regs; struct task_struct; static inline void crash_kexec(struct pt_regs *regs) { } static inline int kexec_should_crash(struct task_struct *p) { return 0; } -#endif /* CONFIG_KEXEC */ +#define kexec_in_progress false +#endif /* CONFIG_KEXEC_CORE */ #endif /* !defined(__ASSEBMLY__) */ diff --git a/kernel/include/linux/key-type.h b/kernel/include/linux/key-type.h index ff9f1d394..7463355a1 100644 --- a/kernel/include/linux/key-type.h +++ b/kernel/include/linux/key-type.h @@ -40,8 +40,7 @@ struct key_construction { */ struct key_preparsed_payload { char *description; /* Proposed key description (or NULL) */ - void *type_data[2]; /* Private key-type data */ - void *payload[2]; /* Proposed payload */ + union key_payload payload; /* Proposed payload */ const void *data; /* Raw data */ size_t datalen; /* Raw datalen */ size_t quotalen; /* Quota length for proposed payload */ diff --git a/kernel/include/linux/key.h b/kernel/include/linux/key.h index e1d4715f3..66f705243 100644 --- a/kernel/include/linux/key.h +++ b/kernel/include/linux/key.h @@ -89,6 +89,11 @@ struct keyring_index_key { size_t desc_len; }; +union key_payload { + void __rcu *rcu_data0; + void *data[4]; +}; + /*****************************************************************************/ /* * key reference with possession attribute handling @@ -186,28 +191,18 @@ struct key { }; }; - /* type specific data - * - this is used by the keyring type to index the name - */ - union { - struct list_head link; - unsigned long x[2]; - void *p[2]; - int reject_error; - } type_data; - /* key data * - this is used to hold the data actually used in cryptography or * whatever */ union { - union { - unsigned long value; - void __rcu *rcudata; - void *data; - void *data2[2]; - } payload; - struct assoc_array keys; + union key_payload payload; + struct { + /* Keyring bits */ + struct list_head name_link; + struct assoc_array keys; + }; + int reject_error; }; }; @@ -336,12 +331,12 @@ static inline bool key_is_instantiated(const struct key *key) } #define rcu_dereference_key(KEY) \ - (rcu_dereference_protected((KEY)->payload.rcudata, \ + (rcu_dereference_protected((KEY)->payload.rcu_data0, \ rwsem_is_locked(&((struct key *)(KEY))->sem))) #define rcu_assign_keypointer(KEY, PAYLOAD) \ do { \ - rcu_assign_pointer((KEY)->payload.rcudata, (PAYLOAD)); \ + rcu_assign_pointer((KEY)->payload.rcu_data0, (PAYLOAD)); \ } while (0) #ifdef CONFIG_SYSCTL diff --git a/kernel/include/linux/klist.h b/kernel/include/linux/klist.h index 61e5b723a..953f283f8 100644 --- a/kernel/include/linux/klist.h +++ b/kernel/include/linux/klist.h @@ -63,6 +63,7 @@ extern void klist_iter_init(struct klist *k, struct klist_iter *i); extern void klist_iter_init_node(struct klist *k, struct klist_iter *i, struct klist_node *n); extern void klist_iter_exit(struct klist_iter *i); +extern struct klist_node *klist_prev(struct klist_iter *i); extern struct klist_node *klist_next(struct klist_iter *i); #endif diff --git a/kernel/include/linux/kmemleak.h b/kernel/include/linux/kmemleak.h index d0a1f99e2..4894c6888 100644 --- a/kernel/include/linux/kmemleak.h +++ b/kernel/include/linux/kmemleak.h @@ -25,7 +25,7 @@ #ifdef CONFIG_DEBUG_KMEMLEAK -extern void kmemleak_init(void) __ref; +extern void kmemleak_init(void) __init; extern void kmemleak_alloc(const void *ptr, size_t size, int min_count, gfp_t gfp) __ref; extern void kmemleak_alloc_percpu(const void __percpu *ptr, size_t size, diff --git a/kernel/include/linux/kmod.h b/kernel/include/linux/kmod.h index 0555cc66a..fcfd2bf14 100644 --- a/kernel/include/linux/kmod.h +++ b/kernel/include/linux/kmod.h @@ -85,8 +85,6 @@ enum umh_disable_depth { UMH_DISABLED, }; -extern void usermodehelper_init(void); - extern int __usermodehelper_disable(enum umh_disable_depth depth); extern void __usermodehelper_set_disable_depth(enum umh_disable_depth depth); diff --git a/kernel/include/linux/kobject.h b/kernel/include/linux/kobject.h index 2d61b909f..e62845915 100644 --- a/kernel/include/linux/kobject.h +++ b/kernel/include/linux/kobject.h @@ -66,7 +66,7 @@ struct kobject { struct kobject *parent; struct kset *kset; struct kobj_type *ktype; - struct kernfs_node *sd; + struct kernfs_node *sd; /* sysfs directory entry */ struct kref kref; #ifdef CONFIG_DEBUG_KOBJECT_RELEASE struct delayed_work release; @@ -80,8 +80,9 @@ struct kobject { extern __printf(2, 3) int kobject_set_name(struct kobject *kobj, const char *name, ...); -extern int kobject_set_name_vargs(struct kobject *kobj, const char *fmt, - va_list vargs); +extern __printf(2, 0) +int kobject_set_name_vargs(struct kobject *kobj, const char *fmt, + va_list vargs); static inline const char *kobject_name(const struct kobject *kobj) { diff --git a/kernel/include/linux/kprobes.h b/kernel/include/linux/kprobes.h index 1ab54754a..8f6849084 100644 --- a/kernel/include/linux/kprobes.h +++ b/kernel/include/linux/kprobes.h @@ -267,6 +267,8 @@ extern void show_registers(struct pt_regs *regs); extern void kprobes_inc_nmissed_count(struct kprobe *p); extern bool arch_within_kprobe_blacklist(unsigned long addr); +extern bool within_kprobe_blacklist(unsigned long addr); + struct kprobe_insn_cache { struct mutex mutex; void *(*alloc)(void); /* allocate insn page */ diff --git a/kernel/include/linux/kref.h b/kernel/include/linux/kref.h index 484604d18..e15828fd7 100644 --- a/kernel/include/linux/kref.h +++ b/kernel/include/linux/kref.h @@ -19,7 +19,6 @@ #include <linux/atomic.h> #include <linux/kernel.h> #include <linux/mutex.h> -#include <linux/spinlock.h> struct kref { atomic_t refcount; @@ -99,38 +98,6 @@ static inline int kref_put(struct kref *kref, void (*release)(struct kref *kref) return kref_sub(kref, 1, release); } -/** - * kref_put_spinlock_irqsave - decrement refcount for object. - * @kref: object. - * @release: pointer to the function that will clean up the object when the - * last reference to the object is released. - * This pointer is required, and it is not acceptable to pass kfree - * in as this function. - * @lock: lock to take in release case - * - * Behaves identical to kref_put with one exception. If the reference count - * drops to zero, the lock will be taken atomically wrt dropping the reference - * count. The release function has to call spin_unlock() without _irqrestore. - */ -static inline int kref_put_spinlock_irqsave(struct kref *kref, - void (*release)(struct kref *kref), - spinlock_t *lock) -{ - unsigned long flags; - - WARN_ON(release == NULL); - if (atomic_add_unless(&kref->refcount, -1, 1)) - return 0; - spin_lock_irqsave(lock, flags); - if (atomic_dec_and_test(&kref->refcount)) { - release(kref); - local_irq_restore(flags); - return 1; - } - spin_unlock_irqrestore(lock, flags); - return 0; -} - static inline int kref_put_mutex(struct kref *kref, void (*release)(struct kref *kref), struct mutex *lock) diff --git a/kernel/include/linux/kthread.h b/kernel/include/linux/kthread.h index 13d55206c..e691b6a23 100644 --- a/kernel/include/linux/kthread.h +++ b/kernel/include/linux/kthread.h @@ -11,7 +11,7 @@ struct task_struct *kthread_create_on_node(int (*threadfn)(void *data), const char namefmt[], ...); #define kthread_create(threadfn, data, namefmt, arg...) \ - kthread_create_on_node(threadfn, data, -1, namefmt, ##arg) + kthread_create_on_node(threadfn, data, NUMA_NO_NODE, namefmt, ##arg) struct task_struct *kthread_create_on_cpu(int (*threadfn)(void *data), @@ -38,6 +38,7 @@ struct task_struct *kthread_create_on_cpu(int (*threadfn)(void *data), }) void kthread_bind(struct task_struct *k, unsigned int cpu); +void kthread_bind_mask(struct task_struct *k, const struct cpumask *mask); int kthread_stop(struct task_struct *k); bool kthread_should_stop(void); bool kthread_should_park(void); diff --git a/kernel/include/linux/kvm_host.h b/kernel/include/linux/kvm_host.h index 84df94a3d..c690acc69 100644 --- a/kernel/include/linux/kvm_host.h +++ b/kernel/include/linux/kvm_host.h @@ -24,6 +24,8 @@ #include <linux/err.h> #include <linux/irqflags.h> #include <linux/context_tracking.h> +#include <linux/irqbypass.h> +#include <linux/swait.h> #include <asm/signal.h> #include <linux/kvm.h> @@ -44,6 +46,10 @@ /* Two fragments for cross MMIO pages. */ #define KVM_MAX_MMIO_FRAGMENTS 2 +#ifndef KVM_ADDRESS_SPACE_NUM +#define KVM_ADDRESS_SPACE_NUM 1 +#endif + /* * For the normal pfn, the highest 12 bits should be zero, * so we can mask bit 62 ~ bit 52 to indicate the error pfn, @@ -134,6 +140,10 @@ static inline bool is_error_page(struct page *page) #define KVM_REQ_ENABLE_IBS 23 #define KVM_REQ_DISABLE_IBS 24 #define KVM_REQ_APIC_PAGE_RELOAD 25 +#define KVM_REQ_SMI 26 +#define KVM_REQ_HV_CRASH 27 +#define KVM_REQ_IOAPIC_EOI_EXIT 28 +#define KVM_REQ_HV_RESET 29 #define KVM_USERSPACE_IRQ_SOURCE_ID 0 #define KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID 1 @@ -225,16 +235,21 @@ struct kvm_vcpu { unsigned long requests; unsigned long guest_debug; + int pre_pcpu; + struct list_head blocked_vcpu_list; + struct mutex mutex; struct kvm_run *run; int fpu_active; int guest_fpu_loaded, guest_xcr0_loaded; - struct swait_head wq; + unsigned char fpu_counter; + struct swait_queue_head wq; struct pid *pid; int sigset_active; sigset_t sigset; struct kvm_vcpu_stat stat; + unsigned int halt_poll_ns; #ifdef CONFIG_HAS_IOMEM int mmio_needed; @@ -321,6 +336,18 @@ struct kvm_kernel_irq_routing_entry { struct hlist_node link; }; +#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING +struct kvm_irq_routing_table { + int chip[KVM_NR_IRQCHIPS][KVM_IRQCHIP_NUM_PINS]; + u32 nr_rt_entries; + /* + * Array indexed by gsi. Each entry contains list of irq chips + * the gsi is connected to. + */ + struct hlist_head map[0]; +}; +#endif + #ifndef KVM_PRIVATE_MEM_SLOTS #define KVM_PRIVATE_MEM_SLOTS 0 #endif @@ -329,6 +356,13 @@ struct kvm_kernel_irq_routing_entry { #define KVM_MEM_SLOTS_NUM (KVM_USER_MEM_SLOTS + KVM_PRIVATE_MEM_SLOTS) #endif +#ifndef __KVM_VCPU_MULTIPLE_ADDRESS_SPACE +static inline int kvm_arch_vcpu_memslots_id(struct kvm_vcpu *vcpu) +{ + return 0; +} +#endif + /* * Note: * memslots are not sorted by id anymore, please use id_to_memslot() @@ -347,12 +381,9 @@ struct kvm { spinlock_t mmu_lock; struct mutex slots_lock; struct mm_struct *mm; /* userspace tied to this vm */ - struct kvm_memslots *memslots; + struct kvm_memslots *memslots[KVM_ADDRESS_SPACE_NUM]; struct srcu_struct srcu; struct srcu_struct irq_srcu; -#ifdef CONFIG_KVM_APIC_ARCHITECTURE - u32 bsp_vcpu_id; -#endif struct kvm_vcpu *vcpus[KVM_MAX_VCPUS]; atomic_t online_vcpus; int last_boosted_vcpu; @@ -411,8 +442,15 @@ struct kvm { #define vcpu_unimpl(vcpu, fmt, ...) \ kvm_pr_unimpl("vcpu%i " fmt, (vcpu)->vcpu_id, ## __VA_ARGS__) +#define vcpu_debug(vcpu, fmt, ...) \ + kvm_debug("vcpu%i " fmt, (vcpu)->vcpu_id, ## __VA_ARGS__) + static inline struct kvm_vcpu *kvm_get_vcpu(struct kvm *kvm, int i) { + /* Pairs with smp_wmb() in kvm_vm_ioctl_create_vcpu, in case + * the caller has read kvm->online_vcpus before (as is the case + * for kvm_for_each_vcpu, for example). + */ smp_rmb(); return kvm->vcpus[i]; } @@ -423,6 +461,17 @@ static inline struct kvm_vcpu *kvm_get_vcpu(struct kvm *kvm, int i) (vcpup = kvm_get_vcpu(kvm, idx)) != NULL; \ idx++) +static inline struct kvm_vcpu *kvm_get_vcpu_by_id(struct kvm *kvm, int id) +{ + struct kvm_vcpu *vcpu; + int i; + + kvm_for_each_vcpu(i, vcpu, kvm) + if (vcpu->vcpu_id == id) + return vcpu; + return NULL; +} + #define kvm_for_each_memslot(memslot, slots) \ for (memslot = &slots->memslots[0]; \ memslot < slots->memslots + KVM_MEM_SLOTS_NUM && memslot->npages;\ @@ -436,10 +485,14 @@ void vcpu_put(struct kvm_vcpu *vcpu); #ifdef __KVM_HAVE_IOAPIC void kvm_vcpu_request_scan_ioapic(struct kvm *kvm); +void kvm_arch_irq_routing_update(struct kvm *kvm); #else static inline void kvm_vcpu_request_scan_ioapic(struct kvm *kvm) { } +static inline void kvm_arch_irq_routing_update(struct kvm *kvm) +{ +} #endif #ifdef CONFIG_HAVE_KVM_IRQFD @@ -462,13 +515,25 @@ void kvm_exit(void); void kvm_get_kvm(struct kvm *kvm); void kvm_put_kvm(struct kvm *kvm); -static inline struct kvm_memslots *kvm_memslots(struct kvm *kvm) +static inline struct kvm_memslots *__kvm_memslots(struct kvm *kvm, int as_id) { - return rcu_dereference_check(kvm->memslots, + return rcu_dereference_check(kvm->memslots[as_id], srcu_read_lock_held(&kvm->srcu) || lockdep_is_held(&kvm->slots_lock)); } +static inline struct kvm_memslots *kvm_memslots(struct kvm *kvm) +{ + return __kvm_memslots(kvm, 0); +} + +static inline struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu) +{ + int as_id = kvm_arch_vcpu_memslots_id(vcpu); + + return __kvm_memslots(vcpu->kvm, as_id); +} + static inline struct kvm_memory_slot * id_to_memslot(struct kvm_memslots *slots, int id) { @@ -500,21 +565,22 @@ enum kvm_mr_change { }; int kvm_set_memory_region(struct kvm *kvm, - struct kvm_userspace_memory_region *mem); + const struct kvm_userspace_memory_region *mem); int __kvm_set_memory_region(struct kvm *kvm, - struct kvm_userspace_memory_region *mem); + const struct kvm_userspace_memory_region *mem); void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free, struct kvm_memory_slot *dont); int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, unsigned long npages); -void kvm_arch_memslots_updated(struct kvm *kvm); +void kvm_arch_memslots_updated(struct kvm *kvm, struct kvm_memslots *slots); int kvm_arch_prepare_memory_region(struct kvm *kvm, struct kvm_memory_slot *memslot, - struct kvm_userspace_memory_region *mem, + const struct kvm_userspace_memory_region *mem, enum kvm_mr_change change); void kvm_arch_commit_memory_region(struct kvm *kvm, - struct kvm_userspace_memory_region *mem, + const struct kvm_userspace_memory_region *mem, const struct kvm_memory_slot *old, + const struct kvm_memory_slot *new, enum kvm_mr_change change); bool kvm_largepages_enabled(void); void kvm_disable_largepages(void); @@ -524,8 +590,8 @@ void kvm_arch_flush_shadow_all(struct kvm *kvm); void kvm_arch_flush_shadow_memslot(struct kvm *kvm, struct kvm_memory_slot *slot); -int gfn_to_page_many_atomic(struct kvm *kvm, gfn_t gfn, struct page **pages, - int nr_pages); +int gfn_to_page_many_atomic(struct kvm_memory_slot *slot, gfn_t gfn, + struct page **pages, int nr_pages); struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn); unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn); @@ -538,13 +604,13 @@ void kvm_release_page_dirty(struct page *page); void kvm_set_page_accessed(struct page *page); pfn_t gfn_to_pfn_atomic(struct kvm *kvm, gfn_t gfn); -pfn_t gfn_to_pfn_async(struct kvm *kvm, gfn_t gfn, bool *async, - bool write_fault, bool *writable); pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn); pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault, bool *writable); pfn_t gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn); pfn_t gfn_to_pfn_memslot_atomic(struct kvm_memory_slot *slot, gfn_t gfn); +pfn_t __gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn, bool atomic, + bool *async, bool write_fault, bool *writable); void kvm_release_pfn_clean(pfn_t pfn); void kvm_set_pfn_dirty(pfn_t pfn); @@ -573,7 +639,28 @@ int kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn); unsigned long kvm_host_page_size(struct kvm *kvm, gfn_t gfn); void mark_page_dirty(struct kvm *kvm, gfn_t gfn); +struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu); +struct kvm_memory_slot *kvm_vcpu_gfn_to_memslot(struct kvm_vcpu *vcpu, gfn_t gfn); +pfn_t kvm_vcpu_gfn_to_pfn_atomic(struct kvm_vcpu *vcpu, gfn_t gfn); +pfn_t kvm_vcpu_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn); +struct page *kvm_vcpu_gfn_to_page(struct kvm_vcpu *vcpu, gfn_t gfn); +unsigned long kvm_vcpu_gfn_to_hva(struct kvm_vcpu *vcpu, gfn_t gfn); +unsigned long kvm_vcpu_gfn_to_hva_prot(struct kvm_vcpu *vcpu, gfn_t gfn, bool *writable); +int kvm_vcpu_read_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, void *data, int offset, + int len); +int kvm_vcpu_read_guest_atomic(struct kvm_vcpu *vcpu, gpa_t gpa, void *data, + unsigned long len); +int kvm_vcpu_read_guest(struct kvm_vcpu *vcpu, gpa_t gpa, void *data, + unsigned long len); +int kvm_vcpu_write_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, const void *data, + int offset, int len); +int kvm_vcpu_write_guest(struct kvm_vcpu *vcpu, gpa_t gpa, const void *data, + unsigned long len); +void kvm_vcpu_mark_page_dirty(struct kvm_vcpu *vcpu, gfn_t gfn); + void kvm_vcpu_block(struct kvm_vcpu *vcpu); +void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu); +void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu); void kvm_vcpu_kick(struct kvm_vcpu *vcpu); int kvm_vcpu_yield_to(struct kvm_vcpu *target); void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu); @@ -689,8 +776,26 @@ static inline bool kvm_arch_has_noncoherent_dma(struct kvm *kvm) return false; } #endif +#ifdef __KVM_HAVE_ARCH_ASSIGNED_DEVICE +void kvm_arch_start_assignment(struct kvm *kvm); +void kvm_arch_end_assignment(struct kvm *kvm); +bool kvm_arch_has_assigned_device(struct kvm *kvm); +#else +static inline void kvm_arch_start_assignment(struct kvm *kvm) +{ +} -static inline struct swait_head *kvm_arch_vcpu_wq(struct kvm_vcpu *vcpu) +static inline void kvm_arch_end_assignment(struct kvm *kvm) +{ +} + +static inline bool kvm_arch_has_assigned_device(struct kvm *kvm) +{ + return false; +} +#endif + +static inline struct swait_queue_head *kvm_arch_vcpu_wq(struct kvm_vcpu *vcpu) { #ifdef __KVM_HAVE_ARCH_WQP return vcpu->arch.wqp; @@ -734,10 +839,13 @@ int kvm_irq_map_chip_pin(struct kvm *kvm, unsigned irqchip, unsigned pin); int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level, bool line_status); -int kvm_set_irq_inatomic(struct kvm *kvm, int irq_source_id, u32 irq, int level); int kvm_set_msi(struct kvm_kernel_irq_routing_entry *irq_entry, struct kvm *kvm, int irq_source_id, int level, bool line_status); +int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e, + struct kvm *kvm, int irq_source_id, + int level, bool line_status); bool kvm_irq_has_notifier(struct kvm *kvm, unsigned irqchip, unsigned pin); +void kvm_notify_acked_gsi(struct kvm *kvm, int gsi); void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin); void kvm_register_irq_ack_notifier(struct kvm *kvm, struct kvm_irq_ack_notifier *kian); @@ -762,16 +870,10 @@ static inline void kvm_iommu_unmap_pages(struct kvm *kvm, } #endif -static inline void kvm_guest_enter(void) +/* must be called with irqs disabled */ +static inline void __kvm_guest_enter(void) { - unsigned long flags; - - BUG_ON(preemptible()); - - local_irq_save(flags); guest_enter(); - local_irq_restore(flags); - /* KVM does not hold any references to rcu protected data when it * switches CPU into a guest mode. In fact switching to a guest mode * is very similar to exiting to userspace from rcu point of view. In @@ -783,12 +885,27 @@ static inline void kvm_guest_enter(void) rcu_virt_note_context_switch(smp_processor_id()); } +/* must be called with irqs disabled */ +static inline void __kvm_guest_exit(void) +{ + guest_exit(); +} + +static inline void kvm_guest_enter(void) +{ + unsigned long flags; + + local_irq_save(flags); + __kvm_guest_enter(); + local_irq_restore(flags); +} + static inline void kvm_guest_exit(void) { unsigned long flags; local_irq_save(flags); - guest_exit(); + __kvm_guest_exit(); local_irq_restore(flags); } @@ -924,6 +1041,7 @@ static inline int mmu_notifier_retry(struct kvm *kvm, unsigned long mmu_seq) #endif int kvm_setup_default_irq_routing(struct kvm *kvm); +int kvm_setup_empty_irq_routing(struct kvm *kvm); int kvm_set_irq_routing(struct kvm *kvm, const struct kvm_irq_routing_entry *entries, unsigned nr, @@ -983,22 +1101,9 @@ static inline int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args) #endif /* CONFIG_HAVE_KVM_EVENTFD */ #ifdef CONFIG_KVM_APIC_ARCHITECTURE -static inline bool kvm_vcpu_is_reset_bsp(struct kvm_vcpu *vcpu) -{ - return vcpu->kvm->bsp_vcpu_id == vcpu->vcpu_id; -} - -static inline bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu) -{ - return (vcpu->arch.apic_base & MSR_IA32_APICBASE_BSP) != 0; -} - bool kvm_vcpu_compatible(struct kvm_vcpu *vcpu); - #else - static inline bool kvm_vcpu_compatible(struct kvm_vcpu *vcpu) { return true; } - #endif static inline void kvm_make_request(int req, struct kvm_vcpu *vcpu) @@ -1079,5 +1184,16 @@ static inline void kvm_vcpu_set_dy_eligible(struct kvm_vcpu *vcpu, bool val) { } #endif /* CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT */ -#endif +#ifdef CONFIG_HAVE_KVM_IRQ_BYPASS +int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *, + struct irq_bypass_producer *); +void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *, + struct irq_bypass_producer *); +void kvm_arch_irq_bypass_stop(struct irq_bypass_consumer *); +void kvm_arch_irq_bypass_start(struct irq_bypass_consumer *); +int kvm_arch_update_irqfd_routing(struct kvm *kvm, unsigned int host_irq, + uint32_t guest_irq, bool set); +#endif /* CONFIG_HAVE_KVM_IRQ_BYPASS */ + +#endif diff --git a/kernel/include/linux/kvm_irqfd.h b/kernel/include/linux/kvm_irqfd.h new file mode 100644 index 000000000..0c1de0509 --- /dev/null +++ b/kernel/include/linux/kvm_irqfd.h @@ -0,0 +1,71 @@ +/* + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * irqfd: Allows an fd to be used to inject an interrupt to the guest + * Credit goes to Avi Kivity for the original idea. + */ + +#ifndef __LINUX_KVM_IRQFD_H +#define __LINUX_KVM_IRQFD_H + +#include <linux/kvm_host.h> +#include <linux/poll.h> + +/* + * Resampling irqfds are a special variety of irqfds used to emulate + * level triggered interrupts. The interrupt is asserted on eventfd + * trigger. On acknowledgment through the irq ack notifier, the + * interrupt is de-asserted and userspace is notified through the + * resamplefd. All resamplers on the same gsi are de-asserted + * together, so we don't need to track the state of each individual + * user. We can also therefore share the same irq source ID. + */ +struct kvm_kernel_irqfd_resampler { + struct kvm *kvm; + /* + * List of resampling struct _irqfd objects sharing this gsi. + * RCU list modified under kvm->irqfds.resampler_lock + */ + struct list_head list; + struct kvm_irq_ack_notifier notifier; + /* + * Entry in list of kvm->irqfd.resampler_list. Use for sharing + * resamplers among irqfds on the same gsi. + * Accessed and modified under kvm->irqfds.resampler_lock + */ + struct list_head link; +}; + +struct kvm_kernel_irqfd { + /* Used for MSI fast-path */ + struct kvm *kvm; + wait_queue_t wait; + /* Update side is protected by irqfds.lock */ + struct kvm_kernel_irq_routing_entry irq_entry; + seqcount_t irq_entry_sc; + /* Used for level IRQ fast-path */ + int gsi; + struct work_struct inject; + /* The resampler used by this irqfd (resampler-only) */ + struct kvm_kernel_irqfd_resampler *resampler; + /* Eventfd notified on resample (resampler-only) */ + struct eventfd_ctx *resamplefd; + /* Entry in list of irqfds for a resampler (resampler-only) */ + struct list_head resampler_link; + /* Used for setup/shutdown */ + struct eventfd_ctx *eventfd; + struct list_head list; + poll_table pt; + struct work_struct shutdown; + struct irq_bypass_consumer consumer; + struct irq_bypass_producer *producer; +}; + +#endif /* __LINUX_KVM_IRQFD_H */ diff --git a/kernel/include/linux/kvm_types.h b/kernel/include/linux/kvm_types.h index 931da7e91..1b47a185c 100644 --- a/kernel/include/linux/kvm_types.h +++ b/kernel/include/linux/kvm_types.h @@ -28,6 +28,7 @@ struct kvm_run; struct kvm_userspace_memory_region; struct kvm_vcpu; struct kvm_vcpu_init; +struct kvm_memslots; enum kvm_mr_change; diff --git a/kernel/include/linux/leds.h b/kernel/include/linux/leds.h index 9a2b00009..fa359c79c 100644 --- a/kernel/include/linux/leds.h +++ b/kernel/include/linux/leds.h @@ -12,6 +12,7 @@ #ifndef __LINUX_LEDS_H_INCLUDED #define __LINUX_LEDS_H_INCLUDED +#include <linux/device.h> #include <linux/list.h> #include <linux/mutex.h> #include <linux/rwsem.h> @@ -222,6 +223,11 @@ struct led_trigger { struct list_head next_trig; }; +ssize_t led_trigger_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count); +ssize_t led_trigger_show(struct device *dev, struct device_attribute *attr, + char *buf); + /* Registration functions for complex triggers */ extern int led_trigger_register(struct led_trigger *trigger); extern void led_trigger_unregister(struct led_trigger *trigger); @@ -238,6 +244,16 @@ extern void led_trigger_blink_oneshot(struct led_trigger *trigger, unsigned long *delay_on, unsigned long *delay_off, int invert); +extern void led_trigger_set_default(struct led_classdev *led_cdev); +extern void led_trigger_set(struct led_classdev *led_cdev, + struct led_trigger *trigger); +extern void led_trigger_remove(struct led_classdev *led_cdev); + +static inline void *led_get_trigger_data(struct led_classdev *led_cdev) +{ + return led_cdev->trigger_data; +} + /** * led_trigger_rename_static - rename a trigger * @name: the new trigger name @@ -267,6 +283,22 @@ static inline void led_trigger_register_simple(const char *name, static inline void led_trigger_unregister_simple(struct led_trigger *trigger) {} static inline void led_trigger_event(struct led_trigger *trigger, enum led_brightness event) {} +static inline void led_trigger_blink(struct led_trigger *trigger, + unsigned long *delay_on, + unsigned long *delay_off) {} +static inline void led_trigger_blink_oneshot(struct led_trigger *trigger, + unsigned long *delay_on, + unsigned long *delay_off, + int invert) {} +static inline void led_trigger_set_default(struct led_classdev *led_cdev) {} +static inline void led_trigger_set(struct led_classdev *led_cdev, + struct led_trigger *trigger) {} +static inline void led_trigger_remove(struct led_classdev *led_cdev) {} +static inline void *led_get_trigger_data(struct led_classdev *led_cdev) +{ + return NULL; +} + #endif /* CONFIG_LEDS_TRIGGERS */ /* Trigger specific functions */ diff --git a/kernel/include/linux/lglock.h b/kernel/include/linux/lglock.h index 9603a1500..6f035f635 100644 --- a/kernel/include/linux/lglock.h +++ b/kernel/include/linux/lglock.h @@ -34,10 +34,10 @@ #endif struct lglock { -#ifndef CONFIG_PREEMPT_RT_FULL - arch_spinlock_t __percpu *lock; -#else +#ifdef CONFIG_PREEMPT_RT_FULL struct rt_mutex __percpu *lock; +#else + arch_spinlock_t __percpu *lock; #endif #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lock_class_key lock_key; @@ -45,34 +45,40 @@ struct lglock { #endif }; -#ifndef CONFIG_PREEMPT_RT_FULL +#ifdef CONFIG_PREEMPT_RT_FULL # define DEFINE_LGLOCK(name) \ - static DEFINE_PER_CPU(arch_spinlock_t, name ## _lock) \ - = __ARCH_SPIN_LOCK_UNLOCKED; \ + static DEFINE_PER_CPU(struct rt_mutex, name ## _lock) \ + = __RT_MUTEX_INITIALIZER( name ## _lock); \ struct lglock name = { .lock = &name ## _lock } # define DEFINE_STATIC_LGLOCK(name) \ - static DEFINE_PER_CPU(arch_spinlock_t, name ## _lock) \ - = __ARCH_SPIN_LOCK_UNLOCKED; \ + static DEFINE_PER_CPU(struct rt_mutex, name ## _lock) \ + = __RT_MUTEX_INITIALIZER( name ## _lock); \ static struct lglock name = { .lock = &name ## _lock } + #else -# define DEFINE_LGLOCK(name) \ - static DEFINE_PER_CPU(struct rt_mutex, name ## _lock) \ - = __RT_MUTEX_INITIALIZER( name ## _lock); \ +#define DEFINE_LGLOCK(name) \ + static DEFINE_PER_CPU(arch_spinlock_t, name ## _lock) \ + = __ARCH_SPIN_LOCK_UNLOCKED; \ struct lglock name = { .lock = &name ## _lock } -# define DEFINE_STATIC_LGLOCK(name) \ - static DEFINE_PER_CPU(struct rt_mutex, name ## _lock) \ - = __RT_MUTEX_INITIALIZER( name ## _lock); \ +#define DEFINE_STATIC_LGLOCK(name) \ + static DEFINE_PER_CPU(arch_spinlock_t, name ## _lock) \ + = __ARCH_SPIN_LOCK_UNLOCKED; \ static struct lglock name = { .lock = &name ## _lock } #endif void lg_lock_init(struct lglock *lg, char *name); + void lg_local_lock(struct lglock *lg); void lg_local_unlock(struct lglock *lg); void lg_local_lock_cpu(struct lglock *lg, int cpu); void lg_local_unlock_cpu(struct lglock *lg, int cpu); + +void lg_double_lock(struct lglock *lg, int cpu1, int cpu2); +void lg_double_unlock(struct lglock *lg, int cpu1, int cpu2); + void lg_global_lock(struct lglock *lg); void lg_global_unlock(struct lglock *lg); diff --git a/kernel/include/linux/libata.h b/kernel/include/linux/libata.h index e0e33787c..b20a2752f 100644 --- a/kernel/include/linux/libata.h +++ b/kernel/include/linux/libata.h @@ -134,7 +134,6 @@ enum { ATA_ALL_DEVICES = (1 << ATA_MAX_DEVICES) - 1, ATA_SHT_EMULATED = 1, - ATA_SHT_CMD_PER_LUN = 1, ATA_SHT_THIS_ID = -1, ATA_SHT_USE_CLUSTERING = 1, @@ -211,6 +210,7 @@ enum { ATA_FLAG_SLAVE_POSS = (1 << 0), /* host supports slave dev */ /* (doesn't imply presence) */ ATA_FLAG_SATA = (1 << 1), + ATA_FLAG_NO_LOG_PAGE = (1 << 5), /* do not issue log page read */ ATA_FLAG_NO_ATAPI = (1 << 6), /* No ATAPI support */ ATA_FLAG_PIO_DMA = (1 << 7), /* PIO cmds via DMA */ ATA_FLAG_PIO_LBA48 = (1 << 8), /* Host DMA engine is LBA28 only */ @@ -255,6 +255,7 @@ enum { ATA_PFLAG_PIO32 = (1 << 20), /* 32bit PIO */ ATA_PFLAG_PIO32CHANGE = (1 << 21), /* 32bit PIO can be turned on/off */ + ATA_PFLAG_EXTERNAL = (1 << 22), /* eSATA/external port */ /* struct ata_queued_cmd flags */ ATA_QCFLAG_ACTIVE = (1 << 0), /* cmd not yet ack'd to scsi lyer */ @@ -717,7 +718,7 @@ struct ata_device { union { u16 id[ATA_ID_WORDS]; /* IDENTIFY xxx DEVICE data */ u32 gscr[SATA_PMP_GSCR_DWORDS]; /* PMP GSCR block */ - }; + } ____cacheline_aligned; /* DEVSLP Timing Variables from Identify Device Data Log */ u8 devslp_timing[ATA_LOG_DEVSLP_SIZE]; @@ -1367,7 +1368,6 @@ extern struct device_attribute *ata_common_sdev_attrs[]; .can_queue = ATA_DEF_QUEUE, \ .tag_alloc_policy = BLK_TAG_ALLOC_RR, \ .this_id = ATA_SHT_THIS_ID, \ - .cmd_per_lun = ATA_SHT_CMD_PER_LUN, \ .emulated = ATA_SHT_EMULATED, \ .use_clustering = ATA_SHT_USE_CLUSTERING, \ .proc_name = drv_name, \ diff --git a/kernel/include/linux/libfdt_env.h b/kernel/include/linux/libfdt_env.h index 01508c7b8..2a663c6bb 100644 --- a/kernel/include/linux/libfdt_env.h +++ b/kernel/include/linux/libfdt_env.h @@ -5,6 +5,10 @@ #include <asm/byteorder.h> +typedef __be16 fdt16_t; +typedef __be32 fdt32_t; +typedef __be64 fdt64_t; + #define fdt32_to_cpu(x) be32_to_cpu(x) #define cpu_to_fdt32(x) cpu_to_be32(x) #define fdt64_to_cpu(x) be64_to_cpu(x) diff --git a/kernel/include/linux/libnvdimm.h b/kernel/include/linux/libnvdimm.h new file mode 100644 index 000000000..3f021dc5d --- /dev/null +++ b/kernel/include/linux/libnvdimm.h @@ -0,0 +1,155 @@ +/* + * libnvdimm - Non-volatile-memory Devices Subsystem + * + * Copyright(c) 2013-2015 Intel Corporation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public License as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ +#ifndef __LIBNVDIMM_H__ +#define __LIBNVDIMM_H__ +#include <linux/kernel.h> +#include <linux/sizes.h> +#include <linux/types.h> + +enum { + /* when a dimm supports both PMEM and BLK access a label is required */ + NDD_ALIASING = 1 << 0, + /* unarmed memory devices may not persist writes */ + NDD_UNARMED = 1 << 1, + + /* need to set a limit somewhere, but yes, this is likely overkill */ + ND_IOCTL_MAX_BUFLEN = SZ_4M, + ND_CMD_MAX_ELEM = 4, + ND_CMD_MAX_ENVELOPE = 16, + ND_CMD_ARS_STATUS_MAX = SZ_4K, + ND_MAX_MAPPINGS = 32, + + /* region flag indicating to direct-map persistent memory by default */ + ND_REGION_PAGEMAP = 0, + + /* mark newly adjusted resources as requiring a label update */ + DPA_RESOURCE_ADJUSTED = 1 << 0, +}; + +extern struct attribute_group nvdimm_bus_attribute_group; +extern struct attribute_group nvdimm_attribute_group; +extern struct attribute_group nd_device_attribute_group; +extern struct attribute_group nd_numa_attribute_group; +extern struct attribute_group nd_region_attribute_group; +extern struct attribute_group nd_mapping_attribute_group; + +struct nvdimm; +struct nvdimm_bus_descriptor; +typedef int (*ndctl_fn)(struct nvdimm_bus_descriptor *nd_desc, + struct nvdimm *nvdimm, unsigned int cmd, void *buf, + unsigned int buf_len); + +struct nd_namespace_label; +struct nvdimm_drvdata; +struct nd_mapping { + struct nvdimm *nvdimm; + struct nd_namespace_label **labels; + u64 start; + u64 size; + /* + * @ndd is for private use at region enable / disable time for + * get_ndd() + put_ndd(), all other nd_mapping to ndd + * conversions use to_ndd() which respects enabled state of the + * nvdimm. + */ + struct nvdimm_drvdata *ndd; +}; + +struct nvdimm_bus_descriptor { + const struct attribute_group **attr_groups; + unsigned long dsm_mask; + char *provider_name; + ndctl_fn ndctl; +}; + +struct nd_cmd_desc { + int in_num; + int out_num; + u32 in_sizes[ND_CMD_MAX_ELEM]; + int out_sizes[ND_CMD_MAX_ELEM]; +}; + +struct nd_interleave_set { + u64 cookie; +}; + +struct nd_region_desc { + struct resource *res; + struct nd_mapping *nd_mapping; + u16 num_mappings; + const struct attribute_group **attr_groups; + struct nd_interleave_set *nd_set; + void *provider_data; + int num_lanes; + int numa_node; + unsigned long flags; +}; + +struct nvdimm_bus; +struct module; +struct device; +struct nd_blk_region; +struct nd_blk_region_desc { + int (*enable)(struct nvdimm_bus *nvdimm_bus, struct device *dev); + void (*disable)(struct nvdimm_bus *nvdimm_bus, struct device *dev); + int (*do_io)(struct nd_blk_region *ndbr, resource_size_t dpa, + void *iobuf, u64 len, int rw); + struct nd_region_desc ndr_desc; +}; + +static inline struct nd_blk_region_desc *to_blk_region_desc( + struct nd_region_desc *ndr_desc) +{ + return container_of(ndr_desc, struct nd_blk_region_desc, ndr_desc); + +} + +struct nvdimm_bus *__nvdimm_bus_register(struct device *parent, + struct nvdimm_bus_descriptor *nfit_desc, struct module *module); +#define nvdimm_bus_register(parent, desc) \ + __nvdimm_bus_register(parent, desc, THIS_MODULE) +void nvdimm_bus_unregister(struct nvdimm_bus *nvdimm_bus); +struct nvdimm_bus *to_nvdimm_bus(struct device *dev); +struct nvdimm *to_nvdimm(struct device *dev); +struct nd_region *to_nd_region(struct device *dev); +struct nd_blk_region *to_nd_blk_region(struct device *dev); +struct nvdimm_bus_descriptor *to_nd_desc(struct nvdimm_bus *nvdimm_bus); +const char *nvdimm_name(struct nvdimm *nvdimm); +void *nvdimm_provider_data(struct nvdimm *nvdimm); +struct nvdimm *nvdimm_create(struct nvdimm_bus *nvdimm_bus, void *provider_data, + const struct attribute_group **groups, unsigned long flags, + unsigned long *dsm_mask); +const struct nd_cmd_desc *nd_cmd_dimm_desc(int cmd); +const struct nd_cmd_desc *nd_cmd_bus_desc(int cmd); +u32 nd_cmd_in_size(struct nvdimm *nvdimm, int cmd, + const struct nd_cmd_desc *desc, int idx, void *buf); +u32 nd_cmd_out_size(struct nvdimm *nvdimm, int cmd, + const struct nd_cmd_desc *desc, int idx, const u32 *in_field, + const u32 *out_field); +int nvdimm_bus_check_dimm_count(struct nvdimm_bus *nvdimm_bus, int dimm_count); +struct nd_region *nvdimm_pmem_region_create(struct nvdimm_bus *nvdimm_bus, + struct nd_region_desc *ndr_desc); +struct nd_region *nvdimm_blk_region_create(struct nvdimm_bus *nvdimm_bus, + struct nd_region_desc *ndr_desc); +struct nd_region *nvdimm_volatile_region_create(struct nvdimm_bus *nvdimm_bus, + struct nd_region_desc *ndr_desc); +void *nd_region_provider_data(struct nd_region *nd_region); +void *nd_blk_region_provider_data(struct nd_blk_region *ndbr); +void nd_blk_region_set_provider_data(struct nd_blk_region *ndbr, void *data); +struct nvdimm *nd_blk_region_to_dimm(struct nd_blk_region *ndbr); +unsigned int nd_region_acquire_lane(struct nd_region *nd_region); +void nd_region_release_lane(struct nd_region *nd_region, unsigned int lane); +u64 nd_fletcher64(void *addr, size_t len, bool le); +#endif /* __LIBNVDIMM_H__ */ diff --git a/kernel/include/linux/lightnvm.h b/kernel/include/linux/lightnvm.h new file mode 100644 index 000000000..034117b3b --- /dev/null +++ b/kernel/include/linux/lightnvm.h @@ -0,0 +1,441 @@ +#ifndef NVM_H +#define NVM_H + +enum { + NVM_IO_OK = 0, + NVM_IO_REQUEUE = 1, + NVM_IO_DONE = 2, + NVM_IO_ERR = 3, + + NVM_IOTYPE_NONE = 0, + NVM_IOTYPE_GC = 1, +}; + +#ifdef CONFIG_NVM + +#include <linux/blkdev.h> +#include <linux/types.h> +#include <linux/file.h> +#include <linux/dmapool.h> + +enum { + /* HW Responsibilities */ + NVM_RSP_L2P = 1 << 0, + NVM_RSP_ECC = 1 << 1, + + /* Physical Adressing Mode */ + NVM_ADDRMODE_LINEAR = 0, + NVM_ADDRMODE_CHANNEL = 1, + + /* Plane programming mode for LUN */ + NVM_PLANE_SINGLE = 0, + NVM_PLANE_DOUBLE = 1, + NVM_PLANE_QUAD = 2, + + /* Status codes */ + NVM_RSP_SUCCESS = 0x0, + NVM_RSP_NOT_CHANGEABLE = 0x1, + NVM_RSP_ERR_FAILWRITE = 0x40ff, + NVM_RSP_ERR_EMPTYPAGE = 0x42ff, + + /* Device opcodes */ + NVM_OP_HBREAD = 0x02, + NVM_OP_HBWRITE = 0x81, + NVM_OP_PWRITE = 0x91, + NVM_OP_PREAD = 0x92, + NVM_OP_ERASE = 0x90, + + /* PPA Command Flags */ + NVM_IO_SNGL_ACCESS = 0x0, + NVM_IO_DUAL_ACCESS = 0x1, + NVM_IO_QUAD_ACCESS = 0x2, + + /* NAND Access Modes */ + NVM_IO_SUSPEND = 0x80, + NVM_IO_SLC_MODE = 0x100, + NVM_IO_SCRAMBLE_DISABLE = 0x200, + + /* Block Types */ + NVM_BLK_T_FREE = 0x0, + NVM_BLK_T_BAD = 0x1, + NVM_BLK_T_DEV = 0x2, + NVM_BLK_T_HOST = 0x4, +}; + +struct nvm_id_group { + u8 mtype; + u8 fmtype; + u8 num_ch; + u8 num_lun; + u8 num_pln; + u16 num_blk; + u16 num_pg; + u16 fpg_sz; + u16 csecs; + u16 sos; + u32 trdt; + u32 trdm; + u32 tprt; + u32 tprm; + u32 tbet; + u32 tbem; + u32 mpos; + u32 mccap; + u16 cpar; +}; + +struct nvm_addr_format { + u8 ch_offset; + u8 ch_len; + u8 lun_offset; + u8 lun_len; + u8 pln_offset; + u8 pln_len; + u8 blk_offset; + u8 blk_len; + u8 pg_offset; + u8 pg_len; + u8 sect_offset; + u8 sect_len; +}; + +struct nvm_id { + u8 ver_id; + u8 vmnt; + u8 cgrps; + u32 cap; + u32 dom; + struct nvm_addr_format ppaf; + struct nvm_id_group groups[4]; +} __packed; + +struct nvm_target { + struct list_head list; + struct nvm_tgt_type *type; + struct gendisk *disk; +}; + +struct nvm_tgt_instance { + struct nvm_tgt_type *tt; +}; + +#define ADDR_EMPTY (~0ULL) + +#define NVM_VERSION_MAJOR 1 +#define NVM_VERSION_MINOR 0 +#define NVM_VERSION_PATCH 0 + +#define NVM_BLK_BITS (16) +#define NVM_PG_BITS (16) +#define NVM_SEC_BITS (8) +#define NVM_PL_BITS (8) +#define NVM_LUN_BITS (8) +#define NVM_CH_BITS (8) + +struct ppa_addr { + /* Generic structure for all addresses */ + union { + struct { + u64 blk : NVM_BLK_BITS; + u64 pg : NVM_PG_BITS; + u64 sec : NVM_SEC_BITS; + u64 pl : NVM_PL_BITS; + u64 lun : NVM_LUN_BITS; + u64 ch : NVM_CH_BITS; + } g; + + u64 ppa; + }; +}; + +struct nvm_rq { + struct nvm_tgt_instance *ins; + struct nvm_dev *dev; + + struct bio *bio; + + union { + struct ppa_addr ppa_addr; + dma_addr_t dma_ppa_list; + }; + + struct ppa_addr *ppa_list; + + void *metadata; + dma_addr_t dma_metadata; + + uint8_t opcode; + uint16_t nr_pages; + uint16_t flags; +}; + +static inline struct nvm_rq *nvm_rq_from_pdu(void *pdu) +{ + return pdu - sizeof(struct nvm_rq); +} + +static inline void *nvm_rq_to_pdu(struct nvm_rq *rqdata) +{ + return rqdata + 1; +} + +struct nvm_block; + +typedef int (nvm_l2p_update_fn)(u64, u32, __le64 *, void *); +typedef int (nvm_bb_update_fn)(struct ppa_addr, int, u8 *, void *); +typedef int (nvm_id_fn)(struct nvm_dev *, struct nvm_id *); +typedef int (nvm_get_l2p_tbl_fn)(struct nvm_dev *, u64, u32, + nvm_l2p_update_fn *, void *); +typedef int (nvm_op_bb_tbl_fn)(struct nvm_dev *, struct ppa_addr, int, + nvm_bb_update_fn *, void *); +typedef int (nvm_op_set_bb_fn)(struct nvm_dev *, struct nvm_rq *, int); +typedef int (nvm_submit_io_fn)(struct nvm_dev *, struct nvm_rq *); +typedef int (nvm_erase_blk_fn)(struct nvm_dev *, struct nvm_rq *); +typedef void *(nvm_create_dma_pool_fn)(struct nvm_dev *, char *); +typedef void (nvm_destroy_dma_pool_fn)(void *); +typedef void *(nvm_dev_dma_alloc_fn)(struct nvm_dev *, void *, gfp_t, + dma_addr_t *); +typedef void (nvm_dev_dma_free_fn)(void *, void*, dma_addr_t); + +struct nvm_dev_ops { + nvm_id_fn *identity; + nvm_get_l2p_tbl_fn *get_l2p_tbl; + nvm_op_bb_tbl_fn *get_bb_tbl; + nvm_op_set_bb_fn *set_bb_tbl; + + nvm_submit_io_fn *submit_io; + nvm_erase_blk_fn *erase_block; + + nvm_create_dma_pool_fn *create_dma_pool; + nvm_destroy_dma_pool_fn *destroy_dma_pool; + nvm_dev_dma_alloc_fn *dev_dma_alloc; + nvm_dev_dma_free_fn *dev_dma_free; + + unsigned int max_phys_sect; +}; + +struct nvm_lun { + int id; + + int lun_id; + int chnl_id; + + unsigned int nr_inuse_blocks; /* Number of used blocks */ + unsigned int nr_free_blocks; /* Number of unused blocks */ + unsigned int nr_bad_blocks; /* Number of bad blocks */ + struct nvm_block *blocks; + + spinlock_t lock; +}; + +struct nvm_block { + struct list_head list; + struct nvm_lun *lun; + unsigned long id; + + void *priv; + int type; +}; + +struct nvm_dev { + struct nvm_dev_ops *ops; + + struct list_head devices; + struct list_head online_targets; + + /* Media manager */ + struct nvmm_type *mt; + void *mp; + + /* Device information */ + int nr_chnls; + int nr_planes; + int luns_per_chnl; + int sec_per_pg; /* only sectors for a single page */ + int pgs_per_blk; + int blks_per_lun; + int sec_size; + int oob_size; + struct nvm_addr_format ppaf; + + /* Calculated/Cached values. These do not reflect the actual usable + * blocks at run-time. + */ + int max_rq_size; + int plane_mode; /* drive device in single, double or quad mode */ + + int sec_per_pl; /* all sectors across planes */ + int sec_per_blk; + int sec_per_lun; + + unsigned long total_pages; + unsigned long total_blocks; + int nr_luns; + unsigned max_pages_per_blk; + + void *ppalist_pool; + + struct nvm_id identity; + + /* Backend device */ + struct request_queue *q; + char name[DISK_NAME_LEN]; +}; + +static inline struct ppa_addr generic_to_dev_addr(struct nvm_dev *dev, + struct ppa_addr r) +{ + struct ppa_addr l; + + l.ppa = ((u64)r.g.blk) << dev->ppaf.blk_offset; + l.ppa |= ((u64)r.g.pg) << dev->ppaf.pg_offset; + l.ppa |= ((u64)r.g.sec) << dev->ppaf.sect_offset; + l.ppa |= ((u64)r.g.pl) << dev->ppaf.pln_offset; + l.ppa |= ((u64)r.g.lun) << dev->ppaf.lun_offset; + l.ppa |= ((u64)r.g.ch) << dev->ppaf.ch_offset; + + return l; +} + +static inline struct ppa_addr dev_to_generic_addr(struct nvm_dev *dev, + struct ppa_addr r) +{ + struct ppa_addr l; + + /* + * (r.ppa << X offset) & X len bitmask. X eq. blk, pg, etc. + */ + l.g.blk = (r.ppa >> dev->ppaf.blk_offset) & + (((1 << dev->ppaf.blk_len) - 1)); + l.g.pg |= (r.ppa >> dev->ppaf.pg_offset) & + (((1 << dev->ppaf.pg_len) - 1)); + l.g.sec |= (r.ppa >> dev->ppaf.sect_offset) & + (((1 << dev->ppaf.sect_len) - 1)); + l.g.pl |= (r.ppa >> dev->ppaf.pln_offset) & + (((1 << dev->ppaf.pln_len) - 1)); + l.g.lun |= (r.ppa >> dev->ppaf.lun_offset) & + (((1 << dev->ppaf.lun_len) - 1)); + l.g.ch |= (r.ppa >> dev->ppaf.ch_offset) & + (((1 << dev->ppaf.ch_len) - 1)); + + return l; +} + +static inline int ppa_empty(struct ppa_addr ppa_addr) +{ + return (ppa_addr.ppa == ADDR_EMPTY); +} + +static inline void ppa_set_empty(struct ppa_addr *ppa_addr) +{ + ppa_addr->ppa = ADDR_EMPTY; +} + +static inline struct ppa_addr block_to_ppa(struct nvm_dev *dev, + struct nvm_block *blk) +{ + struct ppa_addr ppa; + struct nvm_lun *lun = blk->lun; + + ppa.ppa = 0; + ppa.g.blk = blk->id % dev->blks_per_lun; + ppa.g.lun = lun->lun_id; + ppa.g.ch = lun->chnl_id; + + return ppa; +} + +typedef blk_qc_t (nvm_tgt_make_rq_fn)(struct request_queue *, struct bio *); +typedef sector_t (nvm_tgt_capacity_fn)(void *); +typedef int (nvm_tgt_end_io_fn)(struct nvm_rq *, int); +typedef void *(nvm_tgt_init_fn)(struct nvm_dev *, struct gendisk *, int, int); +typedef void (nvm_tgt_exit_fn)(void *); + +struct nvm_tgt_type { + const char *name; + unsigned int version[3]; + + /* target entry points */ + nvm_tgt_make_rq_fn *make_rq; + nvm_tgt_capacity_fn *capacity; + nvm_tgt_end_io_fn *end_io; + + /* module-specific init/teardown */ + nvm_tgt_init_fn *init; + nvm_tgt_exit_fn *exit; + + /* For internal use */ + struct list_head list; +}; + +extern int nvm_register_target(struct nvm_tgt_type *); +extern void nvm_unregister_target(struct nvm_tgt_type *); + +extern void *nvm_dev_dma_alloc(struct nvm_dev *, gfp_t, dma_addr_t *); +extern void nvm_dev_dma_free(struct nvm_dev *, void *, dma_addr_t); + +typedef int (nvmm_register_fn)(struct nvm_dev *); +typedef void (nvmm_unregister_fn)(struct nvm_dev *); +typedef struct nvm_block *(nvmm_get_blk_fn)(struct nvm_dev *, + struct nvm_lun *, unsigned long); +typedef void (nvmm_put_blk_fn)(struct nvm_dev *, struct nvm_block *); +typedef int (nvmm_open_blk_fn)(struct nvm_dev *, struct nvm_block *); +typedef int (nvmm_close_blk_fn)(struct nvm_dev *, struct nvm_block *); +typedef void (nvmm_flush_blk_fn)(struct nvm_dev *, struct nvm_block *); +typedef int (nvmm_submit_io_fn)(struct nvm_dev *, struct nvm_rq *); +typedef int (nvmm_end_io_fn)(struct nvm_rq *, int); +typedef int (nvmm_erase_blk_fn)(struct nvm_dev *, struct nvm_block *, + unsigned long); +typedef struct nvm_lun *(nvmm_get_lun_fn)(struct nvm_dev *, int); +typedef void (nvmm_lun_info_print_fn)(struct nvm_dev *); + +struct nvmm_type { + const char *name; + unsigned int version[3]; + + nvmm_register_fn *register_mgr; + nvmm_unregister_fn *unregister_mgr; + + /* Block administration callbacks */ + nvmm_get_blk_fn *get_blk; + nvmm_put_blk_fn *put_blk; + nvmm_open_blk_fn *open_blk; + nvmm_close_blk_fn *close_blk; + nvmm_flush_blk_fn *flush_blk; + + nvmm_submit_io_fn *submit_io; + nvmm_end_io_fn *end_io; + nvmm_erase_blk_fn *erase_blk; + + /* Configuration management */ + nvmm_get_lun_fn *get_lun; + + /* Statistics */ + nvmm_lun_info_print_fn *lun_info_print; + struct list_head list; +}; + +extern int nvm_register_mgr(struct nvmm_type *); +extern void nvm_unregister_mgr(struct nvmm_type *); + +extern struct nvm_block *nvm_get_blk(struct nvm_dev *, struct nvm_lun *, + unsigned long); +extern void nvm_put_blk(struct nvm_dev *, struct nvm_block *); + +extern int nvm_register(struct request_queue *, char *, + struct nvm_dev_ops *); +extern void nvm_unregister(char *); + +extern int nvm_submit_io(struct nvm_dev *, struct nvm_rq *); +extern int nvm_erase_blk(struct nvm_dev *, struct nvm_block *); +#else /* CONFIG_NVM */ +struct nvm_dev_ops; + +static inline int nvm_register(struct request_queue *q, char *disk_name, + struct nvm_dev_ops *ops) +{ + return -EINVAL; +} +static inline void nvm_unregister(char *disk_name) {} +#endif /* CONFIG_NVM */ +#endif /* LIGHTNVM.H */ diff --git a/kernel/include/linux/list.h b/kernel/include/linux/list.h index feb773c76..993395a2e 100644 --- a/kernel/include/linux/list.h +++ b/kernel/include/linux/list.h @@ -87,7 +87,7 @@ static inline void list_add_tail(struct list_head *new, struct list_head *head) static inline void __list_del(struct list_head * prev, struct list_head * next) { next->prev = prev; - prev->next = next; + WRITE_ONCE(prev->next, next); } /** @@ -615,7 +615,8 @@ static inline void __hlist_del(struct hlist_node *n) { struct hlist_node *next = n->next; struct hlist_node **pprev = n->pprev; - *pprev = next; + + WRITE_ONCE(*pprev, next); if (next) next->pprev = pprev; } @@ -672,6 +673,11 @@ static inline void hlist_add_fake(struct hlist_node *n) n->pprev = &n->next; } +static inline bool hlist_fake(struct hlist_node *h) +{ + return h->pprev == &h->next; +} + /* * Move a list from one list head to another. Fixup the pprev * reference of the first entry if it exists. diff --git a/kernel/include/linux/list_bl.h b/kernel/include/linux/list_bl.h index d8876a0cf..89ffaa7bd 100644 --- a/kernel/include/linux/list_bl.h +++ b/kernel/include/linux/list_bl.h @@ -42,13 +42,15 @@ struct hlist_bl_node { struct hlist_bl_node *next, **pprev; }; -static inline void INIT_HLIST_BL_HEAD(struct hlist_bl_head *h) -{ - h->first = NULL; #ifdef CONFIG_PREEMPT_RT_BASE - raw_spin_lock_init(&h->lock); +#define INIT_HLIST_BL_HEAD(h) \ +do { \ + (h)->first = NULL; \ + raw_spin_lock_init(&(h)->lock); \ +} while (0) +#else +#define INIT_HLIST_BL_HEAD(h) (h)->first = NULL #endif -} static inline void INIT_HLIST_BL_NODE(struct hlist_bl_node *h) { @@ -103,9 +105,10 @@ static inline void __hlist_bl_del(struct hlist_bl_node *n) LIST_BL_BUG_ON((unsigned long)n & LIST_BL_LOCKMASK); /* pprev may be `first`, so be careful not to lose the lock bit */ - *pprev = (struct hlist_bl_node *) + WRITE_ONCE(*pprev, + (struct hlist_bl_node *) ((unsigned long)next | - ((unsigned long)*pprev & LIST_BL_LOCKMASK)); + ((unsigned long)*pprev & LIST_BL_LOCKMASK))); if (next) next->pprev = pprev; } diff --git a/kernel/include/linux/list_nulls.h b/kernel/include/linux/list_nulls.h index f266661d2..444d2b131 100644 --- a/kernel/include/linux/list_nulls.h +++ b/kernel/include/linux/list_nulls.h @@ -76,7 +76,8 @@ static inline void __hlist_nulls_del(struct hlist_nulls_node *n) { struct hlist_nulls_node *next = n->next; struct hlist_nulls_node **pprev = n->pprev; - *pprev = next; + + WRITE_ONCE(*pprev, next); if (!is_a_nulls(next)) next->pprev = pprev; } diff --git a/kernel/include/linux/livepatch.h b/kernel/include/linux/livepatch.h index ee6dbb39a..31db7a05d 100644 --- a/kernel/include/linux/livepatch.h +++ b/kernel/include/linux/livepatch.h @@ -99,7 +99,7 @@ struct klp_object { struct klp_func *funcs; /* internal */ - struct kobject *kobj; + struct kobject kobj; struct module *mod; enum klp_state state; }; @@ -123,6 +123,12 @@ struct klp_patch { enum klp_state state; }; +#define klp_for_each_object(patch, obj) \ + for (obj = patch->objs; obj->funcs; obj++) + +#define klp_for_each_func(obj, func) \ + for (func = obj->funcs; func->old_name; func++) + int klp_register_patch(struct klp_patch *); int klp_unregister_patch(struct klp_patch *); int klp_enable_patch(struct klp_patch *); diff --git a/kernel/include/linux/llist.h b/kernel/include/linux/llist.h index fbf10a0bc..fd4ca0b4f 100644 --- a/kernel/include/linux/llist.h +++ b/kernel/include/linux/llist.h @@ -55,8 +55,8 @@ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ +#include <linux/atomic.h> #include <linux/kernel.h> -#include <asm/cmpxchg.h> struct llist_head { struct llist_node *first; diff --git a/kernel/include/linux/locallock.h b/kernel/include/linux/locallock.h index 339ba00ad..6fe5928fc 100644 --- a/kernel/include/linux/locallock.h +++ b/kernel/include/linux/locallock.h @@ -43,9 +43,9 @@ struct local_irq_lock { * for CONFIG_PREEMPT_BASE map to the normal spin_* calls. */ #ifdef CONFIG_PREEMPT_RT_FULL -# define spin_lock_local(lock) rt_spin_lock(lock) -# define spin_trylock_local(lock) rt_spin_trylock(lock) -# define spin_unlock_local(lock) rt_spin_unlock(lock) +# define spin_lock_local(lock) rt_spin_lock__no_mg(lock) +# define spin_trylock_local(lock) rt_spin_trylock__no_mg(lock) +# define spin_unlock_local(lock) rt_spin_unlock__no_mg(lock) #else # define spin_lock_local(lock) spin_lock(lock) # define spin_trylock_local(lock) spin_trylock(lock) diff --git a/kernel/include/linux/lockd/lockd.h b/kernel/include/linux/lockd/lockd.h index ff82a3287..c15373894 100644 --- a/kernel/include/linux/lockd/lockd.h +++ b/kernel/include/linux/lockd/lockd.h @@ -68,6 +68,7 @@ struct nlm_host { struct nsm_handle *h_nsmhandle; /* NSM status handle */ char *h_addrbuf; /* address eyecatcher */ struct net *net; /* host net */ + char nodename[UNX_MAXNODENAME + 1]; }; /* @@ -235,7 +236,8 @@ void nlm_rebind_host(struct nlm_host *); struct nlm_host * nlm_get_host(struct nlm_host *); void nlm_shutdown_hosts(void); void nlm_shutdown_hosts_net(struct net *net); -void nlm_host_rebooted(const struct nlm_reboot *); +void nlm_host_rebooted(const struct net *net, + const struct nlm_reboot *); /* * Host monitoring @@ -243,11 +245,13 @@ void nlm_host_rebooted(const struct nlm_reboot *); int nsm_monitor(const struct nlm_host *host); void nsm_unmonitor(const struct nlm_host *host); -struct nsm_handle *nsm_get_handle(const struct sockaddr *sap, +struct nsm_handle *nsm_get_handle(const struct net *net, + const struct sockaddr *sap, const size_t salen, const char *hostname, const size_t hostname_len); -struct nsm_handle *nsm_reboot_lookup(const struct nlm_reboot *info); +struct nsm_handle *nsm_reboot_lookup(const struct net *net, + const struct nlm_reboot *info); void nsm_release(struct nsm_handle *nsm); /* diff --git a/kernel/include/linux/lockdep.h b/kernel/include/linux/lockdep.h index 066ba4157..c57e424d9 100644 --- a/kernel/include/linux/lockdep.h +++ b/kernel/include/linux/lockdep.h @@ -2,7 +2,7 @@ * Runtime locking correctness validator * * Copyright (C) 2006,2007 Red Hat, Inc., Ingo Molnar <mingo@redhat.com> - * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com> + * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra * * see Documentation/locking/lockdep-design.txt for more details. */ @@ -130,8 +130,8 @@ enum bounce_type { }; struct lock_class_stats { - unsigned long contention_point[4]; - unsigned long contending_point[4]; + unsigned long contention_point[LOCKSTAT_POINTS]; + unsigned long contending_point[LOCKSTAT_POINTS]; struct lock_time read_waittime; struct lock_time write_waittime; struct lock_time read_holdtime; @@ -255,6 +255,7 @@ struct held_lock { unsigned int check:1; /* see lock_acquire() comment */ unsigned int hardirqs_off:1; unsigned int references:12; /* 32 bits */ + unsigned int pin_count; }; /* @@ -354,6 +355,9 @@ extern void lockdep_set_current_reclaim_state(gfp_t gfp_mask); extern void lockdep_clear_current_reclaim_state(void); extern void lockdep_trace_alloc(gfp_t mask); +extern void lock_pin_lock(struct lockdep_map *lock); +extern void lock_unpin_lock(struct lockdep_map *lock); + # define INIT_LOCKDEP .lockdep_recursion = 0, .lockdep_reclaim_gfp = 0, #define lockdep_depth(tsk) (debug_locks ? (tsk)->lockdep_depth : 0) @@ -368,6 +372,9 @@ extern void lockdep_trace_alloc(gfp_t mask); #define lockdep_recursing(tsk) ((tsk)->lockdep_recursion) +#define lockdep_pin_lock(l) lock_pin_lock(&(l)->dep_map) +#define lockdep_unpin_lock(l) lock_unpin_lock(&(l)->dep_map) + #else /* !CONFIG_LOCKDEP */ static inline void lockdep_off(void) @@ -420,6 +427,9 @@ struct lock_class_key { }; #define lockdep_recursing(tsk) (0) +#define lockdep_pin_lock(l) do { (void)(l); } while (0) +#define lockdep_unpin_lock(l) do { (void)(l); } while (0) + #endif /* !LOCKDEP */ #ifdef CONFIG_LOCK_STAT diff --git a/kernel/include/linux/lsm_audit.h b/kernel/include/linux/lsm_audit.h index 1cc89e9df..ffb9c9da4 100644 --- a/kernel/include/linux/lsm_audit.h +++ b/kernel/include/linux/lsm_audit.h @@ -40,6 +40,11 @@ struct lsm_network_audit { } fam; }; +struct lsm_ioctlop_audit { + struct path path; + u16 cmd; +}; + /* Auxiliary data to use in generating the audit record. */ struct common_audit_data { char type; @@ -53,6 +58,7 @@ struct common_audit_data { #define LSM_AUDIT_DATA_KMOD 8 #define LSM_AUDIT_DATA_INODE 9 #define LSM_AUDIT_DATA_DENTRY 10 +#define LSM_AUDIT_DATA_IOCTL_OP 11 union { struct path path; struct dentry *dentry; @@ -68,6 +74,7 @@ struct common_audit_data { } key_struct; #endif char *kmod_name; + struct lsm_ioctlop_audit *op; } u; /* this union contains LSM specific data */ union { diff --git a/kernel/include/linux/lsm_hooks.h b/kernel/include/linux/lsm_hooks.h new file mode 100644 index 000000000..ec3a6bab2 --- /dev/null +++ b/kernel/include/linux/lsm_hooks.h @@ -0,0 +1,1890 @@ +/* + * Linux Security Module interfaces + * + * Copyright (C) 2001 WireX Communications, Inc <chris@wirex.com> + * Copyright (C) 2001 Greg Kroah-Hartman <greg@kroah.com> + * Copyright (C) 2001 Networks Associates Technology, Inc <ssmalley@nai.com> + * Copyright (C) 2001 James Morris <jmorris@intercode.com.au> + * Copyright (C) 2001 Silicon Graphics, Inc. (Trust Technology Group) + * Copyright (C) 2015 Intel Corporation. + * Copyright (C) 2015 Casey Schaufler <casey@schaufler-ca.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * Due to this file being licensed under the GPL there is controversy over + * whether this permits you to write a module that #includes this file + * without placing your module under the GPL. Please consult a lawyer for + * advice before doing this. + * + */ + +#ifndef __LINUX_LSM_HOOKS_H +#define __LINUX_LSM_HOOKS_H + +#include <linux/security.h> +#include <linux/init.h> +#include <linux/rculist.h> + +/** + * Security hooks for program execution operations. + * + * @bprm_set_creds: + * Save security information in the bprm->security field, typically based + * on information about the bprm->file, for later use by the apply_creds + * hook. This hook may also optionally check permissions (e.g. for + * transitions between security domains). + * This hook may be called multiple times during a single execve, e.g. for + * interpreters. The hook can tell whether it has already been called by + * checking to see if @bprm->security is non-NULL. If so, then the hook + * may decide either to retain the security information saved earlier or + * to replace it. + * @bprm contains the linux_binprm structure. + * Return 0 if the hook is successful and permission is granted. + * @bprm_check_security: + * This hook mediates the point when a search for a binary handler will + * begin. It allows a check the @bprm->security value which is set in the + * preceding set_creds call. The primary difference from set_creds is + * that the argv list and envp list are reliably available in @bprm. This + * hook may be called multiple times during a single execve; and in each + * pass set_creds is called first. + * @bprm contains the linux_binprm structure. + * Return 0 if the hook is successful and permission is granted. + * @bprm_committing_creds: + * Prepare to install the new security attributes of a process being + * transformed by an execve operation, based on the old credentials + * pointed to by @current->cred and the information set in @bprm->cred by + * the bprm_set_creds hook. @bprm points to the linux_binprm structure. + * This hook is a good place to perform state changes on the process such + * as closing open file descriptors to which access will no longer be + * granted when the attributes are changed. This is called immediately + * before commit_creds(). + * @bprm_committed_creds: + * Tidy up after the installation of the new security attributes of a + * process being transformed by an execve operation. The new credentials + * have, by this point, been set to @current->cred. @bprm points to the + * linux_binprm structure. This hook is a good place to perform state + * changes on the process such as clearing out non-inheritable signal + * state. This is called immediately after commit_creds(). + * @bprm_secureexec: + * Return a boolean value (0 or 1) indicating whether a "secure exec" + * is required. The flag is passed in the auxiliary table + * on the initial stack to the ELF interpreter to indicate whether libc + * should enable secure mode. + * @bprm contains the linux_binprm structure. + * + * Security hooks for filesystem operations. + * + * @sb_alloc_security: + * Allocate and attach a security structure to the sb->s_security field. + * The s_security field is initialized to NULL when the structure is + * allocated. + * @sb contains the super_block structure to be modified. + * Return 0 if operation was successful. + * @sb_free_security: + * Deallocate and clear the sb->s_security field. + * @sb contains the super_block structure to be modified. + * @sb_statfs: + * Check permission before obtaining filesystem statistics for the @mnt + * mountpoint. + * @dentry is a handle on the superblock for the filesystem. + * Return 0 if permission is granted. + * @sb_mount: + * Check permission before an object specified by @dev_name is mounted on + * the mount point named by @nd. For an ordinary mount, @dev_name + * identifies a device if the file system type requires a device. For a + * remount (@flags & MS_REMOUNT), @dev_name is irrelevant. For a + * loopback/bind mount (@flags & MS_BIND), @dev_name identifies the + * pathname of the object being mounted. + * @dev_name contains the name for object being mounted. + * @path contains the path for mount point object. + * @type contains the filesystem type. + * @flags contains the mount flags. + * @data contains the filesystem-specific data. + * Return 0 if permission is granted. + * @sb_copy_data: + * Allow mount option data to be copied prior to parsing by the filesystem, + * so that the security module can extract security-specific mount + * options cleanly (a filesystem may modify the data e.g. with strsep()). + * This also allows the original mount data to be stripped of security- + * specific options to avoid having to make filesystems aware of them. + * @type the type of filesystem being mounted. + * @orig the original mount data copied from userspace. + * @copy copied data which will be passed to the security module. + * Returns 0 if the copy was successful. + * @sb_remount: + * Extracts security system specific mount options and verifies no changes + * are being made to those options. + * @sb superblock being remounted + * @data contains the filesystem-specific data. + * Return 0 if permission is granted. + * @sb_umount: + * Check permission before the @mnt file system is unmounted. + * @mnt contains the mounted file system. + * @flags contains the unmount flags, e.g. MNT_FORCE. + * Return 0 if permission is granted. + * @sb_pivotroot: + * Check permission before pivoting the root filesystem. + * @old_path contains the path for the new location of the + * current root (put_old). + * @new_path contains the path for the new root (new_root). + * Return 0 if permission is granted. + * @sb_set_mnt_opts: + * Set the security relevant mount options used for a superblock + * @sb the superblock to set security mount options for + * @opts binary data structure containing all lsm mount data + * @sb_clone_mnt_opts: + * Copy all security options from a given superblock to another + * @oldsb old superblock which contain information to clone + * @newsb new superblock which needs filled in + * @sb_parse_opts_str: + * Parse a string of security data filling in the opts structure + * @options string containing all mount options known by the LSM + * @opts binary data structure usable by the LSM + * @dentry_init_security: + * Compute a context for a dentry as the inode is not yet available + * since NFSv4 has no label backed by an EA anyway. + * @dentry dentry to use in calculating the context. + * @mode mode used to determine resource type. + * @name name of the last path component used to create file + * @ctx pointer to place the pointer to the resulting context in. + * @ctxlen point to place the length of the resulting context. + * + * + * Security hooks for inode operations. + * + * @inode_alloc_security: + * Allocate and attach a security structure to @inode->i_security. The + * i_security field is initialized to NULL when the inode structure is + * allocated. + * @inode contains the inode structure. + * Return 0 if operation was successful. + * @inode_free_security: + * @inode contains the inode structure. + * Deallocate the inode security structure and set @inode->i_security to + * NULL. + * @inode_init_security: + * Obtain the security attribute name suffix and value to set on a newly + * created inode and set up the incore security field for the new inode. + * This hook is called by the fs code as part of the inode creation + * transaction and provides for atomic labeling of the inode, unlike + * the post_create/mkdir/... hooks called by the VFS. The hook function + * is expected to allocate the name and value via kmalloc, with the caller + * being responsible for calling kfree after using them. + * If the security module does not use security attributes or does + * not wish to put a security attribute on this particular inode, + * then it should return -EOPNOTSUPP to skip this processing. + * @inode contains the inode structure of the newly created inode. + * @dir contains the inode structure of the parent directory. + * @qstr contains the last path component of the new object + * @name will be set to the allocated name suffix (e.g. selinux). + * @value will be set to the allocated attribute value. + * @len will be set to the length of the value. + * Returns 0 if @name and @value have been successfully set, + * -EOPNOTSUPP if no security attribute is needed, or + * -ENOMEM on memory allocation failure. + * @inode_create: + * Check permission to create a regular file. + * @dir contains inode structure of the parent of the new file. + * @dentry contains the dentry structure for the file to be created. + * @mode contains the file mode of the file to be created. + * Return 0 if permission is granted. + * @inode_link: + * Check permission before creating a new hard link to a file. + * @old_dentry contains the dentry structure for an existing + * link to the file. + * @dir contains the inode structure of the parent directory + * of the new link. + * @new_dentry contains the dentry structure for the new link. + * Return 0 if permission is granted. + * @path_link: + * Check permission before creating a new hard link to a file. + * @old_dentry contains the dentry structure for an existing link + * to the file. + * @new_dir contains the path structure of the parent directory of + * the new link. + * @new_dentry contains the dentry structure for the new link. + * Return 0 if permission is granted. + * @inode_unlink: + * Check the permission to remove a hard link to a file. + * @dir contains the inode structure of parent directory of the file. + * @dentry contains the dentry structure for file to be unlinked. + * Return 0 if permission is granted. + * @path_unlink: + * Check the permission to remove a hard link to a file. + * @dir contains the path structure of parent directory of the file. + * @dentry contains the dentry structure for file to be unlinked. + * Return 0 if permission is granted. + * @inode_symlink: + * Check the permission to create a symbolic link to a file. + * @dir contains the inode structure of parent directory of + * the symbolic link. + * @dentry contains the dentry structure of the symbolic link. + * @old_name contains the pathname of file. + * Return 0 if permission is granted. + * @path_symlink: + * Check the permission to create a symbolic link to a file. + * @dir contains the path structure of parent directory of + * the symbolic link. + * @dentry contains the dentry structure of the symbolic link. + * @old_name contains the pathname of file. + * Return 0 if permission is granted. + * @inode_mkdir: + * Check permissions to create a new directory in the existing directory + * associated with inode structure @dir. + * @dir contains the inode structure of parent of the directory + * to be created. + * @dentry contains the dentry structure of new directory. + * @mode contains the mode of new directory. + * Return 0 if permission is granted. + * @path_mkdir: + * Check permissions to create a new directory in the existing directory + * associated with path structure @path. + * @dir contains the path structure of parent of the directory + * to be created. + * @dentry contains the dentry structure of new directory. + * @mode contains the mode of new directory. + * Return 0 if permission is granted. + * @inode_rmdir: + * Check the permission to remove a directory. + * @dir contains the inode structure of parent of the directory + * to be removed. + * @dentry contains the dentry structure of directory to be removed. + * Return 0 if permission is granted. + * @path_rmdir: + * Check the permission to remove a directory. + * @dir contains the path structure of parent of the directory to be + * removed. + * @dentry contains the dentry structure of directory to be removed. + * Return 0 if permission is granted. + * @inode_mknod: + * Check permissions when creating a special file (or a socket or a fifo + * file created via the mknod system call). Note that if mknod operation + * is being done for a regular file, then the create hook will be called + * and not this hook. + * @dir contains the inode structure of parent of the new file. + * @dentry contains the dentry structure of the new file. + * @mode contains the mode of the new file. + * @dev contains the device number. + * Return 0 if permission is granted. + * @path_mknod: + * Check permissions when creating a file. Note that this hook is called + * even if mknod operation is being done for a regular file. + * @dir contains the path structure of parent of the new file. + * @dentry contains the dentry structure of the new file. + * @mode contains the mode of the new file. + * @dev contains the undecoded device number. Use new_decode_dev() to get + * the decoded device number. + * Return 0 if permission is granted. + * @inode_rename: + * Check for permission to rename a file or directory. + * @old_dir contains the inode structure for parent of the old link. + * @old_dentry contains the dentry structure of the old link. + * @new_dir contains the inode structure for parent of the new link. + * @new_dentry contains the dentry structure of the new link. + * Return 0 if permission is granted. + * @path_rename: + * Check for permission to rename a file or directory. + * @old_dir contains the path structure for parent of the old link. + * @old_dentry contains the dentry structure of the old link. + * @new_dir contains the path structure for parent of the new link. + * @new_dentry contains the dentry structure of the new link. + * Return 0 if permission is granted. + * @path_chmod: + * Check for permission to change DAC's permission of a file or directory. + * @dentry contains the dentry structure. + * @mnt contains the vfsmnt structure. + * @mode contains DAC's mode. + * Return 0 if permission is granted. + * @path_chown: + * Check for permission to change owner/group of a file or directory. + * @path contains the path structure. + * @uid contains new owner's ID. + * @gid contains new group's ID. + * Return 0 if permission is granted. + * @path_chroot: + * Check for permission to change root directory. + * @path contains the path structure. + * Return 0 if permission is granted. + * @inode_readlink: + * Check the permission to read the symbolic link. + * @dentry contains the dentry structure for the file link. + * Return 0 if permission is granted. + * @inode_follow_link: + * Check permission to follow a symbolic link when looking up a pathname. + * @dentry contains the dentry structure for the link. + * @inode contains the inode, which itself is not stable in RCU-walk + * @rcu indicates whether we are in RCU-walk mode. + * Return 0 if permission is granted. + * @inode_permission: + * Check permission before accessing an inode. This hook is called by the + * existing Linux permission function, so a security module can use it to + * provide additional checking for existing Linux permission checks. + * Notice that this hook is called when a file is opened (as well as many + * other operations), whereas the file_security_ops permission hook is + * called when the actual read/write operations are performed. + * @inode contains the inode structure to check. + * @mask contains the permission mask. + * Return 0 if permission is granted. + * @inode_setattr: + * Check permission before setting file attributes. Note that the kernel + * call to notify_change is performed from several locations, whenever + * file attributes change (such as when a file is truncated, chown/chmod + * operations, transferring disk quotas, etc). + * @dentry contains the dentry structure for the file. + * @attr is the iattr structure containing the new file attributes. + * Return 0 if permission is granted. + * @path_truncate: + * Check permission before truncating a file. + * @path contains the path structure for the file. + * Return 0 if permission is granted. + * @inode_getattr: + * Check permission before obtaining file attributes. + * @mnt is the vfsmount where the dentry was looked up + * @dentry contains the dentry structure for the file. + * Return 0 if permission is granted. + * @inode_setxattr: + * Check permission before setting the extended attributes + * @value identified by @name for @dentry. + * Return 0 if permission is granted. + * @inode_post_setxattr: + * Update inode security field after successful setxattr operation. + * @value identified by @name for @dentry. + * @inode_getxattr: + * Check permission before obtaining the extended attributes + * identified by @name for @dentry. + * Return 0 if permission is granted. + * @inode_listxattr: + * Check permission before obtaining the list of extended attribute + * names for @dentry. + * Return 0 if permission is granted. + * @inode_removexattr: + * Check permission before removing the extended attribute + * identified by @name for @dentry. + * Return 0 if permission is granted. + * @inode_getsecurity: + * Retrieve a copy of the extended attribute representation of the + * security label associated with @name for @inode via @buffer. Note that + * @name is the remainder of the attribute name after the security prefix + * has been removed. @alloc is used to specify of the call should return a + * value via the buffer or just the value length Return size of buffer on + * success. + * @inode_setsecurity: + * Set the security label associated with @name for @inode from the + * extended attribute value @value. @size indicates the size of the + * @value in bytes. @flags may be XATTR_CREATE, XATTR_REPLACE, or 0. + * Note that @name is the remainder of the attribute name after the + * security. prefix has been removed. + * Return 0 on success. + * @inode_listsecurity: + * Copy the extended attribute names for the security labels + * associated with @inode into @buffer. The maximum size of @buffer + * is specified by @buffer_size. @buffer may be NULL to request + * the size of the buffer required. + * Returns number of bytes used/required on success. + * @inode_need_killpriv: + * Called when an inode has been changed. + * @dentry is the dentry being changed. + * Return <0 on error to abort the inode change operation. + * Return 0 if inode_killpriv does not need to be called. + * Return >0 if inode_killpriv does need to be called. + * @inode_killpriv: + * The setuid bit is being removed. Remove similar security labels. + * Called with the dentry->d_inode->i_mutex held. + * @dentry is the dentry being changed. + * Return 0 on success. If error is returned, then the operation + * causing setuid bit removal is failed. + * @inode_getsecid: + * Get the secid associated with the node. + * @inode contains a pointer to the inode. + * @secid contains a pointer to the location where result will be saved. + * In case of failure, @secid will be set to zero. + * + * Security hooks for file operations + * + * @file_permission: + * Check file permissions before accessing an open file. This hook is + * called by various operations that read or write files. A security + * module can use this hook to perform additional checking on these + * operations, e.g. to revalidate permissions on use to support privilege + * bracketing or policy changes. Notice that this hook is used when the + * actual read/write operations are performed, whereas the + * inode_security_ops hook is called when a file is opened (as well as + * many other operations). + * Caveat: Although this hook can be used to revalidate permissions for + * various system call operations that read or write files, it does not + * address the revalidation of permissions for memory-mapped files. + * Security modules must handle this separately if they need such + * revalidation. + * @file contains the file structure being accessed. + * @mask contains the requested permissions. + * Return 0 if permission is granted. + * @file_alloc_security: + * Allocate and attach a security structure to the file->f_security field. + * The security field is initialized to NULL when the structure is first + * created. + * @file contains the file structure to secure. + * Return 0 if the hook is successful and permission is granted. + * @file_free_security: + * Deallocate and free any security structures stored in file->f_security. + * @file contains the file structure being modified. + * @file_ioctl: + * @file contains the file structure. + * @cmd contains the operation to perform. + * @arg contains the operational arguments. + * Check permission for an ioctl operation on @file. Note that @arg + * sometimes represents a user space pointer; in other cases, it may be a + * simple integer value. When @arg represents a user space pointer, it + * should never be used by the security module. + * Return 0 if permission is granted. + * @mmap_addr : + * Check permissions for a mmap operation at @addr. + * @addr contains virtual address that will be used for the operation. + * Return 0 if permission is granted. + * @mmap_file : + * Check permissions for a mmap operation. The @file may be NULL, e.g. + * if mapping anonymous memory. + * @file contains the file structure for file to map (may be NULL). + * @reqprot contains the protection requested by the application. + * @prot contains the protection that will be applied by the kernel. + * @flags contains the operational flags. + * Return 0 if permission is granted. + * @file_mprotect: + * Check permissions before changing memory access permissions. + * @vma contains the memory region to modify. + * @reqprot contains the protection requested by the application. + * @prot contains the protection that will be applied by the kernel. + * Return 0 if permission is granted. + * @file_lock: + * Check permission before performing file locking operations. + * Note: this hook mediates both flock and fcntl style locks. + * @file contains the file structure. + * @cmd contains the posix-translated lock operation to perform + * (e.g. F_RDLCK, F_WRLCK). + * Return 0 if permission is granted. + * @file_fcntl: + * Check permission before allowing the file operation specified by @cmd + * from being performed on the file @file. Note that @arg sometimes + * represents a user space pointer; in other cases, it may be a simple + * integer value. When @arg represents a user space pointer, it should + * never be used by the security module. + * @file contains the file structure. + * @cmd contains the operation to be performed. + * @arg contains the operational arguments. + * Return 0 if permission is granted. + * @file_set_fowner: + * Save owner security information (typically from current->security) in + * file->f_security for later use by the send_sigiotask hook. + * @file contains the file structure to update. + * Return 0 on success. + * @file_send_sigiotask: + * Check permission for the file owner @fown to send SIGIO or SIGURG to the + * process @tsk. Note that this hook is sometimes called from interrupt. + * Note that the fown_struct, @fown, is never outside the context of a + * struct file, so the file structure (and associated security information) + * can always be obtained: + * container_of(fown, struct file, f_owner) + * @tsk contains the structure of task receiving signal. + * @fown contains the file owner information. + * @sig is the signal that will be sent. When 0, kernel sends SIGIO. + * Return 0 if permission is granted. + * @file_receive: + * This hook allows security modules to control the ability of a process + * to receive an open file descriptor via socket IPC. + * @file contains the file structure being received. + * Return 0 if permission is granted. + * @file_open + * Save open-time permission checking state for later use upon + * file_permission, and recheck access if anything has changed + * since inode_permission. + * + * Security hooks for task operations. + * + * @task_create: + * Check permission before creating a child process. See the clone(2) + * manual page for definitions of the @clone_flags. + * @clone_flags contains the flags indicating what should be shared. + * Return 0 if permission is granted. + * @task_free: + * @task task being freed + * Handle release of task-related resources. (Note that this can be called + * from interrupt context.) + * @cred_alloc_blank: + * @cred points to the credentials. + * @gfp indicates the atomicity of any memory allocations. + * Only allocate sufficient memory and attach to @cred such that + * cred_transfer() will not get ENOMEM. + * @cred_free: + * @cred points to the credentials. + * Deallocate and clear the cred->security field in a set of credentials. + * @cred_prepare: + * @new points to the new credentials. + * @old points to the original credentials. + * @gfp indicates the atomicity of any memory allocations. + * Prepare a new set of credentials by copying the data from the old set. + * @cred_transfer: + * @new points to the new credentials. + * @old points to the original credentials. + * Transfer data from original creds to new creds + * @kernel_act_as: + * Set the credentials for a kernel service to act as (subjective context). + * @new points to the credentials to be modified. + * @secid specifies the security ID to be set + * The current task must be the one that nominated @secid. + * Return 0 if successful. + * @kernel_create_files_as: + * Set the file creation context in a set of credentials to be the same as + * the objective context of the specified inode. + * @new points to the credentials to be modified. + * @inode points to the inode to use as a reference. + * The current task must be the one that nominated @inode. + * Return 0 if successful. + * @kernel_fw_from_file: + * Load firmware from userspace (not called for built-in firmware). + * @file contains the file structure pointing to the file containing + * the firmware to load. This argument will be NULL if the firmware + * was loaded via the uevent-triggered blob-based interface exposed + * by CONFIG_FW_LOADER_USER_HELPER. + * @buf pointer to buffer containing firmware contents. + * @size length of the firmware contents. + * Return 0 if permission is granted. + * @kernel_module_request: + * Ability to trigger the kernel to automatically upcall to userspace for + * userspace to load a kernel module with the given name. + * @kmod_name name of the module requested by the kernel + * Return 0 if successful. + * @kernel_module_from_file: + * Load a kernel module from userspace. + * @file contains the file structure pointing to the file containing + * the kernel module to load. If the module is being loaded from a blob, + * this argument will be NULL. + * Return 0 if permission is granted. + * @task_fix_setuid: + * Update the module's state after setting one or more of the user + * identity attributes of the current process. The @flags parameter + * indicates which of the set*uid system calls invoked this hook. If + * @new is the set of credentials that will be installed. Modifications + * should be made to this rather than to @current->cred. + * @old is the set of credentials that are being replaces + * @flags contains one of the LSM_SETID_* values. + * Return 0 on success. + * @task_setpgid: + * Check permission before setting the process group identifier of the + * process @p to @pgid. + * @p contains the task_struct for process being modified. + * @pgid contains the new pgid. + * Return 0 if permission is granted. + * @task_getpgid: + * Check permission before getting the process group identifier of the + * process @p. + * @p contains the task_struct for the process. + * Return 0 if permission is granted. + * @task_getsid: + * Check permission before getting the session identifier of the process + * @p. + * @p contains the task_struct for the process. + * Return 0 if permission is granted. + * @task_getsecid: + * Retrieve the security identifier of the process @p. + * @p contains the task_struct for the process and place is into @secid. + * In case of failure, @secid will be set to zero. + * + * @task_setnice: + * Check permission before setting the nice value of @p to @nice. + * @p contains the task_struct of process. + * @nice contains the new nice value. + * Return 0 if permission is granted. + * @task_setioprio + * Check permission before setting the ioprio value of @p to @ioprio. + * @p contains the task_struct of process. + * @ioprio contains the new ioprio value + * Return 0 if permission is granted. + * @task_getioprio + * Check permission before getting the ioprio value of @p. + * @p contains the task_struct of process. + * Return 0 if permission is granted. + * @task_setrlimit: + * Check permission before setting the resource limits of the current + * process for @resource to @new_rlim. The old resource limit values can + * be examined by dereferencing (current->signal->rlim + resource). + * @resource contains the resource whose limit is being set. + * @new_rlim contains the new limits for @resource. + * Return 0 if permission is granted. + * @task_setscheduler: + * Check permission before setting scheduling policy and/or parameters of + * process @p based on @policy and @lp. + * @p contains the task_struct for process. + * @policy contains the scheduling policy. + * @lp contains the scheduling parameters. + * Return 0 if permission is granted. + * @task_getscheduler: + * Check permission before obtaining scheduling information for process + * @p. + * @p contains the task_struct for process. + * Return 0 if permission is granted. + * @task_movememory + * Check permission before moving memory owned by process @p. + * @p contains the task_struct for process. + * Return 0 if permission is granted. + * @task_kill: + * Check permission before sending signal @sig to @p. @info can be NULL, + * the constant 1, or a pointer to a siginfo structure. If @info is 1 or + * SI_FROMKERNEL(info) is true, then the signal should be viewed as coming + * from the kernel and should typically be permitted. + * SIGIO signals are handled separately by the send_sigiotask hook in + * file_security_ops. + * @p contains the task_struct for process. + * @info contains the signal information. + * @sig contains the signal value. + * @secid contains the sid of the process where the signal originated + * Return 0 if permission is granted. + * @task_wait: + * Check permission before allowing a process to reap a child process @p + * and collect its status information. + * @p contains the task_struct for process. + * Return 0 if permission is granted. + * @task_prctl: + * Check permission before performing a process control operation on the + * current process. + * @option contains the operation. + * @arg2 contains a argument. + * @arg3 contains a argument. + * @arg4 contains a argument. + * @arg5 contains a argument. + * Return -ENOSYS if no-one wanted to handle this op, any other value to + * cause prctl() to return immediately with that value. + * @task_to_inode: + * Set the security attributes for an inode based on an associated task's + * security attributes, e.g. for /proc/pid inodes. + * @p contains the task_struct for the task. + * @inode contains the inode structure for the inode. + * + * Security hooks for Netlink messaging. + * + * @netlink_send: + * Save security information for a netlink message so that permission + * checking can be performed when the message is processed. The security + * information can be saved using the eff_cap field of the + * netlink_skb_parms structure. Also may be used to provide fine + * grained control over message transmission. + * @sk associated sock of task sending the message. + * @skb contains the sk_buff structure for the netlink message. + * Return 0 if the information was successfully saved and message + * is allowed to be transmitted. + * + * Security hooks for Unix domain networking. + * + * @unix_stream_connect: + * Check permissions before establishing a Unix domain stream connection + * between @sock and @other. + * @sock contains the sock structure. + * @other contains the peer sock structure. + * @newsk contains the new sock structure. + * Return 0 if permission is granted. + * @unix_may_send: + * Check permissions before connecting or sending datagrams from @sock to + * @other. + * @sock contains the socket structure. + * @other contains the peer socket structure. + * Return 0 if permission is granted. + * + * The @unix_stream_connect and @unix_may_send hooks were necessary because + * Linux provides an alternative to the conventional file name space for Unix + * domain sockets. Whereas binding and connecting to sockets in the file name + * space is mediated by the typical file permissions (and caught by the mknod + * and permission hooks in inode_security_ops), binding and connecting to + * sockets in the abstract name space is completely unmediated. Sufficient + * control of Unix domain sockets in the abstract name space isn't possible + * using only the socket layer hooks, since we need to know the actual target + * socket, which is not looked up until we are inside the af_unix code. + * + * Security hooks for socket operations. + * + * @socket_create: + * Check permissions prior to creating a new socket. + * @family contains the requested protocol family. + * @type contains the requested communications type. + * @protocol contains the requested protocol. + * @kern set to 1 if a kernel socket. + * Return 0 if permission is granted. + * @socket_post_create: + * This hook allows a module to update or allocate a per-socket security + * structure. Note that the security field was not added directly to the + * socket structure, but rather, the socket security information is stored + * in the associated inode. Typically, the inode alloc_security hook will + * allocate and and attach security information to + * sock->inode->i_security. This hook may be used to update the + * sock->inode->i_security field with additional information that wasn't + * available when the inode was allocated. + * @sock contains the newly created socket structure. + * @family contains the requested protocol family. + * @type contains the requested communications type. + * @protocol contains the requested protocol. + * @kern set to 1 if a kernel socket. + * @socket_bind: + * Check permission before socket protocol layer bind operation is + * performed and the socket @sock is bound to the address specified in the + * @address parameter. + * @sock contains the socket structure. + * @address contains the address to bind to. + * @addrlen contains the length of address. + * Return 0 if permission is granted. + * @socket_connect: + * Check permission before socket protocol layer connect operation + * attempts to connect socket @sock to a remote address, @address. + * @sock contains the socket structure. + * @address contains the address of remote endpoint. + * @addrlen contains the length of address. + * Return 0 if permission is granted. + * @socket_listen: + * Check permission before socket protocol layer listen operation. + * @sock contains the socket structure. + * @backlog contains the maximum length for the pending connection queue. + * Return 0 if permission is granted. + * @socket_accept: + * Check permission before accepting a new connection. Note that the new + * socket, @newsock, has been created and some information copied to it, + * but the accept operation has not actually been performed. + * @sock contains the listening socket structure. + * @newsock contains the newly created server socket for connection. + * Return 0 if permission is granted. + * @socket_sendmsg: + * Check permission before transmitting a message to another socket. + * @sock contains the socket structure. + * @msg contains the message to be transmitted. + * @size contains the size of message. + * Return 0 if permission is granted. + * @socket_recvmsg: + * Check permission before receiving a message from a socket. + * @sock contains the socket structure. + * @msg contains the message structure. + * @size contains the size of message structure. + * @flags contains the operational flags. + * Return 0 if permission is granted. + * @socket_getsockname: + * Check permission before the local address (name) of the socket object + * @sock is retrieved. + * @sock contains the socket structure. + * Return 0 if permission is granted. + * @socket_getpeername: + * Check permission before the remote address (name) of a socket object + * @sock is retrieved. + * @sock contains the socket structure. + * Return 0 if permission is granted. + * @socket_getsockopt: + * Check permissions before retrieving the options associated with socket + * @sock. + * @sock contains the socket structure. + * @level contains the protocol level to retrieve option from. + * @optname contains the name of option to retrieve. + * Return 0 if permission is granted. + * @socket_setsockopt: + * Check permissions before setting the options associated with socket + * @sock. + * @sock contains the socket structure. + * @level contains the protocol level to set options for. + * @optname contains the name of the option to set. + * Return 0 if permission is granted. + * @socket_shutdown: + * Checks permission before all or part of a connection on the socket + * @sock is shut down. + * @sock contains the socket structure. + * @how contains the flag indicating how future sends and receives + * are handled. + * Return 0 if permission is granted. + * @socket_sock_rcv_skb: + * Check permissions on incoming network packets. This hook is distinct + * from Netfilter's IP input hooks since it is the first time that the + * incoming sk_buff @skb has been associated with a particular socket, @sk. + * Must not sleep inside this hook because some callers hold spinlocks. + * @sk contains the sock (not socket) associated with the incoming sk_buff. + * @skb contains the incoming network data. + * @socket_getpeersec_stream: + * This hook allows the security module to provide peer socket security + * state for unix or connected tcp sockets to userspace via getsockopt + * SO_GETPEERSEC. For tcp sockets this can be meaningful if the + * socket is associated with an ipsec SA. + * @sock is the local socket. + * @optval userspace memory where the security state is to be copied. + * @optlen userspace int where the module should copy the actual length + * of the security state. + * @len as input is the maximum length to copy to userspace provided + * by the caller. + * Return 0 if all is well, otherwise, typical getsockopt return + * values. + * @socket_getpeersec_dgram: + * This hook allows the security module to provide peer socket security + * state for udp sockets on a per-packet basis to userspace via + * getsockopt SO_GETPEERSEC. The application must first have indicated + * the IP_PASSSEC option via getsockopt. It can then retrieve the + * security state returned by this hook for a packet via the SCM_SECURITY + * ancillary message type. + * @skb is the skbuff for the packet being queried + * @secdata is a pointer to a buffer in which to copy the security data + * @seclen is the maximum length for @secdata + * Return 0 on success, error on failure. + * @sk_alloc_security: + * Allocate and attach a security structure to the sk->sk_security field, + * which is used to copy security attributes between local stream sockets. + * @sk_free_security: + * Deallocate security structure. + * @sk_clone_security: + * Clone/copy security structure. + * @sk_getsecid: + * Retrieve the LSM-specific secid for the sock to enable caching + * of network authorizations. + * @sock_graft: + * Sets the socket's isec sid to the sock's sid. + * @inet_conn_request: + * Sets the openreq's sid to socket's sid with MLS portion taken + * from peer sid. + * @inet_csk_clone: + * Sets the new child socket's sid to the openreq sid. + * @inet_conn_established: + * Sets the connection's peersid to the secmark on skb. + * @secmark_relabel_packet: + * check if the process should be allowed to relabel packets to + * the given secid + * @security_secmark_refcount_inc + * tells the LSM to increment the number of secmark labeling rules loaded + * @security_secmark_refcount_dec + * tells the LSM to decrement the number of secmark labeling rules loaded + * @req_classify_flow: + * Sets the flow's sid to the openreq sid. + * @tun_dev_alloc_security: + * This hook allows a module to allocate a security structure for a TUN + * device. + * @security pointer to a security structure pointer. + * Returns a zero on success, negative values on failure. + * @tun_dev_free_security: + * This hook allows a module to free the security structure for a TUN + * device. + * @security pointer to the TUN device's security structure + * @tun_dev_create: + * Check permissions prior to creating a new TUN device. + * @tun_dev_attach_queue: + * Check permissions prior to attaching to a TUN device queue. + * @security pointer to the TUN device's security structure. + * @tun_dev_attach: + * This hook can be used by the module to update any security state + * associated with the TUN device's sock structure. + * @sk contains the existing sock structure. + * @security pointer to the TUN device's security structure. + * @tun_dev_open: + * This hook can be used by the module to update any security state + * associated with the TUN device's security structure. + * @security pointer to the TUN devices's security structure. + * + * Security hooks for XFRM operations. + * + * @xfrm_policy_alloc_security: + * @ctxp is a pointer to the xfrm_sec_ctx being added to Security Policy + * Database used by the XFRM system. + * @sec_ctx contains the security context information being provided by + * the user-level policy update program (e.g., setkey). + * Allocate a security structure to the xp->security field; the security + * field is initialized to NULL when the xfrm_policy is allocated. + * Return 0 if operation was successful (memory to allocate, legal context) + * @gfp is to specify the context for the allocation + * @xfrm_policy_clone_security: + * @old_ctx contains an existing xfrm_sec_ctx. + * @new_ctxp contains a new xfrm_sec_ctx being cloned from old. + * Allocate a security structure in new_ctxp that contains the + * information from the old_ctx structure. + * Return 0 if operation was successful (memory to allocate). + * @xfrm_policy_free_security: + * @ctx contains the xfrm_sec_ctx + * Deallocate xp->security. + * @xfrm_policy_delete_security: + * @ctx contains the xfrm_sec_ctx. + * Authorize deletion of xp->security. + * @xfrm_state_alloc: + * @x contains the xfrm_state being added to the Security Association + * Database by the XFRM system. + * @sec_ctx contains the security context information being provided by + * the user-level SA generation program (e.g., setkey or racoon). + * Allocate a security structure to the x->security field; the security + * field is initialized to NULL when the xfrm_state is allocated. Set the + * context to correspond to sec_ctx. Return 0 if operation was successful + * (memory to allocate, legal context). + * @xfrm_state_alloc_acquire: + * @x contains the xfrm_state being added to the Security Association + * Database by the XFRM system. + * @polsec contains the policy's security context. + * @secid contains the secid from which to take the mls portion of the + * context. + * Allocate a security structure to the x->security field; the security + * field is initialized to NULL when the xfrm_state is allocated. Set the + * context to correspond to secid. Return 0 if operation was successful + * (memory to allocate, legal context). + * @xfrm_state_free_security: + * @x contains the xfrm_state. + * Deallocate x->security. + * @xfrm_state_delete_security: + * @x contains the xfrm_state. + * Authorize deletion of x->security. + * @xfrm_policy_lookup: + * @ctx contains the xfrm_sec_ctx for which the access control is being + * checked. + * @fl_secid contains the flow security label that is used to authorize + * access to the policy xp. + * @dir contains the direction of the flow (input or output). + * Check permission when a flow selects a xfrm_policy for processing + * XFRMs on a packet. The hook is called when selecting either a + * per-socket policy or a generic xfrm policy. + * Return 0 if permission is granted, -ESRCH otherwise, or -errno + * on other errors. + * @xfrm_state_pol_flow_match: + * @x contains the state to match. + * @xp contains the policy to check for a match. + * @fl contains the flow to check for a match. + * Return 1 if there is a match. + * @xfrm_decode_session: + * @skb points to skb to decode. + * @secid points to the flow key secid to set. + * @ckall says if all xfrms used should be checked for same secid. + * Return 0 if ckall is zero or all xfrms used have the same secid. + * + * Security hooks affecting all Key Management operations + * + * @key_alloc: + * Permit allocation of a key and assign security data. Note that key does + * not have a serial number assigned at this point. + * @key points to the key. + * @flags is the allocation flags + * Return 0 if permission is granted, -ve error otherwise. + * @key_free: + * Notification of destruction; free security data. + * @key points to the key. + * No return value. + * @key_permission: + * See whether a specific operational right is granted to a process on a + * key. + * @key_ref refers to the key (key pointer + possession attribute bit). + * @cred points to the credentials to provide the context against which to + * evaluate the security data on the key. + * @perm describes the combination of permissions required of this key. + * Return 0 if permission is granted, -ve error otherwise. + * @key_getsecurity: + * Get a textual representation of the security context attached to a key + * for the purposes of honouring KEYCTL_GETSECURITY. This function + * allocates the storage for the NUL-terminated string and the caller + * should free it. + * @key points to the key to be queried. + * @_buffer points to a pointer that should be set to point to the + * resulting string (if no label or an error occurs). + * Return the length of the string (including terminating NUL) or -ve if + * an error. + * May also return 0 (and a NULL buffer pointer) if there is no label. + * + * Security hooks affecting all System V IPC operations. + * + * @ipc_permission: + * Check permissions for access to IPC + * @ipcp contains the kernel IPC permission structure + * @flag contains the desired (requested) permission set + * Return 0 if permission is granted. + * @ipc_getsecid: + * Get the secid associated with the ipc object. + * @ipcp contains the kernel IPC permission structure. + * @secid contains a pointer to the location where result will be saved. + * In case of failure, @secid will be set to zero. + * + * Security hooks for individual messages held in System V IPC message queues + * @msg_msg_alloc_security: + * Allocate and attach a security structure to the msg->security field. + * The security field is initialized to NULL when the structure is first + * created. + * @msg contains the message structure to be modified. + * Return 0 if operation was successful and permission is granted. + * @msg_msg_free_security: + * Deallocate the security structure for this message. + * @msg contains the message structure to be modified. + * + * Security hooks for System V IPC Message Queues + * + * @msg_queue_alloc_security: + * Allocate and attach a security structure to the + * msq->q_perm.security field. The security field is initialized to + * NULL when the structure is first created. + * @msq contains the message queue structure to be modified. + * Return 0 if operation was successful and permission is granted. + * @msg_queue_free_security: + * Deallocate security structure for this message queue. + * @msq contains the message queue structure to be modified. + * @msg_queue_associate: + * Check permission when a message queue is requested through the + * msgget system call. This hook is only called when returning the + * message queue identifier for an existing message queue, not when a + * new message queue is created. + * @msq contains the message queue to act upon. + * @msqflg contains the operation control flags. + * Return 0 if permission is granted. + * @msg_queue_msgctl: + * Check permission when a message control operation specified by @cmd + * is to be performed on the message queue @msq. + * The @msq may be NULL, e.g. for IPC_INFO or MSG_INFO. + * @msq contains the message queue to act upon. May be NULL. + * @cmd contains the operation to be performed. + * Return 0 if permission is granted. + * @msg_queue_msgsnd: + * Check permission before a message, @msg, is enqueued on the message + * queue, @msq. + * @msq contains the message queue to send message to. + * @msg contains the message to be enqueued. + * @msqflg contains operational flags. + * Return 0 if permission is granted. + * @msg_queue_msgrcv: + * Check permission before a message, @msg, is removed from the message + * queue, @msq. The @target task structure contains a pointer to the + * process that will be receiving the message (not equal to the current + * process when inline receives are being performed). + * @msq contains the message queue to retrieve message from. + * @msg contains the message destination. + * @target contains the task structure for recipient process. + * @type contains the type of message requested. + * @mode contains the operational flags. + * Return 0 if permission is granted. + * + * Security hooks for System V Shared Memory Segments + * + * @shm_alloc_security: + * Allocate and attach a security structure to the shp->shm_perm.security + * field. The security field is initialized to NULL when the structure is + * first created. + * @shp contains the shared memory structure to be modified. + * Return 0 if operation was successful and permission is granted. + * @shm_free_security: + * Deallocate the security struct for this memory segment. + * @shp contains the shared memory structure to be modified. + * @shm_associate: + * Check permission when a shared memory region is requested through the + * shmget system call. This hook is only called when returning the shared + * memory region identifier for an existing region, not when a new shared + * memory region is created. + * @shp contains the shared memory structure to be modified. + * @shmflg contains the operation control flags. + * Return 0 if permission is granted. + * @shm_shmctl: + * Check permission when a shared memory control operation specified by + * @cmd is to be performed on the shared memory region @shp. + * The @shp may be NULL, e.g. for IPC_INFO or SHM_INFO. + * @shp contains shared memory structure to be modified. + * @cmd contains the operation to be performed. + * Return 0 if permission is granted. + * @shm_shmat: + * Check permissions prior to allowing the shmat system call to attach the + * shared memory segment @shp to the data segment of the calling process. + * The attaching address is specified by @shmaddr. + * @shp contains the shared memory structure to be modified. + * @shmaddr contains the address to attach memory region to. + * @shmflg contains the operational flags. + * Return 0 if permission is granted. + * + * Security hooks for System V Semaphores + * + * @sem_alloc_security: + * Allocate and attach a security structure to the sma->sem_perm.security + * field. The security field is initialized to NULL when the structure is + * first created. + * @sma contains the semaphore structure + * Return 0 if operation was successful and permission is granted. + * @sem_free_security: + * deallocate security struct for this semaphore + * @sma contains the semaphore structure. + * @sem_associate: + * Check permission when a semaphore is requested through the semget + * system call. This hook is only called when returning the semaphore + * identifier for an existing semaphore, not when a new one must be + * created. + * @sma contains the semaphore structure. + * @semflg contains the operation control flags. + * Return 0 if permission is granted. + * @sem_semctl: + * Check permission when a semaphore operation specified by @cmd is to be + * performed on the semaphore @sma. The @sma may be NULL, e.g. for + * IPC_INFO or SEM_INFO. + * @sma contains the semaphore structure. May be NULL. + * @cmd contains the operation to be performed. + * Return 0 if permission is granted. + * @sem_semop + * Check permissions before performing operations on members of the + * semaphore set @sma. If the @alter flag is nonzero, the semaphore set + * may be modified. + * @sma contains the semaphore structure. + * @sops contains the operations to perform. + * @nsops contains the number of operations to perform. + * @alter contains the flag indicating whether changes are to be made. + * Return 0 if permission is granted. + * + * @binder_set_context_mgr + * Check whether @mgr is allowed to be the binder context manager. + * @mgr contains the task_struct for the task being registered. + * Return 0 if permission is granted. + * @binder_transaction + * Check whether @from is allowed to invoke a binder transaction call + * to @to. + * @from contains the task_struct for the sending task. + * @to contains the task_struct for the receiving task. + * @binder_transfer_binder + * Check whether @from is allowed to transfer a binder reference to @to. + * @from contains the task_struct for the sending task. + * @to contains the task_struct for the receiving task. + * @binder_transfer_file + * Check whether @from is allowed to transfer @file to @to. + * @from contains the task_struct for the sending task. + * @file contains the struct file being transferred. + * @to contains the task_struct for the receiving task. + * + * @ptrace_access_check: + * Check permission before allowing the current process to trace the + * @child process. + * Security modules may also want to perform a process tracing check + * during an execve in the set_security or apply_creds hooks of + * tracing check during an execve in the bprm_set_creds hook of + * binprm_security_ops if the process is being traced and its security + * attributes would be changed by the execve. + * @child contains the task_struct structure for the target process. + * @mode contains the PTRACE_MODE flags indicating the form of access. + * Return 0 if permission is granted. + * @ptrace_traceme: + * Check that the @parent process has sufficient permission to trace the + * current process before allowing the current process to present itself + * to the @parent process for tracing. + * @parent contains the task_struct structure for debugger process. + * Return 0 if permission is granted. + * @capget: + * Get the @effective, @inheritable, and @permitted capability sets for + * the @target process. The hook may also perform permission checking to + * determine if the current process is allowed to see the capability sets + * of the @target process. + * @target contains the task_struct structure for target process. + * @effective contains the effective capability set. + * @inheritable contains the inheritable capability set. + * @permitted contains the permitted capability set. + * Return 0 if the capability sets were successfully obtained. + * @capset: + * Set the @effective, @inheritable, and @permitted capability sets for + * the current process. + * @new contains the new credentials structure for target process. + * @old contains the current credentials structure for target process. + * @effective contains the effective capability set. + * @inheritable contains the inheritable capability set. + * @permitted contains the permitted capability set. + * Return 0 and update @new if permission is granted. + * @capable: + * Check whether the @tsk process has the @cap capability in the indicated + * credentials. + * @cred contains the credentials to use. + * @ns contains the user namespace we want the capability in + * @cap contains the capability <include/linux/capability.h>. + * @audit: Whether to write an audit message or not + * Return 0 if the capability is granted for @tsk. + * @syslog: + * Check permission before accessing the kernel message ring or changing + * logging to the console. + * See the syslog(2) manual page for an explanation of the @type values. + * @type contains the type of action. + * @from_file indicates the context of action (if it came from /proc). + * Return 0 if permission is granted. + * @settime: + * Check permission to change the system time. + * struct timespec and timezone are defined in include/linux/time.h + * @ts contains new time + * @tz contains new timezone + * Return 0 if permission is granted. + * @vm_enough_memory: + * Check permissions for allocating a new virtual mapping. + * @mm contains the mm struct it is being added to. + * @pages contains the number of pages. + * Return 0 if permission is granted. + * + * @ismaclabel: + * Check if the extended attribute specified by @name + * represents a MAC label. Returns 1 if name is a MAC + * attribute otherwise returns 0. + * @name full extended attribute name to check against + * LSM as a MAC label. + * + * @secid_to_secctx: + * Convert secid to security context. If secdata is NULL the length of + * the result will be returned in seclen, but no secdata will be returned. + * This does mean that the length could change between calls to check the + * length and the next call which actually allocates and returns the + * secdata. + * @secid contains the security ID. + * @secdata contains the pointer that stores the converted security + * context. + * @seclen pointer which contains the length of the data + * @secctx_to_secid: + * Convert security context to secid. + * @secid contains the pointer to the generated security ID. + * @secdata contains the security context. + * + * @release_secctx: + * Release the security context. + * @secdata contains the security context. + * @seclen contains the length of the security context. + * + * Security hooks for Audit + * + * @audit_rule_init: + * Allocate and initialize an LSM audit rule structure. + * @field contains the required Audit action. + * Fields flags are defined in include/linux/audit.h + * @op contains the operator the rule uses. + * @rulestr contains the context where the rule will be applied to. + * @lsmrule contains a pointer to receive the result. + * Return 0 if @lsmrule has been successfully set, + * -EINVAL in case of an invalid rule. + * + * @audit_rule_known: + * Specifies whether given @rule contains any fields related to + * current LSM. + * @rule contains the audit rule of interest. + * Return 1 in case of relation found, 0 otherwise. + * + * @audit_rule_match: + * Determine if given @secid matches a rule previously approved + * by @audit_rule_known. + * @secid contains the security id in question. + * @field contains the field which relates to current LSM. + * @op contains the operator that will be used for matching. + * @rule points to the audit rule that will be checked against. + * @actx points to the audit context associated with the check. + * Return 1 if secid matches the rule, 0 if it does not, -ERRNO on failure. + * + * @audit_rule_free: + * Deallocate the LSM audit rule structure previously allocated by + * audit_rule_init. + * @rule contains the allocated rule + * + * @inode_notifysecctx: + * Notify the security module of what the security context of an inode + * should be. Initializes the incore security context managed by the + * security module for this inode. Example usage: NFS client invokes + * this hook to initialize the security context in its incore inode to the + * value provided by the server for the file when the server returned the + * file's attributes to the client. + * + * Must be called with inode->i_mutex locked. + * + * @inode we wish to set the security context of. + * @ctx contains the string which we wish to set in the inode. + * @ctxlen contains the length of @ctx. + * + * @inode_setsecctx: + * Change the security context of an inode. Updates the + * incore security context managed by the security module and invokes the + * fs code as needed (via __vfs_setxattr_noperm) to update any backing + * xattrs that represent the context. Example usage: NFS server invokes + * this hook to change the security context in its incore inode and on the + * backing filesystem to a value provided by the client on a SETATTR + * operation. + * + * Must be called with inode->i_mutex locked. + * + * @dentry contains the inode we wish to set the security context of. + * @ctx contains the string which we wish to set in the inode. + * @ctxlen contains the length of @ctx. + * + * @inode_getsecctx: + * On success, returns 0 and fills out @ctx and @ctxlen with the security + * context for the given @inode. + * + * @inode we wish to get the security context of. + * @ctx is a pointer in which to place the allocated security context. + * @ctxlen points to the place to put the length of @ctx. + * This is the main security structure. + */ + +union security_list_options { + int (*binder_set_context_mgr)(struct task_struct *mgr); + int (*binder_transaction)(struct task_struct *from, + struct task_struct *to); + int (*binder_transfer_binder)(struct task_struct *from, + struct task_struct *to); + int (*binder_transfer_file)(struct task_struct *from, + struct task_struct *to, + struct file *file); + + int (*ptrace_access_check)(struct task_struct *child, + unsigned int mode); + int (*ptrace_traceme)(struct task_struct *parent); + int (*capget)(struct task_struct *target, kernel_cap_t *effective, + kernel_cap_t *inheritable, kernel_cap_t *permitted); + int (*capset)(struct cred *new, const struct cred *old, + const kernel_cap_t *effective, + const kernel_cap_t *inheritable, + const kernel_cap_t *permitted); + int (*capable)(const struct cred *cred, struct user_namespace *ns, + int cap, int audit); + int (*quotactl)(int cmds, int type, int id, struct super_block *sb); + int (*quota_on)(struct dentry *dentry); + int (*syslog)(int type); + int (*settime)(const struct timespec *ts, const struct timezone *tz); + int (*vm_enough_memory)(struct mm_struct *mm, long pages); + + int (*bprm_set_creds)(struct linux_binprm *bprm); + int (*bprm_check_security)(struct linux_binprm *bprm); + int (*bprm_secureexec)(struct linux_binprm *bprm); + void (*bprm_committing_creds)(struct linux_binprm *bprm); + void (*bprm_committed_creds)(struct linux_binprm *bprm); + + int (*sb_alloc_security)(struct super_block *sb); + void (*sb_free_security)(struct super_block *sb); + int (*sb_copy_data)(char *orig, char *copy); + int (*sb_remount)(struct super_block *sb, void *data); + int (*sb_kern_mount)(struct super_block *sb, int flags, void *data); + int (*sb_show_options)(struct seq_file *m, struct super_block *sb); + int (*sb_statfs)(struct dentry *dentry); + int (*sb_mount)(const char *dev_name, struct path *path, + const char *type, unsigned long flags, void *data); + int (*sb_umount)(struct vfsmount *mnt, int flags); + int (*sb_pivotroot)(struct path *old_path, struct path *new_path); + int (*sb_set_mnt_opts)(struct super_block *sb, + struct security_mnt_opts *opts, + unsigned long kern_flags, + unsigned long *set_kern_flags); + int (*sb_clone_mnt_opts)(const struct super_block *oldsb, + struct super_block *newsb); + int (*sb_parse_opts_str)(char *options, struct security_mnt_opts *opts); + int (*dentry_init_security)(struct dentry *dentry, int mode, + struct qstr *name, void **ctx, + u32 *ctxlen); + + +#ifdef CONFIG_SECURITY_PATH + int (*path_unlink)(struct path *dir, struct dentry *dentry); + int (*path_mkdir)(struct path *dir, struct dentry *dentry, + umode_t mode); + int (*path_rmdir)(struct path *dir, struct dentry *dentry); + int (*path_mknod)(struct path *dir, struct dentry *dentry, + umode_t mode, unsigned int dev); + int (*path_truncate)(struct path *path); + int (*path_symlink)(struct path *dir, struct dentry *dentry, + const char *old_name); + int (*path_link)(struct dentry *old_dentry, struct path *new_dir, + struct dentry *new_dentry); + int (*path_rename)(struct path *old_dir, struct dentry *old_dentry, + struct path *new_dir, + struct dentry *new_dentry); + int (*path_chmod)(struct path *path, umode_t mode); + int (*path_chown)(struct path *path, kuid_t uid, kgid_t gid); + int (*path_chroot)(struct path *path); +#endif + + int (*inode_alloc_security)(struct inode *inode); + void (*inode_free_security)(struct inode *inode); + int (*inode_init_security)(struct inode *inode, struct inode *dir, + const struct qstr *qstr, + const char **name, void **value, + size_t *len); + int (*inode_create)(struct inode *dir, struct dentry *dentry, + umode_t mode); + int (*inode_link)(struct dentry *old_dentry, struct inode *dir, + struct dentry *new_dentry); + int (*inode_unlink)(struct inode *dir, struct dentry *dentry); + int (*inode_symlink)(struct inode *dir, struct dentry *dentry, + const char *old_name); + int (*inode_mkdir)(struct inode *dir, struct dentry *dentry, + umode_t mode); + int (*inode_rmdir)(struct inode *dir, struct dentry *dentry); + int (*inode_mknod)(struct inode *dir, struct dentry *dentry, + umode_t mode, dev_t dev); + int (*inode_rename)(struct inode *old_dir, struct dentry *old_dentry, + struct inode *new_dir, + struct dentry *new_dentry); + int (*inode_readlink)(struct dentry *dentry); + int (*inode_follow_link)(struct dentry *dentry, struct inode *inode, + bool rcu); + int (*inode_permission)(struct inode *inode, int mask); + int (*inode_setattr)(struct dentry *dentry, struct iattr *attr); + int (*inode_getattr)(const struct path *path); + int (*inode_setxattr)(struct dentry *dentry, const char *name, + const void *value, size_t size, int flags); + void (*inode_post_setxattr)(struct dentry *dentry, const char *name, + const void *value, size_t size, + int flags); + int (*inode_getxattr)(struct dentry *dentry, const char *name); + int (*inode_listxattr)(struct dentry *dentry); + int (*inode_removexattr)(struct dentry *dentry, const char *name); + int (*inode_need_killpriv)(struct dentry *dentry); + int (*inode_killpriv)(struct dentry *dentry); + int (*inode_getsecurity)(const struct inode *inode, const char *name, + void **buffer, bool alloc); + int (*inode_setsecurity)(struct inode *inode, const char *name, + const void *value, size_t size, + int flags); + int (*inode_listsecurity)(struct inode *inode, char *buffer, + size_t buffer_size); + void (*inode_getsecid)(const struct inode *inode, u32 *secid); + + int (*file_permission)(struct file *file, int mask); + int (*file_alloc_security)(struct file *file); + void (*file_free_security)(struct file *file); + int (*file_ioctl)(struct file *file, unsigned int cmd, + unsigned long arg); + int (*mmap_addr)(unsigned long addr); + int (*mmap_file)(struct file *file, unsigned long reqprot, + unsigned long prot, unsigned long flags); + int (*file_mprotect)(struct vm_area_struct *vma, unsigned long reqprot, + unsigned long prot); + int (*file_lock)(struct file *file, unsigned int cmd); + int (*file_fcntl)(struct file *file, unsigned int cmd, + unsigned long arg); + void (*file_set_fowner)(struct file *file); + int (*file_send_sigiotask)(struct task_struct *tsk, + struct fown_struct *fown, int sig); + int (*file_receive)(struct file *file); + int (*file_open)(struct file *file, const struct cred *cred); + + int (*task_create)(unsigned long clone_flags); + void (*task_free)(struct task_struct *task); + int (*cred_alloc_blank)(struct cred *cred, gfp_t gfp); + void (*cred_free)(struct cred *cred); + int (*cred_prepare)(struct cred *new, const struct cred *old, + gfp_t gfp); + void (*cred_transfer)(struct cred *new, const struct cred *old); + int (*kernel_act_as)(struct cred *new, u32 secid); + int (*kernel_create_files_as)(struct cred *new, struct inode *inode); + int (*kernel_fw_from_file)(struct file *file, char *buf, size_t size); + int (*kernel_module_request)(char *kmod_name); + int (*kernel_module_from_file)(struct file *file); + int (*task_fix_setuid)(struct cred *new, const struct cred *old, + int flags); + int (*task_setpgid)(struct task_struct *p, pid_t pgid); + int (*task_getpgid)(struct task_struct *p); + int (*task_getsid)(struct task_struct *p); + void (*task_getsecid)(struct task_struct *p, u32 *secid); + int (*task_setnice)(struct task_struct *p, int nice); + int (*task_setioprio)(struct task_struct *p, int ioprio); + int (*task_getioprio)(struct task_struct *p); + int (*task_setrlimit)(struct task_struct *p, unsigned int resource, + struct rlimit *new_rlim); + int (*task_setscheduler)(struct task_struct *p); + int (*task_getscheduler)(struct task_struct *p); + int (*task_movememory)(struct task_struct *p); + int (*task_kill)(struct task_struct *p, struct siginfo *info, + int sig, u32 secid); + int (*task_wait)(struct task_struct *p); + int (*task_prctl)(int option, unsigned long arg2, unsigned long arg3, + unsigned long arg4, unsigned long arg5); + void (*task_to_inode)(struct task_struct *p, struct inode *inode); + + int (*ipc_permission)(struct kern_ipc_perm *ipcp, short flag); + void (*ipc_getsecid)(struct kern_ipc_perm *ipcp, u32 *secid); + + int (*msg_msg_alloc_security)(struct msg_msg *msg); + void (*msg_msg_free_security)(struct msg_msg *msg); + + int (*msg_queue_alloc_security)(struct msg_queue *msq); + void (*msg_queue_free_security)(struct msg_queue *msq); + int (*msg_queue_associate)(struct msg_queue *msq, int msqflg); + int (*msg_queue_msgctl)(struct msg_queue *msq, int cmd); + int (*msg_queue_msgsnd)(struct msg_queue *msq, struct msg_msg *msg, + int msqflg); + int (*msg_queue_msgrcv)(struct msg_queue *msq, struct msg_msg *msg, + struct task_struct *target, long type, + int mode); + + int (*shm_alloc_security)(struct shmid_kernel *shp); + void (*shm_free_security)(struct shmid_kernel *shp); + int (*shm_associate)(struct shmid_kernel *shp, int shmflg); + int (*shm_shmctl)(struct shmid_kernel *shp, int cmd); + int (*shm_shmat)(struct shmid_kernel *shp, char __user *shmaddr, + int shmflg); + + int (*sem_alloc_security)(struct sem_array *sma); + void (*sem_free_security)(struct sem_array *sma); + int (*sem_associate)(struct sem_array *sma, int semflg); + int (*sem_semctl)(struct sem_array *sma, int cmd); + int (*sem_semop)(struct sem_array *sma, struct sembuf *sops, + unsigned nsops, int alter); + + int (*netlink_send)(struct sock *sk, struct sk_buff *skb); + + void (*d_instantiate)(struct dentry *dentry, struct inode *inode); + + int (*getprocattr)(struct task_struct *p, char *name, char **value); + int (*setprocattr)(struct task_struct *p, char *name, void *value, + size_t size); + int (*ismaclabel)(const char *name); + int (*secid_to_secctx)(u32 secid, char **secdata, u32 *seclen); + int (*secctx_to_secid)(const char *secdata, u32 seclen, u32 *secid); + void (*release_secctx)(char *secdata, u32 seclen); + + int (*inode_notifysecctx)(struct inode *inode, void *ctx, u32 ctxlen); + int (*inode_setsecctx)(struct dentry *dentry, void *ctx, u32 ctxlen); + int (*inode_getsecctx)(struct inode *inode, void **ctx, u32 *ctxlen); + +#ifdef CONFIG_SECURITY_NETWORK + int (*unix_stream_connect)(struct sock *sock, struct sock *other, + struct sock *newsk); + int (*unix_may_send)(struct socket *sock, struct socket *other); + + int (*socket_create)(int family, int type, int protocol, int kern); + int (*socket_post_create)(struct socket *sock, int family, int type, + int protocol, int kern); + int (*socket_bind)(struct socket *sock, struct sockaddr *address, + int addrlen); + int (*socket_connect)(struct socket *sock, struct sockaddr *address, + int addrlen); + int (*socket_listen)(struct socket *sock, int backlog); + int (*socket_accept)(struct socket *sock, struct socket *newsock); + int (*socket_sendmsg)(struct socket *sock, struct msghdr *msg, + int size); + int (*socket_recvmsg)(struct socket *sock, struct msghdr *msg, + int size, int flags); + int (*socket_getsockname)(struct socket *sock); + int (*socket_getpeername)(struct socket *sock); + int (*socket_getsockopt)(struct socket *sock, int level, int optname); + int (*socket_setsockopt)(struct socket *sock, int level, int optname); + int (*socket_shutdown)(struct socket *sock, int how); + int (*socket_sock_rcv_skb)(struct sock *sk, struct sk_buff *skb); + int (*socket_getpeersec_stream)(struct socket *sock, + char __user *optval, + int __user *optlen, unsigned len); + int (*socket_getpeersec_dgram)(struct socket *sock, + struct sk_buff *skb, u32 *secid); + int (*sk_alloc_security)(struct sock *sk, int family, gfp_t priority); + void (*sk_free_security)(struct sock *sk); + void (*sk_clone_security)(const struct sock *sk, struct sock *newsk); + void (*sk_getsecid)(struct sock *sk, u32 *secid); + void (*sock_graft)(struct sock *sk, struct socket *parent); + int (*inet_conn_request)(struct sock *sk, struct sk_buff *skb, + struct request_sock *req); + void (*inet_csk_clone)(struct sock *newsk, + const struct request_sock *req); + void (*inet_conn_established)(struct sock *sk, struct sk_buff *skb); + int (*secmark_relabel_packet)(u32 secid); + void (*secmark_refcount_inc)(void); + void (*secmark_refcount_dec)(void); + void (*req_classify_flow)(const struct request_sock *req, + struct flowi *fl); + int (*tun_dev_alloc_security)(void **security); + void (*tun_dev_free_security)(void *security); + int (*tun_dev_create)(void); + int (*tun_dev_attach_queue)(void *security); + int (*tun_dev_attach)(struct sock *sk, void *security); + int (*tun_dev_open)(void *security); +#endif /* CONFIG_SECURITY_NETWORK */ + +#ifdef CONFIG_SECURITY_NETWORK_XFRM + int (*xfrm_policy_alloc_security)(struct xfrm_sec_ctx **ctxp, + struct xfrm_user_sec_ctx *sec_ctx, + gfp_t gfp); + int (*xfrm_policy_clone_security)(struct xfrm_sec_ctx *old_ctx, + struct xfrm_sec_ctx **new_ctx); + void (*xfrm_policy_free_security)(struct xfrm_sec_ctx *ctx); + int (*xfrm_policy_delete_security)(struct xfrm_sec_ctx *ctx); + int (*xfrm_state_alloc)(struct xfrm_state *x, + struct xfrm_user_sec_ctx *sec_ctx); + int (*xfrm_state_alloc_acquire)(struct xfrm_state *x, + struct xfrm_sec_ctx *polsec, + u32 secid); + void (*xfrm_state_free_security)(struct xfrm_state *x); + int (*xfrm_state_delete_security)(struct xfrm_state *x); + int (*xfrm_policy_lookup)(struct xfrm_sec_ctx *ctx, u32 fl_secid, + u8 dir); + int (*xfrm_state_pol_flow_match)(struct xfrm_state *x, + struct xfrm_policy *xp, + const struct flowi *fl); + int (*xfrm_decode_session)(struct sk_buff *skb, u32 *secid, int ckall); +#endif /* CONFIG_SECURITY_NETWORK_XFRM */ + + /* key management security hooks */ +#ifdef CONFIG_KEYS + int (*key_alloc)(struct key *key, const struct cred *cred, + unsigned long flags); + void (*key_free)(struct key *key); + int (*key_permission)(key_ref_t key_ref, const struct cred *cred, + unsigned perm); + int (*key_getsecurity)(struct key *key, char **_buffer); +#endif /* CONFIG_KEYS */ + +#ifdef CONFIG_AUDIT + int (*audit_rule_init)(u32 field, u32 op, char *rulestr, + void **lsmrule); + int (*audit_rule_known)(struct audit_krule *krule); + int (*audit_rule_match)(u32 secid, u32 field, u32 op, void *lsmrule, + struct audit_context *actx); + void (*audit_rule_free)(void *lsmrule); +#endif /* CONFIG_AUDIT */ +}; + +struct security_hook_heads { + struct list_head binder_set_context_mgr; + struct list_head binder_transaction; + struct list_head binder_transfer_binder; + struct list_head binder_transfer_file; + struct list_head ptrace_access_check; + struct list_head ptrace_traceme; + struct list_head capget; + struct list_head capset; + struct list_head capable; + struct list_head quotactl; + struct list_head quota_on; + struct list_head syslog; + struct list_head settime; + struct list_head vm_enough_memory; + struct list_head bprm_set_creds; + struct list_head bprm_check_security; + struct list_head bprm_secureexec; + struct list_head bprm_committing_creds; + struct list_head bprm_committed_creds; + struct list_head sb_alloc_security; + struct list_head sb_free_security; + struct list_head sb_copy_data; + struct list_head sb_remount; + struct list_head sb_kern_mount; + struct list_head sb_show_options; + struct list_head sb_statfs; + struct list_head sb_mount; + struct list_head sb_umount; + struct list_head sb_pivotroot; + struct list_head sb_set_mnt_opts; + struct list_head sb_clone_mnt_opts; + struct list_head sb_parse_opts_str; + struct list_head dentry_init_security; +#ifdef CONFIG_SECURITY_PATH + struct list_head path_unlink; + struct list_head path_mkdir; + struct list_head path_rmdir; + struct list_head path_mknod; + struct list_head path_truncate; + struct list_head path_symlink; + struct list_head path_link; + struct list_head path_rename; + struct list_head path_chmod; + struct list_head path_chown; + struct list_head path_chroot; +#endif + struct list_head inode_alloc_security; + struct list_head inode_free_security; + struct list_head inode_init_security; + struct list_head inode_create; + struct list_head inode_link; + struct list_head inode_unlink; + struct list_head inode_symlink; + struct list_head inode_mkdir; + struct list_head inode_rmdir; + struct list_head inode_mknod; + struct list_head inode_rename; + struct list_head inode_readlink; + struct list_head inode_follow_link; + struct list_head inode_permission; + struct list_head inode_setattr; + struct list_head inode_getattr; + struct list_head inode_setxattr; + struct list_head inode_post_setxattr; + struct list_head inode_getxattr; + struct list_head inode_listxattr; + struct list_head inode_removexattr; + struct list_head inode_need_killpriv; + struct list_head inode_killpriv; + struct list_head inode_getsecurity; + struct list_head inode_setsecurity; + struct list_head inode_listsecurity; + struct list_head inode_getsecid; + struct list_head file_permission; + struct list_head file_alloc_security; + struct list_head file_free_security; + struct list_head file_ioctl; + struct list_head mmap_addr; + struct list_head mmap_file; + struct list_head file_mprotect; + struct list_head file_lock; + struct list_head file_fcntl; + struct list_head file_set_fowner; + struct list_head file_send_sigiotask; + struct list_head file_receive; + struct list_head file_open; + struct list_head task_create; + struct list_head task_free; + struct list_head cred_alloc_blank; + struct list_head cred_free; + struct list_head cred_prepare; + struct list_head cred_transfer; + struct list_head kernel_act_as; + struct list_head kernel_create_files_as; + struct list_head kernel_fw_from_file; + struct list_head kernel_module_request; + struct list_head kernel_module_from_file; + struct list_head task_fix_setuid; + struct list_head task_setpgid; + struct list_head task_getpgid; + struct list_head task_getsid; + struct list_head task_getsecid; + struct list_head task_setnice; + struct list_head task_setioprio; + struct list_head task_getioprio; + struct list_head task_setrlimit; + struct list_head task_setscheduler; + struct list_head task_getscheduler; + struct list_head task_movememory; + struct list_head task_kill; + struct list_head task_wait; + struct list_head task_prctl; + struct list_head task_to_inode; + struct list_head ipc_permission; + struct list_head ipc_getsecid; + struct list_head msg_msg_alloc_security; + struct list_head msg_msg_free_security; + struct list_head msg_queue_alloc_security; + struct list_head msg_queue_free_security; + struct list_head msg_queue_associate; + struct list_head msg_queue_msgctl; + struct list_head msg_queue_msgsnd; + struct list_head msg_queue_msgrcv; + struct list_head shm_alloc_security; + struct list_head shm_free_security; + struct list_head shm_associate; + struct list_head shm_shmctl; + struct list_head shm_shmat; + struct list_head sem_alloc_security; + struct list_head sem_free_security; + struct list_head sem_associate; + struct list_head sem_semctl; + struct list_head sem_semop; + struct list_head netlink_send; + struct list_head d_instantiate; + struct list_head getprocattr; + struct list_head setprocattr; + struct list_head ismaclabel; + struct list_head secid_to_secctx; + struct list_head secctx_to_secid; + struct list_head release_secctx; + struct list_head inode_notifysecctx; + struct list_head inode_setsecctx; + struct list_head inode_getsecctx; +#ifdef CONFIG_SECURITY_NETWORK + struct list_head unix_stream_connect; + struct list_head unix_may_send; + struct list_head socket_create; + struct list_head socket_post_create; + struct list_head socket_bind; + struct list_head socket_connect; + struct list_head socket_listen; + struct list_head socket_accept; + struct list_head socket_sendmsg; + struct list_head socket_recvmsg; + struct list_head socket_getsockname; + struct list_head socket_getpeername; + struct list_head socket_getsockopt; + struct list_head socket_setsockopt; + struct list_head socket_shutdown; + struct list_head socket_sock_rcv_skb; + struct list_head socket_getpeersec_stream; + struct list_head socket_getpeersec_dgram; + struct list_head sk_alloc_security; + struct list_head sk_free_security; + struct list_head sk_clone_security; + struct list_head sk_getsecid; + struct list_head sock_graft; + struct list_head inet_conn_request; + struct list_head inet_csk_clone; + struct list_head inet_conn_established; + struct list_head secmark_relabel_packet; + struct list_head secmark_refcount_inc; + struct list_head secmark_refcount_dec; + struct list_head req_classify_flow; + struct list_head tun_dev_alloc_security; + struct list_head tun_dev_free_security; + struct list_head tun_dev_create; + struct list_head tun_dev_attach_queue; + struct list_head tun_dev_attach; + struct list_head tun_dev_open; + struct list_head skb_owned_by; +#endif /* CONFIG_SECURITY_NETWORK */ +#ifdef CONFIG_SECURITY_NETWORK_XFRM + struct list_head xfrm_policy_alloc_security; + struct list_head xfrm_policy_clone_security; + struct list_head xfrm_policy_free_security; + struct list_head xfrm_policy_delete_security; + struct list_head xfrm_state_alloc; + struct list_head xfrm_state_alloc_acquire; + struct list_head xfrm_state_free_security; + struct list_head xfrm_state_delete_security; + struct list_head xfrm_policy_lookup; + struct list_head xfrm_state_pol_flow_match; + struct list_head xfrm_decode_session; +#endif /* CONFIG_SECURITY_NETWORK_XFRM */ +#ifdef CONFIG_KEYS + struct list_head key_alloc; + struct list_head key_free; + struct list_head key_permission; + struct list_head key_getsecurity; +#endif /* CONFIG_KEYS */ +#ifdef CONFIG_AUDIT + struct list_head audit_rule_init; + struct list_head audit_rule_known; + struct list_head audit_rule_match; + struct list_head audit_rule_free; +#endif /* CONFIG_AUDIT */ +}; + +/* + * Security module hook list structure. + * For use with generic list macros for common operations. + */ +struct security_hook_list { + struct list_head list; + struct list_head *head; + union security_list_options hook; +}; + +/* + * Initializing a security_hook_list structure takes + * up a lot of space in a source file. This macro takes + * care of the common case and reduces the amount of + * text involved. + */ +#define LSM_HOOK_INIT(HEAD, HOOK) \ + { .head = &security_hook_heads.HEAD, .hook = { .HEAD = HOOK } } + +extern struct security_hook_heads security_hook_heads; + +static inline void security_add_hooks(struct security_hook_list *hooks, + int count) +{ + int i; + + for (i = 0; i < count; i++) + list_add_tail_rcu(&hooks[i].list, hooks[i].head); +} + +#ifdef CONFIG_SECURITY_SELINUX_DISABLE +/* + * Assuring the safety of deleting a security module is up to + * the security module involved. This may entail ordering the + * module's hook list in a particular way, refusing to disable + * the module once a policy is loaded or any number of other + * actions better imagined than described. + * + * The name of the configuration option reflects the only module + * that currently uses the mechanism. Any developer who thinks + * disabling their module is a good idea needs to be at least as + * careful as the SELinux team. + */ +static inline void security_delete_hooks(struct security_hook_list *hooks, + int count) +{ + int i; + + for (i = 0; i < count; i++) + list_del_rcu(&hooks[i].list); +} +#endif /* CONFIG_SECURITY_SELINUX_DISABLE */ + +extern int __init security_module_enable(const char *module); +extern void __init capability_add_hooks(void); +#ifdef CONFIG_SECURITY_YAMA +extern void __init yama_add_hooks(void); +#else +static inline void __init yama_add_hooks(void) { } +#endif + +#endif /* ! __LINUX_LSM_HOOKS_H */ diff --git a/kernel/include/linux/mailbox_client.h b/kernel/include/linux/mailbox_client.h index 1726ccbd8..443487109 100644 --- a/kernel/include/linux/mailbox_client.h +++ b/kernel/include/linux/mailbox_client.h @@ -40,6 +40,8 @@ struct mbox_client { void (*tx_done)(struct mbox_client *cl, void *mssg, int r); }; +struct mbox_chan *mbox_request_channel_byname(struct mbox_client *cl, + const char *name); struct mbox_chan *mbox_request_channel(struct mbox_client *cl, int index); int mbox_send_message(struct mbox_chan *chan, void *mssg); void mbox_client_txdone(struct mbox_chan *chan, int r); /* atomic */ diff --git a/kernel/include/linux/mailbox_controller.h b/kernel/include/linux/mailbox_controller.h index d4cf96f07..74deadb42 100644 --- a/kernel/include/linux/mailbox_controller.h +++ b/kernel/include/linux/mailbox_controller.h @@ -9,7 +9,7 @@ #include <linux/of.h> #include <linux/types.h> -#include <linux/timer.h> +#include <linux/hrtimer.h> #include <linux/device.h> #include <linux/completion.h> @@ -67,12 +67,13 @@ struct mbox_chan_ops { * @txpoll_period: If 'txdone_poll' is in effect, the API polls for * last TX's status after these many millisecs * @of_xlate: Controller driver specific mapping of channel via DT - * @poll: API private. Used to poll for TXDONE on all channels. + * @poll_hrt: API private. hrtimer used to poll for TXDONE on all + * channels. * @node: API private. To hook into list of controllers. */ struct mbox_controller { struct device *dev; - struct mbox_chan_ops *ops; + const struct mbox_chan_ops *ops; struct mbox_chan *chans; int num_chans; bool txdone_irq; @@ -81,7 +82,7 @@ struct mbox_controller { struct mbox_chan *(*of_xlate)(struct mbox_controller *mbox, const struct of_phandle_args *sp); /* Internal to API */ - struct timer_list poll; + struct hrtimer poll_hrt; struct list_head node; }; diff --git a/kernel/include/linux/marvell_phy.h b/kernel/include/linux/marvell_phy.h index e6982ac32..a57f0dfb6 100644 --- a/kernel/include/linux/marvell_phy.h +++ b/kernel/include/linux/marvell_phy.h @@ -16,6 +16,7 @@ #define MARVELL_PHY_ID_88E1318S 0x01410e90 #define MARVELL_PHY_ID_88E1116R 0x01410e40 #define MARVELL_PHY_ID_88E1510 0x01410dd0 +#define MARVELL_PHY_ID_88E1540 0x01410eb0 #define MARVELL_PHY_ID_88E3016 0x01410e60 /* struct phy_device dev_flags definitions */ diff --git a/kernel/include/linux/math64.h b/kernel/include/linux/math64.h index c45c089bf..6e8b5b270 100644 --- a/kernel/include/linux/math64.h +++ b/kernel/include/linux/math64.h @@ -142,6 +142,13 @@ static inline u64 mul_u64_u32_shr(u64 a, u32 mul, unsigned int shift) } #endif /* mul_u64_u32_shr */ +#ifndef mul_u64_u64_shr +static inline u64 mul_u64_u64_shr(u64 a, u64 mul, unsigned int shift) +{ + return (u64)(((unsigned __int128)a * mul) >> shift); +} +#endif /* mul_u64_u64_shr */ + #else #ifndef mul_u64_u32_shr @@ -161,6 +168,79 @@ static inline u64 mul_u64_u32_shr(u64 a, u32 mul, unsigned int shift) } #endif /* mul_u64_u32_shr */ +#ifndef mul_u64_u64_shr +static inline u64 mul_u64_u64_shr(u64 a, u64 b, unsigned int shift) +{ + union { + u64 ll; + struct { +#ifdef __BIG_ENDIAN + u32 high, low; +#else + u32 low, high; +#endif + } l; + } rl, rm, rn, rh, a0, b0; + u64 c; + + a0.ll = a; + b0.ll = b; + + rl.ll = (u64)a0.l.low * b0.l.low; + rm.ll = (u64)a0.l.low * b0.l.high; + rn.ll = (u64)a0.l.high * b0.l.low; + rh.ll = (u64)a0.l.high * b0.l.high; + + /* + * Each of these lines computes a 64-bit intermediate result into "c", + * starting at bits 32-95. The low 32-bits go into the result of the + * multiplication, the high 32-bits are carried into the next step. + */ + rl.l.high = c = (u64)rl.l.high + rm.l.low + rn.l.low; + rh.l.low = c = (c >> 32) + rm.l.high + rn.l.high + rh.l.low; + rh.l.high = (c >> 32) + rh.l.high; + + /* + * The 128-bit result of the multiplication is in rl.ll and rh.ll, + * shift it right and throw away the high part of the result. + */ + if (shift == 0) + return rl.ll; + if (shift < 64) + return (rl.ll >> shift) | (rh.ll << (64 - shift)); + return rh.ll >> (shift & 63); +} +#endif /* mul_u64_u64_shr */ + #endif +#ifndef mul_u64_u32_div +static inline u64 mul_u64_u32_div(u64 a, u32 mul, u32 divisor) +{ + union { + u64 ll; + struct { +#ifdef __BIG_ENDIAN + u32 high, low; +#else + u32 low, high; +#endif + } l; + } u, rl, rh; + + u.ll = a; + rl.ll = (u64)u.l.low * mul; + rh.ll = (u64)u.l.high * mul + rl.l.high; + + /* Bits 32-63 of the result will be in rh.l.low. */ + rl.l.high = do_div(rh.ll, divisor); + + /* Bits 0-31 of the result will be in rl.l.low. */ + do_div(rl.ll, divisor); + + rl.l.high = rh.l.low; + return rl.ll; +} +#endif /* mul_u64_u32_div */ + #endif /* _LINUX_MATH64_H */ diff --git a/kernel/include/linux/mbus.h b/kernel/include/linux/mbus.h index 611b69fa8..1f7bc630d 100644 --- a/kernel/include/linux/mbus.h +++ b/kernel/include/linux/mbus.h @@ -54,11 +54,16 @@ struct mbus_dram_target_info */ #ifdef CONFIG_PLAT_ORION extern const struct mbus_dram_target_info *mv_mbus_dram_info(void); +extern const struct mbus_dram_target_info *mv_mbus_dram_info_nooverlap(void); #else static inline const struct mbus_dram_target_info *mv_mbus_dram_info(void) { return NULL; } +static inline const struct mbus_dram_target_info *mv_mbus_dram_info_nooverlap(void) +{ + return NULL; +} #endif int mvebu_mbus_save_cpu_target(u32 *store_addr); diff --git a/kernel/include/linux/mei_cl_bus.h b/kernel/include/linux/mei_cl_bus.h index 0819d36a3..e74691953 100644 --- a/kernel/include/linux/mei_cl_bus.h +++ b/kernel/include/linux/mei_cl_bus.h @@ -6,6 +6,55 @@ #include <linux/mod_devicetable.h> struct mei_cl_device; +struct mei_device; + +typedef void (*mei_cldev_event_cb_t)(struct mei_cl_device *cldev, + u32 events, void *context); + +/** + * struct mei_cl_device - MEI device handle + * An mei_cl_device pointer is returned from mei_add_device() + * and links MEI bus clients to their actual ME host client pointer. + * Drivers for MEI devices will get an mei_cl_device pointer + * when being probed and shall use it for doing ME bus I/O. + * + * @bus_list: device on the bus list + * @bus: parent mei device + * @dev: linux driver model device pointer + * @me_cl: me client + * @cl: mei client + * @name: device name + * @event_work: async work to execute event callback + * @event_cb: Drivers register this callback to get asynchronous ME + * events (e.g. Rx buffer pending) notifications. + * @event_context: event callback run context + * @events_mask: Events bit mask requested by driver. + * @events: Events bitmask sent to the driver. + * + * @do_match: wheather device can be matched with a driver + * @is_added: device is already scanned + * @priv_data: client private data + */ +struct mei_cl_device { + struct list_head bus_list; + struct mei_device *bus; + struct device dev; + + struct mei_me_client *me_cl; + struct mei_cl *cl; + char name[MEI_CL_NAME_SIZE]; + + struct work_struct event_work; + mei_cldev_event_cb_t event_cb; + void *event_context; + unsigned long events_mask; + unsigned long events; + + unsigned int do_match:1; + unsigned int is_added:1; + + void *priv_data; +}; struct mei_cl_driver { struct device_driver driver; @@ -13,33 +62,37 @@ struct mei_cl_driver { const struct mei_cl_device_id *id_table; - int (*probe)(struct mei_cl_device *dev, + int (*probe)(struct mei_cl_device *cldev, const struct mei_cl_device_id *id); - int (*remove)(struct mei_cl_device *dev); + int (*remove)(struct mei_cl_device *cldev); }; -int __mei_cl_driver_register(struct mei_cl_driver *driver, +int __mei_cldev_driver_register(struct mei_cl_driver *cldrv, struct module *owner); -#define mei_cl_driver_register(driver) \ - __mei_cl_driver_register(driver, THIS_MODULE) +#define mei_cldev_driver_register(cldrv) \ + __mei_cldev_driver_register(cldrv, THIS_MODULE) -void mei_cl_driver_unregister(struct mei_cl_driver *driver); +void mei_cldev_driver_unregister(struct mei_cl_driver *cldrv); -ssize_t mei_cl_send(struct mei_cl_device *device, u8 *buf, size_t length); -ssize_t mei_cl_recv(struct mei_cl_device *device, u8 *buf, size_t length); +ssize_t mei_cldev_send(struct mei_cl_device *cldev, u8 *buf, size_t length); +ssize_t mei_cldev_recv(struct mei_cl_device *cldev, u8 *buf, size_t length); -typedef void (*mei_cl_event_cb_t)(struct mei_cl_device *device, - u32 events, void *context); -int mei_cl_register_event_cb(struct mei_cl_device *device, - mei_cl_event_cb_t read_cb, void *context); +int mei_cldev_register_event_cb(struct mei_cl_device *cldev, + unsigned long event_mask, + mei_cldev_event_cb_t read_cb, void *context); #define MEI_CL_EVENT_RX 0 #define MEI_CL_EVENT_TX 1 +#define MEI_CL_EVENT_NOTIF 2 + +const uuid_le *mei_cldev_uuid(const struct mei_cl_device *cldev); +u8 mei_cldev_ver(const struct mei_cl_device *cldev); -void *mei_cl_get_drvdata(const struct mei_cl_device *device); -void mei_cl_set_drvdata(struct mei_cl_device *device, void *data); +void *mei_cldev_get_drvdata(const struct mei_cl_device *cldev); +void mei_cldev_set_drvdata(struct mei_cl_device *cldev, void *data); -int mei_cl_enable_device(struct mei_cl_device *device); -int mei_cl_disable_device(struct mei_cl_device *device); +int mei_cldev_enable(struct mei_cl_device *cldev); +int mei_cldev_disable(struct mei_cl_device *cldev); +bool mei_cldev_enabled(struct mei_cl_device *cldev); #endif /* _LINUX_MEI_CL_BUS_H */ diff --git a/kernel/include/linux/memblock.h b/kernel/include/linux/memblock.h index 9497ec7c7..24daf8fc4 100644 --- a/kernel/include/linux/memblock.h +++ b/kernel/include/linux/memblock.h @@ -21,7 +21,11 @@ #define INIT_PHYSMEM_REGIONS 4 /* Definition of memblock flags. */ -#define MEMBLOCK_HOTPLUG 0x1 /* hotpluggable region */ +enum { + MEMBLOCK_NONE = 0x0, /* No special request */ + MEMBLOCK_HOTPLUG = 0x1, /* hotpluggable region */ + MEMBLOCK_MIRROR = 0x2, /* mirrored region */ +}; struct memblock_region { phys_addr_t base; @@ -61,7 +65,7 @@ extern bool movable_node_enabled; phys_addr_t memblock_find_in_range_node(phys_addr_t size, phys_addr_t align, phys_addr_t start, phys_addr_t end, - int nid); + int nid, ulong flags); phys_addr_t memblock_find_in_range(phys_addr_t start, phys_addr_t end, phys_addr_t size, phys_addr_t align); phys_addr_t get_allocated_memblock_reserved_regions_info(phys_addr_t *addr); @@ -73,26 +77,31 @@ int memblock_remove(phys_addr_t base, phys_addr_t size); int memblock_free(phys_addr_t base, phys_addr_t size); int memblock_reserve(phys_addr_t base, phys_addr_t size); void memblock_trim_memory(phys_addr_t align); +bool memblock_overlaps_region(struct memblock_type *type, + phys_addr_t base, phys_addr_t size); int memblock_mark_hotplug(phys_addr_t base, phys_addr_t size); int memblock_clear_hotplug(phys_addr_t base, phys_addr_t size); +int memblock_mark_mirror(phys_addr_t base, phys_addr_t size); +ulong choose_memblock_flags(void); /* Low level functions */ int memblock_add_range(struct memblock_type *type, phys_addr_t base, phys_addr_t size, int nid, unsigned long flags); -int memblock_remove_range(struct memblock_type *type, - phys_addr_t base, - phys_addr_t size); - -void __next_mem_range(u64 *idx, int nid, struct memblock_type *type_a, +void __next_mem_range(u64 *idx, int nid, ulong flags, + struct memblock_type *type_a, struct memblock_type *type_b, phys_addr_t *out_start, phys_addr_t *out_end, int *out_nid); -void __next_mem_range_rev(u64 *idx, int nid, struct memblock_type *type_a, +void __next_mem_range_rev(u64 *idx, int nid, ulong flags, + struct memblock_type *type_a, struct memblock_type *type_b, phys_addr_t *out_start, phys_addr_t *out_end, int *out_nid); +void __next_reserved_mem_region(u64 *idx, phys_addr_t *out_start, + phys_addr_t *out_end); + /** * for_each_mem_range - iterate through memblock areas from type_a and not * included in type_b. Or just type_a if type_b is NULL. @@ -100,16 +109,17 @@ void __next_mem_range_rev(u64 *idx, int nid, struct memblock_type *type_a, * @type_a: ptr to memblock_type to iterate * @type_b: ptr to memblock_type which excludes from the iteration * @nid: node selector, %NUMA_NO_NODE for all nodes + * @flags: pick from blocks based on memory attributes * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL * @p_nid: ptr to int for nid of the range, can be %NULL */ -#define for_each_mem_range(i, type_a, type_b, nid, \ +#define for_each_mem_range(i, type_a, type_b, nid, flags, \ p_start, p_end, p_nid) \ - for (i = 0, __next_mem_range(&i, nid, type_a, type_b, \ + for (i = 0, __next_mem_range(&i, nid, flags, type_a, type_b, \ p_start, p_end, p_nid); \ i != (u64)ULLONG_MAX; \ - __next_mem_range(&i, nid, type_a, type_b, \ + __next_mem_range(&i, nid, flags, type_a, type_b, \ p_start, p_end, p_nid)) /** @@ -119,19 +129,35 @@ void __next_mem_range_rev(u64 *idx, int nid, struct memblock_type *type_a, * @type_a: ptr to memblock_type to iterate * @type_b: ptr to memblock_type which excludes from the iteration * @nid: node selector, %NUMA_NO_NODE for all nodes + * @flags: pick from blocks based on memory attributes * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL * @p_nid: ptr to int for nid of the range, can be %NULL */ -#define for_each_mem_range_rev(i, type_a, type_b, nid, \ +#define for_each_mem_range_rev(i, type_a, type_b, nid, flags, \ p_start, p_end, p_nid) \ for (i = (u64)ULLONG_MAX, \ - __next_mem_range_rev(&i, nid, type_a, type_b, \ + __next_mem_range_rev(&i, nid, flags, type_a, type_b,\ p_start, p_end, p_nid); \ i != (u64)ULLONG_MAX; \ - __next_mem_range_rev(&i, nid, type_a, type_b, \ + __next_mem_range_rev(&i, nid, flags, type_a, type_b, \ p_start, p_end, p_nid)) +/** + * for_each_reserved_mem_region - iterate over all reserved memblock areas + * @i: u64 used as loop variable + * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL + * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL + * + * Walks over reserved areas of memblock. Available as soon as memblock + * is initialized. + */ +#define for_each_reserved_mem_region(i, p_start, p_end) \ + for (i = 0UL, \ + __next_reserved_mem_region(&i, p_start, p_end); \ + i != (u64)ULLONG_MAX; \ + __next_reserved_mem_region(&i, p_start, p_end)) + #ifdef CONFIG_MOVABLE_NODE static inline bool memblock_is_hotpluggable(struct memblock_region *m) { @@ -153,6 +179,11 @@ static inline bool movable_node_is_enabled(void) } #endif +static inline bool memblock_is_mirror(struct memblock_region *m) +{ + return m->flags & MEMBLOCK_MIRROR; +} + #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP int memblock_search_pfn_nid(unsigned long pfn, unsigned long *start_pfn, unsigned long *end_pfn); @@ -181,13 +212,14 @@ void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn, * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL * @p_nid: ptr to int for nid of the range, can be %NULL + * @flags: pick from blocks based on memory attributes * * Walks over free (memory && !reserved) areas of memblock. Available as * soon as memblock is initialized. */ -#define for_each_free_mem_range(i, nid, p_start, p_end, p_nid) \ +#define for_each_free_mem_range(i, nid, flags, p_start, p_end, p_nid) \ for_each_mem_range(i, &memblock.memory, &memblock.reserved, \ - nid, p_start, p_end, p_nid) + nid, flags, p_start, p_end, p_nid) /** * for_each_free_mem_range_reverse - rev-iterate through free memblock areas @@ -196,13 +228,15 @@ void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn, * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL * @p_nid: ptr to int for nid of the range, can be %NULL + * @flags: pick from blocks based on memory attributes * * Walks over free (memory && !reserved) areas of memblock in reverse * order. Available as soon as memblock is initialized. */ -#define for_each_free_mem_range_reverse(i, nid, p_start, p_end, p_nid) \ +#define for_each_free_mem_range_reverse(i, nid, flags, p_start, p_end, \ + p_nid) \ for_each_mem_range_rev(i, &memblock.memory, &memblock.reserved, \ - nid, p_start, p_end, p_nid) + nid, flags, p_start, p_end, p_nid) static inline void memblock_set_region_flags(struct memblock_region *r, unsigned long flags) @@ -273,7 +307,8 @@ static inline bool memblock_bottom_up(void) { return false; } #define MEMBLOCK_ALLOC_ACCESSIBLE 0 phys_addr_t __init memblock_alloc_range(phys_addr_t size, phys_addr_t align, - phys_addr_t start, phys_addr_t end); + phys_addr_t start, phys_addr_t end, + ulong flags); phys_addr_t memblock_alloc_base(phys_addr_t size, phys_addr_t align, phys_addr_t max_addr); phys_addr_t __memblock_alloc_base(phys_addr_t size, phys_addr_t align, @@ -286,7 +321,7 @@ void memblock_enforce_memory_limit(phys_addr_t memory_limit); int memblock_is_memory(phys_addr_t addr); int memblock_is_region_memory(phys_addr_t base, phys_addr_t size); int memblock_is_reserved(phys_addr_t addr); -int memblock_is_region_reserved(phys_addr_t base, phys_addr_t size); +bool memblock_is_region_reserved(phys_addr_t base, phys_addr_t size); extern void __memblock_dump_all(void); diff --git a/kernel/include/linux/memcontrol.h b/kernel/include/linux/memcontrol.h index 6c8918114..cd0e2413c 100644 --- a/kernel/include/linux/memcontrol.h +++ b/kernel/include/linux/memcontrol.h @@ -23,6 +23,11 @@ #include <linux/vm_event_item.h> #include <linux/hardirq.h> #include <linux/jump_label.h> +#include <linux/page_counter.h> +#include <linux/vmpressure.h> +#include <linux/eventfd.h> +#include <linux/mmzone.h> +#include <linux/writeback.h> struct mem_cgroup; struct page; @@ -41,6 +46,7 @@ enum mem_cgroup_stat_index { MEM_CGROUP_STAT_RSS, /* # of pages charged as anon rss */ MEM_CGROUP_STAT_RSS_HUGE, /* # of pages charged as anon huge */ MEM_CGROUP_STAT_FILE_MAPPED, /* # of pages charged as file rss */ + MEM_CGROUP_STAT_DIRTY, /* # of dirty pages in page cache */ MEM_CGROUP_STAT_WRITEBACK, /* # of pages under writeback */ MEM_CGROUP_STAT_SWAP, /* # of pages, swapped out */ MEM_CGROUP_STAT_NSTATS, @@ -66,10 +72,224 @@ enum mem_cgroup_events_index { MEMCG_NR_EVENTS, }; +/* + * Per memcg event counter is incremented at every pagein/pageout. With THP, + * it will be incremated by the number of pages. This counter is used for + * for trigger some periodic events. This is straightforward and better + * than using jiffies etc. to handle periodic memcg event. + */ +enum mem_cgroup_events_target { + MEM_CGROUP_TARGET_THRESH, + MEM_CGROUP_TARGET_SOFTLIMIT, + MEM_CGROUP_TARGET_NUMAINFO, + MEM_CGROUP_NTARGETS, +}; + +/* + * Bits in struct cg_proto.flags + */ +enum cg_proto_flags { + /* Currently active and new sockets should be assigned to cgroups */ + MEMCG_SOCK_ACTIVE, + /* It was ever activated; we must disarm static keys on destruction */ + MEMCG_SOCK_ACTIVATED, +}; + +struct cg_proto { + struct page_counter memory_allocated; /* Current allocated memory. */ + struct percpu_counter sockets_allocated; /* Current number of sockets. */ + int memory_pressure; + long sysctl_mem[3]; + unsigned long flags; + /* + * memcg field is used to find which memcg we belong directly + * Each memcg struct can hold more than one cg_proto, so container_of + * won't really cut. + * + * The elegant solution would be having an inverse function to + * proto_cgroup in struct proto, but that means polluting the structure + * for everybody, instead of just for memcg users. + */ + struct mem_cgroup *memcg; +}; + #ifdef CONFIG_MEMCG -void mem_cgroup_events(struct mem_cgroup *memcg, +struct mem_cgroup_stat_cpu { + long count[MEM_CGROUP_STAT_NSTATS]; + unsigned long events[MEMCG_NR_EVENTS]; + unsigned long nr_page_events; + unsigned long targets[MEM_CGROUP_NTARGETS]; +}; + +struct mem_cgroup_reclaim_iter { + struct mem_cgroup *position; + /* scan generation, increased every round-trip */ + unsigned int generation; +}; + +/* + * per-zone information in memory controller. + */ +struct mem_cgroup_per_zone { + struct lruvec lruvec; + unsigned long lru_size[NR_LRU_LISTS]; + + struct mem_cgroup_reclaim_iter iter[DEF_PRIORITY + 1]; + + struct rb_node tree_node; /* RB tree node */ + unsigned long usage_in_excess;/* Set to the value by which */ + /* the soft limit is exceeded*/ + bool on_tree; + struct mem_cgroup *memcg; /* Back pointer, we cannot */ + /* use container_of */ +}; + +struct mem_cgroup_per_node { + struct mem_cgroup_per_zone zoneinfo[MAX_NR_ZONES]; +}; + +struct mem_cgroup_threshold { + struct eventfd_ctx *eventfd; + unsigned long threshold; +}; + +/* For threshold */ +struct mem_cgroup_threshold_ary { + /* An array index points to threshold just below or equal to usage. */ + int current_threshold; + /* Size of entries[] */ + unsigned int size; + /* Array of thresholds */ + struct mem_cgroup_threshold entries[0]; +}; + +struct mem_cgroup_thresholds { + /* Primary thresholds array */ + struct mem_cgroup_threshold_ary *primary; + /* + * Spare threshold array. + * This is needed to make mem_cgroup_unregister_event() "never fail". + * It must be able to store at least primary->size - 1 entries. + */ + struct mem_cgroup_threshold_ary *spare; +}; + +/* + * The memory controller data structure. The memory controller controls both + * page cache and RSS per cgroup. We would eventually like to provide + * statistics based on the statistics developed by Rik Van Riel for clock-pro, + * to help the administrator determine what knobs to tune. + */ +struct mem_cgroup { + struct cgroup_subsys_state css; + + /* Accounted resources */ + struct page_counter memory; + struct page_counter memsw; + struct page_counter kmem; + + /* Normal memory consumption range */ + unsigned long low; + unsigned long high; + + unsigned long soft_limit; + + /* vmpressure notifications */ + struct vmpressure vmpressure; + + /* css_online() has been completed */ + int initialized; + + /* + * Should the accounting and control be hierarchical, per subtree? + */ + bool use_hierarchy; + + /* protected by memcg_oom_lock */ + bool oom_lock; + int under_oom; + + int swappiness; + /* OOM-Killer disable */ + int oom_kill_disable; + + /* handle for "memory.events" */ + struct cgroup_file events_file; + + /* protect arrays of thresholds */ + struct mutex thresholds_lock; + + /* thresholds for memory usage. RCU-protected */ + struct mem_cgroup_thresholds thresholds; + + /* thresholds for mem+swap usage. RCU-protected */ + struct mem_cgroup_thresholds memsw_thresholds; + + /* For oom notifier event fd */ + struct list_head oom_notify; + + /* + * Should we move charges of a task when a task is moved into this + * mem_cgroup ? And what type of charges should we move ? + */ + unsigned long move_charge_at_immigrate; + /* + * set > 0 if pages under this cgroup are moving to other cgroup. + */ + atomic_t moving_account; + /* taken only while moving_account > 0 */ + spinlock_t move_lock; + struct task_struct *move_lock_task; + unsigned long move_lock_flags; + /* + * percpu counter. + */ + struct mem_cgroup_stat_cpu __percpu *stat; + +#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_INET) + struct cg_proto tcp_mem; +#endif +#if defined(CONFIG_MEMCG_KMEM) + /* Index in the kmem_cache->memcg_params.memcg_caches array */ + int kmemcg_id; + bool kmem_acct_activated; + bool kmem_acct_active; +#endif + + int last_scanned_node; +#if MAX_NUMNODES > 1 + nodemask_t scan_nodes; + atomic_t numainfo_events; + atomic_t numainfo_updating; +#endif + +#ifdef CONFIG_CGROUP_WRITEBACK + struct list_head cgwb_list; + struct wb_domain cgwb_domain; +#endif + + /* List of events which userspace want to receive */ + struct list_head event_list; + spinlock_t event_list_lock; + + struct mem_cgroup_per_node *nodeinfo[0]; + /* WARNING: nodeinfo must be the last member here */ +}; +extern struct cgroup_subsys_state *mem_cgroup_root_css; + +/** + * mem_cgroup_events - count memory events against a cgroup + * @memcg: the memory cgroup + * @idx: the event index + * @nr: the number of events to account for + */ +static inline void mem_cgroup_events(struct mem_cgroup *memcg, enum mem_cgroup_events_index idx, - unsigned int nr); + unsigned int nr) +{ + this_cpu_add(memcg->stat->events[idx], nr); + cgroup_file_notify(&memcg->events_file); +} bool mem_cgroup_low(struct mem_cgroup *root, struct mem_cgroup *memcg); @@ -81,21 +301,34 @@ void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg); void mem_cgroup_uncharge(struct page *page); void mem_cgroup_uncharge_list(struct list_head *page_list); -void mem_cgroup_migrate(struct page *oldpage, struct page *newpage, - bool lrucare); +void mem_cgroup_replace_page(struct page *oldpage, struct page *newpage); struct lruvec *mem_cgroup_zone_lruvec(struct zone *, struct mem_cgroup *); struct lruvec *mem_cgroup_page_lruvec(struct page *, struct zone *); -bool mem_cgroup_is_descendant(struct mem_cgroup *memcg, - struct mem_cgroup *root); bool task_in_mem_cgroup(struct task_struct *task, struct mem_cgroup *memcg); +struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p); +struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg); -extern struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page); -extern struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p); +static inline +struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css){ + return css ? container_of(css, struct mem_cgroup, css) : NULL; +} -extern struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg); -extern struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css); +struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *, + struct mem_cgroup *, + struct mem_cgroup_reclaim_cookie *); +void mem_cgroup_iter_break(struct mem_cgroup *, struct mem_cgroup *); + +static inline bool mem_cgroup_is_descendant(struct mem_cgroup *memcg, + struct mem_cgroup *root) +{ + if (root == memcg) + return true; + if (!root->use_hierarchy) + return false; + return cgroup_is_descendant(memcg->css.cgroup, root->css.cgroup); +} static inline bool mm_match_cgroup(struct mm_struct *mm, struct mem_cgroup *memcg) @@ -111,39 +344,84 @@ static inline bool mm_match_cgroup(struct mm_struct *mm, return match; } -extern struct cgroup_subsys_state *mem_cgroup_css(struct mem_cgroup *memcg); +struct cgroup_subsys_state *mem_cgroup_css_from_page(struct page *page); +ino_t page_cgroup_ino(struct page *page); -struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *, - struct mem_cgroup *, - struct mem_cgroup_reclaim_cookie *); -void mem_cgroup_iter_break(struct mem_cgroup *, struct mem_cgroup *); +static inline bool mem_cgroup_disabled(void) +{ + return !cgroup_subsys_enabled(memory_cgrp_subsys); +} /* * For memory reclaim. */ -int mem_cgroup_inactive_anon_is_low(struct lruvec *lruvec); -bool mem_cgroup_lruvec_online(struct lruvec *lruvec); int mem_cgroup_select_victim_node(struct mem_cgroup *memcg); -unsigned long mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list); -void mem_cgroup_update_lru_size(struct lruvec *, enum lru_list, int); -extern void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, - struct task_struct *p); + +void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru, + int nr_pages); + +static inline bool mem_cgroup_lruvec_online(struct lruvec *lruvec) +{ + struct mem_cgroup_per_zone *mz; + struct mem_cgroup *memcg; + + if (mem_cgroup_disabled()) + return true; + + mz = container_of(lruvec, struct mem_cgroup_per_zone, lruvec); + memcg = mz->memcg; + + return !!(memcg->css.flags & CSS_ONLINE); +} + +static inline +unsigned long mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list lru) +{ + struct mem_cgroup_per_zone *mz; + + mz = container_of(lruvec, struct mem_cgroup_per_zone, lruvec); + return mz->lru_size[lru]; +} + +static inline bool mem_cgroup_inactive_anon_is_low(struct lruvec *lruvec) +{ + unsigned long inactive_ratio; + unsigned long inactive; + unsigned long active; + unsigned long gb; + + inactive = mem_cgroup_get_lru_size(lruvec, LRU_INACTIVE_ANON); + active = mem_cgroup_get_lru_size(lruvec, LRU_ACTIVE_ANON); + + gb = (inactive + active) >> (30 - PAGE_SHIFT); + if (gb) + inactive_ratio = int_sqrt(10 * gb); + else + inactive_ratio = 1; + + return inactive * inactive_ratio < active; +} + +void mem_cgroup_handle_over_high(void); + +void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, + struct task_struct *p); static inline void mem_cgroup_oom_enable(void) { - WARN_ON(current->memcg_oom.may_oom); - current->memcg_oom.may_oom = 1; + WARN_ON(current->memcg_may_oom); + current->memcg_may_oom = 1; } static inline void mem_cgroup_oom_disable(void) { - WARN_ON(!current->memcg_oom.may_oom); - current->memcg_oom.may_oom = 0; + WARN_ON(!current->memcg_may_oom); + current->memcg_may_oom = 0; } static inline bool task_in_memcg_oom(struct task_struct *p) { - return p->memcg_oom.memcg; + return p->memcg_in_oom; } bool mem_cgroup_oom_synchronize(bool wait); @@ -152,18 +430,26 @@ bool mem_cgroup_oom_synchronize(bool wait); extern int do_swap_account; #endif -static inline bool mem_cgroup_disabled(void) -{ - if (memory_cgrp_subsys.disabled) - return true; - return false; -} - struct mem_cgroup *mem_cgroup_begin_page_stat(struct page *page); -void mem_cgroup_update_page_stat(struct mem_cgroup *memcg, - enum mem_cgroup_stat_index idx, int val); void mem_cgroup_end_page_stat(struct mem_cgroup *memcg); +/** + * mem_cgroup_update_page_stat - update page state statistics + * @memcg: memcg to account against + * @idx: page state item to account + * @val: number of pages (positive or negative) + * + * See mem_cgroup_begin_page_stat() for locking requirements. + */ +static inline void mem_cgroup_update_page_stat(struct mem_cgroup *memcg, + enum mem_cgroup_stat_index idx, int val) +{ + VM_BUG_ON(!rcu_read_lock_held()); + + if (memcg) + this_cpu_add(memcg->stat->count[idx], val); +} + static inline void mem_cgroup_inc_page_stat(struct mem_cgroup *memcg, enum mem_cgroup_stat_index idx) { @@ -180,13 +466,31 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order, gfp_t gfp_mask, unsigned long *total_scanned); -void __mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx); static inline void mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx) { + struct mem_cgroup *memcg; + if (mem_cgroup_disabled()) return; - __mem_cgroup_count_vm_event(mm, idx); + + rcu_read_lock(); + memcg = mem_cgroup_from_task(rcu_dereference(mm->owner)); + if (unlikely(!memcg)) + goto out; + + switch (idx) { + case PGFAULT: + this_cpu_inc(memcg->stat->events[MEM_CGROUP_EVENTS_PGFAULT]); + break; + case PGMAJFAULT: + this_cpu_inc(memcg->stat->events[MEM_CGROUP_EVENTS_PGMAJFAULT]); + break; + default: + BUG(); + } +out: + rcu_read_unlock(); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE void mem_cgroup_split_huge_fixup(struct page *head); @@ -234,9 +538,7 @@ static inline void mem_cgroup_uncharge_list(struct list_head *page_list) { } -static inline void mem_cgroup_migrate(struct page *oldpage, - struct page *newpage, - bool lrucare) +static inline void mem_cgroup_replace_page(struct page *old, struct page *new) { } @@ -252,11 +554,6 @@ static inline struct lruvec *mem_cgroup_page_lruvec(struct page *page, return &zone->lruvec; } -static inline struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page) -{ - return NULL; -} - static inline bool mm_match_cgroup(struct mm_struct *mm, struct mem_cgroup *memcg) { @@ -269,12 +566,6 @@ static inline bool task_in_mem_cgroup(struct task_struct *task, return true; } -static inline struct cgroup_subsys_state - *mem_cgroup_css(struct mem_cgroup *memcg) -{ - return NULL; -} - static inline struct mem_cgroup * mem_cgroup_iter(struct mem_cgroup *root, struct mem_cgroup *prev, @@ -293,10 +584,10 @@ static inline bool mem_cgroup_disabled(void) return true; } -static inline int +static inline bool mem_cgroup_inactive_anon_is_low(struct lruvec *lruvec) { - return 1; + return true; } static inline bool mem_cgroup_lruvec_online(struct lruvec *lruvec) @@ -330,6 +621,10 @@ static inline void mem_cgroup_end_page_stat(struct mem_cgroup *memcg) { } +static inline void mem_cgroup_handle_over_high(void) +{ +} + static inline void mem_cgroup_oom_enable(void) { } @@ -382,6 +677,31 @@ enum { OVER_LIMIT, }; +#ifdef CONFIG_CGROUP_WRITEBACK + +struct list_head *mem_cgroup_cgwb_list(struct mem_cgroup *memcg); +struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb); +void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages, + unsigned long *pheadroom, unsigned long *pdirty, + unsigned long *pwriteback); + +#else /* CONFIG_CGROUP_WRITEBACK */ + +static inline struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb) +{ + return NULL; +} + +static inline void mem_cgroup_wb_stats(struct bdi_writeback *wb, + unsigned long *pfilepages, + unsigned long *pheadroom, + unsigned long *pdirty, + unsigned long *pwriteback) +{ +} + +#endif /* CONFIG_CGROUP_WRITEBACK */ + struct sock; #if defined(CONFIG_INET) && defined(CONFIG_MEMCG_KMEM) void sock_update_memcg(struct sock *sk); @@ -399,8 +719,8 @@ static inline void sock_release_memcg(struct sock *sk) extern struct static_key memcg_kmem_enabled_key; extern int memcg_nr_cache_ids; -extern void memcg_get_cache_ids(void); -extern void memcg_put_cache_ids(void); +void memcg_get_cache_ids(void); +void memcg_put_cache_ids(void); /* * Helper macro to loop through all memcg-specific caches. Callers must still @@ -415,7 +735,10 @@ static inline bool memcg_kmem_enabled(void) return static_key_false(&memcg_kmem_enabled_key); } -bool memcg_kmem_is_active(struct mem_cgroup *memcg); +static inline bool memcg_kmem_is_active(struct mem_cgroup *memcg) +{ + return memcg->kmem_acct_active; +} /* * In general, we'll do everything in our power to not incur in any overhead @@ -428,88 +751,60 @@ bool memcg_kmem_is_active(struct mem_cgroup *memcg); * conditions, but because they are pretty simple, they are expected to be * fast. */ -bool __memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **memcg, - int order); -void __memcg_kmem_commit_charge(struct page *page, - struct mem_cgroup *memcg, int order); -void __memcg_kmem_uncharge_pages(struct page *page, int order); +int __memcg_kmem_charge_memcg(struct page *page, gfp_t gfp, int order, + struct mem_cgroup *memcg); +int __memcg_kmem_charge(struct page *page, gfp_t gfp, int order); +void __memcg_kmem_uncharge(struct page *page, int order); -int memcg_cache_id(struct mem_cgroup *memcg); +/* + * helper for acessing a memcg's index. It will be used as an index in the + * child cache array in kmem_cache, and also to derive its name. This function + * will return -1 when this is not a kmem-limited memcg. + */ +static inline int memcg_cache_id(struct mem_cgroup *memcg) +{ + return memcg ? memcg->kmemcg_id : -1; +} struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep); void __memcg_kmem_put_cache(struct kmem_cache *cachep); -struct mem_cgroup *__mem_cgroup_from_kmem(void *ptr); - -int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp, - unsigned long nr_pages); -void memcg_uncharge_kmem(struct mem_cgroup *memcg, unsigned long nr_pages); - -/** - * memcg_kmem_newpage_charge: verify if a new kmem allocation is allowed. - * @gfp: the gfp allocation flags. - * @memcg: a pointer to the memcg this was charged against. - * @order: allocation order. - * - * returns true if the memcg where the current task belongs can hold this - * allocation. - * - * We return true automatically if this allocation is not to be accounted to - * any memcg. - */ -static inline bool -memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **memcg, int order) +static inline bool __memcg_kmem_bypass(gfp_t gfp) { if (!memcg_kmem_enabled()) return true; - if (gfp & __GFP_NOACCOUNT) return true; - /* - * __GFP_NOFAIL allocations will move on even if charging is not - * possible. Therefore we don't even try, and have this allocation - * unaccounted. We could in theory charge it forcibly, but we hope - * those allocations are rare, and won't be worth the trouble. - */ - if (gfp & __GFP_NOFAIL) - return true; if (in_interrupt() || (!current->mm) || (current->flags & PF_KTHREAD)) return true; - - /* If the test is dying, just let it go. */ - if (unlikely(fatal_signal_pending(current))) - return true; - - return __memcg_kmem_newpage_charge(gfp, memcg, order); + return false; } /** - * memcg_kmem_uncharge_pages: uncharge pages from memcg - * @page: pointer to struct page being freed - * @order: allocation order. + * memcg_kmem_charge: charge a kmem page + * @page: page to charge + * @gfp: reclaim mode + * @order: allocation order + * + * Returns 0 on success, an error code on failure. */ -static inline void -memcg_kmem_uncharge_pages(struct page *page, int order) +static __always_inline int memcg_kmem_charge(struct page *page, + gfp_t gfp, int order) { - if (memcg_kmem_enabled()) - __memcg_kmem_uncharge_pages(page, order); + if (__memcg_kmem_bypass(gfp)) + return 0; + return __memcg_kmem_charge(page, gfp, order); } /** - * memcg_kmem_commit_charge: embeds correct memcg in a page - * @page: pointer to struct page recently allocated - * @memcg: the memcg structure we charged against - * @order: allocation order. - * - * Needs to be called after memcg_kmem_newpage_charge, regardless of success or - * failure of the allocation. if @page is NULL, this function will revert the - * charges. Otherwise, it will commit @page to @memcg. + * memcg_kmem_uncharge: uncharge a kmem page + * @page: page to uncharge + * @order: allocation order */ -static inline void -memcg_kmem_commit_charge(struct page *page, struct mem_cgroup *memcg, int order) +static __always_inline void memcg_kmem_uncharge(struct page *page, int order) { - if (memcg_kmem_enabled() && memcg) - __memcg_kmem_commit_charge(page, memcg, order); + if (memcg_kmem_enabled()) + __memcg_kmem_uncharge(page, order); } /** @@ -522,17 +817,8 @@ memcg_kmem_commit_charge(struct page *page, struct mem_cgroup *memcg, int order) static __always_inline struct kmem_cache * memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp) { - if (!memcg_kmem_enabled()) - return cachep; - if (gfp & __GFP_NOACCOUNT) - return cachep; - if (gfp & __GFP_NOFAIL) - return cachep; - if (in_interrupt() || (!current->mm) || (current->flags & PF_KTHREAD)) + if (__memcg_kmem_bypass(gfp)) return cachep; - if (unlikely(fatal_signal_pending(current))) - return cachep; - return __memcg_kmem_get_cache(cachep); } @@ -541,13 +827,6 @@ static __always_inline void memcg_kmem_put_cache(struct kmem_cache *cachep) if (memcg_kmem_enabled()) __memcg_kmem_put_cache(cachep); } - -static __always_inline struct mem_cgroup *mem_cgroup_from_kmem(void *ptr) -{ - if (!memcg_kmem_enabled()) - return NULL; - return __mem_cgroup_from_kmem(ptr); -} #else #define for_each_memcg_cache_index(_idx) \ for (; NULL; ) @@ -562,18 +841,12 @@ static inline bool memcg_kmem_is_active(struct mem_cgroup *memcg) return false; } -static inline bool -memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **memcg, int order) -{ - return true; -} - -static inline void memcg_kmem_uncharge_pages(struct page *page, int order) +static inline int memcg_kmem_charge(struct page *page, gfp_t gfp, int order) { + return 0; } -static inline void -memcg_kmem_commit_charge(struct page *page, struct mem_cgroup *memcg, int order) +static inline void memcg_kmem_uncharge(struct page *page, int order) { } @@ -599,11 +872,5 @@ memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp) static inline void memcg_kmem_put_cache(struct kmem_cache *cachep) { } - -static inline struct mem_cgroup *mem_cgroup_from_kmem(void *ptr) -{ - return NULL; -} #endif /* CONFIG_MEMCG_KMEM */ #endif /* _LINUX_MEMCONTROL_H */ - diff --git a/kernel/include/linux/memory_hotplug.h b/kernel/include/linux/memory_hotplug.h index 6ffa0ac7f..2ea574ff9 100644 --- a/kernel/include/linux/memory_hotplug.h +++ b/kernel/include/linux/memory_hotplug.h @@ -11,6 +11,7 @@ struct zone; struct pglist_data; struct mem_section; struct memory_block; +struct resource; #ifdef CONFIG_MEMORY_HOTPLUG @@ -266,8 +267,10 @@ static inline void remove_memory(int nid, u64 start, u64 size) {} extern int walk_memory_range(unsigned long start_pfn, unsigned long end_pfn, void *arg, int (*func)(struct memory_block *, void *)); extern int add_memory(int nid, u64 start, u64 size); -extern int zone_for_memory(int nid, u64 start, u64 size, int zone_default); -extern int arch_add_memory(int nid, u64 start, u64 size); +extern int add_memory_resource(int nid, struct resource *resource); +extern int zone_for_memory(int nid, u64 start, u64 size, int zone_default, + bool for_device); +extern int arch_add_memory(int nid, u64 start, u64 size, bool for_device); extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages); extern bool is_memblock_offlined(struct memory_block *mem); extern void remove_memory(int nid, u64 start, u64 size); diff --git a/kernel/include/linux/mfd/88pm80x.h b/kernel/include/linux/mfd/88pm80x.h index 97cb283cc..d409ceb22 100644 --- a/kernel/include/linux/mfd/88pm80x.h +++ b/kernel/include/linux/mfd/88pm80x.h @@ -21,6 +21,7 @@ enum { CHIP_INVALID = 0, CHIP_PM800, CHIP_PM805, + CHIP_PM860, CHIP_MAX, }; @@ -60,60 +61,60 @@ enum { /* page 0 basic: slave adder 0x60 */ #define PM800_STATUS_1 (0x01) -#define PM800_ONKEY_STS1 (1 << 0) -#define PM800_EXTON_STS1 (1 << 1) -#define PM800_CHG_STS1 (1 << 2) -#define PM800_BAT_STS1 (1 << 3) -#define PM800_VBUS_STS1 (1 << 4) -#define PM800_LDO_PGOOD_STS1 (1 << 5) -#define PM800_BUCK_PGOOD_STS1 (1 << 6) +#define PM800_ONKEY_STS1 BIT(0) +#define PM800_EXTON_STS1 BIT(1) +#define PM800_CHG_STS1 BIT(2) +#define PM800_BAT_STS1 BIT(3) +#define PM800_VBUS_STS1 BIT(4) +#define PM800_LDO_PGOOD_STS1 BIT(5) +#define PM800_BUCK_PGOOD_STS1 BIT(6) #define PM800_STATUS_2 (0x02) -#define PM800_RTC_ALARM_STS2 (1 << 0) +#define PM800_RTC_ALARM_STS2 BIT(0) /* Wakeup Registers */ -#define PM800_WAKEUP1 (0x0D) +#define PM800_WAKEUP1 (0x0D) -#define PM800_WAKEUP2 (0x0E) -#define PM800_WAKEUP2_INV_INT (1 << 0) -#define PM800_WAKEUP2_INT_CLEAR (1 << 1) -#define PM800_WAKEUP2_INT_MASK (1 << 2) +#define PM800_WAKEUP2 (0x0E) +#define PM800_WAKEUP2_INV_INT BIT(0) +#define PM800_WAKEUP2_INT_CLEAR BIT(1) +#define PM800_WAKEUP2_INT_MASK BIT(2) -#define PM800_POWER_UP_LOG (0x10) +#define PM800_POWER_UP_LOG (0x10) /* Referance and low power registers */ #define PM800_LOW_POWER1 (0x20) #define PM800_LOW_POWER2 (0x21) -#define PM800_LOW_POWER_CONFIG3 (0x22) -#define PM800_LOW_POWER_CONFIG4 (0x23) +#define PM800_LOW_POWER_CONFIG3 (0x22) +#define PM800_LOW_POWER_CONFIG4 (0x23) /* GPIO register */ #define PM800_GPIO_0_1_CNTRL (0x30) -#define PM800_GPIO0_VAL (1 << 0) +#define PM800_GPIO0_VAL BIT(0) #define PM800_GPIO0_GPIO_MODE(x) (x << 1) -#define PM800_GPIO1_VAL (1 << 4) +#define PM800_GPIO1_VAL BIT(4) #define PM800_GPIO1_GPIO_MODE(x) (x << 5) #define PM800_GPIO_2_3_CNTRL (0x31) -#define PM800_GPIO2_VAL (1 << 0) +#define PM800_GPIO2_VAL BIT(0) #define PM800_GPIO2_GPIO_MODE(x) (x << 1) -#define PM800_GPIO3_VAL (1 << 4) +#define PM800_GPIO3_VAL BIT(4) #define PM800_GPIO3_GPIO_MODE(x) (x << 5) #define PM800_GPIO3_MODE_MASK 0x1F #define PM800_GPIO3_HEADSET_MODE PM800_GPIO3_GPIO_MODE(6) -#define PM800_GPIO_4_CNTRL (0x32) -#define PM800_GPIO4_VAL (1 << 0) +#define PM800_GPIO_4_CNTRL (0x32) +#define PM800_GPIO4_VAL BIT(0) #define PM800_GPIO4_GPIO_MODE(x) (x << 1) #define PM800_HEADSET_CNTRL (0x38) -#define PM800_HEADSET_DET_EN (1 << 7) -#define PM800_HSDET_SLP (1 << 1) +#define PM800_HEADSET_DET_EN BIT(7) +#define PM800_HSDET_SLP BIT(1) /* PWM register */ -#define PM800_PWM1 (0x40) -#define PM800_PWM2 (0x41) -#define PM800_PWM3 (0x42) -#define PM800_PWM4 (0x43) +#define PM800_PWM1 (0x40) +#define PM800_PWM2 (0x41) +#define PM800_PWM3 (0x42) +#define PM800_PWM4 (0x43) /* RTC Registers */ #define PM800_RTC_CONTROL (0xD0) @@ -123,55 +124,55 @@ enum { #define PM800_RTC_MISC4 (0xE4) #define PM800_RTC_MISC5 (0xE7) /* bit definitions of RTC Register 1 (0xD0) */ -#define PM800_ALARM1_EN (1 << 0) -#define PM800_ALARM_WAKEUP (1 << 4) -#define PM800_ALARM (1 << 5) -#define PM800_RTC1_USE_XO (1 << 7) +#define PM800_ALARM1_EN BIT(0) +#define PM800_ALARM_WAKEUP BIT(4) +#define PM800_ALARM BIT(5) +#define PM800_RTC1_USE_XO BIT(7) /* Regulator Control Registers: BUCK1,BUCK5,LDO1 have DVC */ /* buck registers */ -#define PM800_SLEEP_BUCK1 (0x30) +#define PM800_SLEEP_BUCK1 (0x30) /* BUCK Sleep Mode Register 1: BUCK[1..4] */ -#define PM800_BUCK_SLP1 (0x5A) -#define PM800_BUCK1_SLP1_SHIFT 0 -#define PM800_BUCK1_SLP1_MASK (0x3 << PM800_BUCK1_SLP1_SHIFT) +#define PM800_BUCK_SLP1 (0x5A) +#define PM800_BUCK1_SLP1_SHIFT 0 +#define PM800_BUCK1_SLP1_MASK (0x3 << PM800_BUCK1_SLP1_SHIFT) /* page 2 GPADC: slave adder 0x02 */ #define PM800_GPADC_MEAS_EN1 (0x01) -#define PM800_MEAS_EN1_VBAT (1 << 2) +#define PM800_MEAS_EN1_VBAT BIT(2) #define PM800_GPADC_MEAS_EN2 (0x02) -#define PM800_MEAS_EN2_RFTMP (1 << 0) -#define PM800_MEAS_GP0_EN (1 << 2) -#define PM800_MEAS_GP1_EN (1 << 3) -#define PM800_MEAS_GP2_EN (1 << 4) -#define PM800_MEAS_GP3_EN (1 << 5) -#define PM800_MEAS_GP4_EN (1 << 6) +#define PM800_MEAS_EN2_RFTMP BIT(0) +#define PM800_MEAS_GP0_EN BIT(2) +#define PM800_MEAS_GP1_EN BIT(3) +#define PM800_MEAS_GP2_EN BIT(4) +#define PM800_MEAS_GP3_EN BIT(5) +#define PM800_MEAS_GP4_EN BIT(6) #define PM800_GPADC_MISC_CONFIG1 (0x05) #define PM800_GPADC_MISC_CONFIG2 (0x06) -#define PM800_GPADC_MISC_GPFSM_EN (1 << 0) +#define PM800_GPADC_MISC_GPFSM_EN BIT(0) #define PM800_GPADC_SLOW_MODE(x) (x << 3) -#define PM800_GPADC_MISC_CONFIG3 (0x09) -#define PM800_GPADC_MISC_CONFIG4 (0x0A) +#define PM800_GPADC_MISC_CONFIG3 (0x09) +#define PM800_GPADC_MISC_CONFIG4 (0x0A) -#define PM800_GPADC_PREBIAS1 (0x0F) +#define PM800_GPADC_PREBIAS1 (0x0F) #define PM800_GPADC0_GP_PREBIAS_TIME(x) (x << 0) -#define PM800_GPADC_PREBIAS2 (0x10) +#define PM800_GPADC_PREBIAS2 (0x10) -#define PM800_GP_BIAS_ENA1 (0x14) -#define PM800_GPADC_GP_BIAS_EN0 (1 << 0) -#define PM800_GPADC_GP_BIAS_EN1 (1 << 1) -#define PM800_GPADC_GP_BIAS_EN2 (1 << 2) -#define PM800_GPADC_GP_BIAS_EN3 (1 << 3) +#define PM800_GP_BIAS_ENA1 (0x14) +#define PM800_GPADC_GP_BIAS_EN0 BIT(0) +#define PM800_GPADC_GP_BIAS_EN1 BIT(1) +#define PM800_GPADC_GP_BIAS_EN2 BIT(2) +#define PM800_GPADC_GP_BIAS_EN3 BIT(3) #define PM800_GP_BIAS_OUT1 (0x15) -#define PM800_BIAS_OUT_GP0 (1 << 0) -#define PM800_BIAS_OUT_GP1 (1 << 1) -#define PM800_BIAS_OUT_GP2 (1 << 2) -#define PM800_BIAS_OUT_GP3 (1 << 3) +#define PM800_BIAS_OUT_GP0 BIT(0) +#define PM800_BIAS_OUT_GP1 BIT(1) +#define PM800_BIAS_OUT_GP2 BIT(2) +#define PM800_BIAS_OUT_GP3 BIT(3) #define PM800_GPADC0_LOW_TH 0x20 #define PM800_GPADC1_LOW_TH 0x21 @@ -222,37 +223,37 @@ enum { #define PM805_INT_STATUS1 (0x03) -#define PM805_INT1_HP1_SHRT (1 << 0) -#define PM805_INT1_HP2_SHRT (1 << 1) -#define PM805_INT1_MIC_CONFLICT (1 << 2) -#define PM805_INT1_CLIP_FAULT (1 << 3) -#define PM805_INT1_LDO_OFF (1 << 4) -#define PM805_INT1_SRC_DPLL_LOCK (1 << 5) +#define PM805_INT1_HP1_SHRT BIT(0) +#define PM805_INT1_HP2_SHRT BIT(1) +#define PM805_INT1_MIC_CONFLICT BIT(2) +#define PM805_INT1_CLIP_FAULT BIT(3) +#define PM805_INT1_LDO_OFF BIT(4) +#define PM805_INT1_SRC_DPLL_LOCK BIT(5) #define PM805_INT_STATUS2 (0x04) -#define PM805_INT2_MIC_DET (1 << 0) -#define PM805_INT2_SHRT_BTN_DET (1 << 1) -#define PM805_INT2_VOLM_BTN_DET (1 << 2) -#define PM805_INT2_VOLP_BTN_DET (1 << 3) -#define PM805_INT2_RAW_PLL_FAULT (1 << 4) -#define PM805_INT2_FINE_PLL_FAULT (1 << 5) +#define PM805_INT2_MIC_DET BIT(0) +#define PM805_INT2_SHRT_BTN_DET BIT(1) +#define PM805_INT2_VOLM_BTN_DET BIT(2) +#define PM805_INT2_VOLP_BTN_DET BIT(3) +#define PM805_INT2_RAW_PLL_FAULT BIT(4) +#define PM805_INT2_FINE_PLL_FAULT BIT(5) #define PM805_INT_MASK1 (0x05) #define PM805_INT_MASK2 (0x06) -#define PM805_SHRT_BTN_DET (1 << 1) +#define PM805_SHRT_BTN_DET BIT(1) /* number of status and int reg in a row */ #define PM805_INT_REG_NUM (2) #define PM805_MIC_DET1 (0x07) -#define PM805_MIC_DET_EN_MIC_DET (1 << 0) +#define PM805_MIC_DET_EN_MIC_DET BIT(0) #define PM805_MIC_DET2 (0x08) -#define PM805_MIC_DET_STATUS1 (0x09) +#define PM805_MIC_DET_STATUS1 (0x09) -#define PM805_MIC_DET_STATUS3 (0x0A) -#define PM805_AUTO_SEQ_STATUS1 (0x0B) -#define PM805_AUTO_SEQ_STATUS2 (0x0C) +#define PM805_MIC_DET_STATUS3 (0x0A) +#define PM805_AUTO_SEQ_STATUS1 (0x0B) +#define PM805_AUTO_SEQ_STATUS2 (0x0C) #define PM805_ADC_SETTING1 (0x10) #define PM805_ADC_SETTING2 (0x11) @@ -261,7 +262,7 @@ enum { #define PM805_ADC_GAIN2 (0x13) #define PM805_DMIC_SETTING (0x15) #define PM805_DWS_SETTING (0x16) -#define PM805_MIC_CONFLICT_STS (0x17) +#define PM805_MIC_CONFLICT_STS (0x17) #define PM805_PDM_SETTING1 (0x20) #define PM805_PDM_SETTING2 (0x21) @@ -270,11 +271,11 @@ enum { #define PM805_PDM_CONTROL2 (0x24) #define PM805_PDM_CONTROL3 (0x25) -#define PM805_HEADPHONE_SETTING (0x26) -#define PM805_HEADPHONE_GAIN_A2A (0x27) -#define PM805_HEADPHONE_SHORT_STATE (0x28) -#define PM805_EARPHONE_SETTING (0x29) -#define PM805_AUTO_SEQ_SETTING (0x2A) +#define PM805_HEADPHONE_SETTING (0x26) +#define PM805_HEADPHONE_GAIN_A2A (0x27) +#define PM805_HEADPHONE_SHORT_STATE (0x28) +#define PM805_EARPHONE_SETTING (0x29) +#define PM805_AUTO_SEQ_SETTING (0x2A) struct pm80x_rtc_pdata { int vrtc; diff --git a/kernel/include/linux/mfd/arizona/core.h b/kernel/include/linux/mfd/arizona/core.h index 16a498f48..79e607e2f 100644 --- a/kernel/include/linux/mfd/arizona/core.h +++ b/kernel/include/linux/mfd/arizona/core.h @@ -25,6 +25,8 @@ enum arizona_type { WM5110 = 2, WM8997 = 3, WM8280 = 4, + WM8998 = 5, + WM1814 = 6, }; #define ARIZONA_IRQ_GP1 0 @@ -117,6 +119,7 @@ struct arizona { int num_core_supplies; struct regulator_bulk_data core_supplies[ARIZONA_MAX_CORE_SUPPLIES]; struct regulator *dcvdd; + bool has_fully_powered_off; struct arizona_pdata pdata; @@ -153,9 +156,18 @@ int arizona_request_irq(struct arizona *arizona, int irq, char *name, void arizona_free_irq(struct arizona *arizona, int irq, void *data); int arizona_set_irq_wake(struct arizona *arizona, int irq, int on); +#ifdef CONFIG_MFD_WM5102 int wm5102_patch(struct arizona *arizona); +#else +static inline int wm5102_patch(struct arizona *arizona) +{ + return 0; +} +#endif + int wm5110_patch(struct arizona *arizona); int wm8997_patch(struct arizona *arizona); +int wm8998_patch(struct arizona *arizona); extern int arizona_of_get_named_gpio(struct arizona *arizona, const char *prop, bool mandatory); diff --git a/kernel/include/linux/mfd/arizona/pdata.h b/kernel/include/linux/mfd/arizona/pdata.h index 1789cb0f4..57b45caae 100644 --- a/kernel/include/linux/mfd/arizona/pdata.h +++ b/kernel/include/linux/mfd/arizona/pdata.h @@ -101,7 +101,7 @@ struct arizona_pdata { * useful for systems where and I2S bus with multiple data * lines is mastered. */ - int max_channels_clocked[ARIZONA_MAX_AIF]; + unsigned int max_channels_clocked[ARIZONA_MAX_AIF]; /** GPIO5 is used for jack detection */ bool jd_gpio5; @@ -121,23 +121,29 @@ struct arizona_pdata { /** GPIO used for mic isolation with HPDET */ int hpdet_id_gpio; + /** Channel to use for headphone detection */ + unsigned int hpdet_channel; + + /** Use software comparison to determine mic presence */ + bool micd_software_compare; + /** Extra debounce timeout used during initial mic detection (ms) */ - int micd_detect_debounce; + unsigned int micd_detect_debounce; /** GPIO for mic detection polarity */ int micd_pol_gpio; /** Mic detect ramp rate */ - int micd_bias_start_time; + unsigned int micd_bias_start_time; /** Mic detect sample rate */ - int micd_rate; + unsigned int micd_rate; /** Mic detect debounce level */ - int micd_dbtime; + unsigned int micd_dbtime; /** Mic detect timeout (ms) */ - int micd_timeout; + unsigned int micd_timeout; /** Force MICBIAS on for mic detect */ bool micd_force_micbias; @@ -156,7 +162,12 @@ struct arizona_pdata { /** MICBIAS configurations */ struct arizona_micbias micbias[ARIZONA_MAX_MICBIAS]; - /** Mode of input structures */ + /** + * Mode of input structures + * One of the ARIZONA_INMODE_xxx values + * wm5102/wm5110/wm8280/wm8997: [0]=IN1 [1]=IN2 [2]=IN3 [3]=IN4 + * wm8998: [0]=IN1A [1]=IN2A [2]=IN1B [3]=IN2B + */ int inmode[ARIZONA_MAX_INPUT]; /** Mode for outputs */ @@ -173,6 +184,9 @@ struct arizona_pdata { /** GPIO for primary IRQ (used for edge triggered emulation) */ int irq_gpio; + + /** General purpose switch control */ + unsigned int gpsw; }; #endif diff --git a/kernel/include/linux/mfd/arizona/registers.h b/kernel/include/linux/mfd/arizona/registers.h index aacc10d77..cd7e78eae 100644 --- a/kernel/include/linux/mfd/arizona/registers.h +++ b/kernel/include/linux/mfd/arizona/registers.h @@ -39,6 +39,7 @@ #define ARIZONA_PWM_DRIVE_3 0x32 #define ARIZONA_WAKE_CONTROL 0x40 #define ARIZONA_SEQUENCE_CONTROL 0x41 +#define ARIZONA_SPARE_TRIGGERS 0x42 #define ARIZONA_SAMPLE_RATE_SEQUENCE_SELECT_1 0x61 #define ARIZONA_SAMPLE_RATE_SEQUENCE_SELECT_2 0x62 #define ARIZONA_SAMPLE_RATE_SEQUENCE_SELECT_3 0x63 @@ -139,6 +140,7 @@ #define ARIZONA_MIC_DETECT_LEVEL_2 0x2A7 #define ARIZONA_MIC_DETECT_LEVEL_3 0x2A8 #define ARIZONA_MIC_DETECT_LEVEL_4 0x2A9 +#define ARIZONA_MIC_DETECT_4 0x2AB #define ARIZONA_MIC_NOISE_MIX_CONTROL_1 0x2C3 #define ARIZONA_ISOLATION_CONTROL 0x2CB #define ARIZONA_JACK_DETECT_ANALOGUE 0x2D3 @@ -225,17 +227,22 @@ #define ARIZONA_DAC_VOLUME_LIMIT_6R 0x43E #define ARIZONA_NOISE_GATE_SELECT_6R 0x43F #define ARIZONA_DRE_ENABLE 0x440 +#define ARIZONA_DRE_CONTROL_1 0x441 #define ARIZONA_DRE_CONTROL_2 0x442 #define ARIZONA_DRE_CONTROL_3 0x443 +#define ARIZONA_EDRE_ENABLE 0x448 #define ARIZONA_DAC_AEC_CONTROL_1 0x450 +#define ARIZONA_DAC_AEC_CONTROL_2 0x451 #define ARIZONA_NOISE_GATE_CONTROL 0x458 #define ARIZONA_PDM_SPK1_CTRL_1 0x490 #define ARIZONA_PDM_SPK1_CTRL_2 0x491 #define ARIZONA_PDM_SPK2_CTRL_1 0x492 #define ARIZONA_PDM_SPK2_CTRL_2 0x493 +#define ARIZONA_HP_TEST_CTRL_13 0x49A #define ARIZONA_HP1_SHORT_CIRCUIT_CTRL 0x4A0 #define ARIZONA_HP2_SHORT_CIRCUIT_CTRL 0x4A1 #define ARIZONA_HP3_SHORT_CIRCUIT_CTRL 0x4A2 +#define ARIZONA_HP_TEST_CTRL_1 0x4A4 #define ARIZONA_SPK_CTRL_2 0x4B5 #define ARIZONA_SPK_CTRL_3 0x4B6 #define ARIZONA_DAC_COMP_1 0x4DC @@ -310,6 +317,10 @@ #define ARIZONA_AIF3_TX_ENABLES 0x599 #define ARIZONA_AIF3_RX_ENABLES 0x59A #define ARIZONA_AIF3_FORCE_WRITE 0x59B +#define ARIZONA_SPD1_TX_CONTROL 0x5C2 +#define ARIZONA_SPD1_TX_CHANNEL_STATUS_1 0x5C3 +#define ARIZONA_SPD1_TX_CHANNEL_STATUS_2 0x5C4 +#define ARIZONA_SPD1_TX_CHANNEL_STATUS_3 0x5C5 #define ARIZONA_SLIMBUS_FRAMER_REF_GEAR 0x5E3 #define ARIZONA_SLIMBUS_RATES_1 0x5E5 #define ARIZONA_SLIMBUS_RATES_2 0x5E6 @@ -643,6 +654,10 @@ #define ARIZONA_SLIMTX8MIX_INPUT_3_VOLUME 0x7FD #define ARIZONA_SLIMTX8MIX_INPUT_4_SOURCE 0x7FE #define ARIZONA_SLIMTX8MIX_INPUT_4_VOLUME 0x7FF +#define ARIZONA_SPDIFTX1MIX_INPUT_1_SOURCE 0x800 +#define ARIZONA_SPDIFTX1MIX_INPUT_1_VOLUME 0x801 +#define ARIZONA_SPDIFTX2MIX_INPUT_1_SOURCE 0x808 +#define ARIZONA_SPDIFTX2MIX_INPUT_1_VOLUME 0x809 #define ARIZONA_EQ1MIX_INPUT_1_SOURCE 0x880 #define ARIZONA_EQ1MIX_INPUT_1_VOLUME 0x881 #define ARIZONA_EQ1MIX_INPUT_2_SOURCE 0x882 @@ -868,6 +883,7 @@ #define ARIZONA_GPIO5_CTRL 0xC04 #define ARIZONA_IRQ_CTRL_1 0xC0F #define ARIZONA_GPIO_DEBOUNCE_CONFIG 0xC10 +#define ARIZONA_GP_SWITCH_1 0xC18 #define ARIZONA_MISC_PAD_CTRL_1 0xC20 #define ARIZONA_MISC_PAD_CTRL_2 0xC21 #define ARIZONA_MISC_PAD_CTRL_3 0xC22 @@ -1049,6 +1065,16 @@ #define ARIZONA_CLOCK_CONTROL 0xF00 #define ARIZONA_ANC_SRC 0xF01 #define ARIZONA_DSP_STATUS 0xF02 +#define ARIZONA_ANC_COEFF_START 0xF08 +#define ARIZONA_ANC_COEFF_END 0xF12 +#define ARIZONA_FCL_FILTER_CONTROL 0xF15 +#define ARIZONA_FCL_ADC_REFORMATTER_CONTROL 0xF17 +#define ARIZONA_FCL_COEFF_START 0xF18 +#define ARIZONA_FCL_COEFF_END 0xF69 +#define ARIZONA_FCR_FILTER_CONTROL 0xF70 +#define ARIZONA_FCR_ADC_REFORMATTER_CONTROL 0xF72 +#define ARIZONA_FCR_COEFF_START 0xF73 +#define ARIZONA_FCR_COEFF_END 0xFC4 #define ARIZONA_DSP1_CONTROL_1 0x1100 #define ARIZONA_DSP1_CLOCKING_1 0x1101 #define ARIZONA_DSP1_STATUS_1 0x1104 @@ -1169,6 +1195,13 @@ #define ARIZONA_DSP4_SCRATCH_1 0x1441 #define ARIZONA_DSP4_SCRATCH_2 0x1442 #define ARIZONA_DSP4_SCRATCH_3 0x1443 +#define ARIZONA_FRF_COEFF_1 0x1700 +#define ARIZONA_FRF_COEFF_2 0x1701 +#define ARIZONA_FRF_COEFF_3 0x1702 +#define ARIZONA_FRF_COEFF_4 0x1703 +#define ARIZONA_V2_DAC_COMP_1 0x1704 +#define ARIZONA_V2_DAC_COMP_2 0x1705 + /* * Field Definitions. @@ -1431,6 +1464,42 @@ #define ARIZONA_WSEQ_ENA_JD2_RISE_WIDTH 1 /* WSEQ_ENA_JD2_RISE */ /* + * R66 (0x42) - Spare Triggers + */ +#define ARIZONA_WS_TRG8 0x0080 /* WS_TRG8 */ +#define ARIZONA_WS_TRG8_MASK 0x0080 /* WS_TRG8 */ +#define ARIZONA_WS_TRG8_SHIFT 7 /* WS_TRG8 */ +#define ARIZONA_WS_TRG8_WIDTH 1 /* WS_TRG8 */ +#define ARIZONA_WS_TRG7 0x0040 /* WS_TRG7 */ +#define ARIZONA_WS_TRG7_MASK 0x0040 /* WS_TRG7 */ +#define ARIZONA_WS_TRG7_SHIFT 6 /* WS_TRG7 */ +#define ARIZONA_WS_TRG7_WIDTH 1 /* WS_TRG7 */ +#define ARIZONA_WS_TRG6 0x0020 /* WS_TRG6 */ +#define ARIZONA_WS_TRG6_MASK 0x0020 /* WS_TRG6 */ +#define ARIZONA_WS_TRG6_SHIFT 5 /* WS_TRG6 */ +#define ARIZONA_WS_TRG6_WIDTH 1 /* WS_TRG6 */ +#define ARIZONA_WS_TRG5 0x0010 /* WS_TRG5 */ +#define ARIZONA_WS_TRG5_MASK 0x0010 /* WS_TRG5 */ +#define ARIZONA_WS_TRG5_SHIFT 4 /* WS_TRG5 */ +#define ARIZONA_WS_TRG5_WIDTH 1 /* WS_TRG5 */ +#define ARIZONA_WS_TRG4 0x0008 /* WS_TRG4 */ +#define ARIZONA_WS_TRG4_MASK 0x0008 /* WS_TRG4 */ +#define ARIZONA_WS_TRG4_SHIFT 3 /* WS_TRG4 */ +#define ARIZONA_WS_TRG4_WIDTH 1 /* WS_TRG4 */ +#define ARIZONA_WS_TRG3 0x0004 /* WS_TRG3 */ +#define ARIZONA_WS_TRG3_MASK 0x0004 /* WS_TRG3 */ +#define ARIZONA_WS_TRG3_SHIFT 2 /* WS_TRG3 */ +#define ARIZONA_WS_TRG3_WIDTH 1 /* WS_TRG3 */ +#define ARIZONA_WS_TRG2 0x0002 /* WS_TRG2 */ +#define ARIZONA_WS_TRG2_MASK 0x0002 /* WS_TRG2 */ +#define ARIZONA_WS_TRG2_SHIFT 1 /* WS_TRG2 */ +#define ARIZONA_WS_TRG2_WIDTH 1 /* WS_TRG2 */ +#define ARIZONA_WS_TRG1 0x0001 /* WS_TRG1 */ +#define ARIZONA_WS_TRG1_MASK 0x0001 /* WS_TRG1 */ +#define ARIZONA_WS_TRG1_SHIFT 0 /* WS_TRG1 */ +#define ARIZONA_WS_TRG1_WIDTH 1 /* WS_TRG1 */ + +/* * R97 (0x61) - Sample Rate Sequence Select 1 */ #define ARIZONA_WSEQ_SAMPLE_RATE_DETECT_A_SEQ_ADDR_MASK 0x01FF /* WSEQ_SAMPLE_RATE_DETECT_A_SEQ_ADDR - [8:0] */ @@ -2301,9 +2370,9 @@ #define ARIZONA_ACCDET_SRC_MASK 0x2000 /* ACCDET_SRC */ #define ARIZONA_ACCDET_SRC_SHIFT 13 /* ACCDET_SRC */ #define ARIZONA_ACCDET_SRC_WIDTH 1 /* ACCDET_SRC */ -#define ARIZONA_ACCDET_MODE_MASK 0x0003 /* ACCDET_MODE - [1:0] */ -#define ARIZONA_ACCDET_MODE_SHIFT 0 /* ACCDET_MODE - [1:0] */ -#define ARIZONA_ACCDET_MODE_WIDTH 2 /* ACCDET_MODE - [1:0] */ +#define ARIZONA_ACCDET_MODE_MASK 0x0007 /* ACCDET_MODE - [2:0] */ +#define ARIZONA_ACCDET_MODE_SHIFT 0 /* ACCDET_MODE - [2:0] */ +#define ARIZONA_ACCDET_MODE_WIDTH 3 /* ACCDET_MODE - [2:0] */ /* * R667 (0x29B) - Headphone Detect 1 @@ -2325,6 +2394,9 @@ #define ARIZONA_HP_IDAC_STEER_MASK 0x0004 /* HP_IDAC_STEER */ #define ARIZONA_HP_IDAC_STEER_SHIFT 2 /* HP_IDAC_STEER */ #define ARIZONA_HP_IDAC_STEER_WIDTH 1 /* HP_IDAC_STEER */ +#define WM8998_HP_RATE_MASK 0x0006 /* HP_RATE - [2:1] */ +#define WM8998_HP_RATE_SHIFT 1 /* HP_RATE - [2:1] */ +#define WM8998_HP_RATE_WIDTH 2 /* HP_RATE - [2:1] */ #define ARIZONA_HP_RATE 0x0002 /* HP_RATE */ #define ARIZONA_HP_RATE_MASK 0x0002 /* HP_RATE */ #define ARIZONA_HP_RATE_SHIFT 1 /* HP_RATE */ @@ -2413,6 +2485,16 @@ #define ARIZONA_MICD_STS_WIDTH 1 /* MICD_STS */ /* + * R683 (0x2AB) - Mic Detect 4 + */ +#define ARIZONA_MICDET_ADCVAL_DIFF_MASK 0xFF00 /* MICDET_ADCVAL_DIFF - [15:8] */ +#define ARIZONA_MICDET_ADCVAL_DIFF_SHIFT 8 /* MICDET_ADCVAL_DIFF - [15:8] */ +#define ARIZONA_MICDET_ADCVAL_DIFF_WIDTH 8 /* MICDET_ADCVAL_DIFF - [15:8] */ +#define ARIZONA_MICDET_ADCVAL_MASK 0x007F /* MICDET_ADCVAL - [15:8] */ +#define ARIZONA_MICDET_ADCVAL_SHIFT 0 /* MICDET_ADCVAL - [15:8] */ +#define ARIZONA_MICDET_ADCVAL_WIDTH 7 /* MICDET_ADCVAL - [15:8] */ + +/* * R707 (0x2C3) - Mic noise mix control 1 */ #define ARIZONA_MICMUTE_RATE_MASK 0x7800 /* MICMUTE_RATE - [14:11] */ @@ -2515,9 +2597,12 @@ #define ARIZONA_IN1_DMIC_SUP_MASK 0x1800 /* IN1_DMIC_SUP - [12:11] */ #define ARIZONA_IN1_DMIC_SUP_SHIFT 11 /* IN1_DMIC_SUP - [12:11] */ #define ARIZONA_IN1_DMIC_SUP_WIDTH 2 /* IN1_DMIC_SUP - [12:11] */ -#define ARIZONA_IN1_MODE_MASK 0x0600 /* IN1_MODE - [10:9] */ -#define ARIZONA_IN1_MODE_SHIFT 9 /* IN1_MODE - [10:9] */ -#define ARIZONA_IN1_MODE_WIDTH 2 /* IN1_MODE - [10:9] */ +#define ARIZONA_IN1_MODE_MASK 0x0400 /* IN1_MODE - [10] */ +#define ARIZONA_IN1_MODE_SHIFT 10 /* IN1_MODE - [10] */ +#define ARIZONA_IN1_MODE_WIDTH 1 /* IN1_MODE - [10] */ +#define ARIZONA_IN1_SINGLE_ENDED_MASK 0x0200 /* IN1_MODE - [9] */ +#define ARIZONA_IN1_SINGLE_ENDED_SHIFT 9 /* IN1_MODE - [9] */ +#define ARIZONA_IN1_SINGLE_ENDED_WIDTH 1 /* IN1_MODE - [9] */ #define ARIZONA_IN1L_PGA_VOL_MASK 0x00FE /* IN1L_PGA_VOL - [7:1] */ #define ARIZONA_IN1L_PGA_VOL_SHIFT 1 /* IN1L_PGA_VOL - [7:1] */ #define ARIZONA_IN1L_PGA_VOL_WIDTH 7 /* IN1L_PGA_VOL - [7:1] */ @@ -2525,6 +2610,12 @@ /* * R785 (0x311) - ADC Digital Volume 1L */ +#define ARIZONA_IN1L_SRC_MASK 0x4000 /* IN1L_SRC - [14] */ +#define ARIZONA_IN1L_SRC_SHIFT 14 /* IN1L_SRC - [14] */ +#define ARIZONA_IN1L_SRC_WIDTH 1 /* IN1L_SRC - [14] */ +#define ARIZONA_IN1L_SRC_SE_MASK 0x2000 /* IN1L_SRC - [13] */ +#define ARIZONA_IN1L_SRC_SE_SHIFT 13 /* IN1L_SRC - [13] */ +#define ARIZONA_IN1L_SRC_SE_WIDTH 1 /* IN1L_SRC - [13] */ #define ARIZONA_IN_VU 0x0200 /* IN_VU */ #define ARIZONA_IN_VU_MASK 0x0200 /* IN_VU */ #define ARIZONA_IN_VU_SHIFT 9 /* IN_VU */ @@ -2557,6 +2648,12 @@ /* * R789 (0x315) - ADC Digital Volume 1R */ +#define ARIZONA_IN1R_SRC_MASK 0x4000 /* IN1R_SRC - [14] */ +#define ARIZONA_IN1R_SRC_SHIFT 14 /* IN1R_SRC - [14] */ +#define ARIZONA_IN1R_SRC_WIDTH 1 /* IN1R_SRC - [14] */ +#define ARIZONA_IN1R_SRC_SE_MASK 0x2000 /* IN1R_SRC - [13] */ +#define ARIZONA_IN1R_SRC_SE_SHIFT 13 /* IN1R_SRC - [13] */ +#define ARIZONA_IN1R_SRC_SE_WIDTH 1 /* IN1R_SRC - [13] */ #define ARIZONA_IN_VU 0x0200 /* IN_VU */ #define ARIZONA_IN_VU_MASK 0x0200 /* IN_VU */ #define ARIZONA_IN_VU_SHIFT 9 /* IN_VU */ @@ -2588,9 +2685,12 @@ #define ARIZONA_IN2_DMIC_SUP_MASK 0x1800 /* IN2_DMIC_SUP - [12:11] */ #define ARIZONA_IN2_DMIC_SUP_SHIFT 11 /* IN2_DMIC_SUP - [12:11] */ #define ARIZONA_IN2_DMIC_SUP_WIDTH 2 /* IN2_DMIC_SUP - [12:11] */ -#define ARIZONA_IN2_MODE_MASK 0x0600 /* IN2_MODE - [10:9] */ -#define ARIZONA_IN2_MODE_SHIFT 9 /* IN2_MODE - [10:9] */ -#define ARIZONA_IN2_MODE_WIDTH 2 /* IN2_MODE - [10:9] */ +#define ARIZONA_IN2_MODE_MASK 0x0400 /* IN2_MODE - [10] */ +#define ARIZONA_IN2_MODE_SHIFT 10 /* IN2_MODE - [10] */ +#define ARIZONA_IN2_MODE_WIDTH 1 /* IN2_MODE - [10] */ +#define ARIZONA_IN2_SINGLE_ENDED_MASK 0x0200 /* IN2_MODE - [9] */ +#define ARIZONA_IN2_SINGLE_ENDED_SHIFT 9 /* IN2_MODE - [9] */ +#define ARIZONA_IN2_SINGLE_ENDED_WIDTH 1 /* IN2_MODE - [9] */ #define ARIZONA_IN2L_PGA_VOL_MASK 0x00FE /* IN2L_PGA_VOL - [7:1] */ #define ARIZONA_IN2L_PGA_VOL_SHIFT 1 /* IN2L_PGA_VOL - [7:1] */ #define ARIZONA_IN2L_PGA_VOL_WIDTH 7 /* IN2L_PGA_VOL - [7:1] */ @@ -2598,6 +2698,12 @@ /* * R793 (0x319) - ADC Digital Volume 2L */ +#define ARIZONA_IN2L_SRC_MASK 0x4000 /* IN2L_SRC - [14] */ +#define ARIZONA_IN2L_SRC_SHIFT 14 /* IN2L_SRC - [14] */ +#define ARIZONA_IN2L_SRC_WIDTH 1 /* IN2L_SRC - [14] */ +#define ARIZONA_IN2L_SRC_SE_MASK 0x2000 /* IN2L_SRC - [13] */ +#define ARIZONA_IN2L_SRC_SE_SHIFT 13 /* IN2L_SRC - [13] */ +#define ARIZONA_IN2L_SRC_SE_WIDTH 1 /* IN2L_SRC - [13] */ #define ARIZONA_IN_VU 0x0200 /* IN_VU */ #define ARIZONA_IN_VU_MASK 0x0200 /* IN_VU */ #define ARIZONA_IN_VU_SHIFT 9 /* IN_VU */ @@ -2661,9 +2767,12 @@ #define ARIZONA_IN3_DMIC_SUP_MASK 0x1800 /* IN3_DMIC_SUP - [12:11] */ #define ARIZONA_IN3_DMIC_SUP_SHIFT 11 /* IN3_DMIC_SUP - [12:11] */ #define ARIZONA_IN3_DMIC_SUP_WIDTH 2 /* IN3_DMIC_SUP - [12:11] */ -#define ARIZONA_IN3_MODE_MASK 0x0600 /* IN3_MODE - [10:9] */ -#define ARIZONA_IN3_MODE_SHIFT 9 /* IN3_MODE - [10:9] */ -#define ARIZONA_IN3_MODE_WIDTH 2 /* IN3_MODE - [10:9] */ +#define ARIZONA_IN3_MODE_MASK 0x0400 /* IN3_MODE - [10] */ +#define ARIZONA_IN3_MODE_SHIFT 10 /* IN3_MODE - [10] */ +#define ARIZONA_IN3_MODE_WIDTH 1 /* IN3_MODE - [10] */ +#define ARIZONA_IN3_SINGLE_ENDED_MASK 0x0200 /* IN3_MODE - [9] */ +#define ARIZONA_IN3_SINGLE_ENDED_SHIFT 9 /* IN3_MODE - [9] */ +#define ARIZONA_IN3_SINGLE_ENDED_WIDTH 1 /* IN3_MODE - [9] */ #define ARIZONA_IN3L_PGA_VOL_MASK 0x00FE /* IN3L_PGA_VOL - [7:1] */ #define ARIZONA_IN3L_PGA_VOL_SHIFT 1 /* IN3L_PGA_VOL - [7:1] */ #define ARIZONA_IN3L_PGA_VOL_WIDTH 7 /* IN3L_PGA_VOL - [7:1] */ @@ -3403,11 +3512,45 @@ #define ARIZONA_DRE1L_ENA_WIDTH 1 /* DRE1L_ENA */ /* + * R1088 (0x440) - DRE Enable (WM8998) + */ +#define WM8998_DRE3L_ENA 0x0020 /* DRE3L_ENA */ +#define WM8998_DRE3L_ENA_MASK 0x0020 /* DRE3L_ENA */ +#define WM8998_DRE3L_ENA_SHIFT 5 /* DRE3L_ENA */ +#define WM8998_DRE3L_ENA_WIDTH 1 /* DRE3L_ENA */ +#define WM8998_DRE2L_ENA 0x0008 /* DRE2L_ENA */ +#define WM8998_DRE2L_ENA_MASK 0x0008 /* DRE2L_ENA */ +#define WM8998_DRE2L_ENA_SHIFT 3 /* DRE2L_ENA */ +#define WM8998_DRE2L_ENA_WIDTH 1 /* DRE2L_ENA */ +#define WM8998_DRE2R_ENA 0x0004 /* DRE2R_ENA */ +#define WM8998_DRE2R_ENA_MASK 0x0004 /* DRE2R_ENA */ +#define WM8998_DRE2R_ENA_SHIFT 2 /* DRE2R_ENA */ +#define WM8998_DRE2R_ENA_WIDTH 1 /* DRE2R_ENA */ +#define WM8998_DRE1L_ENA 0x0002 /* DRE1L_ENA */ +#define WM8998_DRE1L_ENA_MASK 0x0002 /* DRE1L_ENA */ +#define WM8998_DRE1L_ENA_SHIFT 1 /* DRE1L_ENA */ +#define WM8998_DRE1L_ENA_WIDTH 1 /* DRE1L_ENA */ +#define WM8998_DRE1R_ENA 0x0001 /* DRE1R_ENA */ +#define WM8998_DRE1R_ENA_MASK 0x0001 /* DRE1R_ENA */ +#define WM8998_DRE1R_ENA_SHIFT 0 /* DRE1R_ENA */ +#define WM8998_DRE1R_ENA_WIDTH 1 /* DRE1R_ENA */ + +/* + * R1089 (0x441) - DRE Control 1 + */ +#define ARIZONA_DRE_ENV_TC_FAST_MASK 0x0F00 /* DRE_ENV_TC_FAST - [11:8] */ +#define ARIZONA_DRE_ENV_TC_FAST_SHIFT 8 /* DRE_ENV_TC_FAST - [11:8] */ +#define ARIZONA_DRE_ENV_TC_FAST_WIDTH 4 /* DRE_ENV_TC_FAST - [11:8] */ + +/* * R1090 (0x442) - DRE Control 2 */ #define ARIZONA_DRE_T_LOW_MASK 0x3F00 /* DRE_T_LOW - [13:8] */ #define ARIZONA_DRE_T_LOW_SHIFT 8 /* DRE_T_LOW - [13:8] */ #define ARIZONA_DRE_T_LOW_WIDTH 6 /* DRE_T_LOW - [13:8] */ +#define ARIZONA_DRE_ALOG_VOL_DELAY_MASK 0x000F /* DRE_ALOG_VOL_DELAY - [3:0] */ +#define ARIZONA_DRE_ALOG_VOL_DELAY_SHIFT 0 /* DRE_ALOG_VOL_DELAY - [3:0] */ +#define ARIZONA_DRE_ALOG_VOL_DELAY_WIDTH 4 /* DRE_ALOG_VOL_DELAY - [3:0] */ /* * R1091 (0x443) - DRE Control 3 @@ -3419,6 +3562,49 @@ #define ARIZONA_DRE_LOW_LEVEL_ABS_SHIFT 0 /* LOW_LEVEL_ABS - [3:0] */ #define ARIZONA_DRE_LOW_LEVEL_ABS_WIDTH 4 /* LOW_LEVEL_ABS - [3:0] */ +/* R486 (0x448) - EDRE_Enable + */ +#define ARIZONA_EDRE_OUT4L_THR2_ENA 0x0200 /* EDRE_OUT4L_THR2_ENA */ +#define ARIZONA_EDRE_OUT4L_THR2_ENA_MASK 0x0200 /* EDRE_OUT4L_THR2_ENA */ +#define ARIZONA_EDRE_OUT4L_THR2_ENA_SHIFT 9 /* EDRE_OUT4L_THR2_ENA */ +#define ARIZONA_EDRE_OUT4L_THR2_ENA_WIDTH 1 /* EDRE_OUT4L_THR2_ENA */ +#define ARIZONA_EDRE_OUT4R_THR2_ENA 0x0100 /* EDRE_OUT4R_THR2_ENA */ +#define ARIZONA_EDRE_OUT4R_THR2_ENA_MASK 0x0100 /* EDRE_OUT4R_THR2_ENA */ +#define ARIZONA_EDRE_OUT4R_THR2_ENA_SHIFT 8 /* EDRE_OUT4R_THR2_ENA */ +#define ARIZONA_EDRE_OUT4R_THR2_ENA_WIDTH 1 /* EDRE_OUT4R_THR2_ENA */ +#define ARIZONA_EDRE_OUT4L_THR1_ENA 0x0080 /* EDRE_OUT4L_THR1_ENA */ +#define ARIZONA_EDRE_OUT4L_THR1_ENA_MASK 0x0080 /* EDRE_OUT4L_THR1_ENA */ +#define ARIZONA_EDRE_OUT4L_THR1_ENA_SHIFT 7 /* EDRE_OUT4L_THR1_ENA */ +#define ARIZONA_EDRE_OUT4L_THR1_ENA_WIDTH 1 /* EDRE_OUT4L_THR1_ENA */ +#define ARIZONA_EDRE_OUT4R_THR1_ENA 0x0040 /* EDRE_OUT4R_THR1_ENA */ +#define ARIZONA_EDRE_OUT4R_THR1_ENA_MASK 0x0040 /* EDRE_OUT4R_THR1_ENA */ +#define ARIZONA_EDRE_OUT4R_THR1_ENA_SHIFT 6 /* EDRE_OUT4R_THR1_ENA */ +#define ARIZONA_EDRE_OUT4R_THR1_ENA_WIDTH 1 /* EDRE_OUT4R_THR1_ENA */ +#define ARIZONA_EDRE_OUT3L_THR1_ENA 0x0020 /* EDRE_OUT3L_THR1_ENA */ +#define ARIZONA_EDRE_OUT3L_THR1_ENA_MASK 0x0020 /* EDRE_OUT3L_THR1_ENA */ +#define ARIZONA_EDRE_OUT3L_THR1_ENA_SHIFT 5 /* EDRE_OUT3L_THR1_ENA */ +#define ARIZONA_EDRE_OUT3L_THR1_ENA_WIDTH 1 /* EDRE_OUT3L_THR1_ENA */ +#define ARIZONA_EDRE_OUT3R_THR1_ENA 0x0010 /* EDRE_OUT3R_THR1_ENA */ +#define ARIZONA_EDRE_OUT3R_THR1_ENA_MASK 0x0010 /* EDRE_OUT3R_THR1_ENA */ +#define ARIZONA_EDRE_OUT3R_THR1_ENA_SHIFT 4 /* EDRE_OUT3R_THR1_ENA */ +#define ARIZONA_EDRE_OUT3R_THR1_ENA_WIDTH 1 /* EDRE_OUT3R_THR1_ENA */ +#define ARIZONA_EDRE_OUT2L_THR1_ENA 0x0008 /* EDRE_OUT2L_THR1_ENA */ +#define ARIZONA_EDRE_OUT2L_THR1_ENA_MASK 0x0008 /* EDRE_OUT2L_THR1_ENA */ +#define ARIZONA_EDRE_OUT2L_THR1_ENA_SHIFT 3 /* EDRE_OUT2L_THR1_ENA */ +#define ARIZONA_EDRE_OUT2L_THR1_ENA_WIDTH 1 /* EDRE_OUT2L_THR1_ENA */ +#define ARIZONA_EDRE_OUT2R_THR1_ENA 0x0004 /* EDRE_OUT2R_THR1_ENA */ +#define ARIZONA_EDRE_OUT2R_THR1_ENA_MASK 0x0004 /* EDRE_OUT2R_THR1_ENA */ +#define ARIZONA_EDRE_OUT2R_THR1_ENA_SHIFT 2 /* EDRE_OUT2R_THR1_ENA */ +#define ARIZONA_EDRE_OUT2R_THR1_ENA_WIDTH 1 /* EDRE_OUT2R_THR1_ENA */ +#define ARIZONA_EDRE_OUT1L_THR1_ENA 0x0002 /* EDRE_OUT1L_THR1_ENA */ +#define ARIZONA_EDRE_OUT1L_THR1_ENA_MASK 0x0002 /* EDRE_OUT1L_THR1_ENA */ +#define ARIZONA_EDRE_OUT1L_THR1_ENA_SHIFT 1 /* EDRE_OUT1L_THR1_ENA */ +#define ARIZONA_EDRE_OUT1L_THR1_ENA_WIDTH 1 /* EDRE_OUT1L_THR1_ENA */ +#define ARIZONA_EDRE_OUT1R_THR1_ENA 0x0001 /* EDRE_OUT1R_THR1_ENA */ +#define ARIZONA_EDRE_OUT1R_THR1_ENA_MASK 0x0001 /* EDRE_OUT1R_THR1_ENA */ +#define ARIZONA_EDRE_OUT1R_THR1_ENA_SHIFT 0 /* EDRE_OUT1R_THR1_ENA */ +#define ARIZONA_EDRE_OUT1R_THR1_ENA_WIDTH 1 /* EDRE_OUT1R_THR1_ENA */ + /* * R1104 (0x450) - DAC AEC Control 1 */ @@ -3527,6 +3713,13 @@ #define ARIZONA_HP3_SC_ENA_WIDTH 1 /* HP3_SC_ENA */ /* + * R1188 (0x4A4) HP Test Ctrl 1 + */ +#define ARIZONA_HP1_TST_CAP_SEL_MASK 0x0003 /* HP1_TST_CAP_SEL - [1:0] */ +#define ARIZONA_HP1_TST_CAP_SEL_SHIFT 0 /* HP1_TST_CAP_SEL - [1:0] */ +#define ARIZONA_HP1_TST_CAP_SEL_WIDTH 2 /* HP1_TST_CAP_SEL - [1:0] */ + +/* * R1244 (0x4DC) - DAC comp 1 */ #define ARIZONA_OUT_COMP_COEFF_MASK 0xFFFF /* OUT_COMP_COEFF - [15:0] */ @@ -4299,6 +4492,86 @@ #define ARIZONA_AIF3_FRC_WR_WIDTH 1 /* AIF3_FRC_WR */ /* + * R1474 (0x5C2) - SPD1 TX Control + */ +#define ARIZONA_SPD1_VAL2 0x2000 /* SPD1_VAL2 */ +#define ARIZONA_SPD1_VAL2_MASK 0x2000 /* SPD1_VAL2 */ +#define ARIZONA_SPD1_VAL2_SHIFT 13 /* SPD1_VAL2 */ +#define ARIZONA_SPD1_VAL2_WIDTH 1 /* SPD1_VAL2 */ +#define ARIZONA_SPD1_VAL1 0x1000 /* SPD1_VAL1 */ +#define ARIZONA_SPD1_VAL1_MASK 0x1000 /* SPD1_VAL1 */ +#define ARIZONA_SPD1_VAL1_SHIFT 12 /* SPD1_VAL1 */ +#define ARIZONA_SPD1_VAL1_WIDTH 1 /* SPD1_VAL1 */ +#define ARIZONA_SPD1_RATE_MASK 0x00F0 /* SPD1_RATE */ +#define ARIZONA_SPD1_RATE_SHIFT 4 /* SPD1_RATE */ +#define ARIZONA_SPD1_RATE_WIDTH 4 /* SPD1_RATE */ +#define ARIZONA_SPD1_ENA 0x0001 /* SPD1_ENA */ +#define ARIZONA_SPD1_ENA_MASK 0x0001 /* SPD1_ENA */ +#define ARIZONA_SPD1_ENA_SHIFT 0 /* SPD1_ENA */ +#define ARIZONA_SPD1_ENA_WIDTH 1 /* SPD1_ENA */ + +/* + * R1475 (0x5C3) - SPD1 TX Channel Status 1 + */ +#define ARIZONA_SPD1_CATCODE_MASK 0xFF00 /* SPD1_CATCODE */ +#define ARIZONA_SPD1_CATCODE_SHIFT 8 /* SPD1_CATCODE */ +#define ARIZONA_SPD1_CATCODE_WIDTH 8 /* SPD1_CATCODE */ +#define ARIZONA_SPD1_CHSTMODE_MASK 0x00C0 /* SPD1_CHSTMODE */ +#define ARIZONA_SPD1_CHSTMODE_SHIFT 6 /* SPD1_CHSTMODE */ +#define ARIZONA_SPD1_CHSTMODE_WIDTH 2 /* SPD1_CHSTMODE */ +#define ARIZONA_SPD1_PREEMPH_MASK 0x0038 /* SPD1_PREEMPH */ +#define ARIZONA_SPD1_PREEMPH_SHIFT 3 /* SPD1_PREEMPH */ +#define ARIZONA_SPD1_PREEMPH_WIDTH 3 /* SPD1_PREEMPH */ +#define ARIZONA_SPD1_NOCOPY 0x0004 /* SPD1_NOCOPY */ +#define ARIZONA_SPD1_NOCOPY_MASK 0x0004 /* SPD1_NOCOPY */ +#define ARIZONA_SPD1_NOCOPY_SHIFT 2 /* SPD1_NOCOPY */ +#define ARIZONA_SPD1_NOCOPY_WIDTH 1 /* SPD1_NOCOPY */ +#define ARIZONA_SPD1_NOAUDIO 0x0002 /* SPD1_NOAUDIO */ +#define ARIZONA_SPD1_NOAUDIO_MASK 0x0002 /* SPD1_NOAUDIO */ +#define ARIZONA_SPD1_NOAUDIO_SHIFT 1 /* SPD1_NOAUDIO */ +#define ARIZONA_SPD1_NOAUDIO_WIDTH 1 /* SPD1_NOAUDIO */ +#define ARIZONA_SPD1_PRO 0x0001 /* SPD1_PRO */ +#define ARIZONA_SPD1_PRO_MASK 0x0001 /* SPD1_PRO */ +#define ARIZONA_SPD1_PRO_SHIFT 0 /* SPD1_PRO */ +#define ARIZONA_SPD1_PRO_WIDTH 1 /* SPD1_PRO */ + +/* + * R1475 (0x5C4) - SPD1 TX Channel Status 2 + */ +#define ARIZONA_SPD1_FREQ_MASK 0xF000 /* SPD1_FREQ */ +#define ARIZONA_SPD1_FREQ_SHIFT 12 /* SPD1_FREQ */ +#define ARIZONA_SPD1_FREQ_WIDTH 4 /* SPD1_FREQ */ +#define ARIZONA_SPD1_CHNUM2_MASK 0x0F00 /* SPD1_CHNUM2 */ +#define ARIZONA_SPD1_CHNUM2_SHIFT 8 /* SPD1_CHNUM2 */ +#define ARIZONA_SPD1_CHNUM2_WIDTH 4 /* SPD1_CHNUM2 */ +#define ARIZONA_SPD1_CHNUM1_MASK 0x00F0 /* SPD1_CHNUM1 */ +#define ARIZONA_SPD1_CHNUM1_SHIFT 4 /* SPD1_CHNUM1 */ +#define ARIZONA_SPD1_CHNUM1_WIDTH 4 /* SPD1_CHNUM1 */ +#define ARIZONA_SPD1_SRCNUM_MASK 0x000F /* SPD1_SRCNUM */ +#define ARIZONA_SPD1_SRCNUM_SHIFT 0 /* SPD1_SRCNUM */ +#define ARIZONA_SPD1_SRCNUM_WIDTH 4 /* SPD1_SRCNUM */ + +/* + * R1475 (0x5C5) - SPD1 TX Channel Status 3 + */ +#define ARIZONA_SPD1_ORGSAMP_MASK 0x0F00 /* SPD1_ORGSAMP */ +#define ARIZONA_SPD1_ORGSAMP_SHIFT 8 /* SPD1_ORGSAMP */ +#define ARIZONA_SPD1_ORGSAMP_WIDTH 4 /* SPD1_ORGSAMP */ +#define ARIZONA_SPD1_TXWL_MASK 0x00E0 /* SPD1_TXWL */ +#define ARIZONA_SPD1_TXWL_SHIFT 5 /* SPD1_TXWL */ +#define ARIZONA_SPD1_TXWL_WIDTH 3 /* SPD1_TXWL */ +#define ARIZONA_SPD1_MAXWL 0x0010 /* SPD1_MAXWL */ +#define ARIZONA_SPD1_MAXWL_MASK 0x0010 /* SPD1_MAXWL */ +#define ARIZONA_SPD1_MAXWL_SHIFT 4 /* SPD1_MAXWL */ +#define ARIZONA_SPD1_MAXWL_WIDTH 1 /* SPD1_MAXWL */ +#define ARIZONA_SPD1_CS31_30_MASK 0x000C /* SPD1_CS31_30 */ +#define ARIZONA_SPD1_CS31_30_SHIFT 2 /* SPD1_CS31_30 */ +#define ARIZONA_SPD1_CS31_30_WIDTH 2 /* SPD1_CS31_30 */ +#define ARIZONA_SPD1_CLKACU_MASK 0x0003 /* SPD1_CLKACU */ +#define ARIZONA_SPD1_CLKACU_SHIFT 2 /* SPD1_CLKACU */ +#define ARIZONA_SPD1_CLKACU_WIDTH 0 /* SPD1_CLKACU */ + +/* * R1507 (0x5E3) - SLIMbus Framer Ref Gear */ #define ARIZONA_SLIMCLK_SRC 0x0010 /* SLIMCLK_SRC */ @@ -4553,6 +4826,13 @@ #define ARIZONA_GP_DBTIME_WIDTH 4 /* GP_DBTIME - [15:12] */ /* + * R3096 (0xC18) - GP Switch 1 + */ +#define ARIZONA_SW1_MODE_MASK 0x0003 /* SW1_MODE - [1:0] */ +#define ARIZONA_SW1_MODE_SHIFT 0 /* SW1_MODE - [1:0] */ +#define ARIZONA_SW1_MODE_WIDTH 2 /* SW1_MODE - [1:0] */ + +/* * R3104 (0xC20) - Misc Pad Ctrl 1 */ #define ARIZONA_LDO1ENA_PD 0x8000 /* LDO1ENA_PD */ @@ -6292,6 +6572,10 @@ /* * R3366 (0xD26) - Interrupt Raw Status 8 */ +#define ARIZONA_SPDIF_OVERCLOCKED_STS 0x8000 /* SPDIF_OVERCLOCKED_STS */ +#define ARIZONA_SPDIF_OVERCLOCKED_STS_MASK 0x8000 /* SPDIF_OVERCLOCKED_STS */ +#define ARIZONA_SPDIF_OVERCLOCKED_STS_SHIFT 15 /* SPDIF_OVERCLOCKED_STS */ +#define ARIZONA_SPDIF_OVERCLOCKED_STS_WIDTH 1 /* SPDIF_OVERCLOCKED_STS */ #define ARIZONA_AIF3_UNDERCLOCKED_STS 0x0400 /* AIF3_UNDERCLOCKED_STS */ #define ARIZONA_AIF3_UNDERCLOCKED_STS_MASK 0x0400 /* AIF3_UNDERCLOCKED_STS */ #define ARIZONA_AIF3_UNDERCLOCKED_STS_SHIFT 10 /* AIF3_UNDERCLOCKED_STS */ @@ -7777,6 +8061,66 @@ #define ARIZONA_ISRC3_NOTCH_ENA_WIDTH 1 /* ISRC3_NOTCH_ENA */ /* + * R3840 (0xF00) - Clock Control + */ +#define ARIZONA_EXT_NG_SEL_CLR 0x0080 /* EXT_NG_SEL_CLR */ +#define ARIZONA_EXT_NG_SEL_CLR_MASK 0x0080 /* EXT_NG_SEL_CLR */ +#define ARIZONA_EXT_NG_SEL_CLR_SHIFT 7 /* EXT_NG_SEL_CLR */ +#define ARIZONA_EXT_NG_SEL_CLR_WIDTH 1 /* EXT_NG_SEL_CLR */ +#define ARIZONA_EXT_NG_SEL_SET 0x0040 /* EXT_NG_SEL_SET */ +#define ARIZONA_EXT_NG_SEL_SET_MASK 0x0040 /* EXT_NG_SEL_SET */ +#define ARIZONA_EXT_NG_SEL_SET_SHIFT 6 /* EXT_NG_SEL_SET */ +#define ARIZONA_EXT_NG_SEL_SET_WIDTH 1 /* EXT_NG_SEL_SET */ +#define ARIZONA_CLK_R_ENA_CLR 0x0020 /* CLK_R_ENA_CLR */ +#define ARIZONA_CLK_R_ENA_CLR_MASK 0x0020 /* CLK_R_ENA_CLR */ +#define ARIZONA_CLK_R_ENA_CLR_SHIFT 5 /* CLK_R_ENA_CLR */ +#define ARIZONA_CLK_R_ENA_CLR_WIDTH 1 /* CLK_R_ENA_CLR */ +#define ARIZONA_CLK_R_ENA_SET 0x0010 /* CLK_R_ENA_SET */ +#define ARIZONA_CLK_R_ENA_SET_MASK 0x0010 /* CLK_R_ENA_SET */ +#define ARIZONA_CLK_R_ENA_SET_SHIFT 4 /* CLK_R_ENA_SET */ +#define ARIZONA_CLK_R_ENA_SET_WIDTH 1 /* CLK_R_ENA_SET */ +#define ARIZONA_CLK_NG_ENA_CLR 0x0008 /* CLK_NG_ENA_CLR */ +#define ARIZONA_CLK_NG_ENA_CLR_MASK 0x0008 /* CLK_NG_ENA_CLR */ +#define ARIZONA_CLK_NG_ENA_CLR_SHIFT 3 /* CLK_NG_ENA_CLR */ +#define ARIZONA_CLK_NG_ENA_CLR_WIDTH 1 /* CLK_NG_ENA_CLR */ +#define ARIZONA_CLK_NG_ENA_SET 0x0004 /* CLK_NG_ENA_SET */ +#define ARIZONA_CLK_NG_ENA_SET_MASK 0x0004 /* CLK_NG_ENA_SET */ +#define ARIZONA_CLK_NG_ENA_SET_SHIFT 2 /* CLK_NG_ENA_SET */ +#define ARIZONA_CLK_NG_ENA_SET_WIDTH 1 /* CLK_NG_ENA_SET */ +#define ARIZONA_CLK_L_ENA_CLR 0x0002 /* CLK_L_ENA_CLR */ +#define ARIZONA_CLK_L_ENA_CLR_MASK 0x0002 /* CLK_L_ENA_CLR */ +#define ARIZONA_CLK_L_ENA_CLR_SHIFT 1 /* CLK_L_ENA_CLR */ +#define ARIZONA_CLK_L_ENA_CLR_WIDTH 1 /* CLK_L_ENA_CLR */ +#define ARIZONA_CLK_L_ENA_SET 0x0001 /* CLK_L_ENA_SET */ +#define ARIZONA_CLK_L_ENA_SET_MASK 0x0001 /* CLK_L_ENA_SET */ +#define ARIZONA_CLK_L_ENA_SET_SHIFT 0 /* CLK_L_ENA_SET */ +#define ARIZONA_CLK_L_ENA_SET_WIDTH 1 /* CLK_L_ENA_SET */ + +/* + * R3841 (0xF01) - ANC SRC + */ +#define ARIZONA_IN_RXANCR_SEL_MASK 0x0070 /* IN_RXANCR_SEL - [4:6] */ +#define ARIZONA_IN_RXANCR_SEL_SHIFT 4 /* IN_RXANCR_SEL - [4:6] */ +#define ARIZONA_IN_RXANCR_SEL_WIDTH 3 /* IN_RXANCR_SEL - [4:6] */ +#define ARIZONA_IN_RXANCL_SEL_MASK 0x0007 /* IN_RXANCL_SEL - [0:2] */ +#define ARIZONA_IN_RXANCL_SEL_SHIFT 0 /* IN_RXANCL_SEL - [0:2] */ +#define ARIZONA_IN_RXANCL_SEL_WIDTH 3 /* IN_RXANCL_SEL - [0:2] */ + +/* + * R3863 (0xF17) - FCL ADC Reformatter Control + */ +#define ARIZONA_FCL_MIC_MODE_SEL 0x000C /* FCL_MIC_MODE_SEL - [2:3] */ +#define ARIZONA_FCL_MIC_MODE_SEL_SHIFT 2 /* FCL_MIC_MODE_SEL - [2:3] */ +#define ARIZONA_FCL_MIC_MODE_SEL_WIDTH 2 /* FCL_MIC_MODE_SEL - [2:3] */ + +/* + * R3954 (0xF72) - FCR ADC Reformatter Control + */ +#define ARIZONA_FCR_MIC_MODE_SEL 0x000C /* FCR_MIC_MODE_SEL - [2:3] */ +#define ARIZONA_FCR_MIC_MODE_SEL_SHIFT 2 /* FCR_MIC_MODE_SEL - [2:3] */ +#define ARIZONA_FCR_MIC_MODE_SEL_WIDTH 2 /* FCR_MIC_MODE_SEL - [2:3] */ + +/* * R4352 (0x1100) - DSP1 Control 1 */ #define ARIZONA_DSP1_RATE_MASK 0x7800 /* DSP1_RATE - [14:11] */ diff --git a/kernel/include/linux/mfd/axp20x.h b/kernel/include/linux/mfd/axp20x.h index dfabd6db7..b24c771ce 100644 --- a/kernel/include/linux/mfd/axp20x.h +++ b/kernel/include/linux/mfd/axp20x.h @@ -11,9 +11,13 @@ #ifndef __LINUX_MFD_AXP20X_H #define __LINUX_MFD_AXP20X_H +#include <linux/regmap.h> + enum { - AXP202_ID = 0, + AXP152_ID = 0, + AXP202_ID, AXP209_ID, + AXP221_ID, AXP288_ID, NR_AXP20X_VARIANTS, }; @@ -21,6 +25,24 @@ enum { #define AXP20X_DATACACHE(m) (0x04 + (m)) /* Power supply */ +#define AXP152_PWR_OP_MODE 0x01 +#define AXP152_LDO3456_DC1234_CTRL 0x12 +#define AXP152_ALDO_OP_MODE 0x13 +#define AXP152_LDO0_CTRL 0x15 +#define AXP152_DCDC2_V_OUT 0x23 +#define AXP152_DCDC2_V_SCAL 0x25 +#define AXP152_DCDC1_V_OUT 0x26 +#define AXP152_DCDC3_V_OUT 0x27 +#define AXP152_ALDO12_V_OUT 0x28 +#define AXP152_DLDO1_V_OUT 0x29 +#define AXP152_DLDO2_V_OUT 0x2a +#define AXP152_DCDC4_V_OUT 0x2b +#define AXP152_V_OFF 0x31 +#define AXP152_OFF_CTRL 0x32 +#define AXP152_PEK_KEY 0x36 +#define AXP152_DCDC_FREQ 0x37 +#define AXP152_DCDC_MODE 0x80 + #define AXP20X_PWR_INPUT_STATUS 0x00 #define AXP20X_PWR_OP_MODE 0x01 #define AXP20X_USB_OTG_STATUS 0x02 @@ -45,7 +67,36 @@ enum { #define AXP20X_V_LTF_DISCHRG 0x3c #define AXP20X_V_HTF_DISCHRG 0x3d +#define AXP22X_PWR_OUT_CTRL1 0x10 +#define AXP22X_PWR_OUT_CTRL2 0x12 +#define AXP22X_PWR_OUT_CTRL3 0x13 +#define AXP22X_DLDO1_V_OUT 0x15 +#define AXP22X_DLDO2_V_OUT 0x16 +#define AXP22X_DLDO3_V_OUT 0x17 +#define AXP22X_DLDO4_V_OUT 0x18 +#define AXP22X_ELDO1_V_OUT 0x19 +#define AXP22X_ELDO2_V_OUT 0x1a +#define AXP22X_ELDO3_V_OUT 0x1b +#define AXP22X_DC5LDO_V_OUT 0x1c +#define AXP22X_DCDC1_V_OUT 0x21 +#define AXP22X_DCDC2_V_OUT 0x22 +#define AXP22X_DCDC3_V_OUT 0x23 +#define AXP22X_DCDC4_V_OUT 0x24 +#define AXP22X_DCDC5_V_OUT 0x25 +#define AXP22X_DCDC23_V_RAMP_CTRL 0x27 +#define AXP22X_ALDO1_V_OUT 0x28 +#define AXP22X_ALDO2_V_OUT 0x29 +#define AXP22X_ALDO3_V_OUT 0x2a +#define AXP22X_CHRG_CTRL3 0x35 + /* Interrupt */ +#define AXP152_IRQ1_EN 0x40 +#define AXP152_IRQ2_EN 0x41 +#define AXP152_IRQ3_EN 0x42 +#define AXP152_IRQ1_STATE 0x48 +#define AXP152_IRQ2_STATE 0x49 +#define AXP152_IRQ3_STATE 0x4a + #define AXP20X_IRQ1_EN 0x40 #define AXP20X_IRQ2_EN 0x41 #define AXP20X_IRQ3_EN 0x42 @@ -100,7 +151,23 @@ enum { #define AXP20X_VBUS_MON 0x8b #define AXP20X_OVER_TMP 0x8f +#define AXP22X_PWREN_CTRL1 0x8c +#define AXP22X_PWREN_CTRL2 0x8d + /* GPIO */ +#define AXP152_GPIO0_CTRL 0x90 +#define AXP152_GPIO1_CTRL 0x91 +#define AXP152_GPIO2_CTRL 0x92 +#define AXP152_GPIO3_CTRL 0x93 +#define AXP152_LDOGPIO2_V_OUT 0x96 +#define AXP152_GPIO_INPUT 0x97 +#define AXP152_PWM0_FREQ_X 0x98 +#define AXP152_PWM0_FREQ_Y 0x99 +#define AXP152_PWM0_DUTY_CYCLE 0x9a +#define AXP152_PWM1_FREQ_X 0x9b +#define AXP152_PWM1_FREQ_Y 0x9c +#define AXP152_PWM1_DUTY_CYCLE 0x9d + #define AXP20X_GPIO0_CTRL 0x90 #define AXP20X_LDO5_V_OUT 0x91 #define AXP20X_GPIO1_CTRL 0x92 @@ -108,6 +175,11 @@ enum { #define AXP20X_GPIO20_SS 0x94 #define AXP20X_GPIO3_CTRL 0x95 +#define AXP22X_LDO_IO0_V_OUT 0x91 +#define AXP22X_LDO_IO1_V_OUT 0x93 +#define AXP22X_GPIO_STATE 0x94 +#define AXP22X_GPIO_PULL_DOWN 0x95 + /* Battery */ #define AXP20X_CHRG_CC_31_24 0xb0 #define AXP20X_CHRG_CC_23_16 0xb1 @@ -120,6 +192,15 @@ enum { #define AXP20X_CC_CTRL 0xb8 #define AXP20X_FG_RES 0xb9 +/* OCV */ +#define AXP20X_RDC_H 0xba +#define AXP20X_RDC_L 0xbb +#define AXP20X_OCV(m) (0xc0 + (m)) +#define AXP20X_OCV_MAX 0xf + +/* AXP22X specific registers */ +#define AXP22X_BATLOW_THRES1 0xe6 + /* AXP288 specific registers */ #define AXP288_PMIC_ADC_H 0x56 #define AXP288_PMIC_ADC_L 0x57 @@ -158,8 +239,52 @@ enum { AXP20X_REG_ID_MAX, }; +enum { + AXP22X_DCDC1 = 0, + AXP22X_DCDC2, + AXP22X_DCDC3, + AXP22X_DCDC4, + AXP22X_DCDC5, + AXP22X_DC1SW, + AXP22X_DC5LDO, + AXP22X_ALDO1, + AXP22X_ALDO2, + AXP22X_ALDO3, + AXP22X_ELDO1, + AXP22X_ELDO2, + AXP22X_ELDO3, + AXP22X_DLDO1, + AXP22X_DLDO2, + AXP22X_DLDO3, + AXP22X_DLDO4, + AXP22X_RTC_LDO, + AXP22X_LDO_IO0, + AXP22X_LDO_IO1, + AXP22X_REG_ID_MAX, +}; + /* IRQs */ enum { + AXP152_IRQ_LDO0IN_CONNECT = 1, + AXP152_IRQ_LDO0IN_REMOVAL, + AXP152_IRQ_ALDO0IN_CONNECT, + AXP152_IRQ_ALDO0IN_REMOVAL, + AXP152_IRQ_DCDC1_V_LOW, + AXP152_IRQ_DCDC2_V_LOW, + AXP152_IRQ_DCDC3_V_LOW, + AXP152_IRQ_DCDC4_V_LOW, + AXP152_IRQ_PEK_SHORT, + AXP152_IRQ_PEK_LONG, + AXP152_IRQ_TIMER, + AXP152_IRQ_PEK_RIS_EDGE, + AXP152_IRQ_PEK_FAL_EDGE, + AXP152_IRQ_GPIO3_INPUT, + AXP152_IRQ_GPIO2_INPUT, + AXP152_IRQ_GPIO1_INPUT, + AXP152_IRQ_GPIO0_INPUT, +}; + +enum { AXP20X_IRQ_ACIN_OVER_V = 1, AXP20X_IRQ_ACIN_PLUGIN, AXP20X_IRQ_ACIN_REMOVAL, @@ -199,6 +324,34 @@ enum { AXP20X_IRQ_GPIO0_INPUT, }; +enum axp22x_irqs { + AXP22X_IRQ_ACIN_OVER_V = 1, + AXP22X_IRQ_ACIN_PLUGIN, + AXP22X_IRQ_ACIN_REMOVAL, + AXP22X_IRQ_VBUS_OVER_V, + AXP22X_IRQ_VBUS_PLUGIN, + AXP22X_IRQ_VBUS_REMOVAL, + AXP22X_IRQ_VBUS_V_LOW, + AXP22X_IRQ_BATT_PLUGIN, + AXP22X_IRQ_BATT_REMOVAL, + AXP22X_IRQ_BATT_ENT_ACT_MODE, + AXP22X_IRQ_BATT_EXIT_ACT_MODE, + AXP22X_IRQ_CHARG, + AXP22X_IRQ_CHARG_DONE, + AXP22X_IRQ_BATT_TEMP_HIGH, + AXP22X_IRQ_BATT_TEMP_LOW, + AXP22X_IRQ_DIE_TEMP_HIGH, + AXP22X_IRQ_PEK_SHORT, + AXP22X_IRQ_PEK_LONG, + AXP22X_IRQ_LOW_PWR_LVL1, + AXP22X_IRQ_LOW_PWR_LVL2, + AXP22X_IRQ_TIMER, + AXP22X_IRQ_PEK_RIS_EDGE, + AXP22X_IRQ_PEK_FAL_EDGE, + AXP22X_IRQ_GPIO1_INPUT, + AXP22X_IRQ_GPIO0_INPUT, +}; + enum axp288_irqs { AXP288_IRQ_VBUS_FALL = 2, AXP288_IRQ_VBUS_RISE, @@ -275,4 +428,38 @@ struct axp20x_fg_pdata { int thermistor_curve[MAX_THERM_CURVE_SIZE][2]; }; +struct axp20x_chrg_pdata { + int max_cc; + int max_cv; + int def_cc; + int def_cv; +}; + +struct axp288_extcon_pdata { + /* GPIO pin control to switch D+/D- lines b/w PMIC and SOC */ + struct gpio_desc *gpio_mux_cntl; +}; + +/* generic helper function for reading 9-16 bit wide regs */ +static inline int axp20x_read_variable_width(struct regmap *regmap, + unsigned int reg, unsigned int width) +{ + unsigned int reg_val, result; + int err; + + err = regmap_read(regmap, reg, ®_val); + if (err) + return err; + + result = reg_val << (width - 8); + + err = regmap_read(regmap, reg + 1, ®_val); + if (err) + return err; + + result |= reg_val; + + return result; +} + #endif /* __LINUX_MFD_AXP20X_H */ diff --git a/kernel/include/linux/mfd/core.h b/kernel/include/linux/mfd/core.h index a76bc100b..27dac3ff1 100644 --- a/kernel/include/linux/mfd/core.h +++ b/kernel/include/linux/mfd/core.h @@ -18,6 +18,12 @@ struct irq_domain; +/* Matches ACPI PNP id, either _HID or _CID, or ACPI _ADR */ +struct mfd_cell_acpi_match { + const char *pnpid; + const unsigned long long adr; +}; + /* * This struct describes the MFD part ("cell"). * After registration the copy of this structure will become the platform data @@ -44,8 +50,8 @@ struct mfd_cell { */ const char *of_compatible; - /* Matches ACPI PNP id, either _HID or _CID */ - const char *acpi_pnpid; + /* Matches ACPI */ + const struct mfd_cell_acpi_match *acpi_match; /* * These resources can be specified relative to the parent device. diff --git a/kernel/include/linux/mfd/cros_ec.h b/kernel/include/linux/mfd/cros_ec.h index 324a34683..494682ce4 100644 --- a/kernel/include/linux/mfd/cros_ec.h +++ b/kernel/include/linux/mfd/cros_ec.h @@ -17,10 +17,29 @@ #define __LINUX_MFD_CROS_EC_H #include <linux/cdev.h> +#include <linux/device.h> #include <linux/notifier.h> #include <linux/mfd/cros_ec_commands.h> #include <linux/mutex.h> +#define CROS_EC_DEV_NAME "cros_ec" +#define CROS_EC_DEV_PD_NAME "cros_pd" + +/* + * The EC is unresponsive for a time after a reboot command. Add a + * simple delay to make sure that the bus stays locked. + */ +#define EC_REBOOT_DELAY_MS 50 + +/* + * Max bus-specific overhead incurred by request/responses. + * I2C requires 1 additional byte for requests. + * I2C requires 2 additional bytes for responses. + * */ +#define EC_PROTO_VERSION_UNKNOWN 0 +#define EC_MAX_REQUEST_OVERHEAD 1 +#define EC_MAX_RESPONSE_OVERHEAD 2 + /* * Command interface between EC and AP, for LPC, I2C and SPI interfaces. */ @@ -42,8 +61,7 @@ enum { * @outsize: Outgoing length in bytes * @insize: Max number of bytes to accept from EC * @result: EC's response to the command (separate from communication failure) - * @outdata: Outgoing data to EC - * @indata: Where to put the incoming data from EC + * @data: Where to put the incoming data from EC and outgoing data to EC */ struct cros_ec_command { uint32_t version; @@ -51,18 +69,14 @@ struct cros_ec_command { uint32_t outsize; uint32_t insize; uint32_t result; - uint8_t outdata[EC_PROTO2_MAX_PARAM_SIZE]; - uint8_t indata[EC_PROTO2_MAX_PARAM_SIZE]; + uint8_t data[0]; }; /** * struct cros_ec_device - Information about a ChromeOS EC device * - * @ec_name: name of EC device (e.g. 'chromeos-ec') * @phys_name: name of physical comms layer (e.g. 'i2c-4') * @dev: Device pointer for physical comms device - * @vdev: Device pointer for virtual comms device - * @cdev: Character device structure for virtual comms device * @was_wake_device: true if this device was set to wake the system from * sleep at the last suspend * @cmd_readmem: direct read of the EC memory-mapped region, if supported @@ -74,6 +88,7 @@ struct cros_ec_command { * * @priv: Private data * @irq: Interrupt to use + * @id: Device id * @din: input buffer (for data from EC) * @dout: output buffer (for data to EC) * \note @@ -85,41 +100,72 @@ struct cros_ec_command { * to using dword. * @din_size: size of din buffer to allocate (zero to use static din) * @dout_size: size of dout buffer to allocate (zero to use static dout) - * @parent: pointer to parent device (e.g. i2c or spi device) * @wake_enabled: true if this device can wake the system from sleep * @cmd_xfer: send command to EC and get response * Returns the number of bytes received if the communication succeeded, but * that doesn't mean the EC was happy with the command. The caller * should check msg.result for the EC's result code. + * @pkt_xfer: send packet to EC and get response * @lock: one transaction at a time */ struct cros_ec_device { /* These are used by other drivers that want to talk to the EC */ - const char *ec_name; const char *phys_name; struct device *dev; - struct device *vdev; - struct cdev cdev; bool was_wake_device; struct class *cros_class; int (*cmd_readmem)(struct cros_ec_device *ec, unsigned int offset, unsigned int bytes, void *dest); /* These are used to implement the platform-specific interface */ + u16 max_request; + u16 max_response; + u16 max_passthru; + u16 proto_version; void *priv; int irq; - uint8_t *din; - uint8_t *dout; + u8 *din; + u8 *dout; int din_size; int dout_size; - struct device *parent; bool wake_enabled; int (*cmd_xfer)(struct cros_ec_device *ec, struct cros_ec_command *msg); + int (*pkt_xfer)(struct cros_ec_device *ec, + struct cros_ec_command *msg); struct mutex lock; }; +/* struct cros_ec_platform - ChromeOS EC platform information + * + * @ec_name: name of EC device (e.g. 'cros-ec', 'cros-pd', ...) + * used in /dev/ and sysfs. + * @cmd_offset: offset to apply for each command. Set when + * registering a devicde behind another one. + */ +struct cros_ec_platform { + const char *ec_name; + u16 cmd_offset; +}; + +/* + * struct cros_ec_dev - ChromeOS EC device entry point + * + * @class_dev: Device structure used in sysfs + * @cdev: Character device structure in /dev + * @ec_dev: cros_ec_device structure to talk to the physical device + * @dev: pointer to the platform device + * @cmd_offset: offset to apply for each command. + */ +struct cros_ec_dev { + struct device class_dev; + struct cdev cdev; + struct cros_ec_device *ec_dev; + struct device *dev; + u16 cmd_offset; +}; + /** * cros_ec_suspend - Handle a suspend operation for the ChromeOS EC device * @@ -198,4 +244,17 @@ int cros_ec_remove(struct cros_ec_device *ec_dev); */ int cros_ec_register(struct cros_ec_device *ec_dev); +/** + * cros_ec_register - Query the protocol version supported by the ChromeOS EC + * + * @ec_dev: Device to register + * @return 0 if ok, -ve on error + */ +int cros_ec_query_all(struct cros_ec_device *ec_dev); + +/* sysfs stuff */ +extern struct attribute_group cros_ec_attr_group; +extern struct attribute_group cros_ec_lightbar_attr_group; +extern struct attribute_group cros_ec_vbc_attr_group; + #endif /* __LINUX_MFD_CROS_EC_H */ diff --git a/kernel/include/linux/mfd/cros_ec_commands.h b/kernel/include/linux/mfd/cros_ec_commands.h index a49cd41fe..13b630c10 100644 --- a/kernel/include/linux/mfd/cros_ec_commands.h +++ b/kernel/include/linux/mfd/cros_ec_commands.h @@ -515,7 +515,7 @@ struct ec_host_response { /* * Notes on commands: * - * Each command is an 8-byte command value. Commands which take params or + * Each command is an 16-bit command value. Commands which take params or * return response data specify structs for that data. If no struct is * specified, the command does not input or output data, respectively. * Parameter/response length is implicit in the structs. Some underlying @@ -966,7 +966,7 @@ struct rgb_s { /* List of tweakable parameters. NOTE: It's __packed so it can be sent in a * host command, but the alignment is the same regardless. Keep it that way. */ -struct lightbar_params { +struct lightbar_params_v0 { /* Timing */ int32_t google_ramp_up; int32_t google_ramp_down; @@ -1000,32 +1000,81 @@ struct lightbar_params { struct rgb_s color[8]; /* 0-3 are Google colors */ } __packed; +struct lightbar_params_v1 { + /* Timing */ + int32_t google_ramp_up; + int32_t google_ramp_down; + int32_t s3s0_ramp_up; + int32_t s0_tick_delay[2]; /* AC=0/1 */ + int32_t s0a_tick_delay[2]; /* AC=0/1 */ + int32_t s0s3_ramp_down; + int32_t s3_sleep_for; + int32_t s3_ramp_up; + int32_t s3_ramp_down; + int32_t tap_tick_delay; + int32_t tap_display_time; + + /* Tap-for-battery params */ + uint8_t tap_pct_red; + uint8_t tap_pct_green; + uint8_t tap_seg_min_on; + uint8_t tap_seg_max_on; + uint8_t tap_seg_osc; + uint8_t tap_idx[3]; + + /* Oscillation */ + uint8_t osc_min[2]; /* AC=0/1 */ + uint8_t osc_max[2]; /* AC=0/1 */ + uint8_t w_ofs[2]; /* AC=0/1 */ + + /* Brightness limits based on the backlight and AC. */ + uint8_t bright_bl_off_fixed[2]; /* AC=0/1 */ + uint8_t bright_bl_on_min[2]; /* AC=0/1 */ + uint8_t bright_bl_on_max[2]; /* AC=0/1 */ + + /* Battery level thresholds */ + uint8_t battery_threshold[LB_BATTERY_LEVELS - 1]; + + /* Map [AC][battery_level] to color index */ + uint8_t s0_idx[2][LB_BATTERY_LEVELS]; /* AP is running */ + uint8_t s3_idx[2][LB_BATTERY_LEVELS]; /* AP is sleeping */ + + /* Color palette */ + struct rgb_s color[8]; /* 0-3 are Google colors */ +} __packed; + struct ec_params_lightbar { uint8_t cmd; /* Command (see enum lightbar_command) */ union { struct { /* no args */ - } dump, off, on, init, get_seq, get_params, version; + } dump, off, on, init, get_seq, get_params_v0, get_params_v1, + version, get_brightness, get_demo; - struct num { + struct { uint8_t num; - } brightness, seq, demo; + } set_brightness, seq, demo; - struct reg { + struct { uint8_t ctrl, reg, value; } reg; - struct rgb { + struct { uint8_t led, red, green, blue; - } rgb; + } set_rgb; + + struct { + uint8_t led; + } get_rgb; - struct lightbar_params set_params; + struct lightbar_params_v0 set_params_v0; + struct lightbar_params_v1 set_params_v1; }; } __packed; struct ec_response_lightbar { union { - struct dump { + struct { struct { uint8_t reg; uint8_t ic0; @@ -1033,20 +1082,26 @@ struct ec_response_lightbar { } vals[23]; } dump; - struct get_seq { + struct { uint8_t num; - } get_seq; + } get_seq, get_brightness, get_demo; - struct lightbar_params get_params; + struct lightbar_params_v0 get_params_v0; + struct lightbar_params_v1 get_params_v1; - struct version { + struct { uint32_t num; uint32_t flags; } version; struct { + uint8_t red, green, blue; + } get_rgb; + + struct { /* no return params */ - } off, on, init, brightness, seq, reg, rgb, demo, set_params; + } off, on, init, set_brightness, seq, reg, set_rgb, + demo, set_params_v0, set_params_v1; }; } __packed; @@ -1056,15 +1111,20 @@ enum lightbar_command { LIGHTBAR_CMD_OFF = 1, LIGHTBAR_CMD_ON = 2, LIGHTBAR_CMD_INIT = 3, - LIGHTBAR_CMD_BRIGHTNESS = 4, + LIGHTBAR_CMD_SET_BRIGHTNESS = 4, LIGHTBAR_CMD_SEQ = 5, LIGHTBAR_CMD_REG = 6, - LIGHTBAR_CMD_RGB = 7, + LIGHTBAR_CMD_SET_RGB = 7, LIGHTBAR_CMD_GET_SEQ = 8, LIGHTBAR_CMD_DEMO = 9, - LIGHTBAR_CMD_GET_PARAMS = 10, - LIGHTBAR_CMD_SET_PARAMS = 11, + LIGHTBAR_CMD_GET_PARAMS_V0 = 10, + LIGHTBAR_CMD_SET_PARAMS_V0 = 11, LIGHTBAR_CMD_VERSION = 12, + LIGHTBAR_CMD_GET_BRIGHTNESS = 13, + LIGHTBAR_CMD_GET_RGB = 14, + LIGHTBAR_CMD_GET_DEMO = 15, + LIGHTBAR_CMD_GET_PARAMS_V1 = 16, + LIGHTBAR_CMD_SET_PARAMS_V1 = 17, LIGHTBAR_NUM_CMDS }; @@ -1421,8 +1481,40 @@ struct ec_response_rtc { /*****************************************************************************/ /* Port80 log access */ +/* Maximum entries that can be read/written in a single command */ +#define EC_PORT80_SIZE_MAX 32 + /* Get last port80 code from previous boot */ #define EC_CMD_PORT80_LAST_BOOT 0x48 +#define EC_CMD_PORT80_READ 0x48 + +enum ec_port80_subcmd { + EC_PORT80_GET_INFO = 0, + EC_PORT80_READ_BUFFER, +}; + +struct ec_params_port80_read { + uint16_t subcmd; + union { + struct { + uint32_t offset; + uint32_t num_entries; + } read_buffer; + }; +} __packed; + +struct ec_response_port80_read { + union { + struct { + uint32_t writes; + uint32_t history_size; + uint32_t last_boot; + } get_info; + struct { + uint16_t codes[EC_PORT80_SIZE_MAX]; + } data; + }; +} __packed; struct ec_response_port80_last_boot { uint16_t code; @@ -1782,6 +1874,7 @@ struct ec_params_gpio_set { /* Get GPIO value */ #define EC_CMD_GPIO_GET 0x93 +/* Version 0 of input params and response */ struct ec_params_gpio_get { char name[32]; } __packed; @@ -1789,6 +1882,38 @@ struct ec_response_gpio_get { uint8_t val; } __packed; +/* Version 1 of input params and response */ +struct ec_params_gpio_get_v1 { + uint8_t subcmd; + union { + struct { + char name[32]; + } get_value_by_name; + struct { + uint8_t index; + } get_info; + }; +} __packed; + +struct ec_response_gpio_get_v1 { + union { + struct { + uint8_t val; + } get_value_by_name, get_count; + struct { + uint8_t val; + char name[32]; + uint32_t flags; + } get_info; + }; +} __packed; + +enum gpio_get_subcmd { + EC_GPIO_GET_BY_NAME = 0, + EC_GPIO_GET_COUNT = 1, + EC_GPIO_GET_INFO = 2, +}; + /*****************************************************************************/ /* I2C commands. Only available when flash write protect is unlocked. */ @@ -1857,13 +1982,21 @@ struct ec_params_charge_control { /*****************************************************************************/ /* - * Cut off battery power output if the battery supports. + * Cut off battery power immediately or after the host has shut down. * - * For unsupported battery, just don't implement this command and lets EC - * return EC_RES_INVALID_COMMAND. + * return EC_RES_INVALID_COMMAND if unsupported by a board/battery. + * EC_RES_SUCCESS if the command was successful. + * EC_RES_ERROR if the cut off command failed. */ + #define EC_CMD_BATTERY_CUT_OFF 0x99 +#define EC_BATTERY_CUTOFF_FLAG_AT_SHUTDOWN (1 << 0) + +struct ec_params_battery_cutoff { + uint8_t flags; +} __packed; + /*****************************************************************************/ /* USB port mux control. */ @@ -2142,6 +2275,32 @@ struct ec_params_sb_wr_block { } __packed; /*****************************************************************************/ +/* Battery vendor parameters + * + * Get or set vendor-specific parameters in the battery. Implementations may + * differ between boards or batteries. On a set operation, the response + * contains the actual value set, which may be rounded or clipped from the + * requested value. + */ + +#define EC_CMD_BATTERY_VENDOR_PARAM 0xb4 + +enum ec_battery_vendor_param_mode { + BATTERY_VENDOR_PARAM_MODE_GET = 0, + BATTERY_VENDOR_PARAM_MODE_SET, +}; + +struct ec_params_battery_vendor_param { + uint32_t param; + uint32_t value; + uint8_t mode; +} __packed; + +struct ec_response_battery_vendor_param { + uint32_t value; +} __packed; + +/*****************************************************************************/ /* System commands */ /* @@ -2338,6 +2497,80 @@ struct ec_params_reboot_ec { /*****************************************************************************/ /* + * PD commands + * + * These commands are for PD MCU communication. + */ + +/* EC to PD MCU exchange status command */ +#define EC_CMD_PD_EXCHANGE_STATUS 0x100 + +/* Status of EC being sent to PD */ +struct ec_params_pd_status { + int8_t batt_soc; /* battery state of charge */ +} __packed; + +/* Status of PD being sent back to EC */ +struct ec_response_pd_status { + int8_t status; /* PD MCU status */ + uint32_t curr_lim_ma; /* input current limit */ +} __packed; + +/* Set USB type-C port role and muxes */ +#define EC_CMD_USB_PD_CONTROL 0x101 + +enum usb_pd_control_role { + USB_PD_CTRL_ROLE_NO_CHANGE = 0, + USB_PD_CTRL_ROLE_TOGGLE_ON = 1, /* == AUTO */ + USB_PD_CTRL_ROLE_TOGGLE_OFF = 2, + USB_PD_CTRL_ROLE_FORCE_SINK = 3, + USB_PD_CTRL_ROLE_FORCE_SOURCE = 4, +}; + +enum usb_pd_control_mux { + USB_PD_CTRL_MUX_NO_CHANGE = 0, + USB_PD_CTRL_MUX_NONE = 1, + USB_PD_CTRL_MUX_USB = 2, + USB_PD_CTRL_MUX_DP = 3, + USB_PD_CTRL_MUX_DOCK = 4, + USB_PD_CTRL_MUX_AUTO = 5, +}; + +struct ec_params_usb_pd_control { + uint8_t port; + uint8_t role; + uint8_t mux; +} __packed; + +/*****************************************************************************/ +/* + * Passthru commands + * + * Some platforms have sub-processors chained to each other. For example. + * + * AP <--> EC <--> PD MCU + * + * The top 2 bits of the command number are used to indicate which device the + * command is intended for. Device 0 is always the device receiving the + * command; other device mapping is board-specific. + * + * When a device receives a command to be passed to a sub-processor, it passes + * it on with the device number set back to 0. This allows the sub-processor + * to remain blissfully unaware of whether the command originated on the next + * device up the chain, or was passed through from the AP. + * + * In the above example, if the AP wants to send command 0x0002 to the PD MCU, + * AP sends command 0x4002 to the EC + * EC sends command 0x0002 to the PD MCU + * EC forwards PD MCU response back to the AP + */ + +/* Offset and max command number for sub-device n */ +#define EC_CMD_PASSTHRU_OFFSET(n) (0x4000 * (n)) +#define EC_CMD_PASSTHRU_MAX(n) (EC_CMD_PASSTHRU_OFFSET(n) + 0x3fff) + +/*****************************************************************************/ +/* * Deprecated constants. These constants have been renamed for clarity. The * meaning and size has not changed. Programs that use the old names should * switch to the new names soon, as the old names may not be carried forward diff --git a/kernel/include/linux/mfd/da9052/reg.h b/kernel/include/linux/mfd/da9052/reg.h index c4dd3a8ad..5010f9787 100644 --- a/kernel/include/linux/mfd/da9052/reg.h +++ b/kernel/include/linux/mfd/da9052/reg.h @@ -65,6 +65,9 @@ #define DA9052_GPIO_2_3_REG 22 #define DA9052_GPIO_4_5_REG 23 #define DA9052_GPIO_6_7_REG 24 +#define DA9052_GPIO_8_9_REG 25 +#define DA9052_GPIO_10_11_REG 26 +#define DA9052_GPIO_12_13_REG 27 #define DA9052_GPIO_14_15_REG 28 /* POWER SEQUENCER CONTROL REGISTERS */ diff --git a/kernel/include/linux/mfd/da9055/core.h b/kernel/include/linux/mfd/da9055/core.h index 956afa445..5dc743fd6 100644 --- a/kernel/include/linux/mfd/da9055/core.h +++ b/kernel/include/linux/mfd/da9055/core.h @@ -89,6 +89,6 @@ static inline int da9055_reg_update(struct da9055 *da9055, unsigned char reg, int da9055_device_init(struct da9055 *da9055); void da9055_device_exit(struct da9055 *da9055); -extern struct regmap_config da9055_regmap_config; +extern const struct regmap_config da9055_regmap_config; #endif /* __DA9055_CORE_H */ diff --git a/kernel/include/linux/mfd/da9062/core.h b/kernel/include/linux/mfd/da9062/core.h new file mode 100644 index 000000000..376ba8436 --- /dev/null +++ b/kernel/include/linux/mfd/da9062/core.h @@ -0,0 +1,50 @@ +/* + * Copyright (C) 2015 Dialog Semiconductor Ltd. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version 2 + * of the License, or (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef __MFD_DA9062_CORE_H__ +#define __MFD_DA9062_CORE_H__ + +#include <linux/interrupt.h> +#include <linux/mfd/da9062/registers.h> + +/* Interrupts */ +enum da9062_irqs { + /* IRQ A */ + DA9062_IRQ_ONKEY, + DA9062_IRQ_ALARM, + DA9062_IRQ_TICK, + DA9062_IRQ_WDG_WARN, + DA9062_IRQ_SEQ_RDY, + /* IRQ B*/ + DA9062_IRQ_TEMP, + DA9062_IRQ_LDO_LIM, + DA9062_IRQ_DVC_RDY, + DA9062_IRQ_VDD_WARN, + /* IRQ C */ + DA9062_IRQ_GPI0, + DA9062_IRQ_GPI1, + DA9062_IRQ_GPI2, + DA9062_IRQ_GPI3, + DA9062_IRQ_GPI4, + + DA9062_NUM_IRQ, +}; + +struct da9062 { + struct device *dev; + struct regmap *regmap; + struct regmap_irq_chip_data *regmap_irq; +}; + +#endif /* __MFD_DA9062_CORE_H__ */ diff --git a/kernel/include/linux/mfd/da9062/registers.h b/kernel/include/linux/mfd/da9062/registers.h new file mode 100644 index 000000000..97790d1b0 --- /dev/null +++ b/kernel/include/linux/mfd/da9062/registers.h @@ -0,0 +1,1108 @@ +/* + * registers.h - REGISTERS H for DA9062 + * Copyright (C) 2015 Dialog Semiconductor Ltd. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version 2 + * of the License, or (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef __DA9062_H__ +#define __DA9062_H__ + +#define DA9062_PMIC_DEVICE_ID 0x62 +#define DA9062_PMIC_VARIANT_MRC_AA 0x01 + +#define DA9062_I2C_PAGE_SEL_SHIFT 1 + +/* + * Registers + */ + +#define DA9062AA_PAGE_CON 0x000 +#define DA9062AA_STATUS_A 0x001 +#define DA9062AA_STATUS_B 0x002 +#define DA9062AA_STATUS_D 0x004 +#define DA9062AA_FAULT_LOG 0x005 +#define DA9062AA_EVENT_A 0x006 +#define DA9062AA_EVENT_B 0x007 +#define DA9062AA_EVENT_C 0x008 +#define DA9062AA_IRQ_MASK_A 0x00A +#define DA9062AA_IRQ_MASK_B 0x00B +#define DA9062AA_IRQ_MASK_C 0x00C +#define DA9062AA_CONTROL_A 0x00E +#define DA9062AA_CONTROL_B 0x00F +#define DA9062AA_CONTROL_C 0x010 +#define DA9062AA_CONTROL_D 0x011 +#define DA9062AA_CONTROL_E 0x012 +#define DA9062AA_CONTROL_F 0x013 +#define DA9062AA_PD_DIS 0x014 +#define DA9062AA_GPIO_0_1 0x015 +#define DA9062AA_GPIO_2_3 0x016 +#define DA9062AA_GPIO_4 0x017 +#define DA9062AA_GPIO_WKUP_MODE 0x01C +#define DA9062AA_GPIO_MODE0_4 0x01D +#define DA9062AA_GPIO_OUT0_2 0x01E +#define DA9062AA_GPIO_OUT3_4 0x01F +#define DA9062AA_BUCK2_CONT 0x020 +#define DA9062AA_BUCK1_CONT 0x021 +#define DA9062AA_BUCK4_CONT 0x022 +#define DA9062AA_BUCK3_CONT 0x024 +#define DA9062AA_LDO1_CONT 0x026 +#define DA9062AA_LDO2_CONT 0x027 +#define DA9062AA_LDO3_CONT 0x028 +#define DA9062AA_LDO4_CONT 0x029 +#define DA9062AA_DVC_1 0x032 +#define DA9062AA_COUNT_S 0x040 +#define DA9062AA_COUNT_MI 0x041 +#define DA9062AA_COUNT_H 0x042 +#define DA9062AA_COUNT_D 0x043 +#define DA9062AA_COUNT_MO 0x044 +#define DA9062AA_COUNT_Y 0x045 +#define DA9062AA_ALARM_S 0x046 +#define DA9062AA_ALARM_MI 0x047 +#define DA9062AA_ALARM_H 0x048 +#define DA9062AA_ALARM_D 0x049 +#define DA9062AA_ALARM_MO 0x04A +#define DA9062AA_ALARM_Y 0x04B +#define DA9062AA_SECOND_A 0x04C +#define DA9062AA_SECOND_B 0x04D +#define DA9062AA_SECOND_C 0x04E +#define DA9062AA_SECOND_D 0x04F +#define DA9062AA_SEQ 0x081 +#define DA9062AA_SEQ_TIMER 0x082 +#define DA9062AA_ID_2_1 0x083 +#define DA9062AA_ID_4_3 0x084 +#define DA9062AA_ID_12_11 0x088 +#define DA9062AA_ID_14_13 0x089 +#define DA9062AA_ID_16_15 0x08A +#define DA9062AA_ID_22_21 0x08D +#define DA9062AA_ID_24_23 0x08E +#define DA9062AA_ID_26_25 0x08F +#define DA9062AA_ID_28_27 0x090 +#define DA9062AA_ID_30_29 0x091 +#define DA9062AA_ID_32_31 0x092 +#define DA9062AA_SEQ_A 0x095 +#define DA9062AA_SEQ_B 0x096 +#define DA9062AA_WAIT 0x097 +#define DA9062AA_EN_32K 0x098 +#define DA9062AA_RESET 0x099 +#define DA9062AA_BUCK_ILIM_A 0x09A +#define DA9062AA_BUCK_ILIM_B 0x09B +#define DA9062AA_BUCK_ILIM_C 0x09C +#define DA9062AA_BUCK2_CFG 0x09D +#define DA9062AA_BUCK1_CFG 0x09E +#define DA9062AA_BUCK4_CFG 0x09F +#define DA9062AA_BUCK3_CFG 0x0A0 +#define DA9062AA_VBUCK2_A 0x0A3 +#define DA9062AA_VBUCK1_A 0x0A4 +#define DA9062AA_VBUCK4_A 0x0A5 +#define DA9062AA_VBUCK3_A 0x0A7 +#define DA9062AA_VLDO1_A 0x0A9 +#define DA9062AA_VLDO2_A 0x0AA +#define DA9062AA_VLDO3_A 0x0AB +#define DA9062AA_VLDO4_A 0x0AC +#define DA9062AA_VBUCK2_B 0x0B4 +#define DA9062AA_VBUCK1_B 0x0B5 +#define DA9062AA_VBUCK4_B 0x0B6 +#define DA9062AA_VBUCK3_B 0x0B8 +#define DA9062AA_VLDO1_B 0x0BA +#define DA9062AA_VLDO2_B 0x0BB +#define DA9062AA_VLDO3_B 0x0BC +#define DA9062AA_VLDO4_B 0x0BD +#define DA9062AA_BBAT_CONT 0x0C5 +#define DA9062AA_INTERFACE 0x105 +#define DA9062AA_CONFIG_A 0x106 +#define DA9062AA_CONFIG_B 0x107 +#define DA9062AA_CONFIG_C 0x108 +#define DA9062AA_CONFIG_D 0x109 +#define DA9062AA_CONFIG_E 0x10A +#define DA9062AA_CONFIG_G 0x10C +#define DA9062AA_CONFIG_H 0x10D +#define DA9062AA_CONFIG_I 0x10E +#define DA9062AA_CONFIG_J 0x10F +#define DA9062AA_CONFIG_K 0x110 +#define DA9062AA_CONFIG_M 0x112 +#define DA9062AA_TRIM_CLDR 0x120 +#define DA9062AA_GP_ID_0 0x121 +#define DA9062AA_GP_ID_1 0x122 +#define DA9062AA_GP_ID_2 0x123 +#define DA9062AA_GP_ID_3 0x124 +#define DA9062AA_GP_ID_4 0x125 +#define DA9062AA_GP_ID_5 0x126 +#define DA9062AA_GP_ID_6 0x127 +#define DA9062AA_GP_ID_7 0x128 +#define DA9062AA_GP_ID_8 0x129 +#define DA9062AA_GP_ID_9 0x12A +#define DA9062AA_GP_ID_10 0x12B +#define DA9062AA_GP_ID_11 0x12C +#define DA9062AA_GP_ID_12 0x12D +#define DA9062AA_GP_ID_13 0x12E +#define DA9062AA_GP_ID_14 0x12F +#define DA9062AA_GP_ID_15 0x130 +#define DA9062AA_GP_ID_16 0x131 +#define DA9062AA_GP_ID_17 0x132 +#define DA9062AA_GP_ID_18 0x133 +#define DA9062AA_GP_ID_19 0x134 +#define DA9062AA_DEVICE_ID 0x181 +#define DA9062AA_VARIANT_ID 0x182 +#define DA9062AA_CUSTOMER_ID 0x183 +#define DA9062AA_CONFIG_ID 0x184 + +/* + * Bit fields + */ + +/* DA9062AA_PAGE_CON = 0x000 */ +#define DA9062AA_PAGE_SHIFT 0 +#define DA9062AA_PAGE_MASK 0x3f +#define DA9062AA_WRITE_MODE_SHIFT 6 +#define DA9062AA_WRITE_MODE_MASK BIT(6) +#define DA9062AA_REVERT_SHIFT 7 +#define DA9062AA_REVERT_MASK BIT(7) + +/* DA9062AA_STATUS_A = 0x001 */ +#define DA9062AA_NONKEY_SHIFT 0 +#define DA9062AA_NONKEY_MASK 0x01 +#define DA9062AA_DVC_BUSY_SHIFT 2 +#define DA9062AA_DVC_BUSY_MASK BIT(2) + +/* DA9062AA_STATUS_B = 0x002 */ +#define DA9062AA_GPI0_SHIFT 0 +#define DA9062AA_GPI0_MASK 0x01 +#define DA9062AA_GPI1_SHIFT 1 +#define DA9062AA_GPI1_MASK BIT(1) +#define DA9062AA_GPI2_SHIFT 2 +#define DA9062AA_GPI2_MASK BIT(2) +#define DA9062AA_GPI3_SHIFT 3 +#define DA9062AA_GPI3_MASK BIT(3) +#define DA9062AA_GPI4_SHIFT 4 +#define DA9062AA_GPI4_MASK BIT(4) + +/* DA9062AA_STATUS_D = 0x004 */ +#define DA9062AA_LDO1_ILIM_SHIFT 0 +#define DA9062AA_LDO1_ILIM_MASK 0x01 +#define DA9062AA_LDO2_ILIM_SHIFT 1 +#define DA9062AA_LDO2_ILIM_MASK BIT(1) +#define DA9062AA_LDO3_ILIM_SHIFT 2 +#define DA9062AA_LDO3_ILIM_MASK BIT(2) +#define DA9062AA_LDO4_ILIM_SHIFT 3 +#define DA9062AA_LDO4_ILIM_MASK BIT(3) + +/* DA9062AA_FAULT_LOG = 0x005 */ +#define DA9062AA_TWD_ERROR_SHIFT 0 +#define DA9062AA_TWD_ERROR_MASK 0x01 +#define DA9062AA_POR_SHIFT 1 +#define DA9062AA_POR_MASK BIT(1) +#define DA9062AA_VDD_FAULT_SHIFT 2 +#define DA9062AA_VDD_FAULT_MASK BIT(2) +#define DA9062AA_VDD_START_SHIFT 3 +#define DA9062AA_VDD_START_MASK BIT(3) +#define DA9062AA_TEMP_CRIT_SHIFT 4 +#define DA9062AA_TEMP_CRIT_MASK BIT(4) +#define DA9062AA_KEY_RESET_SHIFT 5 +#define DA9062AA_KEY_RESET_MASK BIT(5) +#define DA9062AA_NSHUTDOWN_SHIFT 6 +#define DA9062AA_NSHUTDOWN_MASK BIT(6) +#define DA9062AA_WAIT_SHUT_SHIFT 7 +#define DA9062AA_WAIT_SHUT_MASK BIT(7) + +/* DA9062AA_EVENT_A = 0x006 */ +#define DA9062AA_E_NONKEY_SHIFT 0 +#define DA9062AA_E_NONKEY_MASK 0x01 +#define DA9062AA_E_ALARM_SHIFT 1 +#define DA9062AA_E_ALARM_MASK BIT(1) +#define DA9062AA_E_TICK_SHIFT 2 +#define DA9062AA_E_TICK_MASK BIT(2) +#define DA9062AA_E_WDG_WARN_SHIFT 3 +#define DA9062AA_E_WDG_WARN_MASK BIT(3) +#define DA9062AA_E_SEQ_RDY_SHIFT 4 +#define DA9062AA_E_SEQ_RDY_MASK BIT(4) +#define DA9062AA_EVENTS_B_SHIFT 5 +#define DA9062AA_EVENTS_B_MASK BIT(5) +#define DA9062AA_EVENTS_C_SHIFT 6 +#define DA9062AA_EVENTS_C_MASK BIT(6) + +/* DA9062AA_EVENT_B = 0x007 */ +#define DA9062AA_E_TEMP_SHIFT 1 +#define DA9062AA_E_TEMP_MASK BIT(1) +#define DA9062AA_E_LDO_LIM_SHIFT 3 +#define DA9062AA_E_LDO_LIM_MASK BIT(3) +#define DA9062AA_E_DVC_RDY_SHIFT 5 +#define DA9062AA_E_DVC_RDY_MASK BIT(5) +#define DA9062AA_E_VDD_WARN_SHIFT 7 +#define DA9062AA_E_VDD_WARN_MASK BIT(7) + +/* DA9062AA_EVENT_C = 0x008 */ +#define DA9062AA_E_GPI0_SHIFT 0 +#define DA9062AA_E_GPI0_MASK 0x01 +#define DA9062AA_E_GPI1_SHIFT 1 +#define DA9062AA_E_GPI1_MASK BIT(1) +#define DA9062AA_E_GPI2_SHIFT 2 +#define DA9062AA_E_GPI2_MASK BIT(2) +#define DA9062AA_E_GPI3_SHIFT 3 +#define DA9062AA_E_GPI3_MASK BIT(3) +#define DA9062AA_E_GPI4_SHIFT 4 +#define DA9062AA_E_GPI4_MASK BIT(4) + +/* DA9062AA_IRQ_MASK_A = 0x00A */ +#define DA9062AA_M_NONKEY_SHIFT 0 +#define DA9062AA_M_NONKEY_MASK 0x01 +#define DA9062AA_M_ALARM_SHIFT 1 +#define DA9062AA_M_ALARM_MASK BIT(1) +#define DA9062AA_M_TICK_SHIFT 2 +#define DA9062AA_M_TICK_MASK BIT(2) +#define DA9062AA_M_WDG_WARN_SHIFT 3 +#define DA9062AA_M_WDG_WARN_MASK BIT(3) +#define DA9062AA_M_SEQ_RDY_SHIFT 4 +#define DA9062AA_M_SEQ_RDY_MASK BIT(4) + +/* DA9062AA_IRQ_MASK_B = 0x00B */ +#define DA9062AA_M_TEMP_SHIFT 1 +#define DA9062AA_M_TEMP_MASK BIT(1) +#define DA9062AA_M_LDO_LIM_SHIFT 3 +#define DA9062AA_M_LDO_LIM_MASK BIT(3) +#define DA9062AA_M_DVC_RDY_SHIFT 5 +#define DA9062AA_M_DVC_RDY_MASK BIT(5) +#define DA9062AA_M_VDD_WARN_SHIFT 7 +#define DA9062AA_M_VDD_WARN_MASK BIT(7) + +/* DA9062AA_IRQ_MASK_C = 0x00C */ +#define DA9062AA_M_GPI0_SHIFT 0 +#define DA9062AA_M_GPI0_MASK 0x01 +#define DA9062AA_M_GPI1_SHIFT 1 +#define DA9062AA_M_GPI1_MASK BIT(1) +#define DA9062AA_M_GPI2_SHIFT 2 +#define DA9062AA_M_GPI2_MASK BIT(2) +#define DA9062AA_M_GPI3_SHIFT 3 +#define DA9062AA_M_GPI3_MASK BIT(3) +#define DA9062AA_M_GPI4_SHIFT 4 +#define DA9062AA_M_GPI4_MASK BIT(4) + +/* DA9062AA_CONTROL_A = 0x00E */ +#define DA9062AA_SYSTEM_EN_SHIFT 0 +#define DA9062AA_SYSTEM_EN_MASK 0x01 +#define DA9062AA_POWER_EN_SHIFT 1 +#define DA9062AA_POWER_EN_MASK BIT(1) +#define DA9062AA_POWER1_EN_SHIFT 2 +#define DA9062AA_POWER1_EN_MASK BIT(2) +#define DA9062AA_STANDBY_SHIFT 3 +#define DA9062AA_STANDBY_MASK BIT(3) +#define DA9062AA_M_SYSTEM_EN_SHIFT 4 +#define DA9062AA_M_SYSTEM_EN_MASK BIT(4) +#define DA9062AA_M_POWER_EN_SHIFT 5 +#define DA9062AA_M_POWER_EN_MASK BIT(5) +#define DA9062AA_M_POWER1_EN_SHIFT 6 +#define DA9062AA_M_POWER1_EN_MASK BIT(6) + +/* DA9062AA_CONTROL_B = 0x00F */ +#define DA9062AA_WATCHDOG_PD_SHIFT 1 +#define DA9062AA_WATCHDOG_PD_MASK BIT(1) +#define DA9062AA_FREEZE_EN_SHIFT 2 +#define DA9062AA_FREEZE_EN_MASK BIT(2) +#define DA9062AA_NRES_MODE_SHIFT 3 +#define DA9062AA_NRES_MODE_MASK BIT(3) +#define DA9062AA_NONKEY_LOCK_SHIFT 4 +#define DA9062AA_NONKEY_LOCK_MASK BIT(4) +#define DA9062AA_NFREEZE_SHIFT 5 +#define DA9062AA_NFREEZE_MASK (0x03 << 5) +#define DA9062AA_BUCK_SLOWSTART_SHIFT 7 +#define DA9062AA_BUCK_SLOWSTART_MASK BIT(7) + +/* DA9062AA_CONTROL_C = 0x010 */ +#define DA9062AA_DEBOUNCING_SHIFT 0 +#define DA9062AA_DEBOUNCING_MASK 0x07 +#define DA9062AA_AUTO_BOOT_SHIFT 3 +#define DA9062AA_AUTO_BOOT_MASK BIT(3) +#define DA9062AA_OTPREAD_EN_SHIFT 4 +#define DA9062AA_OTPREAD_EN_MASK BIT(4) +#define DA9062AA_SLEW_RATE_SHIFT 5 +#define DA9062AA_SLEW_RATE_MASK (0x03 << 5) +#define DA9062AA_DEF_SUPPLY_SHIFT 7 +#define DA9062AA_DEF_SUPPLY_MASK BIT(7) + +/* DA9062AA_CONTROL_D = 0x011 */ +#define DA9062AA_TWDSCALE_SHIFT 0 +#define DA9062AA_TWDSCALE_MASK 0x07 + +/* DA9062AA_CONTROL_E = 0x012 */ +#define DA9062AA_RTC_MODE_PD_SHIFT 0 +#define DA9062AA_RTC_MODE_PD_MASK 0x01 +#define DA9062AA_RTC_MODE_SD_SHIFT 1 +#define DA9062AA_RTC_MODE_SD_MASK BIT(1) +#define DA9062AA_RTC_EN_SHIFT 2 +#define DA9062AA_RTC_EN_MASK BIT(2) +#define DA9062AA_V_LOCK_SHIFT 7 +#define DA9062AA_V_LOCK_MASK BIT(7) + +/* DA9062AA_CONTROL_F = 0x013 */ +#define DA9062AA_WATCHDOG_SHIFT 0 +#define DA9062AA_WATCHDOG_MASK 0x01 +#define DA9062AA_SHUTDOWN_SHIFT 1 +#define DA9062AA_SHUTDOWN_MASK BIT(1) +#define DA9062AA_WAKE_UP_SHIFT 2 +#define DA9062AA_WAKE_UP_MASK BIT(2) + +/* DA9062AA_PD_DIS = 0x014 */ +#define DA9062AA_GPI_DIS_SHIFT 0 +#define DA9062AA_GPI_DIS_MASK 0x01 +#define DA9062AA_PMIF_DIS_SHIFT 2 +#define DA9062AA_PMIF_DIS_MASK BIT(2) +#define DA9062AA_CLDR_PAUSE_SHIFT 4 +#define DA9062AA_CLDR_PAUSE_MASK BIT(4) +#define DA9062AA_BBAT_DIS_SHIFT 5 +#define DA9062AA_BBAT_DIS_MASK BIT(5) +#define DA9062AA_OUT32K_PAUSE_SHIFT 6 +#define DA9062AA_OUT32K_PAUSE_MASK BIT(6) +#define DA9062AA_PMCONT_DIS_SHIFT 7 +#define DA9062AA_PMCONT_DIS_MASK BIT(7) + +/* DA9062AA_GPIO_0_1 = 0x015 */ +#define DA9062AA_GPIO0_PIN_SHIFT 0 +#define DA9062AA_GPIO0_PIN_MASK 0x03 +#define DA9062AA_GPIO0_TYPE_SHIFT 2 +#define DA9062AA_GPIO0_TYPE_MASK BIT(2) +#define DA9062AA_GPIO0_WEN_SHIFT 3 +#define DA9062AA_GPIO0_WEN_MASK BIT(3) +#define DA9062AA_GPIO1_PIN_SHIFT 4 +#define DA9062AA_GPIO1_PIN_MASK (0x03 << 4) +#define DA9062AA_GPIO1_TYPE_SHIFT 6 +#define DA9062AA_GPIO1_TYPE_MASK BIT(6) +#define DA9062AA_GPIO1_WEN_SHIFT 7 +#define DA9062AA_GPIO1_WEN_MASK BIT(7) + +/* DA9062AA_GPIO_2_3 = 0x016 */ +#define DA9062AA_GPIO2_PIN_SHIFT 0 +#define DA9062AA_GPIO2_PIN_MASK 0x03 +#define DA9062AA_GPIO2_TYPE_SHIFT 2 +#define DA9062AA_GPIO2_TYPE_MASK BIT(2) +#define DA9062AA_GPIO2_WEN_SHIFT 3 +#define DA9062AA_GPIO2_WEN_MASK BIT(3) +#define DA9062AA_GPIO3_PIN_SHIFT 4 +#define DA9062AA_GPIO3_PIN_MASK (0x03 << 4) +#define DA9062AA_GPIO3_TYPE_SHIFT 6 +#define DA9062AA_GPIO3_TYPE_MASK BIT(6) +#define DA9062AA_GPIO3_WEN_SHIFT 7 +#define DA9062AA_GPIO3_WEN_MASK BIT(7) + +/* DA9062AA_GPIO_4 = 0x017 */ +#define DA9062AA_GPIO4_PIN_SHIFT 0 +#define DA9062AA_GPIO4_PIN_MASK 0x03 +#define DA9062AA_GPIO4_TYPE_SHIFT 2 +#define DA9062AA_GPIO4_TYPE_MASK BIT(2) +#define DA9062AA_GPIO4_WEN_SHIFT 3 +#define DA9062AA_GPIO4_WEN_MASK BIT(3) + +/* DA9062AA_GPIO_WKUP_MODE = 0x01C */ +#define DA9062AA_GPIO0_WKUP_MODE_SHIFT 0 +#define DA9062AA_GPIO0_WKUP_MODE_MASK 0x01 +#define DA9062AA_GPIO1_WKUP_MODE_SHIFT 1 +#define DA9062AA_GPIO1_WKUP_MODE_MASK BIT(1) +#define DA9062AA_GPIO2_WKUP_MODE_SHIFT 2 +#define DA9062AA_GPIO2_WKUP_MODE_MASK BIT(2) +#define DA9062AA_GPIO3_WKUP_MODE_SHIFT 3 +#define DA9062AA_GPIO3_WKUP_MODE_MASK BIT(3) +#define DA9062AA_GPIO4_WKUP_MODE_SHIFT 4 +#define DA9062AA_GPIO4_WKUP_MODE_MASK BIT(4) + +/* DA9062AA_GPIO_MODE0_4 = 0x01D */ +#define DA9062AA_GPIO0_MODE_SHIFT 0 +#define DA9062AA_GPIO0_MODE_MASK 0x01 +#define DA9062AA_GPIO1_MODE_SHIFT 1 +#define DA9062AA_GPIO1_MODE_MASK BIT(1) +#define DA9062AA_GPIO2_MODE_SHIFT 2 +#define DA9062AA_GPIO2_MODE_MASK BIT(2) +#define DA9062AA_GPIO3_MODE_SHIFT 3 +#define DA9062AA_GPIO3_MODE_MASK BIT(3) +#define DA9062AA_GPIO4_MODE_SHIFT 4 +#define DA9062AA_GPIO4_MODE_MASK BIT(4) + +/* DA9062AA_GPIO_OUT0_2 = 0x01E */ +#define DA9062AA_GPIO0_OUT_SHIFT 0 +#define DA9062AA_GPIO0_OUT_MASK 0x07 +#define DA9062AA_GPIO1_OUT_SHIFT 3 +#define DA9062AA_GPIO1_OUT_MASK (0x07 << 3) +#define DA9062AA_GPIO2_OUT_SHIFT 6 +#define DA9062AA_GPIO2_OUT_MASK (0x03 << 6) + +/* DA9062AA_GPIO_OUT3_4 = 0x01F */ +#define DA9062AA_GPIO3_OUT_SHIFT 0 +#define DA9062AA_GPIO3_OUT_MASK 0x07 +#define DA9062AA_GPIO4_OUT_SHIFT 3 +#define DA9062AA_GPIO4_OUT_MASK (0x03 << 3) + +/* DA9062AA_BUCK2_CONT = 0x020 */ +#define DA9062AA_BUCK2_EN_SHIFT 0 +#define DA9062AA_BUCK2_EN_MASK 0x01 +#define DA9062AA_BUCK2_GPI_SHIFT 1 +#define DA9062AA_BUCK2_GPI_MASK (0x03 << 1) +#define DA9062AA_BUCK2_CONF_SHIFT 3 +#define DA9062AA_BUCK2_CONF_MASK BIT(3) +#define DA9062AA_VBUCK2_GPI_SHIFT 5 +#define DA9062AA_VBUCK2_GPI_MASK (0x03 << 5) + +/* DA9062AA_BUCK1_CONT = 0x021 */ +#define DA9062AA_BUCK1_EN_SHIFT 0 +#define DA9062AA_BUCK1_EN_MASK 0x01 +#define DA9062AA_BUCK1_GPI_SHIFT 1 +#define DA9062AA_BUCK1_GPI_MASK (0x03 << 1) +#define DA9062AA_BUCK1_CONF_SHIFT 3 +#define DA9062AA_BUCK1_CONF_MASK BIT(3) +#define DA9062AA_VBUCK1_GPI_SHIFT 5 +#define DA9062AA_VBUCK1_GPI_MASK (0x03 << 5) + +/* DA9062AA_BUCK4_CONT = 0x022 */ +#define DA9062AA_BUCK4_EN_SHIFT 0 +#define DA9062AA_BUCK4_EN_MASK 0x01 +#define DA9062AA_BUCK4_GPI_SHIFT 1 +#define DA9062AA_BUCK4_GPI_MASK (0x03 << 1) +#define DA9062AA_BUCK4_CONF_SHIFT 3 +#define DA9062AA_BUCK4_CONF_MASK BIT(3) +#define DA9062AA_VBUCK4_GPI_SHIFT 5 +#define DA9062AA_VBUCK4_GPI_MASK (0x03 << 5) + +/* DA9062AA_BUCK3_CONT = 0x024 */ +#define DA9062AA_BUCK3_EN_SHIFT 0 +#define DA9062AA_BUCK3_EN_MASK 0x01 +#define DA9062AA_BUCK3_GPI_SHIFT 1 +#define DA9062AA_BUCK3_GPI_MASK (0x03 << 1) +#define DA9062AA_BUCK3_CONF_SHIFT 3 +#define DA9062AA_BUCK3_CONF_MASK BIT(3) +#define DA9062AA_VBUCK3_GPI_SHIFT 5 +#define DA9062AA_VBUCK3_GPI_MASK (0x03 << 5) + +/* DA9062AA_LDO1_CONT = 0x026 */ +#define DA9062AA_LDO1_EN_SHIFT 0 +#define DA9062AA_LDO1_EN_MASK 0x01 +#define DA9062AA_LDO1_GPI_SHIFT 1 +#define DA9062AA_LDO1_GPI_MASK (0x03 << 1) +#define DA9062AA_LDO1_PD_DIS_SHIFT 3 +#define DA9062AA_LDO1_PD_DIS_MASK BIT(3) +#define DA9062AA_VLDO1_GPI_SHIFT 5 +#define DA9062AA_VLDO1_GPI_MASK (0x03 << 5) +#define DA9062AA_LDO1_CONF_SHIFT 7 +#define DA9062AA_LDO1_CONF_MASK BIT(7) + +/* DA9062AA_LDO2_CONT = 0x027 */ +#define DA9062AA_LDO2_EN_SHIFT 0 +#define DA9062AA_LDO2_EN_MASK 0x01 +#define DA9062AA_LDO2_GPI_SHIFT 1 +#define DA9062AA_LDO2_GPI_MASK (0x03 << 1) +#define DA9062AA_LDO2_PD_DIS_SHIFT 3 +#define DA9062AA_LDO2_PD_DIS_MASK BIT(3) +#define DA9062AA_VLDO2_GPI_SHIFT 5 +#define DA9062AA_VLDO2_GPI_MASK (0x03 << 5) +#define DA9062AA_LDO2_CONF_SHIFT 7 +#define DA9062AA_LDO2_CONF_MASK BIT(7) + +/* DA9062AA_LDO3_CONT = 0x028 */ +#define DA9062AA_LDO3_EN_SHIFT 0 +#define DA9062AA_LDO3_EN_MASK 0x01 +#define DA9062AA_LDO3_GPI_SHIFT 1 +#define DA9062AA_LDO3_GPI_MASK (0x03 << 1) +#define DA9062AA_LDO3_PD_DIS_SHIFT 3 +#define DA9062AA_LDO3_PD_DIS_MASK BIT(3) +#define DA9062AA_VLDO3_GPI_SHIFT 5 +#define DA9062AA_VLDO3_GPI_MASK (0x03 << 5) +#define DA9062AA_LDO3_CONF_SHIFT 7 +#define DA9062AA_LDO3_CONF_MASK BIT(7) + +/* DA9062AA_LDO4_CONT = 0x029 */ +#define DA9062AA_LDO4_EN_SHIFT 0 +#define DA9062AA_LDO4_EN_MASK 0x01 +#define DA9062AA_LDO4_GPI_SHIFT 1 +#define DA9062AA_LDO4_GPI_MASK (0x03 << 1) +#define DA9062AA_LDO4_PD_DIS_SHIFT 3 +#define DA9062AA_LDO4_PD_DIS_MASK BIT(3) +#define DA9062AA_VLDO4_GPI_SHIFT 5 +#define DA9062AA_VLDO4_GPI_MASK (0x03 << 5) +#define DA9062AA_LDO4_CONF_SHIFT 7 +#define DA9062AA_LDO4_CONF_MASK BIT(7) + +/* DA9062AA_DVC_1 = 0x032 */ +#define DA9062AA_VBUCK1_SEL_SHIFT 0 +#define DA9062AA_VBUCK1_SEL_MASK 0x01 +#define DA9062AA_VBUCK2_SEL_SHIFT 1 +#define DA9062AA_VBUCK2_SEL_MASK BIT(1) +#define DA9062AA_VBUCK4_SEL_SHIFT 2 +#define DA9062AA_VBUCK4_SEL_MASK BIT(2) +#define DA9062AA_VBUCK3_SEL_SHIFT 3 +#define DA9062AA_VBUCK3_SEL_MASK BIT(3) +#define DA9062AA_VLDO1_SEL_SHIFT 4 +#define DA9062AA_VLDO1_SEL_MASK BIT(4) +#define DA9062AA_VLDO2_SEL_SHIFT 5 +#define DA9062AA_VLDO2_SEL_MASK BIT(5) +#define DA9062AA_VLDO3_SEL_SHIFT 6 +#define DA9062AA_VLDO3_SEL_MASK BIT(6) +#define DA9062AA_VLDO4_SEL_SHIFT 7 +#define DA9062AA_VLDO4_SEL_MASK BIT(7) + +/* DA9062AA_COUNT_S = 0x040 */ +#define DA9062AA_COUNT_SEC_SHIFT 0 +#define DA9062AA_COUNT_SEC_MASK 0x3f +#define DA9062AA_RTC_READ_SHIFT 7 +#define DA9062AA_RTC_READ_MASK BIT(7) + +/* DA9062AA_COUNT_MI = 0x041 */ +#define DA9062AA_COUNT_MIN_SHIFT 0 +#define DA9062AA_COUNT_MIN_MASK 0x3f + +/* DA9062AA_COUNT_H = 0x042 */ +#define DA9062AA_COUNT_HOUR_SHIFT 0 +#define DA9062AA_COUNT_HOUR_MASK 0x1f + +/* DA9062AA_COUNT_D = 0x043 */ +#define DA9062AA_COUNT_DAY_SHIFT 0 +#define DA9062AA_COUNT_DAY_MASK 0x1f + +/* DA9062AA_COUNT_MO = 0x044 */ +#define DA9062AA_COUNT_MONTH_SHIFT 0 +#define DA9062AA_COUNT_MONTH_MASK 0x0f + +/* DA9062AA_COUNT_Y = 0x045 */ +#define DA9062AA_COUNT_YEAR_SHIFT 0 +#define DA9062AA_COUNT_YEAR_MASK 0x3f +#define DA9062AA_MONITOR_SHIFT 6 +#define DA9062AA_MONITOR_MASK BIT(6) + +/* DA9062AA_ALARM_S = 0x046 */ +#define DA9062AA_ALARM_SEC_SHIFT 0 +#define DA9062AA_ALARM_SEC_MASK 0x3f +#define DA9062AA_ALARM_STATUS_SHIFT 6 +#define DA9062AA_ALARM_STATUS_MASK (0x03 << 6) + +/* DA9062AA_ALARM_MI = 0x047 */ +#define DA9062AA_ALARM_MIN_SHIFT 0 +#define DA9062AA_ALARM_MIN_MASK 0x3f + +/* DA9062AA_ALARM_H = 0x048 */ +#define DA9062AA_ALARM_HOUR_SHIFT 0 +#define DA9062AA_ALARM_HOUR_MASK 0x1f + +/* DA9062AA_ALARM_D = 0x049 */ +#define DA9062AA_ALARM_DAY_SHIFT 0 +#define DA9062AA_ALARM_DAY_MASK 0x1f + +/* DA9062AA_ALARM_MO = 0x04A */ +#define DA9062AA_ALARM_MONTH_SHIFT 0 +#define DA9062AA_ALARM_MONTH_MASK 0x0f +#define DA9062AA_TICK_TYPE_SHIFT 4 +#define DA9062AA_TICK_TYPE_MASK BIT(4) +#define DA9062AA_TICK_WAKE_SHIFT 5 +#define DA9062AA_TICK_WAKE_MASK BIT(5) + +/* DA9062AA_ALARM_Y = 0x04B */ +#define DA9062AA_ALARM_YEAR_SHIFT 0 +#define DA9062AA_ALARM_YEAR_MASK 0x3f +#define DA9062AA_ALARM_ON_SHIFT 6 +#define DA9062AA_ALARM_ON_MASK BIT(6) +#define DA9062AA_TICK_ON_SHIFT 7 +#define DA9062AA_TICK_ON_MASK BIT(7) + +/* DA9062AA_SECOND_A = 0x04C */ +#define DA9062AA_SECONDS_A_SHIFT 0 +#define DA9062AA_SECONDS_A_MASK 0xff + +/* DA9062AA_SECOND_B = 0x04D */ +#define DA9062AA_SECONDS_B_SHIFT 0 +#define DA9062AA_SECONDS_B_MASK 0xff + +/* DA9062AA_SECOND_C = 0x04E */ +#define DA9062AA_SECONDS_C_SHIFT 0 +#define DA9062AA_SECONDS_C_MASK 0xff + +/* DA9062AA_SECOND_D = 0x04F */ +#define DA9062AA_SECONDS_D_SHIFT 0 +#define DA9062AA_SECONDS_D_MASK 0xff + +/* DA9062AA_SEQ = 0x081 */ +#define DA9062AA_SEQ_POINTER_SHIFT 0 +#define DA9062AA_SEQ_POINTER_MASK 0x0f +#define DA9062AA_NXT_SEQ_START_SHIFT 4 +#define DA9062AA_NXT_SEQ_START_MASK (0x0f << 4) + +/* DA9062AA_SEQ_TIMER = 0x082 */ +#define DA9062AA_SEQ_TIME_SHIFT 0 +#define DA9062AA_SEQ_TIME_MASK 0x0f +#define DA9062AA_SEQ_DUMMY_SHIFT 4 +#define DA9062AA_SEQ_DUMMY_MASK (0x0f << 4) + +/* DA9062AA_ID_2_1 = 0x083 */ +#define DA9062AA_LDO1_STEP_SHIFT 0 +#define DA9062AA_LDO1_STEP_MASK 0x0f +#define DA9062AA_LDO2_STEP_SHIFT 4 +#define DA9062AA_LDO2_STEP_MASK (0x0f << 4) + +/* DA9062AA_ID_4_3 = 0x084 */ +#define DA9062AA_LDO3_STEP_SHIFT 0 +#define DA9062AA_LDO3_STEP_MASK 0x0f +#define DA9062AA_LDO4_STEP_SHIFT 4 +#define DA9062AA_LDO4_STEP_MASK (0x0f << 4) + +/* DA9062AA_ID_12_11 = 0x088 */ +#define DA9062AA_PD_DIS_STEP_SHIFT 4 +#define DA9062AA_PD_DIS_STEP_MASK (0x0f << 4) + +/* DA9062AA_ID_14_13 = 0x089 */ +#define DA9062AA_BUCK1_STEP_SHIFT 0 +#define DA9062AA_BUCK1_STEP_MASK 0x0f +#define DA9062AA_BUCK2_STEP_SHIFT 4 +#define DA9062AA_BUCK2_STEP_MASK (0x0f << 4) + +/* DA9062AA_ID_16_15 = 0x08A */ +#define DA9062AA_BUCK4_STEP_SHIFT 0 +#define DA9062AA_BUCK4_STEP_MASK 0x0f +#define DA9062AA_BUCK3_STEP_SHIFT 4 +#define DA9062AA_BUCK3_STEP_MASK (0x0f << 4) + +/* DA9062AA_ID_22_21 = 0x08D */ +#define DA9062AA_GP_RISE1_STEP_SHIFT 0 +#define DA9062AA_GP_RISE1_STEP_MASK 0x0f +#define DA9062AA_GP_FALL1_STEP_SHIFT 4 +#define DA9062AA_GP_FALL1_STEP_MASK (0x0f << 4) + +/* DA9062AA_ID_24_23 = 0x08E */ +#define DA9062AA_GP_RISE2_STEP_SHIFT 0 +#define DA9062AA_GP_RISE2_STEP_MASK 0x0f +#define DA9062AA_GP_FALL2_STEP_SHIFT 4 +#define DA9062AA_GP_FALL2_STEP_MASK (0x0f << 4) + +/* DA9062AA_ID_26_25 = 0x08F */ +#define DA9062AA_GP_RISE3_STEP_SHIFT 0 +#define DA9062AA_GP_RISE3_STEP_MASK 0x0f +#define DA9062AA_GP_FALL3_STEP_SHIFT 4 +#define DA9062AA_GP_FALL3_STEP_MASK (0x0f << 4) + +/* DA9062AA_ID_28_27 = 0x090 */ +#define DA9062AA_GP_RISE4_STEP_SHIFT 0 +#define DA9062AA_GP_RISE4_STEP_MASK 0x0f +#define DA9062AA_GP_FALL4_STEP_SHIFT 4 +#define DA9062AA_GP_FALL4_STEP_MASK (0x0f << 4) + +/* DA9062AA_ID_30_29 = 0x091 */ +#define DA9062AA_GP_RISE5_STEP_SHIFT 0 +#define DA9062AA_GP_RISE5_STEP_MASK 0x0f +#define DA9062AA_GP_FALL5_STEP_SHIFT 4 +#define DA9062AA_GP_FALL5_STEP_MASK (0x0f << 4) + +/* DA9062AA_ID_32_31 = 0x092 */ +#define DA9062AA_WAIT_STEP_SHIFT 0 +#define DA9062AA_WAIT_STEP_MASK 0x0f +#define DA9062AA_EN32K_STEP_SHIFT 4 +#define DA9062AA_EN32K_STEP_MASK (0x0f << 4) + +/* DA9062AA_SEQ_A = 0x095 */ +#define DA9062AA_SYSTEM_END_SHIFT 0 +#define DA9062AA_SYSTEM_END_MASK 0x0f +#define DA9062AA_POWER_END_SHIFT 4 +#define DA9062AA_POWER_END_MASK (0x0f << 4) + +/* DA9062AA_SEQ_B = 0x096 */ +#define DA9062AA_MAX_COUNT_SHIFT 0 +#define DA9062AA_MAX_COUNT_MASK 0x0f +#define DA9062AA_PART_DOWN_SHIFT 4 +#define DA9062AA_PART_DOWN_MASK (0x0f << 4) + +/* DA9062AA_WAIT = 0x097 */ +#define DA9062AA_WAIT_TIME_SHIFT 0 +#define DA9062AA_WAIT_TIME_MASK 0x0f +#define DA9062AA_WAIT_MODE_SHIFT 4 +#define DA9062AA_WAIT_MODE_MASK BIT(4) +#define DA9062AA_TIME_OUT_SHIFT 5 +#define DA9062AA_TIME_OUT_MASK BIT(5) +#define DA9062AA_WAIT_DIR_SHIFT 6 +#define DA9062AA_WAIT_DIR_MASK (0x03 << 6) + +/* DA9062AA_EN_32K = 0x098 */ +#define DA9062AA_STABILISATION_TIME_SHIFT 0 +#define DA9062AA_STABILISATION_TIME_MASK 0x07 +#define DA9062AA_CRYSTAL_SHIFT 3 +#define DA9062AA_CRYSTAL_MASK BIT(3) +#define DA9062AA_DELAY_MODE_SHIFT 4 +#define DA9062AA_DELAY_MODE_MASK BIT(4) +#define DA9062AA_OUT_CLOCK_SHIFT 5 +#define DA9062AA_OUT_CLOCK_MASK BIT(5) +#define DA9062AA_RTC_CLOCK_SHIFT 6 +#define DA9062AA_RTC_CLOCK_MASK BIT(6) +#define DA9062AA_EN_32KOUT_SHIFT 7 +#define DA9062AA_EN_32KOUT_MASK BIT(7) + +/* DA9062AA_RESET = 0x099 */ +#define DA9062AA_RESET_TIMER_SHIFT 0 +#define DA9062AA_RESET_TIMER_MASK 0x3f +#define DA9062AA_RESET_EVENT_SHIFT 6 +#define DA9062AA_RESET_EVENT_MASK (0x03 << 6) + +/* DA9062AA_BUCK_ILIM_A = 0x09A */ +#define DA9062AA_BUCK3_ILIM_SHIFT 0 +#define DA9062AA_BUCK3_ILIM_MASK 0x0f + +/* DA9062AA_BUCK_ILIM_B = 0x09B */ +#define DA9062AA_BUCK4_ILIM_SHIFT 0 +#define DA9062AA_BUCK4_ILIM_MASK 0x0f + +/* DA9062AA_BUCK_ILIM_C = 0x09C */ +#define DA9062AA_BUCK1_ILIM_SHIFT 0 +#define DA9062AA_BUCK1_ILIM_MASK 0x0f +#define DA9062AA_BUCK2_ILIM_SHIFT 4 +#define DA9062AA_BUCK2_ILIM_MASK (0x0f << 4) + +/* DA9062AA_BUCK2_CFG = 0x09D */ +#define DA9062AA_BUCK2_PD_DIS_SHIFT 5 +#define DA9062AA_BUCK2_PD_DIS_MASK BIT(5) +#define DA9062AA_BUCK2_MODE_SHIFT 6 +#define DA9062AA_BUCK2_MODE_MASK (0x03 << 6) + +/* DA9062AA_BUCK1_CFG = 0x09E */ +#define DA9062AA_BUCK1_PD_DIS_SHIFT 5 +#define DA9062AA_BUCK1_PD_DIS_MASK BIT(5) +#define DA9062AA_BUCK1_MODE_SHIFT 6 +#define DA9062AA_BUCK1_MODE_MASK (0x03 << 6) + +/* DA9062AA_BUCK4_CFG = 0x09F */ +#define DA9062AA_BUCK4_VTTR_EN_SHIFT 3 +#define DA9062AA_BUCK4_VTTR_EN_MASK BIT(3) +#define DA9062AA_BUCK4_VTT_EN_SHIFT 4 +#define DA9062AA_BUCK4_VTT_EN_MASK BIT(4) +#define DA9062AA_BUCK4_PD_DIS_SHIFT 5 +#define DA9062AA_BUCK4_PD_DIS_MASK BIT(5) +#define DA9062AA_BUCK4_MODE_SHIFT 6 +#define DA9062AA_BUCK4_MODE_MASK (0x03 << 6) + +/* DA9062AA_BUCK3_CFG = 0x0A0 */ +#define DA9062AA_BUCK3_PD_DIS_SHIFT 5 +#define DA9062AA_BUCK3_PD_DIS_MASK BIT(5) +#define DA9062AA_BUCK3_MODE_SHIFT 6 +#define DA9062AA_BUCK3_MODE_MASK (0x03 << 6) + +/* DA9062AA_VBUCK2_A = 0x0A3 */ +#define DA9062AA_VBUCK2_A_SHIFT 0 +#define DA9062AA_VBUCK2_A_MASK 0x7f +#define DA9062AA_BUCK2_SL_A_SHIFT 7 +#define DA9062AA_BUCK2_SL_A_MASK BIT(7) + +/* DA9062AA_VBUCK1_A = 0x0A4 */ +#define DA9062AA_VBUCK1_A_SHIFT 0 +#define DA9062AA_VBUCK1_A_MASK 0x7f +#define DA9062AA_BUCK1_SL_A_SHIFT 7 +#define DA9062AA_BUCK1_SL_A_MASK BIT(7) + +/* DA9062AA_VBUCK4_A = 0x0A5 */ +#define DA9062AA_VBUCK4_A_SHIFT 0 +#define DA9062AA_VBUCK4_A_MASK 0x7f +#define DA9062AA_BUCK4_SL_A_SHIFT 7 +#define DA9062AA_BUCK4_SL_A_MASK BIT(7) + +/* DA9062AA_VBUCK3_A = 0x0A7 */ +#define DA9062AA_VBUCK3_A_SHIFT 0 +#define DA9062AA_VBUCK3_A_MASK 0x7f +#define DA9062AA_BUCK3_SL_A_SHIFT 7 +#define DA9062AA_BUCK3_SL_A_MASK BIT(7) + +/* DA9062AA_VLDO1_A = 0x0A9 */ +#define DA9062AA_VLDO1_A_SHIFT 0 +#define DA9062AA_VLDO1_A_MASK 0x3f +#define DA9062AA_LDO1_SL_A_SHIFT 7 +#define DA9062AA_LDO1_SL_A_MASK BIT(7) + +/* DA9062AA_VLDO2_A = 0x0AA */ +#define DA9062AA_VLDO2_A_SHIFT 0 +#define DA9062AA_VLDO2_A_MASK 0x3f +#define DA9062AA_LDO2_SL_A_SHIFT 7 +#define DA9062AA_LDO2_SL_A_MASK BIT(7) + +/* DA9062AA_VLDO3_A = 0x0AB */ +#define DA9062AA_VLDO3_A_SHIFT 0 +#define DA9062AA_VLDO3_A_MASK 0x3f +#define DA9062AA_LDO3_SL_A_SHIFT 7 +#define DA9062AA_LDO3_SL_A_MASK BIT(7) + +/* DA9062AA_VLDO4_A = 0x0AC */ +#define DA9062AA_VLDO4_A_SHIFT 0 +#define DA9062AA_VLDO4_A_MASK 0x3f +#define DA9062AA_LDO4_SL_A_SHIFT 7 +#define DA9062AA_LDO4_SL_A_MASK BIT(7) + +/* DA9062AA_VBUCK2_B = 0x0B4 */ +#define DA9062AA_VBUCK2_B_SHIFT 0 +#define DA9062AA_VBUCK2_B_MASK 0x7f +#define DA9062AA_BUCK2_SL_B_SHIFT 7 +#define DA9062AA_BUCK2_SL_B_MASK BIT(7) + +/* DA9062AA_VBUCK1_B = 0x0B5 */ +#define DA9062AA_VBUCK1_B_SHIFT 0 +#define DA9062AA_VBUCK1_B_MASK 0x7f +#define DA9062AA_BUCK1_SL_B_SHIFT 7 +#define DA9062AA_BUCK1_SL_B_MASK BIT(7) + +/* DA9062AA_VBUCK4_B = 0x0B6 */ +#define DA9062AA_VBUCK4_B_SHIFT 0 +#define DA9062AA_VBUCK4_B_MASK 0x7f +#define DA9062AA_BUCK4_SL_B_SHIFT 7 +#define DA9062AA_BUCK4_SL_B_MASK BIT(7) + +/* DA9062AA_VBUCK3_B = 0x0B8 */ +#define DA9062AA_VBUCK3_B_SHIFT 0 +#define DA9062AA_VBUCK3_B_MASK 0x7f +#define DA9062AA_BUCK3_SL_B_SHIFT 7 +#define DA9062AA_BUCK3_SL_B_MASK BIT(7) + +/* DA9062AA_VLDO1_B = 0x0BA */ +#define DA9062AA_VLDO1_B_SHIFT 0 +#define DA9062AA_VLDO1_B_MASK 0x3f +#define DA9062AA_LDO1_SL_B_SHIFT 7 +#define DA9062AA_LDO1_SL_B_MASK BIT(7) + +/* DA9062AA_VLDO2_B = 0x0BB */ +#define DA9062AA_VLDO2_B_SHIFT 0 +#define DA9062AA_VLDO2_B_MASK 0x3f +#define DA9062AA_LDO2_SL_B_SHIFT 7 +#define DA9062AA_LDO2_SL_B_MASK BIT(7) + +/* DA9062AA_VLDO3_B = 0x0BC */ +#define DA9062AA_VLDO3_B_SHIFT 0 +#define DA9062AA_VLDO3_B_MASK 0x3f +#define DA9062AA_LDO3_SL_B_SHIFT 7 +#define DA9062AA_LDO3_SL_B_MASK BIT(7) + +/* DA9062AA_VLDO4_B = 0x0BD */ +#define DA9062AA_VLDO4_B_SHIFT 0 +#define DA9062AA_VLDO4_B_MASK 0x3f +#define DA9062AA_LDO4_SL_B_SHIFT 7 +#define DA9062AA_LDO4_SL_B_MASK BIT(7) + +/* DA9062AA_BBAT_CONT = 0x0C5 */ +#define DA9062AA_BCHG_VSET_SHIFT 0 +#define DA9062AA_BCHG_VSET_MASK 0x0f +#define DA9062AA_BCHG_ISET_SHIFT 4 +#define DA9062AA_BCHG_ISET_MASK (0x0f << 4) + +/* DA9062AA_INTERFACE = 0x105 */ +#define DA9062AA_IF_BASE_ADDR_SHIFT 4 +#define DA9062AA_IF_BASE_ADDR_MASK (0x0f << 4) + +/* DA9062AA_CONFIG_A = 0x106 */ +#define DA9062AA_PM_I_V_SHIFT 0 +#define DA9062AA_PM_I_V_MASK 0x01 +#define DA9062AA_PM_O_TYPE_SHIFT 2 +#define DA9062AA_PM_O_TYPE_MASK BIT(2) +#define DA9062AA_IRQ_TYPE_SHIFT 3 +#define DA9062AA_IRQ_TYPE_MASK BIT(3) +#define DA9062AA_PM_IF_V_SHIFT 4 +#define DA9062AA_PM_IF_V_MASK BIT(4) +#define DA9062AA_PM_IF_FMP_SHIFT 5 +#define DA9062AA_PM_IF_FMP_MASK BIT(5) +#define DA9062AA_PM_IF_HSM_SHIFT 6 +#define DA9062AA_PM_IF_HSM_MASK BIT(6) + +/* DA9062AA_CONFIG_B = 0x107 */ +#define DA9062AA_VDD_FAULT_ADJ_SHIFT 0 +#define DA9062AA_VDD_FAULT_ADJ_MASK 0x0f +#define DA9062AA_VDD_HYST_ADJ_SHIFT 4 +#define DA9062AA_VDD_HYST_ADJ_MASK (0x07 << 4) + +/* DA9062AA_CONFIG_C = 0x108 */ +#define DA9062AA_BUCK_ACTV_DISCHRG_SHIFT 2 +#define DA9062AA_BUCK_ACTV_DISCHRG_MASK BIT(2) +#define DA9062AA_BUCK1_CLK_INV_SHIFT 3 +#define DA9062AA_BUCK1_CLK_INV_MASK BIT(3) +#define DA9062AA_BUCK4_CLK_INV_SHIFT 4 +#define DA9062AA_BUCK4_CLK_INV_MASK BIT(4) +#define DA9062AA_BUCK3_CLK_INV_SHIFT 6 +#define DA9062AA_BUCK3_CLK_INV_MASK BIT(6) + +/* DA9062AA_CONFIG_D = 0x109 */ +#define DA9062AA_GPI_V_SHIFT 0 +#define DA9062AA_GPI_V_MASK 0x01 +#define DA9062AA_NIRQ_MODE_SHIFT 1 +#define DA9062AA_NIRQ_MODE_MASK BIT(1) +#define DA9062AA_SYSTEM_EN_RD_SHIFT 2 +#define DA9062AA_SYSTEM_EN_RD_MASK BIT(2) +#define DA9062AA_FORCE_RESET_SHIFT 5 +#define DA9062AA_FORCE_RESET_MASK BIT(5) + +/* DA9062AA_CONFIG_E = 0x10A */ +#define DA9062AA_BUCK1_AUTO_SHIFT 0 +#define DA9062AA_BUCK1_AUTO_MASK 0x01 +#define DA9062AA_BUCK2_AUTO_SHIFT 1 +#define DA9062AA_BUCK2_AUTO_MASK BIT(1) +#define DA9062AA_BUCK4_AUTO_SHIFT 2 +#define DA9062AA_BUCK4_AUTO_MASK BIT(2) +#define DA9062AA_BUCK3_AUTO_SHIFT 4 +#define DA9062AA_BUCK3_AUTO_MASK BIT(4) + +/* DA9062AA_CONFIG_G = 0x10C */ +#define DA9062AA_LDO1_AUTO_SHIFT 0 +#define DA9062AA_LDO1_AUTO_MASK 0x01 +#define DA9062AA_LDO2_AUTO_SHIFT 1 +#define DA9062AA_LDO2_AUTO_MASK BIT(1) +#define DA9062AA_LDO3_AUTO_SHIFT 2 +#define DA9062AA_LDO3_AUTO_MASK BIT(2) +#define DA9062AA_LDO4_AUTO_SHIFT 3 +#define DA9062AA_LDO4_AUTO_MASK BIT(3) + +/* DA9062AA_CONFIG_H = 0x10D */ +#define DA9062AA_BUCK1_2_MERGE_SHIFT 3 +#define DA9062AA_BUCK1_2_MERGE_MASK BIT(3) +#define DA9062AA_BUCK2_OD_SHIFT 5 +#define DA9062AA_BUCK2_OD_MASK BIT(5) +#define DA9062AA_BUCK1_OD_SHIFT 6 +#define DA9062AA_BUCK1_OD_MASK BIT(6) + +/* DA9062AA_CONFIG_I = 0x10E */ +#define DA9062AA_NONKEY_PIN_SHIFT 0 +#define DA9062AA_NONKEY_PIN_MASK 0x03 +#define DA9062AA_nONKEY_SD_SHIFT 2 +#define DA9062AA_nONKEY_SD_MASK BIT(2) +#define DA9062AA_WATCHDOG_SD_SHIFT 3 +#define DA9062AA_WATCHDOG_SD_MASK BIT(3) +#define DA9062AA_KEY_SD_MODE_SHIFT 4 +#define DA9062AA_KEY_SD_MODE_MASK BIT(4) +#define DA9062AA_HOST_SD_MODE_SHIFT 5 +#define DA9062AA_HOST_SD_MODE_MASK BIT(5) +#define DA9062AA_INT_SD_MODE_SHIFT 6 +#define DA9062AA_INT_SD_MODE_MASK BIT(6) +#define DA9062AA_LDO_SD_SHIFT 7 +#define DA9062AA_LDO_SD_MASK BIT(7) + +/* DA9062AA_CONFIG_J = 0x10F */ +#define DA9062AA_KEY_DELAY_SHIFT 0 +#define DA9062AA_KEY_DELAY_MASK 0x03 +#define DA9062AA_SHUT_DELAY_SHIFT 2 +#define DA9062AA_SHUT_DELAY_MASK (0x03 << 2) +#define DA9062AA_RESET_DURATION_SHIFT 4 +#define DA9062AA_RESET_DURATION_MASK (0x03 << 4) +#define DA9062AA_TWOWIRE_TO_SHIFT 6 +#define DA9062AA_TWOWIRE_TO_MASK BIT(6) +#define DA9062AA_IF_RESET_SHIFT 7 +#define DA9062AA_IF_RESET_MASK BIT(7) + +/* DA9062AA_CONFIG_K = 0x110 */ +#define DA9062AA_GPIO0_PUPD_SHIFT 0 +#define DA9062AA_GPIO0_PUPD_MASK 0x01 +#define DA9062AA_GPIO1_PUPD_SHIFT 1 +#define DA9062AA_GPIO1_PUPD_MASK BIT(1) +#define DA9062AA_GPIO2_PUPD_SHIFT 2 +#define DA9062AA_GPIO2_PUPD_MASK BIT(2) +#define DA9062AA_GPIO3_PUPD_SHIFT 3 +#define DA9062AA_GPIO3_PUPD_MASK BIT(3) +#define DA9062AA_GPIO4_PUPD_SHIFT 4 +#define DA9062AA_GPIO4_PUPD_MASK BIT(4) + +/* DA9062AA_CONFIG_M = 0x112 */ +#define DA9062AA_NSHUTDOWN_PU_SHIFT 1 +#define DA9062AA_NSHUTDOWN_PU_MASK BIT(1) +#define DA9062AA_WDG_MODE_SHIFT 3 +#define DA9062AA_WDG_MODE_MASK BIT(3) +#define DA9062AA_OSC_FRQ_SHIFT 4 +#define DA9062AA_OSC_FRQ_MASK (0x0f << 4) + +/* DA9062AA_TRIM_CLDR = 0x120 */ +#define DA9062AA_TRIM_CLDR_SHIFT 0 +#define DA9062AA_TRIM_CLDR_MASK 0xff + +/* DA9062AA_GP_ID_0 = 0x121 */ +#define DA9062AA_GP_0_SHIFT 0 +#define DA9062AA_GP_0_MASK 0xff + +/* DA9062AA_GP_ID_1 = 0x122 */ +#define DA9062AA_GP_1_SHIFT 0 +#define DA9062AA_GP_1_MASK 0xff + +/* DA9062AA_GP_ID_2 = 0x123 */ +#define DA9062AA_GP_2_SHIFT 0 +#define DA9062AA_GP_2_MASK 0xff + +/* DA9062AA_GP_ID_3 = 0x124 */ +#define DA9062AA_GP_3_SHIFT 0 +#define DA9062AA_GP_3_MASK 0xff + +/* DA9062AA_GP_ID_4 = 0x125 */ +#define DA9062AA_GP_4_SHIFT 0 +#define DA9062AA_GP_4_MASK 0xff + +/* DA9062AA_GP_ID_5 = 0x126 */ +#define DA9062AA_GP_5_SHIFT 0 +#define DA9062AA_GP_5_MASK 0xff + +/* DA9062AA_GP_ID_6 = 0x127 */ +#define DA9062AA_GP_6_SHIFT 0 +#define DA9062AA_GP_6_MASK 0xff + +/* DA9062AA_GP_ID_7 = 0x128 */ +#define DA9062AA_GP_7_SHIFT 0 +#define DA9062AA_GP_7_MASK 0xff + +/* DA9062AA_GP_ID_8 = 0x129 */ +#define DA9062AA_GP_8_SHIFT 0 +#define DA9062AA_GP_8_MASK 0xff + +/* DA9062AA_GP_ID_9 = 0x12A */ +#define DA9062AA_GP_9_SHIFT 0 +#define DA9062AA_GP_9_MASK 0xff + +/* DA9062AA_GP_ID_10 = 0x12B */ +#define DA9062AA_GP_10_SHIFT 0 +#define DA9062AA_GP_10_MASK 0xff + +/* DA9062AA_GP_ID_11 = 0x12C */ +#define DA9062AA_GP_11_SHIFT 0 +#define DA9062AA_GP_11_MASK 0xff + +/* DA9062AA_GP_ID_12 = 0x12D */ +#define DA9062AA_GP_12_SHIFT 0 +#define DA9062AA_GP_12_MASK 0xff + +/* DA9062AA_GP_ID_13 = 0x12E */ +#define DA9062AA_GP_13_SHIFT 0 +#define DA9062AA_GP_13_MASK 0xff + +/* DA9062AA_GP_ID_14 = 0x12F */ +#define DA9062AA_GP_14_SHIFT 0 +#define DA9062AA_GP_14_MASK 0xff + +/* DA9062AA_GP_ID_15 = 0x130 */ +#define DA9062AA_GP_15_SHIFT 0 +#define DA9062AA_GP_15_MASK 0xff + +/* DA9062AA_GP_ID_16 = 0x131 */ +#define DA9062AA_GP_16_SHIFT 0 +#define DA9062AA_GP_16_MASK 0xff + +/* DA9062AA_GP_ID_17 = 0x132 */ +#define DA9062AA_GP_17_SHIFT 0 +#define DA9062AA_GP_17_MASK 0xff + +/* DA9062AA_GP_ID_18 = 0x133 */ +#define DA9062AA_GP_18_SHIFT 0 +#define DA9062AA_GP_18_MASK 0xff + +/* DA9062AA_GP_ID_19 = 0x134 */ +#define DA9062AA_GP_19_SHIFT 0 +#define DA9062AA_GP_19_MASK 0xff + +/* DA9062AA_DEVICE_ID = 0x181 */ +#define DA9062AA_DEV_ID_SHIFT 0 +#define DA9062AA_DEV_ID_MASK 0xff + +/* DA9062AA_VARIANT_ID = 0x182 */ +#define DA9062AA_VRC_SHIFT 0 +#define DA9062AA_VRC_MASK 0x0f +#define DA9062AA_MRC_SHIFT 4 +#define DA9062AA_MRC_MASK (0x0f << 4) + +/* DA9062AA_CUSTOMER_ID = 0x183 */ +#define DA9062AA_CUST_ID_SHIFT 0 +#define DA9062AA_CUST_ID_MASK 0xff + +/* DA9062AA_CONFIG_ID = 0x184 */ +#define DA9062AA_CONFIG_REV_SHIFT 0 +#define DA9062AA_CONFIG_REV_MASK 0xff + +#endif /* __DA9062_H__ */ diff --git a/kernel/include/linux/mfd/da9063/core.h b/kernel/include/linux/mfd/da9063/core.h index 79f4d822b..621af8212 100644 --- a/kernel/include/linux/mfd/da9063/core.h +++ b/kernel/include/linux/mfd/da9063/core.h @@ -51,6 +51,7 @@ enum da9063_irqs { DA9063_IRQ_COMP_1V2, DA9063_IRQ_LDO_LIM, DA9063_IRQ_REG_UVOV, + DA9063_IRQ_DVC_RDY, DA9063_IRQ_VDD_MON, DA9063_IRQ_WARN, DA9063_IRQ_GPI0, diff --git a/kernel/include/linux/mfd/da9063/pdata.h b/kernel/include/linux/mfd/da9063/pdata.h index 95c874221..612383bd8 100644 --- a/kernel/include/linux/mfd/da9063/pdata.h +++ b/kernel/include/linux/mfd/da9063/pdata.h @@ -103,6 +103,7 @@ struct da9063; struct da9063_pdata { int (*init)(struct da9063 *da9063); int irq_base; + bool key_power; unsigned flags; struct da9063_regulators_pdata *regulators_pdata; struct led_platform_data *leds_pdata; diff --git a/kernel/include/linux/mfd/da9150/core.h b/kernel/include/linux/mfd/da9150/core.h index 76e668933..1bf50caeb 100644 --- a/kernel/include/linux/mfd/da9150/core.h +++ b/kernel/include/linux/mfd/da9150/core.h @@ -15,6 +15,7 @@ #define __DA9150_CORE_H #include <linux/device.h> +#include <linux/i2c.h> #include <linux/interrupt.h> #include <linux/regmap.h> @@ -46,23 +47,39 @@ #define DA9150_IRQ_GPADC 19 #define DA9150_IRQ_WKUP 20 +/* I2C sub-device address */ +#define DA9150_QIF_I2C_ADDR_LSB 0x5 + +struct da9150_fg_pdata { + u32 update_interval; /* msecs */ + u8 warn_soc_lvl; /* % value */ + u8 crit_soc_lvl; /* % value */ +}; + struct da9150_pdata { int irq_base; + struct da9150_fg_pdata *fg_pdata; }; struct da9150 { struct device *dev; struct regmap *regmap; + struct i2c_client *core_qif; + struct regmap_irq_chip_data *regmap_irq_data; int irq; int irq_base; }; -/* Device I/O */ +/* Device I/O - Query Interface for FG and standard register access */ +void da9150_read_qif(struct da9150 *da9150, u8 addr, int count, u8 *buf); +void da9150_write_qif(struct da9150 *da9150, u8 addr, int count, const u8 *buf); + u8 da9150_reg_read(struct da9150 *da9150, u16 reg); void da9150_reg_write(struct da9150 *da9150, u16 reg, u8 val); void da9150_set_bits(struct da9150 *da9150, u16 reg, u8 mask, u8 val); void da9150_bulk_read(struct da9150 *da9150, u16 reg, int count, u8 *buf); void da9150_bulk_write(struct da9150 *da9150, u16 reg, int count, const u8 *buf); + #endif /* __DA9150_CORE_H */ diff --git a/kernel/include/linux/mfd/intel_bxtwc.h b/kernel/include/linux/mfd/intel_bxtwc.h new file mode 100644 index 000000000..1a0ee9d6e --- /dev/null +++ b/kernel/include/linux/mfd/intel_bxtwc.h @@ -0,0 +1,69 @@ +/* + * intel_bxtwc.h - Header file for Intel Broxton Whiskey Cove PMIC + * + * Copyright (C) 2015 Intel Corporation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ + +#include <linux/mfd/intel_soc_pmic.h> + +#ifndef __INTEL_BXTWC_H__ +#define __INTEL_BXTWC_H__ + +/* BXT WC devices */ +#define BXTWC_DEVICE1_ADDR 0x4E +#define BXTWC_DEVICE2_ADDR 0x4F +#define BXTWC_DEVICE3_ADDR 0x5E + +/* device1 Registers */ +#define BXTWC_CHIPID 0x4E00 +#define BXTWC_CHIPVER 0x4E01 + +#define BXTWC_SCHGRIRQ0_ADDR 0x5E1A +#define BXTWC_CHGRCTRL0_ADDR 0x5E16 +#define BXTWC_CHGRCTRL1_ADDR 0x5E17 +#define BXTWC_CHGRCTRL2_ADDR 0x5E18 +#define BXTWC_CHGRSTATUS_ADDR 0x5E19 +#define BXTWC_THRMBATZONE_ADDR 0x4F22 + +#define BXTWC_USBPATH_ADDR 0x5E19 +#define BXTWC_USBPHYCTRL_ADDR 0x5E07 +#define BXTWC_USBIDCTRL_ADDR 0x5E05 +#define BXTWC_USBIDEN_MASK 0x01 +#define BXTWC_USBIDSTAT_ADDR 0x00FF +#define BXTWC_USBSRCDETSTATUS_ADDR 0x5E29 + +#define BXTWC_DBGUSBBC1_ADDR 0x5FE0 +#define BXTWC_DBGUSBBC2_ADDR 0x5FE1 +#define BXTWC_DBGUSBBCSTAT_ADDR 0x5FE2 + +#define BXTWC_WAKESRC_ADDR 0x4E22 +#define BXTWC_WAKESRC2_ADDR 0x4EE5 +#define BXTWC_CHRTTADDR_ADDR 0x5E22 +#define BXTWC_CHRTTDATA_ADDR 0x5E23 + +#define BXTWC_STHRMIRQ0_ADDR 0x4F19 +#define WC_MTHRMIRQ1_ADDR 0x4E12 +#define WC_STHRMIRQ1_ADDR 0x4F1A +#define WC_STHRMIRQ2_ADDR 0x4F1B + +#define BXTWC_THRMZN0H_ADDR 0x4F44 +#define BXTWC_THRMZN0L_ADDR 0x4F45 +#define BXTWC_THRMZN1H_ADDR 0x4F46 +#define BXTWC_THRMZN1L_ADDR 0x4F47 +#define BXTWC_THRMZN2H_ADDR 0x4F48 +#define BXTWC_THRMZN2L_ADDR 0x4F49 +#define BXTWC_THRMZN3H_ADDR 0x4F4A +#define BXTWC_THRMZN3L_ADDR 0x4F4B +#define BXTWC_THRMZN4H_ADDR 0x4F4C +#define BXTWC_THRMZN4L_ADDR 0x4F4D + +#endif diff --git a/kernel/include/linux/mfd/intel_soc_pmic.h b/kernel/include/linux/mfd/intel_soc_pmic.h index abcbfcf32..cf619dbea 100644 --- a/kernel/include/linux/mfd/intel_soc_pmic.h +++ b/kernel/include/linux/mfd/intel_soc_pmic.h @@ -25,6 +25,8 @@ struct intel_soc_pmic { int irq; struct regmap *regmap; struct regmap_irq_chip_data *irq_chip_data; + struct regmap_irq_chip_data *irq_chip_data_level2; + struct device *dev; }; #endif /* __INTEL_SOC_PMIC_H__ */ diff --git a/kernel/include/linux/mfd/lpc_ich.h b/kernel/include/linux/mfd/lpc_ich.h index 8feac782f..2b300b44f 100644 --- a/kernel/include/linux/mfd/lpc_ich.h +++ b/kernel/include/linux/mfd/lpc_ich.h @@ -20,12 +20,6 @@ #ifndef LPC_ICH_H #define LPC_ICH_H -/* Watchdog resources */ -#define ICH_RES_IO_TCO 0 -#define ICH_RES_IO_SMI 1 -#define ICH_RES_MEM_OFF 2 -#define ICH_RES_MEM_GCS_PMC 0 - /* GPIO resources */ #define ICH_RES_GPIO 0 #define ICH_RES_GPE0 1 diff --git a/kernel/include/linux/mfd/max77686.h b/kernel/include/linux/mfd/max77686.h index bb995ab9a..d4b72d519 100644 --- a/kernel/include/linux/mfd/max77686.h +++ b/kernel/include/linux/mfd/max77686.h @@ -125,9 +125,4 @@ enum max77686_opmode { MAX77686_OPMODE_STANDBY, }; -struct max77686_opmode_data { - int id; - int mode; -}; - #endif /* __LINUX_MFD_MAX77686_H */ diff --git a/kernel/include/linux/mfd/max77693-common.h b/kernel/include/linux/mfd/max77693-common.h new file mode 100644 index 000000000..095b121aa --- /dev/null +++ b/kernel/include/linux/mfd/max77693-common.h @@ -0,0 +1,49 @@ +/* + * Common data shared between Maxim 77693 and 77843 drivers + * + * Copyright (C) 2015 Samsung Electronics + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#ifndef __LINUX_MFD_MAX77693_COMMON_H +#define __LINUX_MFD_MAX77693_COMMON_H + +enum max77693_types { + TYPE_MAX77693_UNKNOWN, + TYPE_MAX77693, + TYPE_MAX77843, + + TYPE_MAX77693_NUM, +}; + +/* + * Shared also with max77843. + */ +struct max77693_dev { + struct device *dev; + struct i2c_client *i2c; /* 0xCC , PMIC, Charger, Flash LED */ + struct i2c_client *i2c_muic; /* 0x4A , MUIC */ + struct i2c_client *i2c_haptic; /* MAX77693: 0x90 , Haptic */ + struct i2c_client *i2c_chg; /* MAX77843: 0xD2, Charger */ + + enum max77693_types type; + + struct regmap *regmap; + struct regmap *regmap_muic; + struct regmap *regmap_haptic; /* Only MAX77693 */ + struct regmap *regmap_chg; /* Only MAX77843 */ + + struct regmap_irq_chip_data *irq_data_led; + struct regmap_irq_chip_data *irq_data_topsys; + struct regmap_irq_chip_data *irq_data_chg; /* Only MAX77693 */ + struct regmap_irq_chip_data *irq_data_muic; + + int irq; +}; + + +#endif /* __LINUX_MFD_MAX77693_COMMON_H */ diff --git a/kernel/include/linux/mfd/max77693-private.h b/kernel/include/linux/mfd/max77693-private.h index 51633ea6f..3c7a63b98 100644 --- a/kernel/include/linux/mfd/max77693-private.h +++ b/kernel/include/linux/mfd/max77693-private.h @@ -310,30 +310,30 @@ enum max77693_muic_reg { #define INTMASK2_CHGTYP_MASK (1 << INTMASK2_CHGTYP_SHIFT) /* MAX77693 MUIC - STATUS1~3 Register */ -#define STATUS1_ADC_SHIFT (0) -#define STATUS1_ADCLOW_SHIFT (5) -#define STATUS1_ADCERR_SHIFT (6) -#define STATUS1_ADC1K_SHIFT (7) -#define STATUS1_ADC_MASK (0x1f << STATUS1_ADC_SHIFT) -#define STATUS1_ADCLOW_MASK (0x1 << STATUS1_ADCLOW_SHIFT) -#define STATUS1_ADCERR_MASK (0x1 << STATUS1_ADCERR_SHIFT) -#define STATUS1_ADC1K_MASK (0x1 << STATUS1_ADC1K_SHIFT) - -#define STATUS2_CHGTYP_SHIFT (0) -#define STATUS2_CHGDETRUN_SHIFT (3) -#define STATUS2_DCDTMR_SHIFT (4) -#define STATUS2_DXOVP_SHIFT (5) -#define STATUS2_VBVOLT_SHIFT (6) -#define STATUS2_VIDRM_SHIFT (7) -#define STATUS2_CHGTYP_MASK (0x7 << STATUS2_CHGTYP_SHIFT) -#define STATUS2_CHGDETRUN_MASK (0x1 << STATUS2_CHGDETRUN_SHIFT) -#define STATUS2_DCDTMR_MASK (0x1 << STATUS2_DCDTMR_SHIFT) -#define STATUS2_DXOVP_MASK (0x1 << STATUS2_DXOVP_SHIFT) -#define STATUS2_VBVOLT_MASK (0x1 << STATUS2_VBVOLT_SHIFT) -#define STATUS2_VIDRM_MASK (0x1 << STATUS2_VIDRM_SHIFT) - -#define STATUS3_OVP_SHIFT (2) -#define STATUS3_OVP_MASK (0x1 << STATUS3_OVP_SHIFT) +#define MAX77693_STATUS1_ADC_SHIFT 0 +#define MAX77693_STATUS1_ADCLOW_SHIFT 5 +#define MAX77693_STATUS1_ADCERR_SHIFT 6 +#define MAX77693_STATUS1_ADC1K_SHIFT 7 +#define MAX77693_STATUS1_ADC_MASK (0x1f << MAX77693_STATUS1_ADC_SHIFT) +#define MAX77693_STATUS1_ADCLOW_MASK BIT(MAX77693_STATUS1_ADCLOW_SHIFT) +#define MAX77693_STATUS1_ADCERR_MASK BIT(MAX77693_STATUS1_ADCERR_SHIFT) +#define MAX77693_STATUS1_ADC1K_MASK BIT(MAX77693_STATUS1_ADC1K_SHIFT) + +#define MAX77693_STATUS2_CHGTYP_SHIFT 0 +#define MAX77693_STATUS2_CHGDETRUN_SHIFT 3 +#define MAX77693_STATUS2_DCDTMR_SHIFT 4 +#define MAX77693_STATUS2_DXOVP_SHIFT 5 +#define MAX77693_STATUS2_VBVOLT_SHIFT 6 +#define MAX77693_STATUS2_VIDRM_SHIFT 7 +#define MAX77693_STATUS2_CHGTYP_MASK (0x7 << MAX77693_STATUS2_CHGTYP_SHIFT) +#define MAX77693_STATUS2_CHGDETRUN_MASK BIT(MAX77693_STATUS2_CHGDETRUN_SHIFT) +#define MAX77693_STATUS2_DCDTMR_MASK BIT(MAX77693_STATUS2_DCDTMR_SHIFT) +#define MAX77693_STATUS2_DXOVP_MASK BIT(MAX77693_STATUS2_DXOVP_SHIFT) +#define MAX77693_STATUS2_VBVOLT_MASK BIT(MAX77693_STATUS2_VBVOLT_SHIFT) +#define MAX77693_STATUS2_VIDRM_MASK BIT(MAX77693_STATUS2_VIDRM_SHIFT) + +#define MAX77693_STATUS3_OVP_SHIFT 2 +#define MAX77693_STATUS3_OVP_MASK BIT(MAX77693_STATUS3_OVP_SHIFT) /* MAX77693 CDETCTRL1~2 register */ #define CDETCTRL1_CHGDETEN_SHIFT (0) @@ -362,38 +362,38 @@ enum max77693_muic_reg { #define COMN1SW_MASK (0x7 << COMN1SW_SHIFT) #define COMP2SW_MASK (0x7 << COMP2SW_SHIFT) #define COMP_SW_MASK (COMP2SW_MASK | COMN1SW_MASK) -#define CONTROL1_SW_USB ((1 << COMP2SW_SHIFT) \ +#define MAX77693_CONTROL1_SW_USB ((1 << COMP2SW_SHIFT) \ | (1 << COMN1SW_SHIFT)) -#define CONTROL1_SW_AUDIO ((2 << COMP2SW_SHIFT) \ +#define MAX77693_CONTROL1_SW_AUDIO ((2 << COMP2SW_SHIFT) \ | (2 << COMN1SW_SHIFT)) -#define CONTROL1_SW_UART ((3 << COMP2SW_SHIFT) \ +#define MAX77693_CONTROL1_SW_UART ((3 << COMP2SW_SHIFT) \ | (3 << COMN1SW_SHIFT)) -#define CONTROL1_SW_OPEN ((0 << COMP2SW_SHIFT) \ +#define MAX77693_CONTROL1_SW_OPEN ((0 << COMP2SW_SHIFT) \ | (0 << COMN1SW_SHIFT)) -#define CONTROL2_LOWPWR_SHIFT (0) -#define CONTROL2_ADCEN_SHIFT (1) -#define CONTROL2_CPEN_SHIFT (2) -#define CONTROL2_SFOUTASRT_SHIFT (3) -#define CONTROL2_SFOUTORD_SHIFT (4) -#define CONTROL2_ACCDET_SHIFT (5) -#define CONTROL2_USBCPINT_SHIFT (6) -#define CONTROL2_RCPS_SHIFT (7) -#define CONTROL2_LOWPWR_MASK (0x1 << CONTROL2_LOWPWR_SHIFT) -#define CONTROL2_ADCEN_MASK (0x1 << CONTROL2_ADCEN_SHIFT) -#define CONTROL2_CPEN_MASK (0x1 << CONTROL2_CPEN_SHIFT) -#define CONTROL2_SFOUTASRT_MASK (0x1 << CONTROL2_SFOUTASRT_SHIFT) -#define CONTROL2_SFOUTORD_MASK (0x1 << CONTROL2_SFOUTORD_SHIFT) -#define CONTROL2_ACCDET_MASK (0x1 << CONTROL2_ACCDET_SHIFT) -#define CONTROL2_USBCPINT_MASK (0x1 << CONTROL2_USBCPINT_SHIFT) -#define CONTROL2_RCPS_MASK (0x1 << CONTROL2_RCPS_SHIFT) - -#define CONTROL3_JIGSET_SHIFT (0) -#define CONTROL3_BTLDSET_SHIFT (2) -#define CONTROL3_ADCDBSET_SHIFT (4) -#define CONTROL3_JIGSET_MASK (0x3 << CONTROL3_JIGSET_SHIFT) -#define CONTROL3_BTLDSET_MASK (0x3 << CONTROL3_BTLDSET_SHIFT) -#define CONTROL3_ADCDBSET_MASK (0x3 << CONTROL3_ADCDBSET_SHIFT) +#define MAX77693_CONTROL2_LOWPWR_SHIFT 0 +#define MAX77693_CONTROL2_ADCEN_SHIFT 1 +#define MAX77693_CONTROL2_CPEN_SHIFT 2 +#define MAX77693_CONTROL2_SFOUTASRT_SHIFT 3 +#define MAX77693_CONTROL2_SFOUTORD_SHIFT 4 +#define MAX77693_CONTROL2_ACCDET_SHIFT 5 +#define MAX77693_CONTROL2_USBCPINT_SHIFT 6 +#define MAX77693_CONTROL2_RCPS_SHIFT 7 +#define MAX77693_CONTROL2_LOWPWR_MASK BIT(MAX77693_CONTROL2_LOWPWR_SHIFT) +#define MAX77693_CONTROL2_ADCEN_MASK BIT(MAX77693_CONTROL2_ADCEN_SHIFT) +#define MAX77693_CONTROL2_CPEN_MASK BIT(MAX77693_CONTROL2_CPEN_SHIFT) +#define MAX77693_CONTROL2_SFOUTASRT_MASK BIT(MAX77693_CONTROL2_SFOUTASRT_SHIFT) +#define MAX77693_CONTROL2_SFOUTORD_MASK BIT(MAX77693_CONTROL2_SFOUTORD_SHIFT) +#define MAX77693_CONTROL2_ACCDET_MASK BIT(MAX77693_CONTROL2_ACCDET_SHIFT) +#define MAX77693_CONTROL2_USBCPINT_MASK BIT(MAX77693_CONTROL2_USBCPINT_SHIFT) +#define MAX77693_CONTROL2_RCPS_MASK BIT(MAX77693_CONTROL2_RCPS_SHIFT) + +#define MAX77693_CONTROL3_JIGSET_SHIFT 0 +#define MAX77693_CONTROL3_BTLDSET_SHIFT 2 +#define MAX77693_CONTROL3_ADCDBSET_SHIFT 4 +#define MAX77693_CONTROL3_JIGSET_MASK (0x3 << MAX77693_CONTROL3_JIGSET_SHIFT) +#define MAX77693_CONTROL3_BTLDSET_MASK (0x3 << MAX77693_CONTROL3_BTLDSET_SHIFT) +#define MAX77693_CONTROL3_ADCDBSET_MASK (0x3 << MAX77693_CONTROL3_ADCDBSET_SHIFT) /* Slave addr = 0x90: Haptic */ enum max77693_haptic_reg { @@ -529,36 +529,4 @@ enum max77693_irq_muic { MAX77693_MUIC_IRQ_NR, }; -struct max77693_dev { - struct device *dev; - struct i2c_client *i2c; /* 0xCC , PMIC, Charger, Flash LED */ - struct i2c_client *muic; /* 0x4A , MUIC */ - struct i2c_client *haptic; /* 0x90 , Haptic */ - - int type; - - struct regmap *regmap; - struct regmap *regmap_muic; - struct regmap *regmap_haptic; - - struct regmap_irq_chip_data *irq_data_led; - struct regmap_irq_chip_data *irq_data_topsys; - struct regmap_irq_chip_data *irq_data_charger; - struct regmap_irq_chip_data *irq_data_muic; - - int irq; - int irq_gpio; - struct mutex irqlock; - int irq_masks_cur[MAX77693_IRQ_GROUP_NR]; - int irq_masks_cache[MAX77693_IRQ_GROUP_NR]; -}; - -enum max77693_types { - TYPE_MAX77693, -}; - -extern int max77693_irq_init(struct max77693_dev *max77686); -extern void max77693_irq_exit(struct max77693_dev *max77686); -extern int max77693_irq_resume(struct max77693_dev *max77686); - #endif /* __LINUX_MFD_MAX77693_PRIV_H */ diff --git a/kernel/include/linux/mfd/max77843-private.h b/kernel/include/linux/mfd/max77843-private.h index 7178ace83..c19303b0c 100644 --- a/kernel/include/linux/mfd/max77843-private.h +++ b/kernel/include/linux/mfd/max77843-private.h @@ -318,62 +318,62 @@ enum max77843_irq_muic { MAX77843_INTSRCMASK_SYS_MASK | MAX77843_INTSRCMASK_CHGR_MASK) /* MAX77843 STATUS register*/ -#define STATUS1_ADC_SHIFT 0 -#define STATUS1_ADCERROR_SHIFT 6 -#define STATUS1_ADC1K_SHIFT 7 -#define STATUS2_CHGTYP_SHIFT 0 -#define STATUS2_CHGDETRUN_SHIFT 3 -#define STATUS2_DCDTMR_SHIFT 4 -#define STATUS2_DXOVP_SHIFT 5 -#define STATUS2_VBVOLT_SHIFT 6 -#define STATUS3_VBADC_SHIFT 0 -#define STATUS3_VDNMON_SHIFT 4 -#define STATUS3_DNRES_SHIFT 5 -#define STATUS3_MPNACK_SHIFT 6 - -#define MAX77843_MUIC_STATUS1_ADC_MASK (0x1f << STATUS1_ADC_SHIFT) -#define MAX77843_MUIC_STATUS1_ADCERROR_MASK BIT(STATUS1_ADCERROR_SHIFT) -#define MAX77843_MUIC_STATUS1_ADC1K_MASK BIT(STATUS1_ADC1K_SHIFT) -#define MAX77843_MUIC_STATUS2_CHGTYP_MASK (0x7 << STATUS2_CHGTYP_SHIFT) -#define MAX77843_MUIC_STATUS2_CHGDETRUN_MASK BIT(STATUS2_CHGDETRUN_SHIFT) -#define MAX77843_MUIC_STATUS2_DCDTMR_MASK BIT(STATUS2_DCDTMR_SHIFT) -#define MAX77843_MUIC_STATUS2_DXOVP_MASK BIT(STATUS2_DXOVP_SHIFT) -#define MAX77843_MUIC_STATUS2_VBVOLT_MASK BIT(STATUS2_VBVOLT_SHIFT) -#define MAX77843_MUIC_STATUS3_VBADC_MASK (0xf << STATUS3_VBADC_SHIFT) -#define MAX77843_MUIC_STATUS3_VDNMON_MASK BIT(STATUS3_VDNMON_SHIFT) -#define MAX77843_MUIC_STATUS3_DNRES_MASK BIT(STATUS3_DNRES_SHIFT) -#define MAX77843_MUIC_STATUS3_MPNACK_MASK BIT(STATUS3_MPNACK_SHIFT) +#define MAX77843_MUIC_STATUS1_ADC_SHIFT 0 +#define MAX77843_MUIC_STATUS1_ADCERROR_SHIFT 6 +#define MAX77843_MUIC_STATUS1_ADC1K_SHIFT 7 +#define MAX77843_MUIC_STATUS2_CHGTYP_SHIFT 0 +#define MAX77843_MUIC_STATUS2_CHGDETRUN_SHIFT 3 +#define MAX77843_MUIC_STATUS2_DCDTMR_SHIFT 4 +#define MAX77843_MUIC_STATUS2_DXOVP_SHIFT 5 +#define MAX77843_MUIC_STATUS2_VBVOLT_SHIFT 6 +#define MAX77843_MUIC_STATUS3_VBADC_SHIFT 0 +#define MAX77843_MUIC_STATUS3_VDNMON_SHIFT 4 +#define MAX77843_MUIC_STATUS3_DNRES_SHIFT 5 +#define MAX77843_MUIC_STATUS3_MPNACK_SHIFT 6 + +#define MAX77843_MUIC_STATUS1_ADC_MASK (0x1f << MAX77843_MUIC_STATUS1_ADC_SHIFT) +#define MAX77843_MUIC_STATUS1_ADCERROR_MASK BIT(MAX77843_MUIC_STATUS1_ADCERROR_SHIFT) +#define MAX77843_MUIC_STATUS1_ADC1K_MASK BIT(MAX77843_MUIC_STATUS1_ADC1K_SHIFT) +#define MAX77843_MUIC_STATUS2_CHGTYP_MASK (0x7 << MAX77843_MUIC_STATUS2_CHGTYP_SHIFT) +#define MAX77843_MUIC_STATUS2_CHGDETRUN_MASK BIT(MAX77843_MUIC_STATUS2_CHGDETRUN_SHIFT) +#define MAX77843_MUIC_STATUS2_DCDTMR_MASK BIT(MAX77843_MUIC_STATUS2_DCDTMR_SHIFT) +#define MAX77843_MUIC_STATUS2_DXOVP_MASK BIT(MAX77843_MUIC_STATUS2_DXOVP_SHIFT) +#define MAX77843_MUIC_STATUS2_VBVOLT_MASK BIT(MAX77843_MUIC_STATUS2_VBVOLT_SHIFT) +#define MAX77843_MUIC_STATUS3_VBADC_MASK (0xf << MAX77843_MUIC_STATUS3_VBADC_SHIFT) +#define MAX77843_MUIC_STATUS3_VDNMON_MASK BIT(MAX77843_MUIC_STATUS3_VDNMON_SHIFT) +#define MAX77843_MUIC_STATUS3_DNRES_MASK BIT(MAX77843_MUIC_STATUS3_DNRES_SHIFT) +#define MAX77843_MUIC_STATUS3_MPNACK_MASK BIT(MAX77843_MUIC_STATUS3_MPNACK_SHIFT) /* MAX77843 CONTROL register */ -#define CONTROL1_COMP1SW_SHIFT 0 -#define CONTROL1_COMP2SW_SHIFT 3 -#define CONTROL1_IDBEN_SHIFT 7 -#define CONTROL2_LOWPWR_SHIFT 0 -#define CONTROL2_ADCEN_SHIFT 1 -#define CONTROL2_CPEN_SHIFT 2 -#define CONTROL2_ACC_DET_SHIFT 5 -#define CONTROL2_USBCPINT_SHIFT 6 -#define CONTROL2_RCPS_SHIFT 7 -#define CONTROL3_JIGSET_SHIFT 0 -#define CONTROL4_ADCDBSET_SHIFT 0 -#define CONTROL4_USBAUTO_SHIFT 4 -#define CONTROL4_FCTAUTO_SHIFT 5 -#define CONTROL4_ADCMODE_SHIFT 6 - -#define MAX77843_MUIC_CONTROL1_COMP1SW_MASK (0x7 << CONTROL1_COMP1SW_SHIFT) -#define MAX77843_MUIC_CONTROL1_COMP2SW_MASK (0x7 << CONTROL1_COMP2SW_SHIFT) -#define MAX77843_MUIC_CONTROL1_IDBEN_MASK BIT(CONTROL1_IDBEN_SHIFT) -#define MAX77843_MUIC_CONTROL2_LOWPWR_MASK BIT(CONTROL2_LOWPWR_SHIFT) -#define MAX77843_MUIC_CONTROL2_ADCEN_MASK BIT(CONTROL2_ADCEN_SHIFT) -#define MAX77843_MUIC_CONTROL2_CPEN_MASK BIT(CONTROL2_CPEN_SHIFT) -#define MAX77843_MUIC_CONTROL2_ACC_DET_MASK BIT(CONTROL2_ACC_DET_SHIFT) -#define MAX77843_MUIC_CONTROL2_USBCPINT_MASK BIT(CONTROL2_USBCPINT_SHIFT) -#define MAX77843_MUIC_CONTROL2_RCPS_MASK BIT(CONTROL2_RCPS_SHIFT) -#define MAX77843_MUIC_CONTROL3_JIGSET_MASK (0x3 << CONTROL3_JIGSET_SHIFT) -#define MAX77843_MUIC_CONTROL4_ADCDBSET_MASK (0x3 << CONTROL4_ADCDBSET_SHIFT) -#define MAX77843_MUIC_CONTROL4_USBAUTO_MASK BIT(CONTROL4_USBAUTO_SHIFT) -#define MAX77843_MUIC_CONTROL4_FCTAUTO_MASK BIT(CONTROL4_FCTAUTO_SHIFT) -#define MAX77843_MUIC_CONTROL4_ADCMODE_MASK (0x3 << CONTROL4_ADCMODE_SHIFT) +#define MAX77843_MUIC_CONTROL1_COMP1SW_SHIFT 0 +#define MAX77843_MUIC_CONTROL1_COMP2SW_SHIFT 3 +#define MAX77843_MUIC_CONTROL1_IDBEN_SHIFT 7 +#define MAX77843_MUIC_CONTROL2_LOWPWR_SHIFT 0 +#define MAX77843_MUIC_CONTROL2_ADCEN_SHIFT 1 +#define MAX77843_MUIC_CONTROL2_CPEN_SHIFT 2 +#define MAX77843_MUIC_CONTROL2_ACC_DET_SHIFT 5 +#define MAX77843_MUIC_CONTROL2_USBCPINT_SHIFT 6 +#define MAX77843_MUIC_CONTROL2_RCPS_SHIFT 7 +#define MAX77843_MUIC_CONTROL3_JIGSET_SHIFT 0 +#define MAX77843_MUIC_CONTROL4_ADCDBSET_SHIFT 0 +#define MAX77843_MUIC_CONTROL4_USBAUTO_SHIFT 4 +#define MAX77843_MUIC_CONTROL4_FCTAUTO_SHIFT 5 +#define MAX77843_MUIC_CONTROL4_ADCMODE_SHIFT 6 + +#define MAX77843_MUIC_CONTROL1_COMP1SW_MASK (0x7 << MAX77843_MUIC_CONTROL1_COMP1SW_SHIFT) +#define MAX77843_MUIC_CONTROL1_COMP2SW_MASK (0x7 << MAX77843_MUIC_CONTROL1_COMP2SW_SHIFT) +#define MAX77843_MUIC_CONTROL1_IDBEN_MASK BIT(MAX77843_MUIC_CONTROL1_IDBEN_SHIFT) +#define MAX77843_MUIC_CONTROL2_LOWPWR_MASK BIT(MAX77843_MUIC_CONTROL2_LOWPWR_SHIFT) +#define MAX77843_MUIC_CONTROL2_ADCEN_MASK BIT(MAX77843_MUIC_CONTROL2_ADCEN_SHIFT) +#define MAX77843_MUIC_CONTROL2_CPEN_MASK BIT(MAX77843_MUIC_CONTROL2_CPEN_SHIFT) +#define MAX77843_MUIC_CONTROL2_ACC_DET_MASK BIT(MAX77843_MUIC_CONTROL2_ACC_DET_SHIFT) +#define MAX77843_MUIC_CONTROL2_USBCPINT_MASK BIT(MAX77843_MUIC_CONTROL2_USBCPINT_SHIFT) +#define MAX77843_MUIC_CONTROL2_RCPS_MASK BIT(MAX77843_MUIC_CONTROL2_RCPS_SHIFT) +#define MAX77843_MUIC_CONTROL3_JIGSET_MASK (0x3 << MAX77843_MUIC_CONTROL3_JIGSET_SHIFT) +#define MAX77843_MUIC_CONTROL4_ADCDBSET_MASK (0x3 << MAX77843_MUIC_CONTROL4_ADCDBSET_SHIFT) +#define MAX77843_MUIC_CONTROL4_USBAUTO_MASK BIT(MAX77843_MUIC_CONTROL4_USBAUTO_SHIFT) +#define MAX77843_MUIC_CONTROL4_FCTAUTO_MASK BIT(MAX77843_MUIC_CONTROL4_FCTAUTO_SHIFT) +#define MAX77843_MUIC_CONTROL4_ADCMODE_MASK (0x3 << MAX77843_MUIC_CONTROL4_ADCMODE_SHIFT) /* MAX77843 switch port */ #define COM_OPEN 0 @@ -383,38 +383,38 @@ enum max77843_irq_muic { #define COM_AUX_USB 4 #define COM_AUX_UART 5 -#define CONTROL1_COM_SW \ +#define MAX77843_MUIC_CONTROL1_COM_SW \ ((MAX77843_MUIC_CONTROL1_COMP1SW_MASK | \ MAX77843_MUIC_CONTROL1_COMP2SW_MASK)) -#define CONTROL1_SW_OPEN \ - ((COM_OPEN << CONTROL1_COMP1SW_SHIFT | \ - COM_OPEN << CONTROL1_COMP2SW_SHIFT)) -#define CONTROL1_SW_USB \ - ((COM_USB << CONTROL1_COMP1SW_SHIFT | \ - COM_USB << CONTROL1_COMP2SW_SHIFT)) -#define CONTROL1_SW_AUDIO \ - ((COM_AUDIO << CONTROL1_COMP1SW_SHIFT | \ - COM_AUDIO << CONTROL1_COMP2SW_SHIFT)) -#define CONTROL1_SW_UART \ - ((COM_UART << CONTROL1_COMP1SW_SHIFT | \ - COM_UART << CONTROL1_COMP2SW_SHIFT)) -#define CONTROL1_SW_AUX_USB \ - ((COM_AUX_USB << CONTROL1_COMP1SW_SHIFT | \ - COM_AUX_USB << CONTROL1_COMP2SW_SHIFT)) -#define CONTROL1_SW_AUX_UART \ - ((COM_AUX_UART << CONTROL1_COMP1SW_SHIFT | \ - COM_AUX_UART << CONTROL1_COMP2SW_SHIFT)) +#define MAX77843_MUIC_CONTROL1_SW_OPEN \ + ((COM_OPEN << MAX77843_MUIC_CONTROL1_COMP1SW_SHIFT | \ + COM_OPEN << MAX77843_MUIC_CONTROL1_COMP2SW_SHIFT)) +#define MAX77843_MUIC_CONTROL1_SW_USB \ + ((COM_USB << MAX77843_MUIC_CONTROL1_COMP1SW_SHIFT | \ + COM_USB << MAX77843_MUIC_CONTROL1_COMP2SW_SHIFT)) +#define MAX77843_MUIC_CONTROL1_SW_AUDIO \ + ((COM_AUDIO << MAX77843_MUIC_CONTROL1_COMP1SW_SHIFT | \ + COM_AUDIO << MAX77843_MUIC_CONTROL1_COMP2SW_SHIFT)) +#define MAX77843_MUIC_CONTROL1_SW_UART \ + ((COM_UART << MAX77843_MUIC_CONTROL1_COMP1SW_SHIFT | \ + COM_UART << MAX77843_MUIC_CONTROL1_COMP2SW_SHIFT)) +#define MAX77843_MUIC_CONTROL1_SW_AUX_USB \ + ((COM_AUX_USB << MAX77843_MUIC_CONTROL1_COMP1SW_SHIFT | \ + COM_AUX_USB << MAX77843_MUIC_CONTROL1_COMP2SW_SHIFT)) +#define MAX77843_MUIC_CONTROL1_SW_AUX_UART \ + ((COM_AUX_UART << MAX77843_MUIC_CONTROL1_COMP1SW_SHIFT | \ + COM_AUX_UART << MAX77843_MUIC_CONTROL1_COMP2SW_SHIFT)) #define MAX77843_DISABLE 0 #define MAX77843_ENABLE 1 #define CONTROL4_AUTO_DISABLE \ - ((MAX77843_DISABLE << CONTROL4_USBAUTO_SHIFT) | \ - (MAX77843_DISABLE << CONTROL4_FCTAUTO_SHIFT)) + ((MAX77843_DISABLE << MAX77843_MUIC_CONTROL4_USBAUTO_SHIFT) | \ + (MAX77843_DISABLE << MAX77843_MUIC_CONTROL4_FCTAUTO_SHIFT)) #define CONTROL4_AUTO_ENABLE \ - ((MAX77843_ENABLE << CONTROL4_USBAUTO_SHIFT) | \ - (MAX77843_ENABLE << CONTROL4_FCTAUTO_SHIFT)) + ((MAX77843_ENABLE << MAX77843_MUIC_CONTROL4_USBAUTO_SHIFT) | \ + (MAX77843_ENABLE << MAX77843_MUIC_CONTROL4_FCTAUTO_SHIFT)) /* MAX77843 SAFEOUT LDO Control register */ #define SAFEOUTCTRL_SAFEOUT1_SHIFT 0 @@ -431,24 +431,4 @@ enum max77843_irq_muic { #define MAX77843_REG_SAFEOUTCTRL_SAFEOUT2_MASK \ (0x3 << SAFEOUTCTRL_SAFEOUT2_SHIFT) -struct max77843 { - struct device *dev; - - struct i2c_client *i2c; - struct i2c_client *i2c_chg; - struct i2c_client *i2c_fuel; - struct i2c_client *i2c_muic; - - struct regmap *regmap; - struct regmap *regmap_chg; - struct regmap *regmap_fuel; - struct regmap *regmap_muic; - - struct regmap_irq_chip_data *irq_data; - struct regmap_irq_chip_data *irq_data_chg; - struct regmap_irq_chip_data *irq_data_fuel; - struct regmap_irq_chip_data *irq_data_muic; - - int irq; -}; #endif /* __MAX77843_H__ */ diff --git a/kernel/include/linux/mfd/mt6397/core.h b/kernel/include/linux/mfd/mt6397/core.h index cf5265b0d..45b8e8aa1 100644 --- a/kernel/include/linux/mfd/mt6397/core.h +++ b/kernel/include/linux/mfd/mt6397/core.h @@ -57,6 +57,7 @@ struct mt6397_chip { int irq; struct irq_domain *irq_domain; struct mutex irqlock; + u16 wake_mask[2]; u16 irq_masks_cur[2]; u16 irq_masks_cache[2]; }; diff --git a/kernel/include/linux/mfd/palmas.h b/kernel/include/linux/mfd/palmas.h index bb270bd03..13e1d9693 100644 --- a/kernel/include/linux/mfd/palmas.h +++ b/kernel/include/linux/mfd/palmas.h @@ -21,6 +21,7 @@ #include <linux/regmap.h> #include <linux/regulator/driver.h> #include <linux/extcon.h> +#include <linux/of_gpio.h> #include <linux/usb/phy_companion.h> #define PALMAS_NUM_CLIENTS 3 @@ -551,10 +552,16 @@ struct palmas_usb { int vbus_otg_irq; int vbus_irq; + int gpio_id_irq; + struct gpio_desc *id_gpiod; + unsigned long sw_debounce_jiffies; + struct delayed_work wq_detectid; + enum palmas_usb_state linkstat; int wakeup; bool enable_vbus_detection; bool enable_id_detection; + bool enable_gpio_id_detection; }; #define comparator_to_palmas(x) container_of((x), struct palmas_usb, comparator) diff --git a/kernel/include/linux/mfd/rtsx_pci.h b/kernel/include/linux/mfd/rtsx_pci.h index ff843e7ca..7eb7cbac0 100644 --- a/kernel/include/linux/mfd/rtsx_pci.h +++ b/kernel/include/linux/mfd/rtsx_pci.h @@ -589,6 +589,7 @@ #define FORCE_ASPM_NO_ASPM 0x00 #define PM_CLK_FORCE_CTL 0xFE58 #define FUNC_FORCE_CTL 0xFE59 +#define FUNC_FORCE_UPME_XMT_DBG 0x02 #define PERST_GLITCH_WIDTH 0xFE5C #define CHANGE_LINK_STATE 0xFE5B #define RESET_LOAD_REG 0xFE5E @@ -712,6 +713,7 @@ #define PHY_RCR1 0x02 #define PHY_RCR1_ADP_TIME_4 0x0400 #define PHY_RCR1_VCO_COARSE 0x001F +#define PHY_RCR1_INIT_27S 0x0A1F #define PHY_SSCCR2 0x02 #define PHY_SSCCR2_PLL_NCODE 0x0A00 #define PHY_SSCCR2_TIME0 0x001C @@ -724,6 +726,7 @@ #define PHY_RCR2_FREQSEL_12 0x0040 #define PHY_RCR2_CDR_SC_12P 0x0010 #define PHY_RCR2_CALIB_LATE 0x0002 +#define PHY_RCR2_INIT_27S 0xC152 #define PHY_SSCCR3 0x03 #define PHY_SSCCR3_STEP_IN 0x2740 #define PHY_SSCCR3_CHECK_DELAY 0x0008 @@ -800,12 +803,14 @@ #define PHY_ANA1A_RXT_BIST 0x0500 #define PHY_ANA1A_TXR_BIST 0x0040 #define PHY_ANA1A_REV 0x0006 +#define PHY_FLD0_INIT_27S 0x2546 #define PHY_FLD1 0x1B #define PHY_FLD2 0x1C #define PHY_FLD3 0x1D #define PHY_FLD3_TIMER_4 0x0800 #define PHY_FLD3_TIMER_6 0x0020 #define PHY_FLD3_RXDELINK 0x0004 +#define PHY_FLD3_INIT_27S 0x0004 #define PHY_ANA1D 0x1D #define PHY_ANA1D_DEBUG_ADDR 0x0004 #define _PHY_FLD0 0x1D @@ -824,6 +829,7 @@ #define PHY_FLD4_BER_COUNT 0x00E0 #define PHY_FLD4_BER_TIMER 0x000A #define PHY_FLD4_BER_CHK_EN 0x0001 +#define PHY_FLD4_INIT_27S 0x5C7F #define PHY_DIG1E 0x1E #define PHY_DIG1E_REV 0x4000 #define PHY_DIG1E_D0_X_D1 0x1000 diff --git a/kernel/include/linux/mfd/samsung/core.h b/kernel/include/linux/mfd/samsung/core.h index 75115384f..a06098639 100644 --- a/kernel/include/linux/mfd/samsung/core.h +++ b/kernel/include/linux/mfd/samsung/core.h @@ -132,6 +132,10 @@ struct sec_platform_data { int buck2_init; int buck3_init; int buck4_init; + /* Whether or not manually set PWRHOLD to low during shutdown. */ + bool manual_poweroff; + /* Disable the WRSTBI (buck voltage warm reset) when probing? */ + bool disable_wrstbi; }; /** diff --git a/kernel/include/linux/mfd/samsung/s2mps11.h b/kernel/include/linux/mfd/samsung/s2mps11.h index 7981a9d77..b288965e8 100644 --- a/kernel/include/linux/mfd/samsung/s2mps11.h +++ b/kernel/include/linux/mfd/samsung/s2mps11.h @@ -179,6 +179,7 @@ enum s2mps11_regulators { #define S2MPS11_BUCK_N_VOLTAGES (S2MPS11_BUCK_VSEL_MASK + 1) #define S2MPS11_RAMP_DELAY 25000 /* uV/us */ +#define S2MPS11_CTRL1_PWRHOLD_MASK BIT(4) #define S2MPS11_BUCK2_RAMP_SHIFT 6 #define S2MPS11_BUCK34_RAMP_SHIFT 4 diff --git a/kernel/include/linux/mfd/samsung/s2mps13.h b/kernel/include/linux/mfd/samsung/s2mps13.h index b1fd675fa..239e977ba 100644 --- a/kernel/include/linux/mfd/samsung/s2mps13.h +++ b/kernel/include/linux/mfd/samsung/s2mps13.h @@ -184,5 +184,6 @@ enum s2mps13_regulators { * Let's assume that default value will be set. */ #define S2MPS13_BUCK_RAMP_DELAY 12500 +#define S2MPS13_REG_WRSTBI_MASK BIT(5) #endif /* __LINUX_MFD_S2MPS13_H */ diff --git a/kernel/include/linux/mfd/stmpe.h b/kernel/include/linux/mfd/stmpe.h index c9d869027..cb8388391 100644 --- a/kernel/include/linux/mfd/stmpe.h +++ b/kernel/include/linux/mfd/stmpe.h @@ -118,47 +118,6 @@ extern int stmpe_disable(struct stmpe *stmpe, unsigned int blocks); #define STMPE_GPIO_NOREQ_811_TOUCH (0xf0) /** - * struct stmpe_ts_platform_data - stmpe811 touch screen controller platform - * data - * @sample_time: ADC converstion time in number of clock. - * (0 -> 36 clocks, 1 -> 44 clocks, 2 -> 56 clocks, 3 -> 64 clocks, - * 4 -> 80 clocks, 5 -> 96 clocks, 6 -> 144 clocks), - * recommended is 4. - * @mod_12b: ADC Bit mode (0 -> 10bit ADC, 1 -> 12bit ADC) - * @ref_sel: ADC reference source - * (0 -> internal reference, 1 -> external reference) - * @adc_freq: ADC Clock speed - * (0 -> 1.625 MHz, 1 -> 3.25 MHz, 2 || 3 -> 6.5 MHz) - * @ave_ctrl: Sample average control - * (0 -> 1 sample, 1 -> 2 samples, 2 -> 4 samples, 3 -> 8 samples) - * @touch_det_delay: Touch detect interrupt delay - * (0 -> 10 us, 1 -> 50 us, 2 -> 100 us, 3 -> 500 us, - * 4-> 1 ms, 5 -> 5 ms, 6 -> 10 ms, 7 -> 50 ms) - * recommended is 3 - * @settling: Panel driver settling time - * (0 -> 10 us, 1 -> 100 us, 2 -> 500 us, 3 -> 1 ms, - * 4 -> 5 ms, 5 -> 10 ms, 6 for 50 ms, 7 -> 100 ms) - * recommended is 2 - * @fraction_z: Length of the fractional part in z - * (fraction_z ([0..7]) = Count of the fractional part) - * recommended is 7 - * @i_drive: current limit value of the touchscreen drivers - * (0 -> 20 mA typical 35 mA max, 1 -> 50 mA typical 80 mA max) - * - * */ -struct stmpe_ts_platform_data { - u8 sample_time; - u8 mod_12b; - u8 ref_sel; - u8 adc_freq; - u8 ave_ctrl; - u8 touch_det_delay; - u8 settling; - u8 fraction_z; - u8 i_drive; -}; - -/** * struct stmpe_platform_data - STMPE platform data * @id: device id to distinguish between multiple STMPEs on the same board * @blocks: bitmask of blocks to enable (use STMPE_BLOCK_*) @@ -168,7 +127,6 @@ struct stmpe_ts_platform_data { * @irq_over_gpio: true if gpio is used to get irq * @irq_gpio: gpio number over which irq will be requested (significant only if * irq_over_gpio is true) - * @ts: touchscreen-specific platform data */ struct stmpe_platform_data { int id; @@ -178,8 +136,6 @@ struct stmpe_platform_data { bool irq_over_gpio; int irq_gpio; int autosleep_timeout; - - struct stmpe_ts_platform_data *ts; }; #endif diff --git a/kernel/include/linux/mfd/syscon/atmel-mc.h b/kernel/include/linux/mfd/syscon/atmel-mc.h new file mode 100644 index 000000000..afd9b8f1e --- /dev/null +++ b/kernel/include/linux/mfd/syscon/atmel-mc.h @@ -0,0 +1,144 @@ +/* + * Copyright (C) 2005 Ivan Kokshaysky + * Copyright (C) SAN People + * + * Memory Controllers (MC, EBI, SMC, SDRAMC, BFC) - System peripherals + * registers. + * Based on AT91RM9200 datasheet revision E. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#ifndef _LINUX_MFD_SYSCON_ATMEL_MC_H_ +#define _LINUX_MFD_SYSCON_ATMEL_MC_H_ + +/* Memory Controller */ +#define AT91_MC_RCR 0x00 +#define AT91_MC_RCB BIT(0) + +#define AT91_MC_ASR 0x04 +#define AT91_MC_UNADD BIT(0) +#define AT91_MC_MISADD BIT(1) +#define AT91_MC_ABTSZ GENMASK(9, 8) +#define AT91_MC_ABTSZ_BYTE (0 << 8) +#define AT91_MC_ABTSZ_HALFWORD (1 << 8) +#define AT91_MC_ABTSZ_WORD (2 << 8) +#define AT91_MC_ABTTYP GENMASK(11, 10) +#define AT91_MC_ABTTYP_DATAREAD (0 << 10) +#define AT91_MC_ABTTYP_DATAWRITE (1 << 10) +#define AT91_MC_ABTTYP_FETCH (2 << 10) +#define AT91_MC_MST(n) BIT(16 + (n)) +#define AT91_MC_SVMST(n) BIT(24 + (n)) + +#define AT91_MC_AASR 0x08 + +#define AT91_MC_MPR 0x0c +#define AT91_MPR_MSTP(n) GENMASK(2 + ((x) * 4), ((x) * 4)) + +/* External Bus Interface (EBI) registers */ +#define AT91_MC_EBI_CSA 0x60 +#define AT91_MC_EBI_CS(n) BIT(x) +#define AT91_MC_EBI_NUM_CS 8 + +#define AT91_MC_EBI_CFGR 0x64 +#define AT91_MC_EBI_DBPUC BIT(0) + +/* Static Memory Controller (SMC) registers */ +#define AT91_MC_SMC_CSR(n) (0x70 + ((n) * 4)) +#define AT91_MC_SMC_NWS GENMASK(6, 0) +#define AT91_MC_SMC_NWS_(x) ((x) << 0) +#define AT91_MC_SMC_WSEN BIT(7) +#define AT91_MC_SMC_TDF GENMASK(11, 8) +#define AT91_MC_SMC_TDF_(x) ((x) << 8) +#define AT91_MC_SMC_TDF_MAX 0xf +#define AT91_MC_SMC_BAT BIT(12) +#define AT91_MC_SMC_DBW GENMASK(14, 13) +#define AT91_MC_SMC_DBW_16 (1 << 13) +#define AT91_MC_SMC_DBW_8 (2 << 13) +#define AT91_MC_SMC_DPR BIT(15) +#define AT91_MC_SMC_ACSS GENMASK(17, 16) +#define AT91_MC_SMC_ACSS_(x) ((x) << 16) +#define AT91_MC_SMC_ACSS_MAX 3 +#define AT91_MC_SMC_RWSETUP GENMASK(26, 24) +#define AT91_MC_SMC_RWSETUP_(x) ((x) << 24) +#define AT91_MC_SMC_RWHOLD GENMASK(30, 28) +#define AT91_MC_SMC_RWHOLD_(x) ((x) << 28) +#define AT91_MC_SMC_RWHOLDSETUP_MAX 7 + +/* SDRAM Controller registers */ +#define AT91_MC_SDRAMC_MR 0x90 +#define AT91_MC_SDRAMC_MODE GENMASK(3, 0) +#define AT91_MC_SDRAMC_MODE_NORMAL (0 << 0) +#define AT91_MC_SDRAMC_MODE_NOP (1 << 0) +#define AT91_MC_SDRAMC_MODE_PRECHARGE (2 << 0) +#define AT91_MC_SDRAMC_MODE_LMR (3 << 0) +#define AT91_MC_SDRAMC_MODE_REFRESH (4 << 0) +#define AT91_MC_SDRAMC_DBW_16 BIT(4) + +#define AT91_MC_SDRAMC_TR 0x94 +#define AT91_MC_SDRAMC_COUNT GENMASK(11, 0) + +#define AT91_MC_SDRAMC_CR 0x98 +#define AT91_MC_SDRAMC_NC GENMASK(1, 0) +#define AT91_MC_SDRAMC_NC_8 (0 << 0) +#define AT91_MC_SDRAMC_NC_9 (1 << 0) +#define AT91_MC_SDRAMC_NC_10 (2 << 0) +#define AT91_MC_SDRAMC_NC_11 (3 << 0) +#define AT91_MC_SDRAMC_NR GENMASK(3, 2) +#define AT91_MC_SDRAMC_NR_11 (0 << 2) +#define AT91_MC_SDRAMC_NR_12 (1 << 2) +#define AT91_MC_SDRAMC_NR_13 (2 << 2) +#define AT91_MC_SDRAMC_NB BIT(4) +#define AT91_MC_SDRAMC_NB_2 (0 << 4) +#define AT91_MC_SDRAMC_NB_4 (1 << 4) +#define AT91_MC_SDRAMC_CAS GENMASK(6, 5) +#define AT91_MC_SDRAMC_CAS_2 (2 << 5) +#define AT91_MC_SDRAMC_TWR GENMASK(10, 7) +#define AT91_MC_SDRAMC_TRC GENMASK(14, 11) +#define AT91_MC_SDRAMC_TRP GENMASK(18, 15) +#define AT91_MC_SDRAMC_TRCD GENMASK(22, 19) +#define AT91_MC_SDRAMC_TRAS GENMASK(26, 23) +#define AT91_MC_SDRAMC_TXSR GENMASK(30, 27) + +#define AT91_MC_SDRAMC_SRR 0x9c +#define AT91_MC_SDRAMC_SRCB BIT(0) + +#define AT91_MC_SDRAMC_LPR 0xa0 +#define AT91_MC_SDRAMC_LPCB BIT(0) + +#define AT91_MC_SDRAMC_IER 0xa4 +#define AT91_MC_SDRAMC_IDR 0xa8 +#define AT91_MC_SDRAMC_IMR 0xac +#define AT91_MC_SDRAMC_ISR 0xb0 +#define AT91_MC_SDRAMC_RES BIT(0) + +/* Burst Flash Controller register */ +#define AT91_MC_BFC_MR 0xc0 +#define AT91_MC_BFC_BFCOM GENMASK(1, 0) +#define AT91_MC_BFC_BFCOM_DISABLED (0 << 0) +#define AT91_MC_BFC_BFCOM_ASYNC (1 << 0) +#define AT91_MC_BFC_BFCOM_BURST (2 << 0) +#define AT91_MC_BFC_BFCC GENMASK(3, 2) +#define AT91_MC_BFC_BFCC_MCK (1 << 2) +#define AT91_MC_BFC_BFCC_DIV2 (2 << 2) +#define AT91_MC_BFC_BFCC_DIV4 (3 << 2) +#define AT91_MC_BFC_AVL GENMASK(7, 4) +#define AT91_MC_BFC_PAGES GENMASK(10, 8) +#define AT91_MC_BFC_PAGES_NO_PAGE (0 << 8) +#define AT91_MC_BFC_PAGES_16 (1 << 8) +#define AT91_MC_BFC_PAGES_32 (2 << 8) +#define AT91_MC_BFC_PAGES_64 (3 << 8) +#define AT91_MC_BFC_PAGES_128 (4 << 8) +#define AT91_MC_BFC_PAGES_256 (5 << 8) +#define AT91_MC_BFC_PAGES_512 (6 << 8) +#define AT91_MC_BFC_PAGES_1024 (7 << 8) +#define AT91_MC_BFC_OEL GENMASK(13, 12) +#define AT91_MC_BFC_BAAEN BIT(16) +#define AT91_MC_BFC_BFOEH BIT(17) +#define AT91_MC_BFC_MUXEN BIT(18) +#define AT91_MC_BFC_RDYEN BIT(19) + +#endif /* _LINUX_MFD_SYSCON_ATMEL_MC_H_ */ diff --git a/kernel/include/linux/mfd/syscon/imx6q-iomuxc-gpr.h b/kernel/include/linux/mfd/syscon/imx6q-iomuxc-gpr.h index d16f4c82c..558a485d0 100644 --- a/kernel/include/linux/mfd/syscon/imx6q-iomuxc-gpr.h +++ b/kernel/include/linux/mfd/syscon/imx6q-iomuxc-gpr.h @@ -435,4 +435,12 @@ #define IMX6SX_GPR5_DISP_MUX_DCIC1_LVDS (0x1 << 1) #define IMX6SX_GPR5_DISP_MUX_DCIC1_MASK (0x1 << 1) +/* For imx6ul iomux gpr register field define */ +#define IMX6UL_GPR1_ENET1_CLK_DIR (0x1 << 17) +#define IMX6UL_GPR1_ENET2_CLK_DIR (0x1 << 18) +#define IMX6UL_GPR1_ENET1_CLK_OUTPUT (0x1 << 17) +#define IMX6UL_GPR1_ENET2_CLK_OUTPUT (0x1 << 18) +#define IMX6UL_GPR1_ENET_CLK_DIR (0x3 << 17) +#define IMX6UL_GPR1_ENET_CLK_OUTPUT (0x3 << 17) + #endif /* __LINUX_IMX6Q_IOMUXC_GPR_H */ diff --git a/kernel/include/linux/mfd/syscon/imx7-iomuxc-gpr.h b/kernel/include/linux/mfd/syscon/imx7-iomuxc-gpr.h new file mode 100644 index 000000000..4585d6105 --- /dev/null +++ b/kernel/include/linux/mfd/syscon/imx7-iomuxc-gpr.h @@ -0,0 +1,47 @@ +/* + * Copyright (C) 2015 Freescale Semiconductor, Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef __LINUX_IMX7_IOMUXC_GPR_H +#define __LINUX_IMX7_IOMUXC_GPR_H + +#define IOMUXC_GPR0 0x00 +#define IOMUXC_GPR1 0x04 +#define IOMUXC_GPR2 0x08 +#define IOMUXC_GPR3 0x0c +#define IOMUXC_GPR4 0x10 +#define IOMUXC_GPR5 0x14 +#define IOMUXC_GPR6 0x18 +#define IOMUXC_GPR7 0x1c +#define IOMUXC_GPR8 0x20 +#define IOMUXC_GPR9 0x24 +#define IOMUXC_GPR10 0x28 +#define IOMUXC_GPR11 0x2c +#define IOMUXC_GPR12 0x30 +#define IOMUXC_GPR13 0x34 +#define IOMUXC_GPR14 0x38 +#define IOMUXC_GPR15 0x3c +#define IOMUXC_GPR16 0x40 +#define IOMUXC_GPR17 0x44 +#define IOMUXC_GPR18 0x48 +#define IOMUXC_GPR19 0x4c +#define IOMUXC_GPR20 0x50 +#define IOMUXC_GPR21 0x54 +#define IOMUXC_GPR22 0x58 + +/* For imx7d iomux gpr register field define */ +#define IMX7D_GPR1_IRQ_MASK (0x1 << 12) +#define IMX7D_GPR1_ENET1_TX_CLK_SEL_MASK (0x1 << 13) +#define IMX7D_GPR1_ENET2_TX_CLK_SEL_MASK (0x1 << 14) +#define IMX7D_GPR1_ENET_TX_CLK_SEL_MASK (0x3 << 13) +#define IMX7D_GPR1_ENET1_CLK_DIR_MASK (0x1 << 17) +#define IMX7D_GPR1_ENET2_CLK_DIR_MASK (0x1 << 18) +#define IMX7D_GPR1_ENET_CLK_DIR_MASK (0x3 << 17) + +#define IMX7D_GPR5_CSI_MUX_CONTROL_MIPI (0x1 << 4) + +#endif /* __LINUX_IMX7_IOMUXC_GPR_H */ diff --git a/kernel/include/linux/mfd/tps6105x.h b/kernel/include/linux/mfd/tps6105x.h index 386743dd9..8bc511808 100644 --- a/kernel/include/linux/mfd/tps6105x.h +++ b/kernel/include/linux/mfd/tps6105x.h @@ -10,6 +10,7 @@ #define MFD_TPS6105X_H #include <linux/i2c.h> +#include <linux/regmap.h> #include <linux/regulator/machine.h> /* @@ -82,20 +83,15 @@ struct tps6105x_platform_data { /** * struct tps6105x - state holder for the TPS6105x drivers - * @mutex: mutex to serialize I2C accesses * @i2c_client: corresponding I2C client * @regulator: regulator device if used in voltage mode + * @regmap: used for i2c communcation on accessing registers */ struct tps6105x { struct tps6105x_platform_data *pdata; - struct mutex lock; struct i2c_client *client; struct regulator_dev *regulator; + struct regmap *regmap; }; -extern int tps6105x_set(struct tps6105x *tps6105x, u8 reg, u8 value); -extern int tps6105x_get(struct tps6105x *tps6105x, u8 reg, u8 *buf); -extern int tps6105x_mask_and_set(struct tps6105x *tps6105x, u8 reg, - u8 bitmask, u8 bitvalues); - #endif diff --git a/kernel/include/linux/mic_bus.h b/kernel/include/linux/mic_bus.h index d5b5f76d5..27d7c95fd 100644 --- a/kernel/include/linux/mic_bus.h +++ b/kernel/include/linux/mic_bus.h @@ -91,7 +91,8 @@ struct mbus_hw_ops { struct mbus_device * mbus_register_device(struct device *pdev, int id, struct dma_map_ops *dma_ops, - struct mbus_hw_ops *hw_ops, void __iomem *mmio_va); + struct mbus_hw_ops *hw_ops, int index, + void __iomem *mmio_va); void mbus_unregister_device(struct mbus_device *mbdev); int mbus_register_driver(struct mbus_driver *drv); diff --git a/kernel/include/linux/microchipphy.h b/kernel/include/linux/microchipphy.h new file mode 100644 index 000000000..eb492d47f --- /dev/null +++ b/kernel/include/linux/microchipphy.h @@ -0,0 +1,73 @@ +/* + * Copyright (C) 2015 Microchip Technology + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version 2 + * of the License, or (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef _MICROCHIPPHY_H +#define _MICROCHIPPHY_H + +#define LAN88XX_INT_MASK (0x19) +#define LAN88XX_INT_MASK_MDINTPIN_EN_ (0x8000) +#define LAN88XX_INT_MASK_SPEED_CHANGE_ (0x4000) +#define LAN88XX_INT_MASK_LINK_CHANGE_ (0x2000) +#define LAN88XX_INT_MASK_FDX_CHANGE_ (0x1000) +#define LAN88XX_INT_MASK_AUTONEG_ERR_ (0x0800) +#define LAN88XX_INT_MASK_AUTONEG_DONE_ (0x0400) +#define LAN88XX_INT_MASK_POE_DETECT_ (0x0200) +#define LAN88XX_INT_MASK_SYMBOL_ERR_ (0x0100) +#define LAN88XX_INT_MASK_FAST_LINK_FAIL_ (0x0080) +#define LAN88XX_INT_MASK_WOL_EVENT_ (0x0040) +#define LAN88XX_INT_MASK_EXTENDED_INT_ (0x0020) +#define LAN88XX_INT_MASK_RESERVED_ (0x0010) +#define LAN88XX_INT_MASK_FALSE_CARRIER_ (0x0008) +#define LAN88XX_INT_MASK_LINK_SPEED_DS_ (0x0004) +#define LAN88XX_INT_MASK_MASTER_SLAVE_DONE_ (0x0002) +#define LAN88XX_INT_MASK_RX__ER_ (0x0001) + +#define LAN88XX_INT_STS (0x1A) +#define LAN88XX_INT_STS_INT_ACTIVE_ (0x8000) +#define LAN88XX_INT_STS_SPEED_CHANGE_ (0x4000) +#define LAN88XX_INT_STS_LINK_CHANGE_ (0x2000) +#define LAN88XX_INT_STS_FDX_CHANGE_ (0x1000) +#define LAN88XX_INT_STS_AUTONEG_ERR_ (0x0800) +#define LAN88XX_INT_STS_AUTONEG_DONE_ (0x0400) +#define LAN88XX_INT_STS_POE_DETECT_ (0x0200) +#define LAN88XX_INT_STS_SYMBOL_ERR_ (0x0100) +#define LAN88XX_INT_STS_FAST_LINK_FAIL_ (0x0080) +#define LAN88XX_INT_STS_WOL_EVENT_ (0x0040) +#define LAN88XX_INT_STS_EXTENDED_INT_ (0x0020) +#define LAN88XX_INT_STS_RESERVED_ (0x0010) +#define LAN88XX_INT_STS_FALSE_CARRIER_ (0x0008) +#define LAN88XX_INT_STS_LINK_SPEED_DS_ (0x0004) +#define LAN88XX_INT_STS_MASTER_SLAVE_DONE_ (0x0002) +#define LAN88XX_INT_STS_RX_ER_ (0x0001) + +#define LAN88XX_EXT_PAGE_ACCESS (0x1F) +#define LAN88XX_EXT_PAGE_SPACE_0 (0x0000) +#define LAN88XX_EXT_PAGE_SPACE_1 (0x0001) +#define LAN88XX_EXT_PAGE_SPACE_2 (0x0002) + +/* Extended Register Page 1 space */ +#define LAN88XX_EXT_MODE_CTRL (0x13) +#define LAN88XX_EXT_MODE_CTRL_MDIX_MASK_ (0x000C) +#define LAN88XX_EXT_MODE_CTRL_AUTO_MDIX_ (0x0000) +#define LAN88XX_EXT_MODE_CTRL_MDI_ (0x0008) +#define LAN88XX_EXT_MODE_CTRL_MDI_X_ (0x000C) + +/* MMD 3 Registers */ +#define LAN88XX_MMD3_CHIP_ID (32877) +#define LAN88XX_MMD3_CHIP_REV (32878) + +#endif /* _MICROCHIPPHY_H */ diff --git a/kernel/include/linux/miscdevice.h b/kernel/include/linux/miscdevice.h index 819077c32..543037465 100644 --- a/kernel/include/linux/miscdevice.h +++ b/kernel/include/linux/miscdevice.h @@ -49,6 +49,7 @@ #define LOOP_CTRL_MINOR 237 #define VHOST_NET_MINOR 238 #define UHID_MINOR 239 +#define USERIO_MINOR 240 #define MISC_DYNAMIC_MINOR 255 struct device; @@ -67,7 +68,7 @@ struct miscdevice { }; extern int misc_register(struct miscdevice *misc); -extern int misc_deregister(struct miscdevice *misc); +extern void misc_deregister(struct miscdevice *misc); #define MODULE_ALIAS_MISCDEV(minor) \ MODULE_ALIAS("char-major-" __stringify(MISC_MAJOR) \ diff --git a/kernel/include/linux/mlx4/cmd.h b/kernel/include/linux/mlx4/cmd.h index f62e7cf22..58391f2e0 100644 --- a/kernel/include/linux/mlx4/cmd.h +++ b/kernel/include/linux/mlx4/cmd.h @@ -35,6 +35,8 @@ #include <linux/dma-mapping.h> #include <linux/if_link.h> +#include <linux/mlx4/device.h> +#include <linux/netdevice.h> enum { /* initialization and general commands */ @@ -300,6 +302,10 @@ static inline int mlx4_cmd_imm(struct mlx4_dev *dev, u64 in_param, u64 *out_para struct mlx4_cmd_mailbox *mlx4_alloc_cmd_mailbox(struct mlx4_dev *dev); void mlx4_free_cmd_mailbox(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbox); +int mlx4_get_counter_stats(struct mlx4_dev *dev, int counter_index, + struct mlx4_counter *counter_stats, int reset); +int mlx4_get_vf_stats(struct mlx4_dev *dev, int port, int vf_idx, + struct ifla_vf_stats *vf_stats); u32 mlx4_comm_get_version(void); int mlx4_set_vf_mac(struct mlx4_dev *dev, int port, int vf, u64 mac); int mlx4_set_vf_vlan(struct mlx4_dev *dev, int port, int vf, u16 vlan, u8 qos); diff --git a/kernel/include/linux/mlx4/cq.h b/kernel/include/linux/mlx4/cq.h index e7ecc12a1..09cebe528 100644 --- a/kernel/include/linux/mlx4/cq.h +++ b/kernel/include/linux/mlx4/cq.h @@ -88,7 +88,8 @@ struct mlx4_ts_cqe { enum { MLX4_CQE_L2_TUNNEL_IPOK = 1 << 31, - MLX4_CQE_VLAN_PRESENT_MASK = 1 << 29, + MLX4_CQE_CVLAN_PRESENT_MASK = 1 << 29, + MLX4_CQE_SVLAN_PRESENT_MASK = 1 << 30, MLX4_CQE_L2_TUNNEL = 1 << 27, MLX4_CQE_L2_TUNNEL_CSUM = 1 << 26, MLX4_CQE_L2_TUNNEL_IPV4 = 1 << 25, diff --git a/kernel/include/linux/mlx4/device.h b/kernel/include/linux/mlx4/device.h index 83e80ab94..d3133be12 100644 --- a/kernel/include/linux/mlx4/device.h +++ b/kernel/include/linux/mlx4/device.h @@ -46,8 +46,9 @@ #define MAX_MSIX_P_PORT 17 #define MAX_MSIX 64 -#define MSIX_LEGACY_SZ 4 #define MIN_MSIX_P_PORT 5 +#define MLX4_IS_LEGACY_EQ_MODE(dev_cap) ((dev_cap).num_comp_vectors < \ + (dev_cap).num_ports * MIN_MSIX_P_PORT) #define MLX4_MAX_100M_UNITS_VAL 255 /* * work around: can't set values @@ -78,7 +79,8 @@ enum { enum { MLX4_MAX_PORTS = 2, - MLX4_MAX_PORT_PKEYS = 128 + MLX4_MAX_PORT_PKEYS = 128, + MLX4_MAX_PORT_GIDS = 128 }; /* base qkey for use in sriov tunnel-qp/proxy-qp communication. @@ -210,6 +212,10 @@ enum { MLX4_DEV_CAP_FLAG2_ETS_CFG = 1LL << 26, MLX4_DEV_CAP_FLAG2_PORT_BEACON = 1LL << 27, MLX4_DEV_CAP_FLAG2_IGNORE_FCS = 1LL << 28, + MLX4_DEV_CAP_FLAG2_PHV_EN = 1LL << 29, + MLX4_DEV_CAP_FLAG2_SKIP_OUTER_VLAN = 1LL << 30, + MLX4_DEV_CAP_FLAG2_UPDATE_QP_SRC_CHECK_LB = 1ULL << 31, + MLX4_DEV_CAP_FLAG2_LB_SRC_CHK = 1ULL << 32, }; enum { @@ -421,6 +427,17 @@ enum { }; enum { + /* + * Max wqe size for rdma read is 512 bytes, so this + * limits our max_sge_rd as the wqe needs to fit: + * - ctrl segment (16 bytes) + * - rdma segment (16 bytes) + * - scatter elements (16 bytes each) + */ + MLX4_MAX_SGE_RD = (512 - 16 - 16) / 16 +}; + +enum { MLX4_DEV_PMC_SUBTYPE_GUID_INFO = 0x14, MLX4_DEV_PMC_SUBTYPE_PORT_INFO = 0x15, MLX4_DEV_PMC_SUBTYPE_PKEY_TABLE = 0x16, @@ -528,7 +545,6 @@ struct mlx4_caps { int num_eqs; int reserved_eqs; int num_comp_vectors; - int comp_pool; int num_mpts; int max_fmr_maps; int num_mtts; @@ -581,6 +597,7 @@ struct mlx4_caps { u64 phys_port_id[MLX4_MAX_PORTS + 1]; int tunnel_offload_mode; u8 rx_checksum_flags_port[MLX4_MAX_PORTS + 1]; + u8 phv_bit[MLX4_MAX_PORTS + 1]; u8 alloc_res_qp_mask; u32 dmfs_high_rate_qpn_base; u32 dmfs_high_rate_qpn_range; @@ -771,6 +788,14 @@ union mlx4_ext_av { struct mlx4_eth_av eth; }; +/* Counters should be saturate once they reach their maximum value */ +#define ASSIGN_32BIT_COUNTER(counter, value) do { \ + if ((value) > U32_MAX) \ + counter = cpu_to_be32(U32_MAX); \ + else \ + counter = cpu_to_be32(value); \ +} while (0) + struct mlx4_counter { u8 reserved1[3]; u8 counter_mode; @@ -821,6 +846,7 @@ struct mlx4_dev { struct mlx4_quotas quotas; struct radix_tree_root qp_table_tree; u8 rev_id; + u8 port_random_macs; char board_id[MLX4_BOARD_ID_LEN]; int numa_node; int oper_log_mgm_entry_size; @@ -829,6 +855,12 @@ struct mlx4_dev { struct mlx4_vf_dev *dev_vfs; }; +struct mlx4_clock_params { + u64 offset; + u8 bar; + u8 size; +}; + struct mlx4_eqe { u8 reserved1; u8 type; @@ -957,6 +989,7 @@ struct mlx4_mad_ifc { ((dev)->caps.flags & MLX4_DEV_CAP_FLAG_IBOE)) #define MLX4_INVALID_SLAVE_ID 0xFF +#define MLX4_SINK_COUNTER_INDEX(dev) (dev->caps.max_counters - 1) void handle_port_mgmt_change_event(struct work_struct *work); @@ -1317,6 +1350,8 @@ int mlx4_SET_PORT_BEACON(struct mlx4_dev *dev, u8 port, u16 time); int mlx4_SET_PORT_fcs_check(struct mlx4_dev *dev, u8 port, u8 ignore_fcs_value); int mlx4_SET_PORT_VXLAN(struct mlx4_dev *dev, u8 port, u8 steering, int enable); +int set_phv_bit(struct mlx4_dev *dev, u8 port, int new_val); +int get_phv_bit(struct mlx4_dev *dev, u8 port, int *phv); int mlx4_find_cached_mac(struct mlx4_dev *dev, u8 port, u64 mac, int *idx); int mlx4_find_cached_vlan(struct mlx4_dev *dev, u8 port, u16 vid, int *idx); int mlx4_register_vlan(struct mlx4_dev *dev, u8 port, u16 vlan, int *index); @@ -1332,10 +1367,13 @@ void mlx4_fmr_unmap(struct mlx4_dev *dev, struct mlx4_fmr *fmr, int mlx4_fmr_free(struct mlx4_dev *dev, struct mlx4_fmr *fmr); int mlx4_SYNC_TPT(struct mlx4_dev *dev); int mlx4_test_interrupts(struct mlx4_dev *dev); -int mlx4_assign_eq(struct mlx4_dev *dev, char *name, struct cpu_rmap *rmap, - int *vector); +u32 mlx4_get_eqs_per_port(struct mlx4_dev *dev, u8 port); +bool mlx4_is_eq_vector_valid(struct mlx4_dev *dev, u8 port, int vector); +struct cpu_rmap *mlx4_get_cpu_rmap(struct mlx4_dev *dev, int port); +int mlx4_assign_eq(struct mlx4_dev *dev, u8 port, int *vector); void mlx4_release_eq(struct mlx4_dev *dev, int vec); +int mlx4_is_eq_shared(struct mlx4_dev *dev, int vector); int mlx4_eq_get_irq(struct mlx4_dev *dev, int vec); int mlx4_get_phys_port_id(struct mlx4_dev *dev); @@ -1344,6 +1382,7 @@ int mlx4_wol_write(struct mlx4_dev *dev, u64 config, int port); int mlx4_counter_alloc(struct mlx4_dev *dev, u32 *idx); void mlx4_counter_free(struct mlx4_dev *dev, u32 idx); +int mlx4_get_default_counter_index(struct mlx4_dev *dev, int port); void mlx4_set_admin_guid(struct mlx4_dev *dev, __be64 guid, int entry, int port); @@ -1485,4 +1524,7 @@ int mlx4_ACCESS_PTYS_REG(struct mlx4_dev *dev, enum mlx4_access_reg_method method, struct mlx4_ptys_reg *ptys_reg); +int mlx4_get_internal_clock_params(struct mlx4_dev *dev, + struct mlx4_clock_params *params); + #endif /* MLX4_DEVICE_H */ diff --git a/kernel/include/linux/mlx4/driver.h b/kernel/include/linux/mlx4/driver.h index 9553a73d2..5a06d9693 100644 --- a/kernel/include/linux/mlx4/driver.h +++ b/kernel/include/linux/mlx4/driver.h @@ -59,6 +59,7 @@ struct mlx4_interface { void (*event) (struct mlx4_dev *dev, void *context, enum mlx4_dev_event event, unsigned long param); void * (*get_dev)(struct mlx4_dev *dev, void *context, u8 port); + void (*activate)(struct mlx4_dev *dev, void *context); struct list_head list; enum mlx4_protocol protocol; int flags; diff --git a/kernel/include/linux/mlx4/qp.h b/kernel/include/linux/mlx4/qp.h index 6fed539e5..fe052e234 100644 --- a/kernel/include/linux/mlx4/qp.h +++ b/kernel/include/linux/mlx4/qp.h @@ -135,7 +135,10 @@ struct mlx4_rss_context { struct mlx4_qp_path { u8 fl; - u8 vlan_control; + union { + u8 vlan_control; + u8 control; + }; u8 disable_pkey_check; u8 pkey_index; u8 counter_index; @@ -156,9 +159,16 @@ struct mlx4_qp_path { }; enum { /* fl */ - MLX4_FL_CV = 1 << 6, - MLX4_FL_ETH_HIDE_CQE_VLAN = 1 << 2 + MLX4_FL_CV = 1 << 6, + MLX4_FL_ETH_HIDE_CQE_VLAN = 1 << 2, + MLX4_FL_ETH_SRC_CHECK_MC_LB = 1 << 1, + MLX4_FL_ETH_SRC_CHECK_UC_LB = 1 << 0, }; + +enum { /* control */ + MLX4_CTRL_ETH_SRC_CHECK_IF_COUNTER = 1 << 7, +}; + enum { /* vlan_control */ MLX4_VLAN_CTRL_ETH_TX_BLOCK_TAGGED = 1 << 6, MLX4_VLAN_CTRL_ETH_TX_BLOCK_PRIO_TAGGED = 1 << 5, /* 802.1p priority tag */ @@ -254,6 +264,8 @@ enum { MLX4_UPD_QP_PATH_MASK_SCHED_QUEUE = 14 + 32, MLX4_UPD_QP_PATH_MASK_IF_COUNTER_INDEX = 15 + 32, MLX4_UPD_QP_PATH_MASK_FVL_RX = 16 + 32, + MLX4_UPD_QP_PATH_MASK_ETH_SRC_CHECK_UC_LB = 18 + 32, + MLX4_UPD_QP_PATH_MASK_ETH_SRC_CHECK_MC_LB = 19 + 32, }; enum { /* param3 */ @@ -272,7 +284,8 @@ enum { MLX4_WQE_CTRL_SOLICITED = 1 << 1, MLX4_WQE_CTRL_IP_CSUM = 1 << 4, MLX4_WQE_CTRL_TCP_UDP_CSUM = 1 << 5, - MLX4_WQE_CTRL_INS_VLAN = 1 << 6, + MLX4_WQE_CTRL_INS_CVLAN = 1 << 6, + MLX4_WQE_CTRL_INS_SVLAN = 1 << 7, MLX4_WQE_CTRL_STRONG_ORDER = 1 << 7, MLX4_WQE_CTRL_FORCE_LOOPBACK = 1 << 0, }; @@ -435,11 +448,13 @@ enum mlx4_update_qp_attr { MLX4_UPDATE_QP_VSD = 1 << 1, MLX4_UPDATE_QP_RATE_LIMIT = 1 << 2, MLX4_UPDATE_QP_QOS_VPORT = 1 << 3, - MLX4_UPDATE_QP_SUPPORTED_ATTRS = (1 << 4) - 1 + MLX4_UPDATE_QP_ETH_SRC_CHECK_MC_LB = 1 << 4, + MLX4_UPDATE_QP_SUPPORTED_ATTRS = (1 << 5) - 1 }; enum mlx4_update_qp_params_flags { - MLX4_UPDATE_QP_PARAMS_FLAGS_VSD_ENABLE = 1 << 0, + MLX4_UPDATE_QP_PARAMS_FLAGS_ETH_CHECK_MC_LB = 1 << 0, + MLX4_UPDATE_QP_PARAMS_FLAGS_VSD_ENABLE = 1 << 1, }; struct mlx4_update_qp_params { diff --git a/kernel/include/linux/mlx5/cq.h b/kernel/include/linux/mlx5/cq.h index 2695ced22..b2c9fada8 100644 --- a/kernel/include/linux/mlx5/cq.h +++ b/kernel/include/linux/mlx5/cq.h @@ -45,7 +45,7 @@ struct mlx5_core_cq { atomic_t refcount; struct completion free; unsigned vector; - int irqn; + unsigned int irqn; void (*comp) (struct mlx5_core_cq *); void (*event) (struct mlx5_core_cq *, enum mlx5_event); struct mlx5_uar *uar; @@ -169,6 +169,9 @@ int mlx5_core_query_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq, struct mlx5_query_cq_mbox_out *out); int mlx5_core_modify_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq, struct mlx5_modify_cq_mbox_in *in, int in_sz); +int mlx5_core_modify_cq_moderation(struct mlx5_core_dev *dev, + struct mlx5_core_cq *cq, u16 cq_period, + u16 cq_max_count); int mlx5_debug_cq_add(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq); void mlx5_debug_cq_remove(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq); diff --git a/kernel/include/linux/mlx5/device.h b/kernel/include/linux/mlx5/device.h index abf65c790..0b473cbfa 100644 --- a/kernel/include/linux/mlx5/device.h +++ b/kernel/include/linux/mlx5/device.h @@ -35,6 +35,7 @@ #include <linux/types.h> #include <rdma/ib_verbs.h> +#include <linux/mlx5/mlx5_ifc.h> #if defined(__LITTLE_ENDIAN) #define MLX5_SET_HOST_ENDIANNESS 0 @@ -58,6 +59,8 @@ #define MLX5_FLD_SZ_BYTES(typ, fld) (__mlx5_bit_sz(typ, fld) / 8) #define MLX5_ST_SZ_BYTES(typ) (sizeof(struct mlx5_ifc_##typ##_bits) / 8) #define MLX5_ST_SZ_DW(typ) (sizeof(struct mlx5_ifc_##typ##_bits) / 32) +#define MLX5_UN_SZ_BYTES(typ) (sizeof(union mlx5_ifc_##typ##_bits) / 8) +#define MLX5_UN_SZ_DW(typ) (sizeof(union mlx5_ifc_##typ##_bits) / 32) #define MLX5_BYTE_OFF(typ, fld) (__mlx5_bit_off(typ, fld) / 8) #define MLX5_ADDR_OF(typ, p, fld) ((char *)(p) + MLX5_BYTE_OFF(typ, fld)) @@ -70,6 +73,14 @@ << __mlx5_dw_bit_off(typ, fld))); \ } while (0) +#define MLX5_SET_TO_ONES(typ, p, fld) do { \ + BUILD_BUG_ON(__mlx5_st_sz_bits(typ) % 32); \ + *((__be32 *)(p) + __mlx5_dw_off(typ, fld)) = \ + cpu_to_be32((be32_to_cpu(*((__be32 *)(p) + __mlx5_dw_off(typ, fld))) & \ + (~__mlx5_dw_mask(typ, fld))) | ((__mlx5_mask(typ, fld)) \ + << __mlx5_dw_bit_off(typ, fld))); \ +} while (0) + #define MLX5_GET(typ, p, fld) ((be32_to_cpu(*((__be32 *)(p) +\ __mlx5_dw_off(typ, fld))) >> __mlx5_dw_bit_off(typ, fld)) & \ __mlx5_mask(typ, fld)) @@ -88,6 +99,12 @@ __mlx5_mask(typ, fld)) #define MLX5_GET64(typ, p, fld) be64_to_cpu(*((__be64 *)(p) + __mlx5_64_off(typ, fld))) +#define MLX5_GET64_PR(typ, p, fld) ({ \ + u64 ___t = MLX5_GET64(typ, p, fld); \ + pr_debug(#fld " = 0x%llx\n", ___t); \ + ___t; \ +}) + enum { MLX5_MAX_COMMANDS = 32, MLX5_CMD_DATA_BLOCK_SIZE = 512, @@ -115,6 +132,10 @@ enum { }; enum { + MLX5_HW_START_PADDING = MLX5_INLINE_SEG, +}; + +enum { MLX5_MIN_PKEY_TABLE_SIZE = 128, MLX5_MAX_LOG_PKEY_TABLE = 5, }; @@ -264,6 +285,7 @@ enum { MLX5_OPCODE_RDMA_WRITE_IMM = 0x09, MLX5_OPCODE_SEND = 0x0a, MLX5_OPCODE_SEND_IMM = 0x0b, + MLX5_OPCODE_LSO = 0x0e, MLX5_OPCODE_RDMA_READ = 0x10, MLX5_OPCODE_ATOMIC_CS = 0x11, MLX5_OPCODE_ATOMIC_FA = 0x12, @@ -312,13 +334,6 @@ enum { MLX5_CAP_OFF_CMDIF_CSUM = 46, }; -enum { - HCA_CAP_OPMOD_GET_MAX = 0, - HCA_CAP_OPMOD_GET_CUR = 1, - HCA_CAP_OPMOD_GET_ODP_MAX = 4, - HCA_CAP_OPMOD_GET_ODP_CUR = 5 -}; - struct mlx5_inbox_hdr { __be16 opcode; u8 rsvd[4]; @@ -414,7 +429,7 @@ struct health_buffer { __be32 rsvd2; u8 irisc_index; u8 synd; - __be16 ext_sync; + __be16 ext_synd; }; struct mlx5_init_seg { @@ -424,7 +439,8 @@ struct mlx5_init_seg { __be32 cmdq_addr_h; __be32 cmdq_addr_l_sz; __be32 cmd_dbell; - __be32 rsvd1[121]; + __be32 rsvd1[120]; + __be32 initializing; struct health_buffer health; __be32 rsvd2[884]; __be32 health_counter; @@ -541,6 +557,10 @@ struct mlx5_cmd_prot_block { u8 sig; }; +enum { + MLX5_CQE_SYND_FLUSHED_IN_ERROR = 5, +}; + struct mlx5_err_cqe { u8 rsvd0[32]; __be32 srqn; @@ -554,13 +574,22 @@ struct mlx5_err_cqe { }; struct mlx5_cqe64 { - u8 rsvd0[17]; + u8 rsvd0[4]; + u8 lro_tcppsh_abort_dupack; + u8 lro_min_ttl; + __be16 lro_tcp_win; + __be32 lro_ack_seq_num; + __be32 rss_hash_result; + u8 rss_hash_type; u8 ml_path; - u8 rsvd20[4]; + u8 rsvd20[2]; + __be16 check_sum; __be16 slid; __be32 flags_rqpn; - u8 rsvd28[4]; - __be32 srqn; + u8 hds_ip_ext; + u8 l4_hdr_type_etc; + __be16 vlan_info; + __be32 srqn; /* [31:24]: lro_num_seg, [23:0]: srqn */ __be32 imm_inval_pkey; u8 rsvd40[4]; __be32 byte_cnt; @@ -571,6 +600,40 @@ struct mlx5_cqe64 { u8 op_own; }; +static inline int get_cqe_lro_tcppsh(struct mlx5_cqe64 *cqe) +{ + return (cqe->lro_tcppsh_abort_dupack >> 6) & 1; +} + +static inline u8 get_cqe_l4_hdr_type(struct mlx5_cqe64 *cqe) +{ + return (cqe->l4_hdr_type_etc >> 4) & 0x7; +} + +static inline int cqe_has_vlan(struct mlx5_cqe64 *cqe) +{ + return !!(cqe->l4_hdr_type_etc & 0x1); +} + +enum { + CQE_L4_HDR_TYPE_NONE = 0x0, + CQE_L4_HDR_TYPE_TCP_NO_ACK = 0x1, + CQE_L4_HDR_TYPE_UDP = 0x2, + CQE_L4_HDR_TYPE_TCP_ACK_NO_DATA = 0x3, + CQE_L4_HDR_TYPE_TCP_ACK_AND_DATA = 0x4, +}; + +enum { + CQE_RSS_HTYPE_IP = 0x3 << 6, + CQE_RSS_HTYPE_L4 = 0x3 << 2, +}; + +enum { + CQE_L2_OK = 1 << 0, + CQE_L3_OK = 1 << 1, + CQE_L4_OK = 1 << 2, +}; + struct mlx5_sig_err_cqe { u8 rsvd0[16]; __be32 expected_trans_sig; @@ -996,4 +1059,145 @@ struct mlx5_destroy_psv_out { u8 rsvd[8]; }; +#define MLX5_CMD_OP_MAX 0x920 + +enum { + VPORT_STATE_DOWN = 0x0, + VPORT_STATE_UP = 0x1, +}; + +enum { + MLX5_L3_PROT_TYPE_IPV4 = 0, + MLX5_L3_PROT_TYPE_IPV6 = 1, +}; + +enum { + MLX5_L4_PROT_TYPE_TCP = 0, + MLX5_L4_PROT_TYPE_UDP = 1, +}; + +enum { + MLX5_HASH_FIELD_SEL_SRC_IP = 1 << 0, + MLX5_HASH_FIELD_SEL_DST_IP = 1 << 1, + MLX5_HASH_FIELD_SEL_L4_SPORT = 1 << 2, + MLX5_HASH_FIELD_SEL_L4_DPORT = 1 << 3, + MLX5_HASH_FIELD_SEL_IPSEC_SPI = 1 << 4, +}; + +enum { + MLX5_MATCH_OUTER_HEADERS = 1 << 0, + MLX5_MATCH_MISC_PARAMETERS = 1 << 1, + MLX5_MATCH_INNER_HEADERS = 1 << 2, + +}; + +enum { + MLX5_FLOW_TABLE_TYPE_NIC_RCV = 0, + MLX5_FLOW_TABLE_TYPE_ESWITCH = 4, +}; + +enum { + MLX5_FLOW_CONTEXT_DEST_TYPE_VPORT = 0, + MLX5_FLOW_CONTEXT_DEST_TYPE_FLOW_TABLE = 1, + MLX5_FLOW_CONTEXT_DEST_TYPE_TIR = 2, +}; + +enum { + MLX5_RQC_RQ_TYPE_MEMORY_RQ_INLINE = 0x0, + MLX5_RQC_RQ_TYPE_MEMORY_RQ_RPM = 0x1, +}; + +/* MLX5 DEV CAPs */ + +/* TODO: EAT.ME */ +enum mlx5_cap_mode { + HCA_CAP_OPMOD_GET_MAX = 0, + HCA_CAP_OPMOD_GET_CUR = 1, +}; + +enum mlx5_cap_type { + MLX5_CAP_GENERAL = 0, + MLX5_CAP_ETHERNET_OFFLOADS, + MLX5_CAP_ODP, + MLX5_CAP_ATOMIC, + MLX5_CAP_ROCE, + MLX5_CAP_IPOIB_OFFLOADS, + MLX5_CAP_EOIB_OFFLOADS, + MLX5_CAP_FLOW_TABLE, + /* NUM OF CAP Types */ + MLX5_CAP_NUM +}; + +/* GET Dev Caps macros */ +#define MLX5_CAP_GEN(mdev, cap) \ + MLX5_GET(cmd_hca_cap, mdev->hca_caps_cur[MLX5_CAP_GENERAL], cap) + +#define MLX5_CAP_GEN_MAX(mdev, cap) \ + MLX5_GET(cmd_hca_cap, mdev->hca_caps_max[MLX5_CAP_GENERAL], cap) + +#define MLX5_CAP_ETH(mdev, cap) \ + MLX5_GET(per_protocol_networking_offload_caps,\ + mdev->hca_caps_cur[MLX5_CAP_ETHERNET_OFFLOADS], cap) + +#define MLX5_CAP_ETH_MAX(mdev, cap) \ + MLX5_GET(per_protocol_networking_offload_caps,\ + mdev->hca_caps_max[MLX5_CAP_ETHERNET_OFFLOADS], cap) + +#define MLX5_CAP_ROCE(mdev, cap) \ + MLX5_GET(roce_cap, mdev->hca_caps_cur[MLX5_CAP_ROCE], cap) + +#define MLX5_CAP_ROCE_MAX(mdev, cap) \ + MLX5_GET(roce_cap, mdev->hca_caps_max[MLX5_CAP_ROCE], cap) + +#define MLX5_CAP_ATOMIC(mdev, cap) \ + MLX5_GET(atomic_caps, mdev->hca_caps_cur[MLX5_CAP_ATOMIC], cap) + +#define MLX5_CAP_ATOMIC_MAX(mdev, cap) \ + MLX5_GET(atomic_caps, mdev->hca_caps_max[MLX5_CAP_ATOMIC], cap) + +#define MLX5_CAP_FLOWTABLE(mdev, cap) \ + MLX5_GET(flow_table_nic_cap, mdev->hca_caps_cur[MLX5_CAP_FLOW_TABLE], cap) + +#define MLX5_CAP_FLOWTABLE_MAX(mdev, cap) \ + MLX5_GET(flow_table_nic_cap, mdev->hca_caps_max[MLX5_CAP_FLOW_TABLE], cap) + +#define MLX5_CAP_ODP(mdev, cap)\ + MLX5_GET(odp_cap, mdev->hca_caps_cur[MLX5_CAP_ODP], cap) + +enum { + MLX5_CMD_STAT_OK = 0x0, + MLX5_CMD_STAT_INT_ERR = 0x1, + MLX5_CMD_STAT_BAD_OP_ERR = 0x2, + MLX5_CMD_STAT_BAD_PARAM_ERR = 0x3, + MLX5_CMD_STAT_BAD_SYS_STATE_ERR = 0x4, + MLX5_CMD_STAT_BAD_RES_ERR = 0x5, + MLX5_CMD_STAT_RES_BUSY = 0x6, + MLX5_CMD_STAT_LIM_ERR = 0x8, + MLX5_CMD_STAT_BAD_RES_STATE_ERR = 0x9, + MLX5_CMD_STAT_IX_ERR = 0xa, + MLX5_CMD_STAT_NO_RES_ERR = 0xf, + MLX5_CMD_STAT_BAD_INP_LEN_ERR = 0x50, + MLX5_CMD_STAT_BAD_OUTP_LEN_ERR = 0x51, + MLX5_CMD_STAT_BAD_QP_STATE_ERR = 0x10, + MLX5_CMD_STAT_BAD_PKT_ERR = 0x30, + MLX5_CMD_STAT_BAD_SIZE_OUTS_CQES_ERR = 0x40, +}; + +enum { + MLX5_IEEE_802_3_COUNTERS_GROUP = 0x0, + MLX5_RFC_2863_COUNTERS_GROUP = 0x1, + MLX5_RFC_2819_COUNTERS_GROUP = 0x2, + MLX5_RFC_3635_COUNTERS_GROUP = 0x3, + MLX5_ETHERNET_EXTENDED_COUNTERS_GROUP = 0x5, + MLX5_PER_PRIORITY_COUNTERS_GROUP = 0x10, + MLX5_PER_TRAFFIC_CLASS_COUNTERS_GROUP = 0x11 +}; + +static inline u16 mlx5_to_sw_pkey_sz(int pkey_sz) +{ + if (pkey_sz > MLX5_MAX_LOG_PKEY_TABLE) + return 0; + return MLX5_MIN_PKEY_TABLE_SIZE << pkey_sz; +} + #endif /* MLX5_DEVICE_H */ diff --git a/kernel/include/linux/mlx5/driver.h b/kernel/include/linux/mlx5/driver.h index 9a90e7523..af3efd915 100644 --- a/kernel/include/linux/mlx5/driver.h +++ b/kernel/include/linux/mlx5/driver.h @@ -44,7 +44,6 @@ #include <linux/mlx5/device.h> #include <linux/mlx5/doorbell.h> -#include <linux/mlx5/mlx5_ifc.h> enum { MLX5_BOARD_ID_LEN = 64, @@ -85,7 +84,7 @@ enum { }; enum { - MLX5_MAX_EQ_NAME = 32 + MLX5_MAX_IRQ_NAME = 32 }; enum { @@ -104,10 +103,13 @@ enum { MLX5_REG_PMTU = 0x5003, MLX5_REG_PTYS = 0x5004, MLX5_REG_PAOS = 0x5006, + MLX5_REG_PFCC = 0x5007, + MLX5_REG_PPCNT = 0x5008, MLX5_REG_PMAOS = 0x5012, MLX5_REG_PUDE = 0x5009, MLX5_REG_PMPE = 0x5010, MLX5_REG_PELC = 0x500e, + MLX5_REG_PVLC = 0x500f, MLX5_REG_PMLP = 0, /* TBD */ MLX5_REG_NODE_DESC = 0x6001, MLX5_REG_HOST_ENDIANNESS = 0x7004, @@ -150,6 +152,11 @@ enum mlx5_dev_event { MLX5_DEV_EVENT_CLIENT_REREG, }; +enum mlx5_port_status { + MLX5_PORT_UP = 1, + MLX5_PORT_DOWN = 2, +}; + struct mlx5_uuar_info { struct mlx5_uar *uars; int num_uars; @@ -269,56 +276,7 @@ struct mlx5_cmd { struct mlx5_port_caps { int gid_table_len; int pkey_table_len; -}; - -struct mlx5_general_caps { - u8 log_max_eq; - u8 log_max_cq; - u8 log_max_qp; - u8 log_max_mkey; - u8 log_max_pd; - u8 log_max_srq; - u8 log_max_strq; - u8 log_max_mrw_sz; - u8 log_max_bsf_list_size; - u8 log_max_klm_list_size; - u32 max_cqes; - int max_wqes; - u32 max_eqes; - u32 max_indirection; - int max_sq_desc_sz; - int max_rq_desc_sz; - int max_dc_sq_desc_sz; - u64 flags; - u16 stat_rate_support; - int log_max_msg; - int num_ports; - u8 log_max_ra_res_qp; - u8 log_max_ra_req_qp; - int max_srq_wqes; - int bf_reg_size; - int bf_regs_per_page; - struct mlx5_port_caps port[MLX5_MAX_PORTS]; - u8 ext_port_cap[MLX5_MAX_PORTS]; - int max_vf; - u32 reserved_lkey; - u8 local_ca_ack_delay; - u8 log_max_mcg; - u32 max_qp_mcg; - int min_page_sz; - int pd_cap; - u32 max_qp_counters; - u32 pkey_table_size; - u8 log_max_ra_req_dc; - u8 log_max_ra_res_dc; - u32 uar_sz; - u8 min_log_pg_sz; - u8 log_max_xrcd; - u16 log_uar_page_sz; -}; - -struct mlx5_caps { - struct mlx5_general_caps gen; + u8 ext_port_cap; }; struct mlx5_cmd_mailbox { @@ -334,8 +292,6 @@ struct mlx5_buf_list { struct mlx5_buf { struct mlx5_buf_list direct; - struct mlx5_buf_list *page_list; - int nbufs; int npages; int size; u8 page_shift; @@ -347,11 +303,10 @@ struct mlx5_eq { u32 cons_index; struct mlx5_buf buf; int size; - u8 irqn; + unsigned int irqn; u8 eqn; int nent; u64 mask; - char name[MLX5_MAX_EQ_NAME]; struct list_head list; int index; struct mlx5_rsc_debug *dbg; @@ -387,6 +342,8 @@ struct mlx5_core_mr { enum mlx5_res_type { MLX5_RES_QP, + MLX5_RES_SRQ, + MLX5_RES_XSRQ, }; struct mlx5_core_rsc_common { @@ -396,6 +353,7 @@ struct mlx5_core_rsc_common { }; struct mlx5_core_srq { + struct mlx5_core_rsc_common common; /* must be first */ u32 srqn; int max; int max_gs; @@ -414,7 +372,6 @@ struct mlx5_eq_table { struct mlx5_eq pages_eq; struct mlx5_eq async_eq; struct mlx5_eq cmd_eq; - struct msix_entry *msix_arr; int num_comp_vectors; /* protect EQs list */ @@ -425,7 +382,7 @@ struct mlx5_uar { u32 index; struct list_head bf_list; unsigned free_bf_bmap; - void __iomem *wc_map; + void __iomem *bf_map; void __iomem *map; }; @@ -434,9 +391,11 @@ struct mlx5_core_health { struct health_buffer __iomem *health; __be32 __iomem *health_counter; struct timer_list timer; - struct list_head list; u32 prev; int miss_counter; + bool sick; + struct workqueue_struct *wq; + struct work_struct work; }; struct mlx5_cq_table { @@ -467,12 +426,21 @@ struct mlx5_mr_table { struct radix_tree_root tree; }; +struct mlx5_irq_info { + cpumask_var_t mask; + char name[MLX5_MAX_IRQ_NAME]; +}; + struct mlx5_priv { char name[MLX5_MAX_NAME_LEN]; struct mlx5_eq_table eq_table; + struct msix_entry *msix_arr; + struct mlx5_irq_info *irq_info; struct mlx5_uuar_info uuari; MLX5_DECLARE_DOORBELL_LOCK(cq_uar_lock); + struct io_mapping *bf_mapping; + /* pages stuff */ struct workqueue_struct *pg_wq; struct rb_root page_root; @@ -501,6 +469,10 @@ struct mlx5_priv { /* end: mr staff */ /* start: alloc staff */ + /* protect buffer alocation according to numa node */ + struct mutex alloc_mutex; + int numa_node; + struct mutex pgdir_mutex; struct list_head pgdir_list; /* end: alloc staff */ @@ -515,20 +487,45 @@ struct mlx5_priv { spinlock_t ctx_lock; }; +enum mlx5_device_state { + MLX5_DEVICE_STATE_UP, + MLX5_DEVICE_STATE_INTERNAL_ERROR, +}; + +enum mlx5_interface_state { + MLX5_INTERFACE_STATE_DOWN, + MLX5_INTERFACE_STATE_UP, +}; + +enum mlx5_pci_status { + MLX5_PCI_STATUS_DISABLED, + MLX5_PCI_STATUS_ENABLED, +}; + struct mlx5_core_dev { struct pci_dev *pdev; + /* sync pci state */ + struct mutex pci_status_mutex; + enum mlx5_pci_status pci_status; u8 rev_id; char board_id[MLX5_BOARD_ID_LEN]; struct mlx5_cmd cmd; - struct mlx5_caps caps; + struct mlx5_port_caps port_caps[MLX5_MAX_PORTS]; + u32 hca_caps_cur[MLX5_CAP_NUM][MLX5_UN_SZ_DW(hca_cap_union)]; + u32 hca_caps_max[MLX5_CAP_NUM][MLX5_UN_SZ_DW(hca_cap_union)]; phys_addr_t iseg_base; struct mlx5_init_seg __iomem *iseg; + enum mlx5_device_state state; + /* sync interface state */ + struct mutex intf_state_mutex; + enum mlx5_interface_state interface_state; void (*event) (struct mlx5_core_dev *dev, enum mlx5_dev_event event, unsigned long param); struct mlx5_priv priv; struct mlx5_profile *profile; atomic_t num_qps; + u32 issi; }; struct mlx5_db { @@ -549,6 +546,11 @@ enum { MLX5_COMP_EQ_SIZE = 1024, }; +enum { + MLX5_PTYS_IB = 1 << 0, + MLX5_PTYS_EN = 1 << 2, +}; + struct mlx5_db_pgdir { struct list_head list; DECLARE_BITMAP(bitmap, MLX5_DB_PER_PAGE); @@ -584,13 +586,44 @@ struct mlx5_pas { u8 log_sz; }; +enum port_state_policy { + MLX5_AAA_000 +}; + +enum phy_port_state { + MLX5_AAA_111 +}; + +struct mlx5_hca_vport_context { + u32 field_select; + bool sm_virt_aware; + bool has_smi; + bool has_raw; + enum port_state_policy policy; + enum phy_port_state phys_state; + enum ib_port_state vport_state; + u8 port_physical_state; + u64 sys_image_guid; + u64 port_guid; + u64 node_guid; + u32 cap_mask1; + u32 cap_mask1_perm; + u32 cap_mask2; + u32 cap_mask2_perm; + u16 lid; + u8 init_type_reply; /* bitmask: see ib spec 14.2.5.6 InitTypeReply */ + u8 lmc; + u8 subnet_timeout; + u16 sm_lid; + u8 sm_sl; + u16 qkey_violation_counter; + u16 pkey_violation_counter; + bool grh_required; +}; + static inline void *mlx5_buf_offset(struct mlx5_buf *buf, int offset) { - if (likely(BITS_PER_LONG == 64 || buf->nbufs == 1)) return buf->direct.buf + offset; - else - return buf->page_list[offset >> PAGE_SHIFT].buf + - (offset & (PAGE_SIZE - 1)); } extern struct workqueue_struct *mlx5_core_wq; @@ -654,8 +687,8 @@ void mlx5_cmd_use_events(struct mlx5_core_dev *dev); void mlx5_cmd_use_polling(struct mlx5_core_dev *dev); int mlx5_cmd_status_to_err(struct mlx5_outbox_hdr *hdr); int mlx5_cmd_status_to_err_v2(void *ptr); -int mlx5_core_get_caps(struct mlx5_core_dev *dev, struct mlx5_caps *caps, - u16 opmod); +int mlx5_core_get_caps(struct mlx5_core_dev *dev, enum mlx5_cap_type cap_type, + enum mlx5_cap_mode cap_mode); int mlx5_cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out, int out_size); int mlx5_cmd_exec_cb(struct mlx5_core_dev *dev, void *in, int in_size, @@ -665,19 +698,23 @@ int mlx5_cmd_alloc_uar(struct mlx5_core_dev *dev, u32 *uarn); int mlx5_cmd_free_uar(struct mlx5_core_dev *dev, u32 uarn); int mlx5_alloc_uuars(struct mlx5_core_dev *dev, struct mlx5_uuar_info *uuari); int mlx5_free_uuars(struct mlx5_core_dev *dev, struct mlx5_uuar_info *uuari); -void mlx5_health_cleanup(void); -void __init mlx5_health_init(void); +int mlx5_alloc_map_uar(struct mlx5_core_dev *mdev, struct mlx5_uar *uar); +void mlx5_unmap_free_uar(struct mlx5_core_dev *mdev, struct mlx5_uar *uar); +void mlx5_health_cleanup(struct mlx5_core_dev *dev); +int mlx5_health_init(struct mlx5_core_dev *dev); void mlx5_start_health_poll(struct mlx5_core_dev *dev); void mlx5_stop_health_poll(struct mlx5_core_dev *dev); -int mlx5_buf_alloc(struct mlx5_core_dev *dev, int size, int max_direct, - struct mlx5_buf *buf); +int mlx5_buf_alloc_node(struct mlx5_core_dev *dev, int size, + struct mlx5_buf *buf, int node); +int mlx5_buf_alloc(struct mlx5_core_dev *dev, int size, struct mlx5_buf *buf); void mlx5_buf_free(struct mlx5_core_dev *dev, struct mlx5_buf *buf); struct mlx5_cmd_mailbox *mlx5_alloc_cmd_mailbox_chain(struct mlx5_core_dev *dev, gfp_t flags, int npages); void mlx5_free_cmd_mailbox_chain(struct mlx5_core_dev *dev, struct mlx5_cmd_mailbox *head); int mlx5_core_create_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq, - struct mlx5_create_srq_mbox_in *in, int inlen); + struct mlx5_create_srq_mbox_in *in, int inlen, + int is_xrc); int mlx5_core_destroy_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq); int mlx5_core_query_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq, struct mlx5_query_srq_mbox_out *out); @@ -696,7 +733,7 @@ int mlx5_core_dump_fill_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mr *mr, u32 *mkey); int mlx5_core_alloc_pd(struct mlx5_core_dev *dev, u32 *pdn); int mlx5_core_dealloc_pd(struct mlx5_core_dev *dev, u32 pdn); -int mlx5_core_mad_ifc(struct mlx5_core_dev *dev, void *inb, void *outb, +int mlx5_core_mad_ifc(struct mlx5_core_dev *dev, const void *inb, void *outb, u16 opmod, u8 port); void mlx5_pagealloc_init(struct mlx5_core_dev *dev); void mlx5_pagealloc_cleanup(struct mlx5_core_dev *dev); @@ -718,14 +755,15 @@ void mlx5_eq_pagefault(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe); #endif void mlx5_srq_event(struct mlx5_core_dev *dev, u32 srqn, int event_type); struct mlx5_core_srq *mlx5_core_get_srq(struct mlx5_core_dev *dev, u32 srqn); -void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, unsigned long vector); +void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec); void mlx5_cq_event(struct mlx5_core_dev *dev, u32 cqn, int event_type); int mlx5_create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u8 vecidx, int nent, u64 mask, const char *name, struct mlx5_uar *uar); int mlx5_destroy_unmap_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq); int mlx5_start_eqs(struct mlx5_core_dev *dev); int mlx5_stop_eqs(struct mlx5_core_dev *dev); -int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn, int *irqn); +int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn, + unsigned int *irqn); int mlx5_core_attach_mcg(struct mlx5_core_dev *dev, union ib_gid *mgid, u32 qpn); int mlx5_core_detach_mcg(struct mlx5_core_dev *dev, union ib_gid *mgid, u32 qpn); @@ -734,7 +772,37 @@ void mlx5_qp_debugfs_cleanup(struct mlx5_core_dev *dev); int mlx5_core_access_reg(struct mlx5_core_dev *dev, void *data_in, int size_in, void *data_out, int size_out, u16 reg_num, int arg, int write); + int mlx5_set_port_caps(struct mlx5_core_dev *dev, u8 port_num, u32 caps); +int mlx5_query_port_ptys(struct mlx5_core_dev *dev, u32 *ptys, + int ptys_size, int proto_mask, u8 local_port); +int mlx5_query_port_proto_cap(struct mlx5_core_dev *dev, + u32 *proto_cap, int proto_mask); +int mlx5_query_port_proto_admin(struct mlx5_core_dev *dev, + u32 *proto_admin, int proto_mask); +int mlx5_query_port_link_width_oper(struct mlx5_core_dev *dev, + u8 *link_width_oper, u8 local_port); +int mlx5_query_port_proto_oper(struct mlx5_core_dev *dev, + u8 *proto_oper, int proto_mask, + u8 local_port); +int mlx5_set_port_proto(struct mlx5_core_dev *dev, u32 proto_admin, + int proto_mask); +int mlx5_set_port_admin_status(struct mlx5_core_dev *dev, + enum mlx5_port_status status); +int mlx5_query_port_admin_status(struct mlx5_core_dev *dev, + enum mlx5_port_status *status); + +int mlx5_set_port_mtu(struct mlx5_core_dev *dev, int mtu, u8 port); +void mlx5_query_port_max_mtu(struct mlx5_core_dev *dev, int *max_mtu, u8 port); +void mlx5_query_port_oper_mtu(struct mlx5_core_dev *dev, int *oper_mtu, + u8 port); + +int mlx5_query_port_vl_hw_cap(struct mlx5_core_dev *dev, + u8 *vl_hw_cap, u8 local_port); + +int mlx5_set_port_pause(struct mlx5_core_dev *dev, u32 rx_pause, u32 tx_pause); +int mlx5_query_port_pause(struct mlx5_core_dev *dev, + u32 *rx_pause, u32 *tx_pause); int mlx5_debug_eq_add(struct mlx5_core_dev *dev, struct mlx5_eq *eq); void mlx5_debug_eq_remove(struct mlx5_core_dev *dev, struct mlx5_eq *eq); @@ -745,6 +813,8 @@ void mlx5_eq_debugfs_cleanup(struct mlx5_core_dev *dev); int mlx5_cq_debugfs_init(struct mlx5_core_dev *dev); void mlx5_cq_debugfs_cleanup(struct mlx5_core_dev *dev); int mlx5_db_alloc(struct mlx5_core_dev *dev, struct mlx5_db *db); +int mlx5_db_alloc_node(struct mlx5_core_dev *dev, struct mlx5_db *db, + int node); void mlx5_db_free(struct mlx5_core_dev *dev, struct mlx5_db *db); const char *mlx5_command_str(int command); @@ -757,6 +827,11 @@ void mlx5_core_put_rsc(struct mlx5_core_rsc_common *common); int mlx5_query_odp_caps(struct mlx5_core_dev *dev, struct mlx5_odp_caps *odp_caps); +static inline int fw_initializing(struct mlx5_core_dev *dev) +{ + return ioread32be(&dev->iseg->initializing) >> 31; +} + static inline u32 mlx5_mkey_to_idx(u32 mkey) { return mkey >> 8; @@ -799,6 +874,7 @@ struct mlx5_interface { void *mlx5_get_protocol_dev(struct mlx5_core_dev *mdev, int protocol); int mlx5_register_interface(struct mlx5_interface *intf); void mlx5_unregister_interface(struct mlx5_interface *intf); +int mlx5_core_query_vendor_id(struct mlx5_core_dev *mdev, u32 *vendor_id); struct mlx5_profile { u64 mask; @@ -809,4 +885,18 @@ struct mlx5_profile { } mr_cache[MAX_MR_CACHE_ENTRIES]; }; +static inline int mlx5_get_gid_table_len(u16 param) +{ + if (param > 4) { + pr_warn("gid table length is zero\n"); + return 0; + } + + return 8 * (1 << param); +} + +enum { + MLX5_TRIGGERED_CMD_COMP = (u64)1 << 32, +}; + #endif /* MLX5_DRIVER_H */ diff --git a/kernel/include/linux/mlx5/flow_table.h b/kernel/include/linux/mlx5/flow_table.h new file mode 100644 index 000000000..5f922c6d4 --- /dev/null +++ b/kernel/include/linux/mlx5/flow_table.h @@ -0,0 +1,54 @@ +/* + * Copyright (c) 2013-2015, Mellanox Technologies, Ltd. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#ifndef MLX5_FLOW_TABLE_H +#define MLX5_FLOW_TABLE_H + +#include <linux/mlx5/driver.h> + +struct mlx5_flow_table_group { + u8 log_sz; + u8 match_criteria_enable; + u32 match_criteria[MLX5_ST_SZ_DW(fte_match_param)]; +}; + +void *mlx5_create_flow_table(struct mlx5_core_dev *dev, u8 level, u8 table_type, + u16 num_groups, + struct mlx5_flow_table_group *group); +void mlx5_destroy_flow_table(void *flow_table); +int mlx5_add_flow_table_entry(void *flow_table, u8 match_criteria_enable, + void *match_criteria, void *flow_context, + u32 *flow_index); +void mlx5_del_flow_table_entry(void *flow_table, u32 flow_index); +u32 mlx5_get_flow_table_id(void *flow_table); + +#endif /* MLX5_FLOW_TABLE_H */ diff --git a/kernel/include/linux/mlx5/mlx5_ifc.h b/kernel/include/linux/mlx5/mlx5_ifc.h index cb3ad17ed..1565324eb 100644 --- a/kernel/include/linux/mlx5/mlx5_ifc.h +++ b/kernel/include/linux/mlx5/mlx5_ifc.h @@ -1,5 +1,5 @@ /* - * Copyright (c) 2013-2015, Mellanox Technologies. All rights reserved. + * Copyright (c) 2013-2015, Mellanox Technologies, Ltd. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU @@ -28,12 +28,45 @@ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. - */ - +*/ #ifndef MLX5_IFC_H #define MLX5_IFC_H enum { + MLX5_EVENT_TYPE_CODING_COMPLETION_EVENTS = 0x0, + MLX5_EVENT_TYPE_CODING_PATH_MIGRATED_SUCCEEDED = 0x1, + MLX5_EVENT_TYPE_CODING_COMMUNICATION_ESTABLISHED = 0x2, + MLX5_EVENT_TYPE_CODING_SEND_QUEUE_DRAINED = 0x3, + MLX5_EVENT_TYPE_CODING_LAST_WQE_REACHED = 0x13, + MLX5_EVENT_TYPE_CODING_SRQ_LIMIT = 0x14, + MLX5_EVENT_TYPE_CODING_DCT_ALL_CONNECTIONS_CLOSED = 0x1c, + MLX5_EVENT_TYPE_CODING_DCT_ACCESS_KEY_VIOLATION = 0x1d, + MLX5_EVENT_TYPE_CODING_CQ_ERROR = 0x4, + MLX5_EVENT_TYPE_CODING_LOCAL_WQ_CATASTROPHIC_ERROR = 0x5, + MLX5_EVENT_TYPE_CODING_PATH_MIGRATION_FAILED = 0x7, + MLX5_EVENT_TYPE_CODING_PAGE_FAULT_EVENT = 0xc, + MLX5_EVENT_TYPE_CODING_INVALID_REQUEST_LOCAL_WQ_ERROR = 0x10, + MLX5_EVENT_TYPE_CODING_LOCAL_ACCESS_VIOLATION_WQ_ERROR = 0x11, + MLX5_EVENT_TYPE_CODING_LOCAL_SRQ_CATASTROPHIC_ERROR = 0x12, + MLX5_EVENT_TYPE_CODING_INTERNAL_ERROR = 0x8, + MLX5_EVENT_TYPE_CODING_PORT_STATE_CHANGE = 0x9, + MLX5_EVENT_TYPE_CODING_GPIO_EVENT = 0x15, + MLX5_EVENT_TYPE_CODING_REMOTE_CONFIGURATION_PROTOCOL_EVENT = 0x19, + MLX5_EVENT_TYPE_CODING_DOORBELL_BLUEFLAME_CONGESTION_EVENT = 0x1a, + MLX5_EVENT_TYPE_CODING_STALL_VL_EVENT = 0x1b, + MLX5_EVENT_TYPE_CODING_DROPPED_PACKET_LOGGED_EVENT = 0x1f, + MLX5_EVENT_TYPE_CODING_COMMAND_INTERFACE_COMPLETION = 0xa, + MLX5_EVENT_TYPE_CODING_PAGE_REQUEST = 0xb +}; + +enum { + MLX5_MODIFY_TIR_BITMASK_LRO = 0x0, + MLX5_MODIFY_TIR_BITMASK_INDIRECT_TABLE = 0x1, + MLX5_MODIFY_TIR_BITMASK_HASH = 0x2, + MLX5_MODIFY_TIR_BITMASK_TUNNELED_OFFLOAD_EN = 0x3 +}; + +enum { MLX5_CMD_OP_QUERY_HCA_CAP = 0x100, MLX5_CMD_OP_QUERY_ADAPTER = 0x101, MLX5_CMD_OP_INIT_HCA = 0x102, @@ -43,6 +76,8 @@ enum { MLX5_CMD_OP_QUERY_PAGES = 0x107, MLX5_CMD_OP_MANAGE_PAGES = 0x108, MLX5_CMD_OP_SET_HCA_CAP = 0x109, + MLX5_CMD_OP_QUERY_ISSI = 0x10a, + MLX5_CMD_OP_SET_ISSI = 0x10b, MLX5_CMD_OP_CREATE_MKEY = 0x200, MLX5_CMD_OP_QUERY_MKEY = 0x201, MLX5_CMD_OP_DESTROY_MKEY = 0x202, @@ -66,6 +101,7 @@ enum { MLX5_CMD_OP_2ERR_QP = 0x507, MLX5_CMD_OP_2RST_QP = 0x50a, MLX5_CMD_OP_QUERY_QP = 0x50b, + MLX5_CMD_OP_SQD_RTS_QP = 0x50c, MLX5_CMD_OP_INIT2INIT_QP = 0x50e, MLX5_CMD_OP_CREATE_PSV = 0x600, MLX5_CMD_OP_DESTROY_PSV = 0x601, @@ -73,7 +109,10 @@ enum { MLX5_CMD_OP_DESTROY_SRQ = 0x701, MLX5_CMD_OP_QUERY_SRQ = 0x702, MLX5_CMD_OP_ARM_RQ = 0x703, - MLX5_CMD_OP_RESIZE_SRQ = 0x704, + MLX5_CMD_OP_CREATE_XRC_SRQ = 0x705, + MLX5_CMD_OP_DESTROY_XRC_SRQ = 0x706, + MLX5_CMD_OP_QUERY_XRC_SRQ = 0x707, + MLX5_CMD_OP_ARM_XRC_SRQ = 0x708, MLX5_CMD_OP_CREATE_DCT = 0x710, MLX5_CMD_OP_DESTROY_DCT = 0x711, MLX5_CMD_OP_DRAIN_DCT = 0x712, @@ -85,8 +124,12 @@ enum { MLX5_CMD_OP_MODIFY_ESW_VPORT_CONTEXT = 0x753, MLX5_CMD_OP_QUERY_NIC_VPORT_CONTEXT = 0x754, MLX5_CMD_OP_MODIFY_NIC_VPORT_CONTEXT = 0x755, - MLX5_CMD_OP_QUERY_RCOE_ADDRESS = 0x760, + MLX5_CMD_OP_QUERY_ROCE_ADDRESS = 0x760, MLX5_CMD_OP_SET_ROCE_ADDRESS = 0x761, + MLX5_CMD_OP_QUERY_HCA_VPORT_CONTEXT = 0x762, + MLX5_CMD_OP_MODIFY_HCA_VPORT_CONTEXT = 0x763, + MLX5_CMD_OP_QUERY_HCA_VPORT_GID = 0x764, + MLX5_CMD_OP_QUERY_HCA_VPORT_PKEY = 0x765, MLX5_CMD_OP_QUERY_VPORT_COUNTER = 0x770, MLX5_CMD_OP_ALLOC_Q_COUNTER = 0x771, MLX5_CMD_OP_DEALLOC_Q_COUNTER = 0x772, @@ -98,7 +141,7 @@ enum { MLX5_CMD_OP_CONFIG_INT_MODERATION = 0x804, MLX5_CMD_OP_ACCESS_REG = 0x805, MLX5_CMD_OP_ATTACH_TO_MCG = 0x806, - MLX5_CMD_OP_DETACH_FROM_MCG = 0x807, + MLX5_CMD_OP_DETTACH_FROM_MCG = 0x807, MLX5_CMD_OP_GET_DROPPED_PACKET_LOG = 0x80a, MLX5_CMD_OP_MAD_IFC = 0x50d, MLX5_CMD_OP_QUERY_MAD_DEMUX = 0x80b, @@ -106,23 +149,22 @@ enum { MLX5_CMD_OP_NOP = 0x80d, MLX5_CMD_OP_ALLOC_XRCD = 0x80e, MLX5_CMD_OP_DEALLOC_XRCD = 0x80f, - MLX5_CMD_OP_SET_BURST_SIZE = 0x812, - MLX5_CMD_OP_QUERY_BURST_SZIE = 0x813, - MLX5_CMD_OP_ACTIVATE_TRACER = 0x814, - MLX5_CMD_OP_DEACTIVATE_TRACER = 0x815, - MLX5_CMD_OP_CREATE_SNIFFER_RULE = 0x820, - MLX5_CMD_OP_DESTROY_SNIFFER_RULE = 0x821, - MLX5_CMD_OP_QUERY_CONG_PARAMS = 0x822, - MLX5_CMD_OP_MODIFY_CONG_PARAMS = 0x823, - MLX5_CMD_OP_QUERY_CONG_STATISTICS = 0x824, + MLX5_CMD_OP_ALLOC_TRANSPORT_DOMAIN = 0x816, + MLX5_CMD_OP_DEALLOC_TRANSPORT_DOMAIN = 0x817, + MLX5_CMD_OP_QUERY_CONG_STATUS = 0x822, + MLX5_CMD_OP_MODIFY_CONG_STATUS = 0x823, + MLX5_CMD_OP_QUERY_CONG_PARAMS = 0x824, + MLX5_CMD_OP_MODIFY_CONG_PARAMS = 0x825, + MLX5_CMD_OP_QUERY_CONG_STATISTICS = 0x826, + MLX5_CMD_OP_ADD_VXLAN_UDP_DPORT = 0x827, + MLX5_CMD_OP_DELETE_VXLAN_UDP_DPORT = 0x828, + MLX5_CMD_OP_SET_L2_TABLE_ENTRY = 0x829, + MLX5_CMD_OP_QUERY_L2_TABLE_ENTRY = 0x82a, + MLX5_CMD_OP_DELETE_L2_TABLE_ENTRY = 0x82b, MLX5_CMD_OP_CREATE_TIR = 0x900, MLX5_CMD_OP_MODIFY_TIR = 0x901, MLX5_CMD_OP_DESTROY_TIR = 0x902, MLX5_CMD_OP_QUERY_TIR = 0x903, - MLX5_CMD_OP_CREATE_TIS = 0x912, - MLX5_CMD_OP_MODIFY_TIS = 0x913, - MLX5_CMD_OP_DESTROY_TIS = 0x914, - MLX5_CMD_OP_QUERY_TIS = 0x915, MLX5_CMD_OP_CREATE_SQ = 0x904, MLX5_CMD_OP_MODIFY_SQ = 0x905, MLX5_CMD_OP_DESTROY_SQ = 0x906, @@ -135,9 +177,432 @@ enum { MLX5_CMD_OP_MODIFY_RMP = 0x90d, MLX5_CMD_OP_DESTROY_RMP = 0x90e, MLX5_CMD_OP_QUERY_RMP = 0x90f, - MLX5_CMD_OP_SET_FLOW_TABLE_ENTRY = 0x910, - MLX5_CMD_OP_QUERY_FLOW_TABLE_ENTRY = 0x911, - MLX5_CMD_OP_MAX = 0x911 + MLX5_CMD_OP_CREATE_TIS = 0x912, + MLX5_CMD_OP_MODIFY_TIS = 0x913, + MLX5_CMD_OP_DESTROY_TIS = 0x914, + MLX5_CMD_OP_QUERY_TIS = 0x915, + MLX5_CMD_OP_CREATE_RQT = 0x916, + MLX5_CMD_OP_MODIFY_RQT = 0x917, + MLX5_CMD_OP_DESTROY_RQT = 0x918, + MLX5_CMD_OP_QUERY_RQT = 0x919, + MLX5_CMD_OP_CREATE_FLOW_TABLE = 0x930, + MLX5_CMD_OP_DESTROY_FLOW_TABLE = 0x931, + MLX5_CMD_OP_QUERY_FLOW_TABLE = 0x932, + MLX5_CMD_OP_CREATE_FLOW_GROUP = 0x933, + MLX5_CMD_OP_DESTROY_FLOW_GROUP = 0x934, + MLX5_CMD_OP_QUERY_FLOW_GROUP = 0x935, + MLX5_CMD_OP_SET_FLOW_TABLE_ENTRY = 0x936, + MLX5_CMD_OP_QUERY_FLOW_TABLE_ENTRY = 0x937, + MLX5_CMD_OP_DELETE_FLOW_TABLE_ENTRY = 0x938 +}; + +struct mlx5_ifc_flow_table_fields_supported_bits { + u8 outer_dmac[0x1]; + u8 outer_smac[0x1]; + u8 outer_ether_type[0x1]; + u8 reserved_0[0x1]; + u8 outer_first_prio[0x1]; + u8 outer_first_cfi[0x1]; + u8 outer_first_vid[0x1]; + u8 reserved_1[0x1]; + u8 outer_second_prio[0x1]; + u8 outer_second_cfi[0x1]; + u8 outer_second_vid[0x1]; + u8 reserved_2[0x1]; + u8 outer_sip[0x1]; + u8 outer_dip[0x1]; + u8 outer_frag[0x1]; + u8 outer_ip_protocol[0x1]; + u8 outer_ip_ecn[0x1]; + u8 outer_ip_dscp[0x1]; + u8 outer_udp_sport[0x1]; + u8 outer_udp_dport[0x1]; + u8 outer_tcp_sport[0x1]; + u8 outer_tcp_dport[0x1]; + u8 outer_tcp_flags[0x1]; + u8 outer_gre_protocol[0x1]; + u8 outer_gre_key[0x1]; + u8 outer_vxlan_vni[0x1]; + u8 reserved_3[0x5]; + u8 source_eswitch_port[0x1]; + + u8 inner_dmac[0x1]; + u8 inner_smac[0x1]; + u8 inner_ether_type[0x1]; + u8 reserved_4[0x1]; + u8 inner_first_prio[0x1]; + u8 inner_first_cfi[0x1]; + u8 inner_first_vid[0x1]; + u8 reserved_5[0x1]; + u8 inner_second_prio[0x1]; + u8 inner_second_cfi[0x1]; + u8 inner_second_vid[0x1]; + u8 reserved_6[0x1]; + u8 inner_sip[0x1]; + u8 inner_dip[0x1]; + u8 inner_frag[0x1]; + u8 inner_ip_protocol[0x1]; + u8 inner_ip_ecn[0x1]; + u8 inner_ip_dscp[0x1]; + u8 inner_udp_sport[0x1]; + u8 inner_udp_dport[0x1]; + u8 inner_tcp_sport[0x1]; + u8 inner_tcp_dport[0x1]; + u8 inner_tcp_flags[0x1]; + u8 reserved_7[0x9]; + + u8 reserved_8[0x40]; +}; + +struct mlx5_ifc_flow_table_prop_layout_bits { + u8 ft_support[0x1]; + u8 reserved_0[0x1f]; + + u8 reserved_1[0x2]; + u8 log_max_ft_size[0x6]; + u8 reserved_2[0x10]; + u8 max_ft_level[0x8]; + + u8 reserved_3[0x20]; + + u8 reserved_4[0x18]; + u8 log_max_ft_num[0x8]; + + u8 reserved_5[0x18]; + u8 log_max_destination[0x8]; + + u8 reserved_6[0x18]; + u8 log_max_flow[0x8]; + + u8 reserved_7[0x40]; + + struct mlx5_ifc_flow_table_fields_supported_bits ft_field_support; + + struct mlx5_ifc_flow_table_fields_supported_bits ft_field_bitmask_support; +}; + +struct mlx5_ifc_odp_per_transport_service_cap_bits { + u8 send[0x1]; + u8 receive[0x1]; + u8 write[0x1]; + u8 read[0x1]; + u8 reserved_0[0x1]; + u8 srq_receive[0x1]; + u8 reserved_1[0x1a]; +}; + +struct mlx5_ifc_fte_match_set_lyr_2_4_bits { + u8 smac_47_16[0x20]; + + u8 smac_15_0[0x10]; + u8 ethertype[0x10]; + + u8 dmac_47_16[0x20]; + + u8 dmac_15_0[0x10]; + u8 first_prio[0x3]; + u8 first_cfi[0x1]; + u8 first_vid[0xc]; + + u8 ip_protocol[0x8]; + u8 ip_dscp[0x6]; + u8 ip_ecn[0x2]; + u8 vlan_tag[0x1]; + u8 reserved_0[0x1]; + u8 frag[0x1]; + u8 reserved_1[0x4]; + u8 tcp_flags[0x9]; + + u8 tcp_sport[0x10]; + u8 tcp_dport[0x10]; + + u8 reserved_2[0x20]; + + u8 udp_sport[0x10]; + u8 udp_dport[0x10]; + + u8 src_ip[4][0x20]; + + u8 dst_ip[4][0x20]; +}; + +struct mlx5_ifc_fte_match_set_misc_bits { + u8 reserved_0[0x20]; + + u8 reserved_1[0x10]; + u8 source_port[0x10]; + + u8 outer_second_prio[0x3]; + u8 outer_second_cfi[0x1]; + u8 outer_second_vid[0xc]; + u8 inner_second_prio[0x3]; + u8 inner_second_cfi[0x1]; + u8 inner_second_vid[0xc]; + + u8 outer_second_vlan_tag[0x1]; + u8 inner_second_vlan_tag[0x1]; + u8 reserved_2[0xe]; + u8 gre_protocol[0x10]; + + u8 gre_key_h[0x18]; + u8 gre_key_l[0x8]; + + u8 vxlan_vni[0x18]; + u8 reserved_3[0x8]; + + u8 reserved_4[0x20]; + + u8 reserved_5[0xc]; + u8 outer_ipv6_flow_label[0x14]; + + u8 reserved_6[0xc]; + u8 inner_ipv6_flow_label[0x14]; + + u8 reserved_7[0xe0]; +}; + +struct mlx5_ifc_cmd_pas_bits { + u8 pa_h[0x20]; + + u8 pa_l[0x14]; + u8 reserved_0[0xc]; +}; + +struct mlx5_ifc_uint64_bits { + u8 hi[0x20]; + + u8 lo[0x20]; +}; + +enum { + MLX5_ADS_STAT_RATE_NO_LIMIT = 0x0, + MLX5_ADS_STAT_RATE_2_5GBPS = 0x7, + MLX5_ADS_STAT_RATE_10GBPS = 0x8, + MLX5_ADS_STAT_RATE_30GBPS = 0x9, + MLX5_ADS_STAT_RATE_5GBPS = 0xa, + MLX5_ADS_STAT_RATE_20GBPS = 0xb, + MLX5_ADS_STAT_RATE_40GBPS = 0xc, + MLX5_ADS_STAT_RATE_60GBPS = 0xd, + MLX5_ADS_STAT_RATE_80GBPS = 0xe, + MLX5_ADS_STAT_RATE_120GBPS = 0xf, +}; + +struct mlx5_ifc_ads_bits { + u8 fl[0x1]; + u8 free_ar[0x1]; + u8 reserved_0[0xe]; + u8 pkey_index[0x10]; + + u8 reserved_1[0x8]; + u8 grh[0x1]; + u8 mlid[0x7]; + u8 rlid[0x10]; + + u8 ack_timeout[0x5]; + u8 reserved_2[0x3]; + u8 src_addr_index[0x8]; + u8 reserved_3[0x4]; + u8 stat_rate[0x4]; + u8 hop_limit[0x8]; + + u8 reserved_4[0x4]; + u8 tclass[0x8]; + u8 flow_label[0x14]; + + u8 rgid_rip[16][0x8]; + + u8 reserved_5[0x4]; + u8 f_dscp[0x1]; + u8 f_ecn[0x1]; + u8 reserved_6[0x1]; + u8 f_eth_prio[0x1]; + u8 ecn[0x2]; + u8 dscp[0x6]; + u8 udp_sport[0x10]; + + u8 dei_cfi[0x1]; + u8 eth_prio[0x3]; + u8 sl[0x4]; + u8 port[0x8]; + u8 rmac_47_32[0x10]; + + u8 rmac_31_0[0x20]; +}; + +struct mlx5_ifc_flow_table_nic_cap_bits { + u8 reserved_0[0x200]; + + struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_nic_receive; + + u8 reserved_1[0x200]; + + struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_nic_receive_sniffer; + + struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_nic_transmit; + + u8 reserved_2[0x200]; + + struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_nic_transmit_sniffer; + + u8 reserved_3[0x7200]; +}; + +struct mlx5_ifc_per_protocol_networking_offload_caps_bits { + u8 csum_cap[0x1]; + u8 vlan_cap[0x1]; + u8 lro_cap[0x1]; + u8 lro_psh_flag[0x1]; + u8 lro_time_stamp[0x1]; + u8 reserved_0[0x3]; + u8 self_lb_en_modifiable[0x1]; + u8 reserved_1[0x2]; + u8 max_lso_cap[0x5]; + u8 reserved_2[0x4]; + u8 rss_ind_tbl_cap[0x4]; + u8 reserved_3[0x3]; + u8 tunnel_lso_const_out_ip_id[0x1]; + u8 reserved_4[0x2]; + u8 tunnel_statless_gre[0x1]; + u8 tunnel_stateless_vxlan[0x1]; + + u8 reserved_5[0x20]; + + u8 reserved_6[0x10]; + u8 lro_min_mss_size[0x10]; + + u8 reserved_7[0x120]; + + u8 lro_timer_supported_periods[4][0x20]; + + u8 reserved_8[0x600]; +}; + +struct mlx5_ifc_roce_cap_bits { + u8 roce_apm[0x1]; + u8 reserved_0[0x1f]; + + u8 reserved_1[0x60]; + + u8 reserved_2[0xc]; + u8 l3_type[0x4]; + u8 reserved_3[0x8]; + u8 roce_version[0x8]; + + u8 reserved_4[0x10]; + u8 r_roce_dest_udp_port[0x10]; + + u8 r_roce_max_src_udp_port[0x10]; + u8 r_roce_min_src_udp_port[0x10]; + + u8 reserved_5[0x10]; + u8 roce_address_table_size[0x10]; + + u8 reserved_6[0x700]; +}; + +enum { + MLX5_ATOMIC_CAPS_ATOMIC_SIZE_QP_1_BYTE = 0x0, + MLX5_ATOMIC_CAPS_ATOMIC_SIZE_QP_2_BYTES = 0x2, + MLX5_ATOMIC_CAPS_ATOMIC_SIZE_QP_4_BYTES = 0x4, + MLX5_ATOMIC_CAPS_ATOMIC_SIZE_QP_8_BYTES = 0x8, + MLX5_ATOMIC_CAPS_ATOMIC_SIZE_QP_16_BYTES = 0x10, + MLX5_ATOMIC_CAPS_ATOMIC_SIZE_QP_32_BYTES = 0x20, + MLX5_ATOMIC_CAPS_ATOMIC_SIZE_QP_64_BYTES = 0x40, + MLX5_ATOMIC_CAPS_ATOMIC_SIZE_QP_128_BYTES = 0x80, + MLX5_ATOMIC_CAPS_ATOMIC_SIZE_QP_256_BYTES = 0x100, +}; + +enum { + MLX5_ATOMIC_CAPS_ATOMIC_SIZE_DC_1_BYTE = 0x1, + MLX5_ATOMIC_CAPS_ATOMIC_SIZE_DC_2_BYTES = 0x2, + MLX5_ATOMIC_CAPS_ATOMIC_SIZE_DC_4_BYTES = 0x4, + MLX5_ATOMIC_CAPS_ATOMIC_SIZE_DC_8_BYTES = 0x8, + MLX5_ATOMIC_CAPS_ATOMIC_SIZE_DC_16_BYTES = 0x10, + MLX5_ATOMIC_CAPS_ATOMIC_SIZE_DC_32_BYTES = 0x20, + MLX5_ATOMIC_CAPS_ATOMIC_SIZE_DC_64_BYTES = 0x40, + MLX5_ATOMIC_CAPS_ATOMIC_SIZE_DC_128_BYTES = 0x80, + MLX5_ATOMIC_CAPS_ATOMIC_SIZE_DC_256_BYTES = 0x100, +}; + +struct mlx5_ifc_atomic_caps_bits { + u8 reserved_0[0x40]; + + u8 atomic_req_endianness[0x1]; + u8 reserved_1[0x1f]; + + u8 reserved_2[0x20]; + + u8 reserved_3[0x10]; + u8 atomic_operations[0x10]; + + u8 reserved_4[0x10]; + u8 atomic_size_qp[0x10]; + + u8 reserved_5[0x10]; + u8 atomic_size_dc[0x10]; + + u8 reserved_6[0x720]; +}; + +struct mlx5_ifc_odp_cap_bits { + u8 reserved_0[0x40]; + + u8 sig[0x1]; + u8 reserved_1[0x1f]; + + u8 reserved_2[0x20]; + + struct mlx5_ifc_odp_per_transport_service_cap_bits rc_odp_caps; + + struct mlx5_ifc_odp_per_transport_service_cap_bits uc_odp_caps; + + struct mlx5_ifc_odp_per_transport_service_cap_bits ud_odp_caps; + + u8 reserved_3[0x720]; +}; + +enum { + MLX5_WQ_TYPE_LINKED_LIST = 0x0, + MLX5_WQ_TYPE_CYCLIC = 0x1, + MLX5_WQ_TYPE_STRQ = 0x2, +}; + +enum { + MLX5_WQ_END_PAD_MODE_NONE = 0x0, + MLX5_WQ_END_PAD_MODE_ALIGN = 0x1, +}; + +enum { + MLX5_CMD_HCA_CAP_GID_TABLE_SIZE_8_GID_ENTRIES = 0x0, + MLX5_CMD_HCA_CAP_GID_TABLE_SIZE_16_GID_ENTRIES = 0x1, + MLX5_CMD_HCA_CAP_GID_TABLE_SIZE_32_GID_ENTRIES = 0x2, + MLX5_CMD_HCA_CAP_GID_TABLE_SIZE_64_GID_ENTRIES = 0x3, + MLX5_CMD_HCA_CAP_GID_TABLE_SIZE_128_GID_ENTRIES = 0x4, +}; + +enum { + MLX5_CMD_HCA_CAP_PKEY_TABLE_SIZE_128_ENTRIES = 0x0, + MLX5_CMD_HCA_CAP_PKEY_TABLE_SIZE_256_ENTRIES = 0x1, + MLX5_CMD_HCA_CAP_PKEY_TABLE_SIZE_512_ENTRIES = 0x2, + MLX5_CMD_HCA_CAP_PKEY_TABLE_SIZE_1K_ENTRIES = 0x3, + MLX5_CMD_HCA_CAP_PKEY_TABLE_SIZE_2K_ENTRIES = 0x4, + MLX5_CMD_HCA_CAP_PKEY_TABLE_SIZE_4K_ENTRIES = 0x5, +}; + +enum { + MLX5_CMD_HCA_CAP_PORT_TYPE_IB = 0x0, + MLX5_CMD_HCA_CAP_PORT_TYPE_ETHERNET = 0x1, +}; + +enum { + MLX5_CMD_HCA_CAP_CMDIF_CHECKSUM_DISABLED = 0x0, + MLX5_CMD_HCA_CAP_CMDIF_CHECKSUM_INITIAL_STATE = 0x1, + MLX5_CMD_HCA_CAP_CMDIF_CHECKSUM_ENABLED = 0x3, +}; + +enum { + MLX5_CAP_PORT_TYPE_IB = 0x0, + MLX5_CAP_PORT_TYPE_ETH = 0x1, }; struct mlx5_ifc_cmd_hca_cap_bits { @@ -148,9 +613,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_1[0xb]; u8 log_max_qp[0x5]; - u8 log_max_strq_sz[0x8]; - u8 reserved_2[0x3]; - u8 log_max_srqs[0x5]; + u8 reserved_2[0xb]; + u8 log_max_srq[0x5]; u8 reserved_3[0x10]; u8 reserved_4[0x8]; @@ -185,123 +649,2112 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 pad_cap[0x1]; u8 cc_query_allowed[0x1]; u8 cc_modify_allowed[0x1]; - u8 reserved_15[0x1d]; + u8 reserved_15[0xd]; + u8 gid_table_size[0x10]; - u8 reserved_16[0x6]; + u8 out_of_seq_cnt[0x1]; + u8 vport_counters[0x1]; + u8 reserved_16[0x4]; u8 max_qp_cnt[0xa]; u8 pkey_table_size[0x10]; - u8 eswitch_owner[0x1]; - u8 reserved_17[0xa]; + u8 vport_group_manager[0x1]; + u8 vhca_group_manager[0x1]; + u8 ib_virt[0x1]; + u8 eth_virt[0x1]; + u8 reserved_17[0x1]; + u8 ets[0x1]; + u8 nic_flow_table[0x1]; + u8 reserved_18[0x4]; u8 local_ca_ack_delay[0x5]; - u8 reserved_18[0x8]; + u8 reserved_19[0x6]; + u8 port_type[0x2]; u8 num_ports[0x8]; - u8 reserved_19[0x3]; + u8 reserved_20[0x3]; u8 log_max_msg[0x5]; - u8 reserved_20[0x18]; + u8 reserved_21[0x18]; u8 stat_rate_support[0x10]; - u8 reserved_21[0x10]; + u8 reserved_22[0xc]; + u8 cqe_version[0x4]; - u8 reserved_22[0x10]; + u8 compact_address_vector[0x1]; + u8 reserved_23[0xe]; + u8 drain_sigerr[0x1]; u8 cmdif_checksum[0x2]; u8 sigerr_cqe[0x1]; - u8 reserved_23[0x1]; + u8 reserved_24[0x1]; u8 wq_signature[0x1]; u8 sctr_data_cqe[0x1]; - u8 reserved_24[0x1]; + u8 reserved_25[0x1]; u8 sho[0x1]; u8 tph[0x1]; u8 rf[0x1]; - u8 dc[0x1]; - u8 reserved_25[0x2]; + u8 dct[0x1]; + u8 reserved_26[0x1]; + u8 eth_net_offloads[0x1]; u8 roce[0x1]; u8 atomic[0x1]; - u8 rsz_srq[0x1]; + u8 reserved_27[0x1]; u8 cq_oi[0x1]; u8 cq_resize[0x1]; u8 cq_moderation[0x1]; - u8 sniffer_rule_flow[0x1]; - u8 sniffer_rule_vport[0x1]; - u8 sniffer_rule_phy[0x1]; - u8 reserved_26[0x1]; + u8 reserved_28[0x3]; + u8 cq_eq_remap[0x1]; u8 pg[0x1]; u8 block_lb_mc[0x1]; - u8 reserved_27[0x3]; + u8 reserved_29[0x1]; + u8 scqe_break_moderation[0x1]; + u8 reserved_30[0x1]; u8 cd[0x1]; - u8 reserved_28[0x1]; + u8 reserved_31[0x1]; u8 apm[0x1]; - u8 reserved_29[0x7]; + u8 reserved_32[0x7]; u8 qkv[0x1]; u8 pkv[0x1]; - u8 reserved_30[0x4]; + u8 reserved_33[0x4]; u8 xrc[0x1]; u8 ud[0x1]; u8 uc[0x1]; u8 rc[0x1]; - u8 reserved_31[0xa]; + u8 reserved_34[0xa]; u8 uar_sz[0x6]; - u8 reserved_32[0x8]; + u8 reserved_35[0x8]; u8 log_pg_sz[0x8]; u8 bf[0x1]; - u8 reserved_33[0xa]; + u8 reserved_36[0x1]; + u8 pad_tx_eth_packet[0x1]; + u8 reserved_37[0x8]; u8 log_bf_reg_size[0x5]; - u8 reserved_34[0x10]; + u8 reserved_38[0x10]; - u8 reserved_35[0x10]; + u8 reserved_39[0x10]; u8 max_wqe_sz_sq[0x10]; - u8 reserved_36[0x10]; + u8 reserved_40[0x10]; u8 max_wqe_sz_rq[0x10]; - u8 reserved_37[0x10]; + u8 reserved_41[0x10]; u8 max_wqe_sz_sq_dc[0x10]; - u8 reserved_38[0x7]; + u8 reserved_42[0x7]; u8 max_qp_mcg[0x19]; - u8 reserved_39[0x18]; + u8 reserved_43[0x18]; u8 log_max_mcg[0x8]; - u8 reserved_40[0xb]; + u8 reserved_44[0x3]; + u8 log_max_transport_domain[0x5]; + u8 reserved_45[0x3]; u8 log_max_pd[0x5]; - u8 reserved_41[0xb]; + u8 reserved_46[0xb]; u8 log_max_xrcd[0x5]; - u8 reserved_42[0x20]; + u8 reserved_47[0x20]; - u8 reserved_43[0x3]; + u8 reserved_48[0x3]; u8 log_max_rq[0x5]; - u8 reserved_44[0x3]; + u8 reserved_49[0x3]; u8 log_max_sq[0x5]; - u8 reserved_45[0x3]; + u8 reserved_50[0x3]; u8 log_max_tir[0x5]; - u8 reserved_46[0x3]; + u8 reserved_51[0x3]; u8 log_max_tis[0x5]; - u8 reserved_47[0x13]; - u8 log_max_rq_per_tir[0x5]; - u8 reserved_48[0x3]; + u8 basic_cyclic_rcv_wqe[0x1]; + u8 reserved_52[0x2]; + u8 log_max_rmp[0x5]; + u8 reserved_53[0x3]; + u8 log_max_rqt[0x5]; + u8 reserved_54[0x3]; + u8 log_max_rqt_size[0x5]; + u8 reserved_55[0x3]; u8 log_max_tis_per_sq[0x5]; - u8 reserved_49[0xe0]; + u8 reserved_56[0x3]; + u8 log_max_stride_sz_rq[0x5]; + u8 reserved_57[0x3]; + u8 log_min_stride_sz_rq[0x5]; + u8 reserved_58[0x3]; + u8 log_max_stride_sz_sq[0x5]; + u8 reserved_59[0x3]; + u8 log_min_stride_sz_sq[0x5]; + + u8 reserved_60[0x1b]; + u8 log_max_wq_sz[0x5]; - u8 reserved_50[0x10]; + u8 reserved_61[0xa0]; + + u8 reserved_62[0x3]; + u8 log_max_l2_table[0x5]; + u8 reserved_63[0x8]; u8 log_uar_page_sz[0x10]; - u8 reserved_51[0x100]; + u8 reserved_64[0x100]; - u8 reserved_52[0x1f]; + u8 reserved_65[0x1f]; u8 cqe_zip[0x1]; u8 cqe_zip_timeout[0x10]; u8 cqe_zip_max_num[0x10]; - u8 reserved_53[0x220]; + u8 reserved_66[0x220]; +}; + +enum { + MLX5_DEST_FORMAT_STRUCT_DESTINATION_TYPE_FLOW_TABLE_ = 0x1, + MLX5_DEST_FORMAT_STRUCT_DESTINATION_TYPE_TIR = 0x2, +}; + +struct mlx5_ifc_dest_format_struct_bits { + u8 destination_type[0x8]; + u8 destination_id[0x18]; + + u8 reserved_0[0x20]; +}; + +struct mlx5_ifc_fte_match_param_bits { + struct mlx5_ifc_fte_match_set_lyr_2_4_bits outer_headers; + + struct mlx5_ifc_fte_match_set_misc_bits misc_parameters; + + struct mlx5_ifc_fte_match_set_lyr_2_4_bits inner_headers; + + u8 reserved_0[0xa00]; +}; + +enum { + MLX5_RX_HASH_FIELD_SELECT_SELECTED_FIELDS_SRC_IP = 0x0, + MLX5_RX_HASH_FIELD_SELECT_SELECTED_FIELDS_DST_IP = 0x1, + MLX5_RX_HASH_FIELD_SELECT_SELECTED_FIELDS_L4_SPORT = 0x2, + MLX5_RX_HASH_FIELD_SELECT_SELECTED_FIELDS_L4_DPORT = 0x3, + MLX5_RX_HASH_FIELD_SELECT_SELECTED_FIELDS_IPSEC_SPI = 0x4, +}; + +struct mlx5_ifc_rx_hash_field_select_bits { + u8 l3_prot_type[0x1]; + u8 l4_prot_type[0x1]; + u8 selected_fields[0x1e]; +}; + +enum { + MLX5_WQ_WQ_TYPE_WQ_LINKED_LIST = 0x0, + MLX5_WQ_WQ_TYPE_WQ_CYCLIC = 0x1, +}; + +enum { + MLX5_WQ_END_PADDING_MODE_END_PAD_NONE = 0x0, + MLX5_WQ_END_PADDING_MODE_END_PAD_ALIGN = 0x1, +}; + +struct mlx5_ifc_wq_bits { + u8 wq_type[0x4]; + u8 wq_signature[0x1]; + u8 end_padding_mode[0x2]; + u8 cd_slave[0x1]; + u8 reserved_0[0x18]; + + u8 hds_skip_first_sge[0x1]; + u8 log2_hds_buf_size[0x3]; + u8 reserved_1[0x7]; + u8 page_offset[0x5]; + u8 lwm[0x10]; + + u8 reserved_2[0x8]; + u8 pd[0x18]; + + u8 reserved_3[0x8]; + u8 uar_page[0x18]; + + u8 dbr_addr[0x40]; + + u8 hw_counter[0x20]; + + u8 sw_counter[0x20]; + + u8 reserved_4[0xc]; + u8 log_wq_stride[0x4]; + u8 reserved_5[0x3]; + u8 log_wq_pg_sz[0x5]; + u8 reserved_6[0x3]; + u8 log_wq_sz[0x5]; + + u8 reserved_7[0x4e0]; + + struct mlx5_ifc_cmd_pas_bits pas[0]; +}; + +struct mlx5_ifc_rq_num_bits { + u8 reserved_0[0x8]; + u8 rq_num[0x18]; +}; + +struct mlx5_ifc_mac_address_layout_bits { + u8 reserved_0[0x10]; + u8 mac_addr_47_32[0x10]; + + u8 mac_addr_31_0[0x20]; +}; + +struct mlx5_ifc_cong_control_r_roce_ecn_np_bits { + u8 reserved_0[0xa0]; + + u8 min_time_between_cnps[0x20]; + + u8 reserved_1[0x12]; + u8 cnp_dscp[0x6]; + u8 reserved_2[0x5]; + u8 cnp_802p_prio[0x3]; + + u8 reserved_3[0x720]; +}; + +struct mlx5_ifc_cong_control_r_roce_ecn_rp_bits { + u8 reserved_0[0x60]; + + u8 reserved_1[0x4]; + u8 clamp_tgt_rate[0x1]; + u8 reserved_2[0x3]; + u8 clamp_tgt_rate_after_time_inc[0x1]; + u8 reserved_3[0x17]; + + u8 reserved_4[0x20]; + + u8 rpg_time_reset[0x20]; + + u8 rpg_byte_reset[0x20]; + + u8 rpg_threshold[0x20]; + + u8 rpg_max_rate[0x20]; + + u8 rpg_ai_rate[0x20]; + + u8 rpg_hai_rate[0x20]; + + u8 rpg_gd[0x20]; + + u8 rpg_min_dec_fac[0x20]; + + u8 rpg_min_rate[0x20]; + + u8 reserved_5[0xe0]; + + u8 rate_to_set_on_first_cnp[0x20]; + + u8 dce_tcp_g[0x20]; + + u8 dce_tcp_rtt[0x20]; + + u8 rate_reduce_monitor_period[0x20]; + + u8 reserved_6[0x20]; + + u8 initial_alpha_value[0x20]; + + u8 reserved_7[0x4a0]; +}; + +struct mlx5_ifc_cong_control_802_1qau_rp_bits { + u8 reserved_0[0x80]; + + u8 rppp_max_rps[0x20]; + + u8 rpg_time_reset[0x20]; + + u8 rpg_byte_reset[0x20]; + + u8 rpg_threshold[0x20]; + + u8 rpg_max_rate[0x20]; + + u8 rpg_ai_rate[0x20]; + + u8 rpg_hai_rate[0x20]; + + u8 rpg_gd[0x20]; + + u8 rpg_min_dec_fac[0x20]; + + u8 rpg_min_rate[0x20]; + + u8 reserved_1[0x640]; +}; + +enum { + MLX5_RESIZE_FIELD_SELECT_RESIZE_FIELD_SELECT_LOG_CQ_SIZE = 0x1, + MLX5_RESIZE_FIELD_SELECT_RESIZE_FIELD_SELECT_PAGE_OFFSET = 0x2, + MLX5_RESIZE_FIELD_SELECT_RESIZE_FIELD_SELECT_LOG_PAGE_SIZE = 0x4, +}; + +struct mlx5_ifc_resize_field_select_bits { + u8 resize_field_select[0x20]; +}; + +enum { + MLX5_MODIFY_FIELD_SELECT_MODIFY_FIELD_SELECT_CQ_PERIOD = 0x1, + MLX5_MODIFY_FIELD_SELECT_MODIFY_FIELD_SELECT_CQ_MAX_COUNT = 0x2, + MLX5_MODIFY_FIELD_SELECT_MODIFY_FIELD_SELECT_OI = 0x4, + MLX5_MODIFY_FIELD_SELECT_MODIFY_FIELD_SELECT_C_EQN = 0x8, +}; + +struct mlx5_ifc_modify_field_select_bits { + u8 modify_field_select[0x20]; +}; + +struct mlx5_ifc_field_select_r_roce_np_bits { + u8 field_select_r_roce_np[0x20]; +}; + +struct mlx5_ifc_field_select_r_roce_rp_bits { + u8 field_select_r_roce_rp[0x20]; +}; + +enum { + MLX5_FIELD_SELECT_802_1QAU_RP_FIELD_SELECT_8021QAURP_RPPP_MAX_RPS = 0x4, + MLX5_FIELD_SELECT_802_1QAU_RP_FIELD_SELECT_8021QAURP_RPG_TIME_RESET = 0x8, + MLX5_FIELD_SELECT_802_1QAU_RP_FIELD_SELECT_8021QAURP_RPG_BYTE_RESET = 0x10, + MLX5_FIELD_SELECT_802_1QAU_RP_FIELD_SELECT_8021QAURP_RPG_THRESHOLD = 0x20, + MLX5_FIELD_SELECT_802_1QAU_RP_FIELD_SELECT_8021QAURP_RPG_MAX_RATE = 0x40, + MLX5_FIELD_SELECT_802_1QAU_RP_FIELD_SELECT_8021QAURP_RPG_AI_RATE = 0x80, + MLX5_FIELD_SELECT_802_1QAU_RP_FIELD_SELECT_8021QAURP_RPG_HAI_RATE = 0x100, + MLX5_FIELD_SELECT_802_1QAU_RP_FIELD_SELECT_8021QAURP_RPG_GD = 0x200, + MLX5_FIELD_SELECT_802_1QAU_RP_FIELD_SELECT_8021QAURP_RPG_MIN_DEC_FAC = 0x400, + MLX5_FIELD_SELECT_802_1QAU_RP_FIELD_SELECT_8021QAURP_RPG_MIN_RATE = 0x800, +}; + +struct mlx5_ifc_field_select_802_1qau_rp_bits { + u8 field_select_8021qaurp[0x20]; +}; + +struct mlx5_ifc_phys_layer_cntrs_bits { + u8 time_since_last_clear_high[0x20]; + + u8 time_since_last_clear_low[0x20]; + + u8 symbol_errors_high[0x20]; + + u8 symbol_errors_low[0x20]; + + u8 sync_headers_errors_high[0x20]; + + u8 sync_headers_errors_low[0x20]; + + u8 edpl_bip_errors_lane0_high[0x20]; + + u8 edpl_bip_errors_lane0_low[0x20]; + + u8 edpl_bip_errors_lane1_high[0x20]; + + u8 edpl_bip_errors_lane1_low[0x20]; + + u8 edpl_bip_errors_lane2_high[0x20]; + + u8 edpl_bip_errors_lane2_low[0x20]; + + u8 edpl_bip_errors_lane3_high[0x20]; + + u8 edpl_bip_errors_lane3_low[0x20]; + + u8 fc_fec_corrected_blocks_lane0_high[0x20]; + + u8 fc_fec_corrected_blocks_lane0_low[0x20]; + + u8 fc_fec_corrected_blocks_lane1_high[0x20]; + + u8 fc_fec_corrected_blocks_lane1_low[0x20]; + + u8 fc_fec_corrected_blocks_lane2_high[0x20]; + + u8 fc_fec_corrected_blocks_lane2_low[0x20]; + + u8 fc_fec_corrected_blocks_lane3_high[0x20]; + + u8 fc_fec_corrected_blocks_lane3_low[0x20]; + + u8 fc_fec_uncorrectable_blocks_lane0_high[0x20]; + + u8 fc_fec_uncorrectable_blocks_lane0_low[0x20]; + + u8 fc_fec_uncorrectable_blocks_lane1_high[0x20]; + + u8 fc_fec_uncorrectable_blocks_lane1_low[0x20]; + + u8 fc_fec_uncorrectable_blocks_lane2_high[0x20]; + + u8 fc_fec_uncorrectable_blocks_lane2_low[0x20]; + + u8 fc_fec_uncorrectable_blocks_lane3_high[0x20]; + + u8 fc_fec_uncorrectable_blocks_lane3_low[0x20]; + + u8 rs_fec_corrected_blocks_high[0x20]; + + u8 rs_fec_corrected_blocks_low[0x20]; + + u8 rs_fec_uncorrectable_blocks_high[0x20]; + + u8 rs_fec_uncorrectable_blocks_low[0x20]; + + u8 rs_fec_no_errors_blocks_high[0x20]; + + u8 rs_fec_no_errors_blocks_low[0x20]; + + u8 rs_fec_single_error_blocks_high[0x20]; + + u8 rs_fec_single_error_blocks_low[0x20]; + + u8 rs_fec_corrected_symbols_total_high[0x20]; + + u8 rs_fec_corrected_symbols_total_low[0x20]; + + u8 rs_fec_corrected_symbols_lane0_high[0x20]; + + u8 rs_fec_corrected_symbols_lane0_low[0x20]; + + u8 rs_fec_corrected_symbols_lane1_high[0x20]; + + u8 rs_fec_corrected_symbols_lane1_low[0x20]; + + u8 rs_fec_corrected_symbols_lane2_high[0x20]; + + u8 rs_fec_corrected_symbols_lane2_low[0x20]; + + u8 rs_fec_corrected_symbols_lane3_high[0x20]; + + u8 rs_fec_corrected_symbols_lane3_low[0x20]; + + u8 link_down_events[0x20]; + + u8 successful_recovery_events[0x20]; + + u8 reserved_0[0x180]; +}; + +struct mlx5_ifc_eth_per_traffic_grp_data_layout_bits { + u8 transmit_queue_high[0x20]; + + u8 transmit_queue_low[0x20]; + + u8 reserved_0[0x780]; +}; + +struct mlx5_ifc_eth_per_prio_grp_data_layout_bits { + u8 rx_octets_high[0x20]; + + u8 rx_octets_low[0x20]; + + u8 reserved_0[0xc0]; + + u8 rx_frames_high[0x20]; + + u8 rx_frames_low[0x20]; + + u8 tx_octets_high[0x20]; + + u8 tx_octets_low[0x20]; + + u8 reserved_1[0xc0]; + + u8 tx_frames_high[0x20]; + + u8 tx_frames_low[0x20]; + + u8 rx_pause_high[0x20]; + + u8 rx_pause_low[0x20]; + + u8 rx_pause_duration_high[0x20]; + + u8 rx_pause_duration_low[0x20]; + + u8 tx_pause_high[0x20]; + + u8 tx_pause_low[0x20]; + + u8 tx_pause_duration_high[0x20]; + + u8 tx_pause_duration_low[0x20]; + + u8 rx_pause_transition_high[0x20]; + + u8 rx_pause_transition_low[0x20]; + + u8 reserved_2[0x400]; +}; + +struct mlx5_ifc_eth_extended_cntrs_grp_data_layout_bits { + u8 port_transmit_wait_high[0x20]; + + u8 port_transmit_wait_low[0x20]; + + u8 reserved_0[0x780]; +}; + +struct mlx5_ifc_eth_3635_cntrs_grp_data_layout_bits { + u8 dot3stats_alignment_errors_high[0x20]; + + u8 dot3stats_alignment_errors_low[0x20]; + + u8 dot3stats_fcs_errors_high[0x20]; + + u8 dot3stats_fcs_errors_low[0x20]; + + u8 dot3stats_single_collision_frames_high[0x20]; + + u8 dot3stats_single_collision_frames_low[0x20]; + + u8 dot3stats_multiple_collision_frames_high[0x20]; + + u8 dot3stats_multiple_collision_frames_low[0x20]; + + u8 dot3stats_sqe_test_errors_high[0x20]; + + u8 dot3stats_sqe_test_errors_low[0x20]; + + u8 dot3stats_deferred_transmissions_high[0x20]; + + u8 dot3stats_deferred_transmissions_low[0x20]; + + u8 dot3stats_late_collisions_high[0x20]; + + u8 dot3stats_late_collisions_low[0x20]; + + u8 dot3stats_excessive_collisions_high[0x20]; + + u8 dot3stats_excessive_collisions_low[0x20]; + + u8 dot3stats_internal_mac_transmit_errors_high[0x20]; + + u8 dot3stats_internal_mac_transmit_errors_low[0x20]; + + u8 dot3stats_carrier_sense_errors_high[0x20]; + + u8 dot3stats_carrier_sense_errors_low[0x20]; + + u8 dot3stats_frame_too_longs_high[0x20]; + + u8 dot3stats_frame_too_longs_low[0x20]; + + u8 dot3stats_internal_mac_receive_errors_high[0x20]; + + u8 dot3stats_internal_mac_receive_errors_low[0x20]; + + u8 dot3stats_symbol_errors_high[0x20]; + + u8 dot3stats_symbol_errors_low[0x20]; + + u8 dot3control_in_unknown_opcodes_high[0x20]; + + u8 dot3control_in_unknown_opcodes_low[0x20]; + + u8 dot3in_pause_frames_high[0x20]; + + u8 dot3in_pause_frames_low[0x20]; + + u8 dot3out_pause_frames_high[0x20]; + + u8 dot3out_pause_frames_low[0x20]; + + u8 reserved_0[0x3c0]; +}; + +struct mlx5_ifc_eth_2819_cntrs_grp_data_layout_bits { + u8 ether_stats_drop_events_high[0x20]; + + u8 ether_stats_drop_events_low[0x20]; + + u8 ether_stats_octets_high[0x20]; + + u8 ether_stats_octets_low[0x20]; + + u8 ether_stats_pkts_high[0x20]; + + u8 ether_stats_pkts_low[0x20]; + + u8 ether_stats_broadcast_pkts_high[0x20]; + + u8 ether_stats_broadcast_pkts_low[0x20]; + + u8 ether_stats_multicast_pkts_high[0x20]; + + u8 ether_stats_multicast_pkts_low[0x20]; + + u8 ether_stats_crc_align_errors_high[0x20]; + + u8 ether_stats_crc_align_errors_low[0x20]; + + u8 ether_stats_undersize_pkts_high[0x20]; + + u8 ether_stats_undersize_pkts_low[0x20]; + + u8 ether_stats_oversize_pkts_high[0x20]; + + u8 ether_stats_oversize_pkts_low[0x20]; + + u8 ether_stats_fragments_high[0x20]; + + u8 ether_stats_fragments_low[0x20]; + + u8 ether_stats_jabbers_high[0x20]; + + u8 ether_stats_jabbers_low[0x20]; + + u8 ether_stats_collisions_high[0x20]; + + u8 ether_stats_collisions_low[0x20]; + + u8 ether_stats_pkts64octets_high[0x20]; + + u8 ether_stats_pkts64octets_low[0x20]; + + u8 ether_stats_pkts65to127octets_high[0x20]; + + u8 ether_stats_pkts65to127octets_low[0x20]; + + u8 ether_stats_pkts128to255octets_high[0x20]; + + u8 ether_stats_pkts128to255octets_low[0x20]; + + u8 ether_stats_pkts256to511octets_high[0x20]; + + u8 ether_stats_pkts256to511octets_low[0x20]; + + u8 ether_stats_pkts512to1023octets_high[0x20]; + + u8 ether_stats_pkts512to1023octets_low[0x20]; + + u8 ether_stats_pkts1024to1518octets_high[0x20]; + + u8 ether_stats_pkts1024to1518octets_low[0x20]; + + u8 ether_stats_pkts1519to2047octets_high[0x20]; + + u8 ether_stats_pkts1519to2047octets_low[0x20]; + + u8 ether_stats_pkts2048to4095octets_high[0x20]; + + u8 ether_stats_pkts2048to4095octets_low[0x20]; + + u8 ether_stats_pkts4096to8191octets_high[0x20]; + + u8 ether_stats_pkts4096to8191octets_low[0x20]; + + u8 ether_stats_pkts8192to10239octets_high[0x20]; + + u8 ether_stats_pkts8192to10239octets_low[0x20]; + + u8 reserved_0[0x280]; +}; + +struct mlx5_ifc_eth_2863_cntrs_grp_data_layout_bits { + u8 if_in_octets_high[0x20]; + + u8 if_in_octets_low[0x20]; + + u8 if_in_ucast_pkts_high[0x20]; + + u8 if_in_ucast_pkts_low[0x20]; + + u8 if_in_discards_high[0x20]; + + u8 if_in_discards_low[0x20]; + + u8 if_in_errors_high[0x20]; + + u8 if_in_errors_low[0x20]; + + u8 if_in_unknown_protos_high[0x20]; + + u8 if_in_unknown_protos_low[0x20]; + + u8 if_out_octets_high[0x20]; + + u8 if_out_octets_low[0x20]; + + u8 if_out_ucast_pkts_high[0x20]; + + u8 if_out_ucast_pkts_low[0x20]; + + u8 if_out_discards_high[0x20]; + + u8 if_out_discards_low[0x20]; + + u8 if_out_errors_high[0x20]; + + u8 if_out_errors_low[0x20]; + + u8 if_in_multicast_pkts_high[0x20]; + + u8 if_in_multicast_pkts_low[0x20]; + + u8 if_in_broadcast_pkts_high[0x20]; + + u8 if_in_broadcast_pkts_low[0x20]; + + u8 if_out_multicast_pkts_high[0x20]; + + u8 if_out_multicast_pkts_low[0x20]; + + u8 if_out_broadcast_pkts_high[0x20]; + + u8 if_out_broadcast_pkts_low[0x20]; + + u8 reserved_0[0x480]; +}; + +struct mlx5_ifc_eth_802_3_cntrs_grp_data_layout_bits { + u8 a_frames_transmitted_ok_high[0x20]; + + u8 a_frames_transmitted_ok_low[0x20]; + + u8 a_frames_received_ok_high[0x20]; + + u8 a_frames_received_ok_low[0x20]; + + u8 a_frame_check_sequence_errors_high[0x20]; + + u8 a_frame_check_sequence_errors_low[0x20]; + + u8 a_alignment_errors_high[0x20]; + + u8 a_alignment_errors_low[0x20]; + + u8 a_octets_transmitted_ok_high[0x20]; + + u8 a_octets_transmitted_ok_low[0x20]; + + u8 a_octets_received_ok_high[0x20]; + + u8 a_octets_received_ok_low[0x20]; + + u8 a_multicast_frames_xmitted_ok_high[0x20]; + + u8 a_multicast_frames_xmitted_ok_low[0x20]; + + u8 a_broadcast_frames_xmitted_ok_high[0x20]; + + u8 a_broadcast_frames_xmitted_ok_low[0x20]; + + u8 a_multicast_frames_received_ok_high[0x20]; + + u8 a_multicast_frames_received_ok_low[0x20]; + + u8 a_broadcast_frames_received_ok_high[0x20]; + + u8 a_broadcast_frames_received_ok_low[0x20]; + + u8 a_in_range_length_errors_high[0x20]; + + u8 a_in_range_length_errors_low[0x20]; + + u8 a_out_of_range_length_field_high[0x20]; + + u8 a_out_of_range_length_field_low[0x20]; + + u8 a_frame_too_long_errors_high[0x20]; + + u8 a_frame_too_long_errors_low[0x20]; + + u8 a_symbol_error_during_carrier_high[0x20]; + + u8 a_symbol_error_during_carrier_low[0x20]; + + u8 a_mac_control_frames_transmitted_high[0x20]; + + u8 a_mac_control_frames_transmitted_low[0x20]; + + u8 a_mac_control_frames_received_high[0x20]; + + u8 a_mac_control_frames_received_low[0x20]; + + u8 a_unsupported_opcodes_received_high[0x20]; + + u8 a_unsupported_opcodes_received_low[0x20]; + + u8 a_pause_mac_ctrl_frames_received_high[0x20]; + + u8 a_pause_mac_ctrl_frames_received_low[0x20]; + + u8 a_pause_mac_ctrl_frames_transmitted_high[0x20]; + + u8 a_pause_mac_ctrl_frames_transmitted_low[0x20]; + + u8 reserved_0[0x300]; +}; + +struct mlx5_ifc_cmd_inter_comp_event_bits { + u8 command_completion_vector[0x20]; + + u8 reserved_0[0xc0]; +}; + +struct mlx5_ifc_stall_vl_event_bits { + u8 reserved_0[0x18]; + u8 port_num[0x1]; + u8 reserved_1[0x3]; + u8 vl[0x4]; + + u8 reserved_2[0xa0]; +}; + +struct mlx5_ifc_db_bf_congestion_event_bits { + u8 event_subtype[0x8]; + u8 reserved_0[0x8]; + u8 congestion_level[0x8]; + u8 reserved_1[0x8]; + + u8 reserved_2[0xa0]; +}; + +struct mlx5_ifc_gpio_event_bits { + u8 reserved_0[0x60]; + + u8 gpio_event_hi[0x20]; + + u8 gpio_event_lo[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_port_state_change_event_bits { + u8 reserved_0[0x40]; + + u8 port_num[0x4]; + u8 reserved_1[0x1c]; + + u8 reserved_2[0x80]; +}; + +struct mlx5_ifc_dropped_packet_logged_bits { + u8 reserved_0[0xe0]; +}; + +enum { + MLX5_CQ_ERROR_SYNDROME_CQ_OVERRUN = 0x1, + MLX5_CQ_ERROR_SYNDROME_CQ_ACCESS_VIOLATION_ERROR = 0x2, +}; + +struct mlx5_ifc_cq_error_bits { + u8 reserved_0[0x8]; + u8 cqn[0x18]; + + u8 reserved_1[0x20]; + + u8 reserved_2[0x18]; + u8 syndrome[0x8]; + + u8 reserved_3[0x80]; +}; + +struct mlx5_ifc_rdma_page_fault_event_bits { + u8 bytes_committed[0x20]; + + u8 r_key[0x20]; + + u8 reserved_0[0x10]; + u8 packet_len[0x10]; + + u8 rdma_op_len[0x20]; + + u8 rdma_va[0x40]; + + u8 reserved_1[0x5]; + u8 rdma[0x1]; + u8 write[0x1]; + u8 requestor[0x1]; + u8 qp_number[0x18]; +}; + +struct mlx5_ifc_wqe_associated_page_fault_event_bits { + u8 bytes_committed[0x20]; + + u8 reserved_0[0x10]; + u8 wqe_index[0x10]; + + u8 reserved_1[0x10]; + u8 len[0x10]; + + u8 reserved_2[0x60]; + + u8 reserved_3[0x5]; + u8 rdma[0x1]; + u8 write_read[0x1]; + u8 requestor[0x1]; + u8 qpn[0x18]; +}; + +struct mlx5_ifc_qp_events_bits { + u8 reserved_0[0xa0]; + + u8 type[0x8]; + u8 reserved_1[0x18]; + + u8 reserved_2[0x8]; + u8 qpn_rqn_sqn[0x18]; +}; + +struct mlx5_ifc_dct_events_bits { + u8 reserved_0[0xc0]; + + u8 reserved_1[0x8]; + u8 dct_number[0x18]; +}; + +struct mlx5_ifc_comp_event_bits { + u8 reserved_0[0xc0]; + + u8 reserved_1[0x8]; + u8 cq_number[0x18]; +}; + +enum { + MLX5_QPC_STATE_RST = 0x0, + MLX5_QPC_STATE_INIT = 0x1, + MLX5_QPC_STATE_RTR = 0x2, + MLX5_QPC_STATE_RTS = 0x3, + MLX5_QPC_STATE_SQER = 0x4, + MLX5_QPC_STATE_ERR = 0x6, + MLX5_QPC_STATE_SQD = 0x7, + MLX5_QPC_STATE_SUSPENDED = 0x9, +}; + +enum { + MLX5_QPC_ST_RC = 0x0, + MLX5_QPC_ST_UC = 0x1, + MLX5_QPC_ST_UD = 0x2, + MLX5_QPC_ST_XRC = 0x3, + MLX5_QPC_ST_DCI = 0x5, + MLX5_QPC_ST_QP0 = 0x7, + MLX5_QPC_ST_QP1 = 0x8, + MLX5_QPC_ST_RAW_DATAGRAM = 0x9, + MLX5_QPC_ST_REG_UMR = 0xc, +}; + +enum { + MLX5_QPC_PM_STATE_ARMED = 0x0, + MLX5_QPC_PM_STATE_REARM = 0x1, + MLX5_QPC_PM_STATE_RESERVED = 0x2, + MLX5_QPC_PM_STATE_MIGRATED = 0x3, +}; + +enum { + MLX5_QPC_END_PADDING_MODE_SCATTER_AS_IS = 0x0, + MLX5_QPC_END_PADDING_MODE_PAD_TO_CACHE_LINE_ALIGNMENT = 0x1, +}; + +enum { + MLX5_QPC_MTU_256_BYTES = 0x1, + MLX5_QPC_MTU_512_BYTES = 0x2, + MLX5_QPC_MTU_1K_BYTES = 0x3, + MLX5_QPC_MTU_2K_BYTES = 0x4, + MLX5_QPC_MTU_4K_BYTES = 0x5, + MLX5_QPC_MTU_RAW_ETHERNET_QP = 0x7, +}; + +enum { + MLX5_QPC_ATOMIC_MODE_IB_SPEC = 0x1, + MLX5_QPC_ATOMIC_MODE_ONLY_8B = 0x2, + MLX5_QPC_ATOMIC_MODE_UP_TO_8B = 0x3, + MLX5_QPC_ATOMIC_MODE_UP_TO_16B = 0x4, + MLX5_QPC_ATOMIC_MODE_UP_TO_32B = 0x5, + MLX5_QPC_ATOMIC_MODE_UP_TO_64B = 0x6, + MLX5_QPC_ATOMIC_MODE_UP_TO_128B = 0x7, + MLX5_QPC_ATOMIC_MODE_UP_TO_256B = 0x8, +}; + +enum { + MLX5_QPC_CS_REQ_DISABLE = 0x0, + MLX5_QPC_CS_REQ_UP_TO_32B = 0x11, + MLX5_QPC_CS_REQ_UP_TO_64B = 0x22, +}; + +enum { + MLX5_QPC_CS_RES_DISABLE = 0x0, + MLX5_QPC_CS_RES_UP_TO_32B = 0x1, + MLX5_QPC_CS_RES_UP_TO_64B = 0x2, +}; + +struct mlx5_ifc_qpc_bits { + u8 state[0x4]; + u8 reserved_0[0x4]; + u8 st[0x8]; + u8 reserved_1[0x3]; + u8 pm_state[0x2]; + u8 reserved_2[0x7]; + u8 end_padding_mode[0x2]; + u8 reserved_3[0x2]; + + u8 wq_signature[0x1]; + u8 block_lb_mc[0x1]; + u8 atomic_like_write_en[0x1]; + u8 latency_sensitive[0x1]; + u8 reserved_4[0x1]; + u8 drain_sigerr[0x1]; + u8 reserved_5[0x2]; + u8 pd[0x18]; + + u8 mtu[0x3]; + u8 log_msg_max[0x5]; + u8 reserved_6[0x1]; + u8 log_rq_size[0x4]; + u8 log_rq_stride[0x3]; + u8 no_sq[0x1]; + u8 log_sq_size[0x4]; + u8 reserved_7[0x6]; + u8 rlky[0x1]; + u8 reserved_8[0x4]; + + u8 counter_set_id[0x8]; + u8 uar_page[0x18]; + + u8 reserved_9[0x8]; + u8 user_index[0x18]; + + u8 reserved_10[0x3]; + u8 log_page_size[0x5]; + u8 remote_qpn[0x18]; + + struct mlx5_ifc_ads_bits primary_address_path; + + struct mlx5_ifc_ads_bits secondary_address_path; + + u8 log_ack_req_freq[0x4]; + u8 reserved_11[0x4]; + u8 log_sra_max[0x3]; + u8 reserved_12[0x2]; + u8 retry_count[0x3]; + u8 rnr_retry[0x3]; + u8 reserved_13[0x1]; + u8 fre[0x1]; + u8 cur_rnr_retry[0x3]; + u8 cur_retry_count[0x3]; + u8 reserved_14[0x5]; + + u8 reserved_15[0x20]; + + u8 reserved_16[0x8]; + u8 next_send_psn[0x18]; + + u8 reserved_17[0x8]; + u8 cqn_snd[0x18]; + + u8 reserved_18[0x40]; + + u8 reserved_19[0x8]; + u8 last_acked_psn[0x18]; + + u8 reserved_20[0x8]; + u8 ssn[0x18]; + + u8 reserved_21[0x8]; + u8 log_rra_max[0x3]; + u8 reserved_22[0x1]; + u8 atomic_mode[0x4]; + u8 rre[0x1]; + u8 rwe[0x1]; + u8 rae[0x1]; + u8 reserved_23[0x1]; + u8 page_offset[0x6]; + u8 reserved_24[0x3]; + u8 cd_slave_receive[0x1]; + u8 cd_slave_send[0x1]; + u8 cd_master[0x1]; + + u8 reserved_25[0x3]; + u8 min_rnr_nak[0x5]; + u8 next_rcv_psn[0x18]; + + u8 reserved_26[0x8]; + u8 xrcd[0x18]; + + u8 reserved_27[0x8]; + u8 cqn_rcv[0x18]; + + u8 dbr_addr[0x40]; + + u8 q_key[0x20]; + + u8 reserved_28[0x5]; + u8 rq_type[0x3]; + u8 srqn_rmpn[0x18]; + + u8 reserved_29[0x8]; + u8 rmsn[0x18]; + + u8 hw_sq_wqebb_counter[0x10]; + u8 sw_sq_wqebb_counter[0x10]; + + u8 hw_rq_counter[0x20]; + + u8 sw_rq_counter[0x20]; + + u8 reserved_30[0x20]; + + u8 reserved_31[0xf]; + u8 cgs[0x1]; + u8 cs_req[0x8]; + u8 cs_res[0x8]; + + u8 dc_access_key[0x40]; + + u8 reserved_32[0xc0]; +}; + +struct mlx5_ifc_roce_addr_layout_bits { + u8 source_l3_address[16][0x8]; + + u8 reserved_0[0x3]; + u8 vlan_valid[0x1]; + u8 vlan_id[0xc]; + u8 source_mac_47_32[0x10]; + + u8 source_mac_31_0[0x20]; + + u8 reserved_1[0x14]; + u8 roce_l3_type[0x4]; + u8 roce_version[0x8]; + + u8 reserved_2[0x20]; +}; + +union mlx5_ifc_hca_cap_union_bits { + struct mlx5_ifc_cmd_hca_cap_bits cmd_hca_cap; + struct mlx5_ifc_odp_cap_bits odp_cap; + struct mlx5_ifc_atomic_caps_bits atomic_caps; + struct mlx5_ifc_roce_cap_bits roce_cap; + struct mlx5_ifc_per_protocol_networking_offload_caps_bits per_protocol_networking_offload_caps; + struct mlx5_ifc_flow_table_nic_cap_bits flow_table_nic_cap; + u8 reserved_0[0x8000]; +}; + +enum { + MLX5_FLOW_CONTEXT_ACTION_ALLOW = 0x1, + MLX5_FLOW_CONTEXT_ACTION_DROP = 0x2, + MLX5_FLOW_CONTEXT_ACTION_FWD_DEST = 0x4, +}; + +struct mlx5_ifc_flow_context_bits { + u8 reserved_0[0x20]; + + u8 group_id[0x20]; + + u8 reserved_1[0x8]; + u8 flow_tag[0x18]; + + u8 reserved_2[0x10]; + u8 action[0x10]; + + u8 reserved_3[0x8]; + u8 destination_list_size[0x18]; + + u8 reserved_4[0x160]; + + struct mlx5_ifc_fte_match_param_bits match_value; + + u8 reserved_5[0x600]; + + struct mlx5_ifc_dest_format_struct_bits destination[0]; +}; + +enum { + MLX5_XRC_SRQC_STATE_GOOD = 0x0, + MLX5_XRC_SRQC_STATE_ERROR = 0x1, +}; + +struct mlx5_ifc_xrc_srqc_bits { + u8 state[0x4]; + u8 log_xrc_srq_size[0x4]; + u8 reserved_0[0x18]; + + u8 wq_signature[0x1]; + u8 cont_srq[0x1]; + u8 reserved_1[0x1]; + u8 rlky[0x1]; + u8 basic_cyclic_rcv_wqe[0x1]; + u8 log_rq_stride[0x3]; + u8 xrcd[0x18]; + + u8 page_offset[0x6]; + u8 reserved_2[0x2]; + u8 cqn[0x18]; + + u8 reserved_3[0x20]; + + u8 user_index_equal_xrc_srqn[0x1]; + u8 reserved_4[0x1]; + u8 log_page_size[0x6]; + u8 user_index[0x18]; + + u8 reserved_5[0x20]; + + u8 reserved_6[0x8]; + u8 pd[0x18]; + + u8 lwm[0x10]; + u8 wqe_cnt[0x10]; + + u8 reserved_7[0x40]; + + u8 db_record_addr_h[0x20]; + + u8 db_record_addr_l[0x1e]; + u8 reserved_8[0x2]; + + u8 reserved_9[0x80]; +}; + +struct mlx5_ifc_traffic_counter_bits { + u8 packets[0x40]; + + u8 octets[0x40]; +}; + +struct mlx5_ifc_tisc_bits { + u8 reserved_0[0xc]; + u8 prio[0x4]; + u8 reserved_1[0x10]; + + u8 reserved_2[0x100]; + + u8 reserved_3[0x8]; + u8 transport_domain[0x18]; + + u8 reserved_4[0x3c0]; +}; + +enum { + MLX5_TIRC_DISP_TYPE_DIRECT = 0x0, + MLX5_TIRC_DISP_TYPE_INDIRECT = 0x1, +}; + +enum { + MLX5_TIRC_LRO_ENABLE_MASK_IPV4_LRO = 0x1, + MLX5_TIRC_LRO_ENABLE_MASK_IPV6_LRO = 0x2, +}; + +enum { + MLX5_RX_HASH_FN_NONE = 0x0, + MLX5_RX_HASH_FN_INVERTED_XOR8 = 0x1, + MLX5_RX_HASH_FN_TOEPLITZ = 0x2, +}; + +enum { + MLX5_TIRC_SELF_LB_BLOCK_BLOCK_UNICAST_ = 0x1, + MLX5_TIRC_SELF_LB_BLOCK_BLOCK_MULTICAST_ = 0x2, +}; + +struct mlx5_ifc_tirc_bits { + u8 reserved_0[0x20]; + + u8 disp_type[0x4]; + u8 reserved_1[0x1c]; + + u8 reserved_2[0x40]; + + u8 reserved_3[0x4]; + u8 lro_timeout_period_usecs[0x10]; + u8 lro_enable_mask[0x4]; + u8 lro_max_ip_payload_size[0x8]; + + u8 reserved_4[0x40]; + + u8 reserved_5[0x8]; + u8 inline_rqn[0x18]; + + u8 rx_hash_symmetric[0x1]; + u8 reserved_6[0x1]; + u8 tunneled_offload_en[0x1]; + u8 reserved_7[0x5]; + u8 indirect_table[0x18]; + + u8 rx_hash_fn[0x4]; + u8 reserved_8[0x2]; + u8 self_lb_block[0x2]; + u8 transport_domain[0x18]; + + u8 rx_hash_toeplitz_key[10][0x20]; + + struct mlx5_ifc_rx_hash_field_select_bits rx_hash_field_selector_outer; + + struct mlx5_ifc_rx_hash_field_select_bits rx_hash_field_selector_inner; + + u8 reserved_9[0x4c0]; +}; + +enum { + MLX5_SRQC_STATE_GOOD = 0x0, + MLX5_SRQC_STATE_ERROR = 0x1, +}; + +struct mlx5_ifc_srqc_bits { + u8 state[0x4]; + u8 log_srq_size[0x4]; + u8 reserved_0[0x18]; + + u8 wq_signature[0x1]; + u8 cont_srq[0x1]; + u8 reserved_1[0x1]; + u8 rlky[0x1]; + u8 reserved_2[0x1]; + u8 log_rq_stride[0x3]; + u8 xrcd[0x18]; + + u8 page_offset[0x6]; + u8 reserved_3[0x2]; + u8 cqn[0x18]; + + u8 reserved_4[0x20]; + + u8 reserved_5[0x2]; + u8 log_page_size[0x6]; + u8 reserved_6[0x18]; + + u8 reserved_7[0x20]; + + u8 reserved_8[0x8]; + u8 pd[0x18]; + + u8 lwm[0x10]; + u8 wqe_cnt[0x10]; + + u8 reserved_9[0x40]; + + u8 dbr_addr[0x40]; + + u8 reserved_10[0x80]; +}; + +enum { + MLX5_SQC_STATE_RST = 0x0, + MLX5_SQC_STATE_RDY = 0x1, + MLX5_SQC_STATE_ERR = 0x3, +}; + +struct mlx5_ifc_sqc_bits { + u8 rlky[0x1]; + u8 cd_master[0x1]; + u8 fre[0x1]; + u8 flush_in_error_en[0x1]; + u8 reserved_0[0x4]; + u8 state[0x4]; + u8 reserved_1[0x14]; + + u8 reserved_2[0x8]; + u8 user_index[0x18]; + + u8 reserved_3[0x8]; + u8 cqn[0x18]; + + u8 reserved_4[0xa0]; + + u8 tis_lst_sz[0x10]; + u8 reserved_5[0x10]; + + u8 reserved_6[0x40]; + + u8 reserved_7[0x8]; + u8 tis_num_0[0x18]; + + struct mlx5_ifc_wq_bits wq; +}; + +struct mlx5_ifc_rqtc_bits { + u8 reserved_0[0xa0]; + + u8 reserved_1[0x10]; + u8 rqt_max_size[0x10]; + + u8 reserved_2[0x10]; + u8 rqt_actual_size[0x10]; + + u8 reserved_3[0x6a0]; + + struct mlx5_ifc_rq_num_bits rq_num[0]; +}; + +enum { + MLX5_RQC_MEM_RQ_TYPE_MEMORY_RQ_INLINE = 0x0, + MLX5_RQC_MEM_RQ_TYPE_MEMORY_RQ_RMP = 0x1, +}; + +enum { + MLX5_RQC_STATE_RST = 0x0, + MLX5_RQC_STATE_RDY = 0x1, + MLX5_RQC_STATE_ERR = 0x3, +}; + +struct mlx5_ifc_rqc_bits { + u8 rlky[0x1]; + u8 reserved_0[0x2]; + u8 vsd[0x1]; + u8 mem_rq_type[0x4]; + u8 state[0x4]; + u8 reserved_1[0x1]; + u8 flush_in_error_en[0x1]; + u8 reserved_2[0x12]; + + u8 reserved_3[0x8]; + u8 user_index[0x18]; + + u8 reserved_4[0x8]; + u8 cqn[0x18]; + + u8 counter_set_id[0x8]; + u8 reserved_5[0x18]; + + u8 reserved_6[0x8]; + u8 rmpn[0x18]; + + u8 reserved_7[0xe0]; + + struct mlx5_ifc_wq_bits wq; +}; + +enum { + MLX5_RMPC_STATE_RDY = 0x1, + MLX5_RMPC_STATE_ERR = 0x3, +}; + +struct mlx5_ifc_rmpc_bits { + u8 reserved_0[0x8]; + u8 state[0x4]; + u8 reserved_1[0x14]; + + u8 basic_cyclic_rcv_wqe[0x1]; + u8 reserved_2[0x1f]; + + u8 reserved_3[0x140]; + + struct mlx5_ifc_wq_bits wq; +}; + +enum { + MLX5_NIC_VPORT_CONTEXT_ALLOWED_LIST_TYPE_CURRENT_UC_MAC_ADDRESS = 0x0, +}; + +struct mlx5_ifc_nic_vport_context_bits { + u8 reserved_0[0x1f]; + u8 roce_en[0x1]; + + u8 reserved_1[0x760]; + + u8 reserved_2[0x5]; + u8 allowed_list_type[0x3]; + u8 reserved_3[0xc]; + u8 allowed_list_size[0xc]; + + struct mlx5_ifc_mac_address_layout_bits permanent_address; + + u8 reserved_4[0x20]; + + u8 current_uc_mac_address[0][0x40]; +}; + +enum { + MLX5_MKC_ACCESS_MODE_PA = 0x0, + MLX5_MKC_ACCESS_MODE_MTT = 0x1, + MLX5_MKC_ACCESS_MODE_KLMS = 0x2, +}; + +struct mlx5_ifc_mkc_bits { + u8 reserved_0[0x1]; + u8 free[0x1]; + u8 reserved_1[0xd]; + u8 small_fence_on_rdma_read_response[0x1]; + u8 umr_en[0x1]; + u8 a[0x1]; + u8 rw[0x1]; + u8 rr[0x1]; + u8 lw[0x1]; + u8 lr[0x1]; + u8 access_mode[0x2]; + u8 reserved_2[0x8]; + + u8 qpn[0x18]; + u8 mkey_7_0[0x8]; + + u8 reserved_3[0x20]; + + u8 length64[0x1]; + u8 bsf_en[0x1]; + u8 sync_umr[0x1]; + u8 reserved_4[0x2]; + u8 expected_sigerr_count[0x1]; + u8 reserved_5[0x1]; + u8 en_rinval[0x1]; + u8 pd[0x18]; + + u8 start_addr[0x40]; + + u8 len[0x40]; + + u8 bsf_octword_size[0x20]; + + u8 reserved_6[0x80]; + + u8 translations_octword_size[0x20]; + + u8 reserved_7[0x1b]; + u8 log_page_size[0x5]; + + u8 reserved_8[0x20]; +}; + +struct mlx5_ifc_pkey_bits { + u8 reserved_0[0x10]; + u8 pkey[0x10]; +}; + +struct mlx5_ifc_array128_auto_bits { + u8 array128_auto[16][0x8]; +}; + +struct mlx5_ifc_hca_vport_context_bits { + u8 field_select[0x20]; + + u8 reserved_0[0xe0]; + + u8 sm_virt_aware[0x1]; + u8 has_smi[0x1]; + u8 has_raw[0x1]; + u8 grh_required[0x1]; + u8 reserved_1[0xc]; + u8 port_physical_state[0x4]; + u8 vport_state_policy[0x4]; + u8 port_state[0x4]; + u8 vport_state[0x4]; + + u8 reserved_2[0x20]; + + u8 system_image_guid[0x40]; + + u8 port_guid[0x40]; + + u8 node_guid[0x40]; + + u8 cap_mask1[0x20]; + + u8 cap_mask1_field_select[0x20]; + + u8 cap_mask2[0x20]; + + u8 cap_mask2_field_select[0x20]; + + u8 reserved_3[0x80]; + + u8 lid[0x10]; + u8 reserved_4[0x4]; + u8 init_type_reply[0x4]; + u8 lmc[0x3]; + u8 subnet_timeout[0x5]; + + u8 sm_lid[0x10]; + u8 sm_sl[0x4]; + u8 reserved_5[0xc]; + + u8 qkey_violation_counter[0x10]; + u8 pkey_violation_counter[0x10]; + + u8 reserved_6[0xca0]; +}; + +enum { + MLX5_EQC_STATUS_OK = 0x0, + MLX5_EQC_STATUS_EQ_WRITE_FAILURE = 0xa, +}; + +enum { + MLX5_EQC_ST_ARMED = 0x9, + MLX5_EQC_ST_FIRED = 0xa, +}; + +struct mlx5_ifc_eqc_bits { + u8 status[0x4]; + u8 reserved_0[0x9]; + u8 ec[0x1]; + u8 oi[0x1]; + u8 reserved_1[0x5]; + u8 st[0x4]; + u8 reserved_2[0x8]; + + u8 reserved_3[0x20]; + + u8 reserved_4[0x14]; + u8 page_offset[0x6]; + u8 reserved_5[0x6]; + + u8 reserved_6[0x3]; + u8 log_eq_size[0x5]; + u8 uar_page[0x18]; + + u8 reserved_7[0x20]; + + u8 reserved_8[0x18]; + u8 intr[0x8]; + + u8 reserved_9[0x3]; + u8 log_page_size[0x5]; + u8 reserved_10[0x18]; + + u8 reserved_11[0x60]; + + u8 reserved_12[0x8]; + u8 consumer_counter[0x18]; + + u8 reserved_13[0x8]; + u8 producer_counter[0x18]; + + u8 reserved_14[0x80]; +}; + +enum { + MLX5_DCTC_STATE_ACTIVE = 0x0, + MLX5_DCTC_STATE_DRAINING = 0x1, + MLX5_DCTC_STATE_DRAINED = 0x2, +}; + +enum { + MLX5_DCTC_CS_RES_DISABLE = 0x0, + MLX5_DCTC_CS_RES_NA = 0x1, + MLX5_DCTC_CS_RES_UP_TO_64B = 0x2, +}; + +enum { + MLX5_DCTC_MTU_256_BYTES = 0x1, + MLX5_DCTC_MTU_512_BYTES = 0x2, + MLX5_DCTC_MTU_1K_BYTES = 0x3, + MLX5_DCTC_MTU_2K_BYTES = 0x4, + MLX5_DCTC_MTU_4K_BYTES = 0x5, +}; + +struct mlx5_ifc_dctc_bits { + u8 reserved_0[0x4]; + u8 state[0x4]; + u8 reserved_1[0x18]; + + u8 reserved_2[0x8]; + u8 user_index[0x18]; + + u8 reserved_3[0x8]; + u8 cqn[0x18]; + + u8 counter_set_id[0x8]; + u8 atomic_mode[0x4]; + u8 rre[0x1]; + u8 rwe[0x1]; + u8 rae[0x1]; + u8 atomic_like_write_en[0x1]; + u8 latency_sensitive[0x1]; + u8 rlky[0x1]; + u8 free_ar[0x1]; + u8 reserved_4[0xd]; + + u8 reserved_5[0x8]; + u8 cs_res[0x8]; + u8 reserved_6[0x3]; + u8 min_rnr_nak[0x5]; + u8 reserved_7[0x8]; + + u8 reserved_8[0x8]; + u8 srqn[0x18]; + + u8 reserved_9[0x8]; + u8 pd[0x18]; + + u8 tclass[0x8]; + u8 reserved_10[0x4]; + u8 flow_label[0x14]; + + u8 dc_access_key[0x40]; + + u8 reserved_11[0x5]; + u8 mtu[0x3]; + u8 port[0x8]; + u8 pkey_index[0x10]; + + u8 reserved_12[0x8]; + u8 my_addr_index[0x8]; + u8 reserved_13[0x8]; + u8 hop_limit[0x8]; + + u8 dc_access_key_violation_count[0x20]; + + u8 reserved_14[0x14]; + u8 dei_cfi[0x1]; + u8 eth_prio[0x3]; + u8 ecn[0x2]; + u8 dscp[0x6]; + + u8 reserved_15[0x40]; +}; + +enum { + MLX5_CQC_STATUS_OK = 0x0, + MLX5_CQC_STATUS_CQ_OVERFLOW = 0x9, + MLX5_CQC_STATUS_CQ_WRITE_FAIL = 0xa, +}; + +enum { + MLX5_CQC_CQE_SZ_64_BYTES = 0x0, + MLX5_CQC_CQE_SZ_128_BYTES = 0x1, +}; + +enum { + MLX5_CQC_ST_SOLICITED_NOTIFICATION_REQUEST_ARMED = 0x6, + MLX5_CQC_ST_NOTIFICATION_REQUEST_ARMED = 0x9, + MLX5_CQC_ST_FIRED = 0xa, +}; + +struct mlx5_ifc_cqc_bits { + u8 status[0x4]; + u8 reserved_0[0x4]; + u8 cqe_sz[0x3]; + u8 cc[0x1]; + u8 reserved_1[0x1]; + u8 scqe_break_moderation_en[0x1]; + u8 oi[0x1]; + u8 reserved_2[0x2]; + u8 cqe_zip_en[0x1]; + u8 mini_cqe_res_format[0x2]; + u8 st[0x4]; + u8 reserved_3[0x8]; + + u8 reserved_4[0x20]; + + u8 reserved_5[0x14]; + u8 page_offset[0x6]; + u8 reserved_6[0x6]; + + u8 reserved_7[0x3]; + u8 log_cq_size[0x5]; + u8 uar_page[0x18]; + + u8 reserved_8[0x4]; + u8 cq_period[0xc]; + u8 cq_max_count[0x10]; + + u8 reserved_9[0x18]; + u8 c_eqn[0x8]; + + u8 reserved_10[0x3]; + u8 log_page_size[0x5]; + u8 reserved_11[0x18]; + + u8 reserved_12[0x20]; + + u8 reserved_13[0x8]; + u8 last_notified_index[0x18]; + + u8 reserved_14[0x8]; + u8 last_solicit_index[0x18]; + + u8 reserved_15[0x8]; + u8 consumer_counter[0x18]; + + u8 reserved_16[0x8]; + u8 producer_counter[0x18]; + + u8 reserved_17[0x40]; + + u8 dbr_addr[0x40]; +}; + +union mlx5_ifc_cong_control_roce_ecn_auto_bits { + struct mlx5_ifc_cong_control_802_1qau_rp_bits cong_control_802_1qau_rp; + struct mlx5_ifc_cong_control_r_roce_ecn_rp_bits cong_control_r_roce_ecn_rp; + struct mlx5_ifc_cong_control_r_roce_ecn_np_bits cong_control_r_roce_ecn_np; + u8 reserved_0[0x800]; +}; + +struct mlx5_ifc_query_adapter_param_block_bits { + u8 reserved_0[0xc0]; + + u8 reserved_1[0x8]; + u8 ieee_vendor_id[0x18]; + + u8 reserved_2[0x10]; + u8 vsd_vendor_id[0x10]; + + u8 vsd[208][0x8]; + + u8 vsd_contd_psid[16][0x8]; +}; + +union mlx5_ifc_modify_field_select_resize_field_select_auto_bits { + struct mlx5_ifc_modify_field_select_bits modify_field_select; + struct mlx5_ifc_resize_field_select_bits resize_field_select; + u8 reserved_0[0x20]; +}; + +union mlx5_ifc_field_select_802_1_r_roce_auto_bits { + struct mlx5_ifc_field_select_802_1qau_rp_bits field_select_802_1qau_rp; + struct mlx5_ifc_field_select_r_roce_rp_bits field_select_r_roce_rp; + struct mlx5_ifc_field_select_r_roce_np_bits field_select_r_roce_np; + u8 reserved_0[0x20]; +}; + +union mlx5_ifc_eth_cntrs_grp_data_layout_auto_bits { + struct mlx5_ifc_eth_802_3_cntrs_grp_data_layout_bits eth_802_3_cntrs_grp_data_layout; + struct mlx5_ifc_eth_2863_cntrs_grp_data_layout_bits eth_2863_cntrs_grp_data_layout; + struct mlx5_ifc_eth_2819_cntrs_grp_data_layout_bits eth_2819_cntrs_grp_data_layout; + struct mlx5_ifc_eth_3635_cntrs_grp_data_layout_bits eth_3635_cntrs_grp_data_layout; + struct mlx5_ifc_eth_extended_cntrs_grp_data_layout_bits eth_extended_cntrs_grp_data_layout; + struct mlx5_ifc_eth_per_prio_grp_data_layout_bits eth_per_prio_grp_data_layout; + struct mlx5_ifc_eth_per_traffic_grp_data_layout_bits eth_per_traffic_grp_data_layout; + struct mlx5_ifc_phys_layer_cntrs_bits phys_layer_cntrs; + u8 reserved_0[0x7c0]; +}; + +union mlx5_ifc_event_auto_bits { + struct mlx5_ifc_comp_event_bits comp_event; + struct mlx5_ifc_dct_events_bits dct_events; + struct mlx5_ifc_qp_events_bits qp_events; + struct mlx5_ifc_wqe_associated_page_fault_event_bits wqe_associated_page_fault_event; + struct mlx5_ifc_rdma_page_fault_event_bits rdma_page_fault_event; + struct mlx5_ifc_cq_error_bits cq_error; + struct mlx5_ifc_dropped_packet_logged_bits dropped_packet_logged; + struct mlx5_ifc_port_state_change_event_bits port_state_change_event; + struct mlx5_ifc_gpio_event_bits gpio_event; + struct mlx5_ifc_db_bf_congestion_event_bits db_bf_congestion_event; + struct mlx5_ifc_stall_vl_event_bits stall_vl_event; + struct mlx5_ifc_cmd_inter_comp_event_bits cmd_inter_comp_event; + u8 reserved_0[0xe0]; +}; + +struct mlx5_ifc_health_buffer_bits { + u8 reserved_0[0x100]; + + u8 assert_existptr[0x20]; + + u8 assert_callra[0x20]; + + u8 reserved_1[0x40]; + + u8 fw_version[0x20]; + + u8 hw_id[0x20]; + + u8 reserved_2[0x20]; + + u8 irisc_index[0x8]; + u8 synd[0x8]; + u8 ext_synd[0x10]; +}; + +struct mlx5_ifc_register_loopback_control_bits { + u8 no_lb[0x1]; + u8 reserved_0[0x7]; + u8 port[0x8]; + u8 reserved_1[0x10]; + + u8 reserved_2[0x60]; +}; + +struct mlx5_ifc_teardown_hca_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +enum { + MLX5_TEARDOWN_HCA_IN_PROFILE_GRACEFUL_CLOSE = 0x0, + MLX5_TEARDOWN_HCA_IN_PROFILE_PANIC_CLOSE = 0x1, +}; + +struct mlx5_ifc_teardown_hca_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x10]; + u8 profile[0x10]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_sqerr2rts_qp_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_sqerr2rts_qp_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 qpn[0x18]; + + u8 reserved_3[0x20]; + + u8 opt_param_mask[0x20]; + + u8 reserved_4[0x20]; + + struct mlx5_ifc_qpc_bits qpc; + + u8 reserved_5[0x80]; +}; + +struct mlx5_ifc_sqd2rts_qp_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_sqd2rts_qp_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 qpn[0x18]; + + u8 reserved_3[0x20]; + + u8 opt_param_mask[0x20]; + + u8 reserved_4[0x20]; + + struct mlx5_ifc_qpc_bits qpc; + + u8 reserved_5[0x80]; +}; + +struct mlx5_ifc_set_roce_address_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_set_roce_address_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 roce_address_index[0x10]; + u8 reserved_2[0x10]; + + u8 reserved_3[0x20]; + + struct mlx5_ifc_roce_addr_layout_bits roce_address; +}; + +struct mlx5_ifc_set_mad_demux_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +enum { + MLX5_SET_MAD_DEMUX_IN_DEMUX_MODE_PASS_ALL = 0x0, + MLX5_SET_MAD_DEMUX_IN_DEMUX_MODE_SELECTIVE = 0x2, +}; + +struct mlx5_ifc_set_mad_demux_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x20]; + + u8 reserved_3[0x6]; + u8 demux_mode[0x2]; + u8 reserved_4[0x18]; +}; + +struct mlx5_ifc_set_l2_table_entry_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_set_l2_table_entry_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x60]; + + u8 reserved_3[0x8]; + u8 table_index[0x18]; + + u8 reserved_4[0x20]; + + u8 reserved_5[0x13]; + u8 vlan_valid[0x1]; + u8 vlan[0xc]; + + struct mlx5_ifc_mac_address_layout_bits mac_address; + + u8 reserved_6[0xc0]; +}; + +struct mlx5_ifc_set_issi_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_set_issi_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x10]; + u8 current_issi[0x10]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_set_hca_cap_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; }; struct mlx5_ifc_set_hca_cap_in_bits { @@ -313,10 +2766,710 @@ struct mlx5_ifc_set_hca_cap_in_bits { u8 reserved_2[0x40]; - struct mlx5_ifc_cmd_hca_cap_bits hca_capability_struct; + union mlx5_ifc_hca_cap_union_bits capability; }; -struct mlx5_ifc_query_hca_cap_in_bits { +struct mlx5_ifc_set_fte_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_set_fte_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; + + u8 table_type[0x8]; + u8 reserved_3[0x18]; + + u8 reserved_4[0x8]; + u8 table_id[0x18]; + + u8 reserved_5[0x40]; + + u8 flow_index[0x20]; + + u8 reserved_6[0xe0]; + + struct mlx5_ifc_flow_context_bits flow_context; +}; + +struct mlx5_ifc_rts2rts_qp_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_rts2rts_qp_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 qpn[0x18]; + + u8 reserved_3[0x20]; + + u8 opt_param_mask[0x20]; + + u8 reserved_4[0x20]; + + struct mlx5_ifc_qpc_bits qpc; + + u8 reserved_5[0x80]; +}; + +struct mlx5_ifc_rtr2rts_qp_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_rtr2rts_qp_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 qpn[0x18]; + + u8 reserved_3[0x20]; + + u8 opt_param_mask[0x20]; + + u8 reserved_4[0x20]; + + struct mlx5_ifc_qpc_bits qpc; + + u8 reserved_5[0x80]; +}; + +struct mlx5_ifc_rst2init_qp_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_rst2init_qp_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 qpn[0x18]; + + u8 reserved_3[0x20]; + + u8 opt_param_mask[0x20]; + + u8 reserved_4[0x20]; + + struct mlx5_ifc_qpc_bits qpc; + + u8 reserved_5[0x80]; +}; + +struct mlx5_ifc_query_xrc_srq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; + + struct mlx5_ifc_xrc_srqc_bits xrc_srq_context_entry; + + u8 reserved_2[0x600]; + + u8 pas[0][0x40]; +}; + +struct mlx5_ifc_query_xrc_srq_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 xrc_srqn[0x18]; + + u8 reserved_3[0x20]; +}; + +enum { + MLX5_QUERY_VPORT_STATE_OUT_STATE_DOWN = 0x0, + MLX5_QUERY_VPORT_STATE_OUT_STATE_UP = 0x1, +}; + +struct mlx5_ifc_query_vport_state_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x20]; + + u8 reserved_2[0x18]; + u8 admin_state[0x4]; + u8 state[0x4]; +}; + +enum { + MLX5_QUERY_VPORT_STATE_IN_OP_MOD_VNIC_VPORT = 0x0, +}; + +struct mlx5_ifc_query_vport_state_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 other_vport[0x1]; + u8 reserved_2[0xf]; + u8 vport_number[0x10]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_query_vport_counter_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; + + struct mlx5_ifc_traffic_counter_bits received_errors; + + struct mlx5_ifc_traffic_counter_bits transmit_errors; + + struct mlx5_ifc_traffic_counter_bits received_ib_unicast; + + struct mlx5_ifc_traffic_counter_bits transmitted_ib_unicast; + + struct mlx5_ifc_traffic_counter_bits received_ib_multicast; + + struct mlx5_ifc_traffic_counter_bits transmitted_ib_multicast; + + struct mlx5_ifc_traffic_counter_bits received_eth_broadcast; + + struct mlx5_ifc_traffic_counter_bits transmitted_eth_broadcast; + + struct mlx5_ifc_traffic_counter_bits received_eth_unicast; + + struct mlx5_ifc_traffic_counter_bits transmitted_eth_unicast; + + struct mlx5_ifc_traffic_counter_bits received_eth_multicast; + + struct mlx5_ifc_traffic_counter_bits transmitted_eth_multicast; + + u8 reserved_2[0xa00]; +}; + +enum { + MLX5_QUERY_VPORT_COUNTER_IN_OP_MOD_VPORT_COUNTERS = 0x0, +}; + +struct mlx5_ifc_query_vport_counter_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 other_vport[0x1]; + u8 reserved_2[0xf]; + u8 vport_number[0x10]; + + u8 reserved_3[0x60]; + + u8 clear[0x1]; + u8 reserved_4[0x1f]; + + u8 reserved_5[0x20]; +}; + +struct mlx5_ifc_query_tis_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; + + struct mlx5_ifc_tisc_bits tis_context; +}; + +struct mlx5_ifc_query_tis_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 tisn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_query_tir_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0xc0]; + + struct mlx5_ifc_tirc_bits tir_context; +}; + +struct mlx5_ifc_query_tir_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 tirn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_query_srq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; + + struct mlx5_ifc_srqc_bits srq_context_entry; + + u8 reserved_2[0x600]; + + u8 pas[0][0x40]; +}; + +struct mlx5_ifc_query_srq_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 srqn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_query_sq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0xc0]; + + struct mlx5_ifc_sqc_bits sq_context; +}; + +struct mlx5_ifc_query_sq_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 sqn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_query_special_contexts_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x20]; + + u8 resd_lkey[0x20]; +}; + +struct mlx5_ifc_query_special_contexts_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; +}; + +struct mlx5_ifc_query_rqt_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0xc0]; + + struct mlx5_ifc_rqtc_bits rqt_context; +}; + +struct mlx5_ifc_query_rqt_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 rqtn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_query_rq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0xc0]; + + struct mlx5_ifc_rqc_bits rq_context; +}; + +struct mlx5_ifc_query_rq_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 rqn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_query_roce_address_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; + + struct mlx5_ifc_roce_addr_layout_bits roce_address; +}; + +struct mlx5_ifc_query_roce_address_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 roce_address_index[0x10]; + u8 reserved_2[0x10]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_query_rmp_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0xc0]; + + struct mlx5_ifc_rmpc_bits rmp_context; +}; + +struct mlx5_ifc_query_rmp_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 rmpn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_query_qp_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; + + u8 opt_param_mask[0x20]; + + u8 reserved_2[0x20]; + + struct mlx5_ifc_qpc_bits qpc; + + u8 reserved_3[0x80]; + + u8 pas[0][0x40]; +}; + +struct mlx5_ifc_query_qp_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 qpn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_query_q_counter_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; + + u8 rx_write_requests[0x20]; + + u8 reserved_2[0x20]; + + u8 rx_read_requests[0x20]; + + u8 reserved_3[0x20]; + + u8 rx_atomic_requests[0x20]; + + u8 reserved_4[0x20]; + + u8 rx_dct_connect[0x20]; + + u8 reserved_5[0x20]; + + u8 out_of_buffer[0x20]; + + u8 reserved_6[0x20]; + + u8 out_of_sequence[0x20]; + + u8 reserved_7[0x620]; +}; + +struct mlx5_ifc_query_q_counter_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x80]; + + u8 clear[0x1]; + u8 reserved_3[0x1f]; + + u8 reserved_4[0x18]; + u8 counter_set_id[0x8]; +}; + +struct mlx5_ifc_query_pages_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x10]; + u8 function_id[0x10]; + + u8 num_pages[0x20]; +}; + +enum { + MLX5_QUERY_PAGES_IN_OP_MOD_BOOT_PAGES = 0x1, + MLX5_QUERY_PAGES_IN_OP_MOD_INIT_PAGES = 0x2, + MLX5_QUERY_PAGES_IN_OP_MOD_REGULAR_PAGES = 0x3, +}; + +struct mlx5_ifc_query_pages_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x10]; + u8 function_id[0x10]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_query_nic_vport_context_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; + + struct mlx5_ifc_nic_vport_context_bits nic_vport_context; +}; + +struct mlx5_ifc_query_nic_vport_context_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 other_vport[0x1]; + u8 reserved_2[0xf]; + u8 vport_number[0x10]; + + u8 reserved_3[0x5]; + u8 allowed_list_type[0x3]; + u8 reserved_4[0x18]; +}; + +struct mlx5_ifc_query_mkey_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; + + struct mlx5_ifc_mkc_bits memory_key_mkey_entry; + + u8 reserved_2[0x600]; + + u8 bsf0_klm0_pas_mtt0_1[16][0x8]; + + u8 bsf1_klm1_pas_mtt2_3[16][0x8]; +}; + +struct mlx5_ifc_query_mkey_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 mkey_index[0x18]; + + u8 pg_access[0x1]; + u8 reserved_3[0x1f]; +}; + +struct mlx5_ifc_query_mad_demux_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; + + u8 mad_dumux_parameters_block[0x20]; +}; + +struct mlx5_ifc_query_mad_demux_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; +}; + +struct mlx5_ifc_query_l2_table_entry_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0xa0]; + + u8 reserved_2[0x13]; + u8 vlan_valid[0x1]; + u8 vlan[0xc]; + + struct mlx5_ifc_mac_address_layout_bits mac_address; + + u8 reserved_3[0xc0]; +}; + +struct mlx5_ifc_query_l2_table_entry_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x60]; + + u8 reserved_3[0x8]; + u8 table_index[0x18]; + + u8 reserved_4[0x140]; +}; + +struct mlx5_ifc_query_issi_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x10]; + u8 current_issi[0x10]; + + u8 reserved_2[0xa0]; + + u8 supported_issi_reserved[76][0x8]; + u8 supported_issi_dw0[0x20]; +}; + +struct mlx5_ifc_query_issi_in_bits { u8 opcode[0x10]; u8 reserved_0[0x10]; @@ -326,6 +3479,89 @@ struct mlx5_ifc_query_hca_cap_in_bits { u8 reserved_2[0x40]; }; +struct mlx5_ifc_query_hca_vport_pkey_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; + + struct mlx5_ifc_pkey_bits pkey[0]; +}; + +struct mlx5_ifc_query_hca_vport_pkey_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 other_vport[0x1]; + u8 reserved_2[0xb]; + u8 port_num[0x4]; + u8 vport_number[0x10]; + + u8 reserved_3[0x10]; + u8 pkey_index[0x10]; +}; + +struct mlx5_ifc_query_hca_vport_gid_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x20]; + + u8 gids_num[0x10]; + u8 reserved_2[0x10]; + + struct mlx5_ifc_array128_auto_bits gid[0]; +}; + +struct mlx5_ifc_query_hca_vport_gid_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 other_vport[0x1]; + u8 reserved_2[0xb]; + u8 port_num[0x4]; + u8 vport_number[0x10]; + + u8 reserved_3[0x10]; + u8 gid_index[0x10]; +}; + +struct mlx5_ifc_query_hca_vport_context_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; + + struct mlx5_ifc_hca_vport_context_bits hca_vport_context; +}; + +struct mlx5_ifc_query_hca_vport_context_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 other_vport[0x1]; + u8 reserved_2[0xb]; + u8 port_num[0x4]; + u8 vport_number[0x10]; + + u8 reserved_3[0x20]; +}; + struct mlx5_ifc_query_hca_cap_out_bits { u8 status[0x8]; u8 reserved_0[0x18]; @@ -334,16 +3570,3232 @@ struct mlx5_ifc_query_hca_cap_out_bits { u8 reserved_1[0x40]; - u8 capability_struct[256][0x8]; + union mlx5_ifc_hca_cap_union_bits capability; }; -struct mlx5_ifc_set_hca_cap_out_bits { +struct mlx5_ifc_query_hca_cap_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; +}; + +struct mlx5_ifc_query_flow_table_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x80]; + + u8 reserved_2[0x8]; + u8 level[0x8]; + u8 reserved_3[0x8]; + u8 log_size[0x8]; + + u8 reserved_4[0x120]; +}; + +struct mlx5_ifc_query_flow_table_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; + + u8 table_type[0x8]; + u8 reserved_3[0x18]; + + u8 reserved_4[0x8]; + u8 table_id[0x18]; + + u8 reserved_5[0x140]; +}; + +struct mlx5_ifc_query_fte_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x1c0]; + + struct mlx5_ifc_flow_context_bits flow_context; +}; + +struct mlx5_ifc_query_fte_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; + + u8 table_type[0x8]; + u8 reserved_3[0x18]; + + u8 reserved_4[0x8]; + u8 table_id[0x18]; + + u8 reserved_5[0x40]; + + u8 flow_index[0x20]; + + u8 reserved_6[0xe0]; +}; + +enum { + MLX5_QUERY_FLOW_GROUP_OUT_MATCH_CRITERIA_ENABLE_OUTER_HEADERS = 0x0, + MLX5_QUERY_FLOW_GROUP_OUT_MATCH_CRITERIA_ENABLE_MISC_PARAMETERS = 0x1, + MLX5_QUERY_FLOW_GROUP_OUT_MATCH_CRITERIA_ENABLE_INNER_HEADERS = 0x2, +}; + +struct mlx5_ifc_query_flow_group_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0xa0]; + + u8 start_flow_index[0x20]; + + u8 reserved_2[0x20]; + + u8 end_flow_index[0x20]; + + u8 reserved_3[0xa0]; + + u8 reserved_4[0x18]; + u8 match_criteria_enable[0x8]; + + struct mlx5_ifc_fte_match_param_bits match_criteria; + + u8 reserved_5[0xe00]; +}; + +struct mlx5_ifc_query_flow_group_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; + + u8 table_type[0x8]; + u8 reserved_3[0x18]; + + u8 reserved_4[0x8]; + u8 table_id[0x18]; + + u8 group_id[0x20]; + + u8 reserved_5[0x120]; +}; + +struct mlx5_ifc_query_eq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; + + struct mlx5_ifc_eqc_bits eq_context_entry; + + u8 reserved_2[0x40]; + + u8 event_bitmask[0x40]; + + u8 reserved_3[0x580]; + + u8 pas[0][0x40]; +}; + +struct mlx5_ifc_query_eq_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x18]; + u8 eq_number[0x8]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_query_dct_out_bits { u8 status[0x8]; u8 reserved_0[0x18]; u8 syndrome[0x20]; u8 reserved_1[0x40]; + + struct mlx5_ifc_dctc_bits dct_context_entry; + + u8 reserved_2[0x180]; +}; + +struct mlx5_ifc_query_dct_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 dctn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_query_cq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; + + struct mlx5_ifc_cqc_bits cq_context; + + u8 reserved_2[0x600]; + + u8 pas[0][0x40]; +}; + +struct mlx5_ifc_query_cq_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 cqn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_query_cong_status_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x20]; + + u8 enable[0x1]; + u8 tag_enable[0x1]; + u8 reserved_2[0x1e]; +}; + +struct mlx5_ifc_query_cong_status_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x18]; + u8 priority[0x4]; + u8 cong_protocol[0x4]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_query_cong_statistics_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; + + u8 cur_flows[0x20]; + + u8 sum_flows[0x20]; + + u8 cnp_ignored_high[0x20]; + + u8 cnp_ignored_low[0x20]; + + u8 cnp_handled_high[0x20]; + + u8 cnp_handled_low[0x20]; + + u8 reserved_2[0x100]; + + u8 time_stamp_high[0x20]; + + u8 time_stamp_low[0x20]; + + u8 accumulators_period[0x20]; + + u8 ecn_marked_roce_packets_high[0x20]; + + u8 ecn_marked_roce_packets_low[0x20]; + + u8 cnps_sent_high[0x20]; + + u8 cnps_sent_low[0x20]; + + u8 reserved_3[0x560]; +}; + +struct mlx5_ifc_query_cong_statistics_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 clear[0x1]; + u8 reserved_2[0x1f]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_query_cong_params_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; + + union mlx5_ifc_cong_control_roce_ecn_auto_bits congestion_parameters; +}; + +struct mlx5_ifc_query_cong_params_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x1c]; + u8 cong_protocol[0x4]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_query_adapter_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; + + struct mlx5_ifc_query_adapter_param_block_bits query_adapter_struct; +}; + +struct mlx5_ifc_query_adapter_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; +}; + +struct mlx5_ifc_qp_2rst_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_qp_2rst_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 qpn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_qp_2err_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_qp_2err_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 qpn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_page_fault_resume_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_page_fault_resume_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 error[0x1]; + u8 reserved_2[0x4]; + u8 rdma[0x1]; + u8 read_write[0x1]; + u8 req_res[0x1]; + u8 qpn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_nop_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_nop_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; +}; + +struct mlx5_ifc_modify_vport_state_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_modify_vport_state_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 other_vport[0x1]; + u8 reserved_2[0xf]; + u8 vport_number[0x10]; + + u8 reserved_3[0x18]; + u8 admin_state[0x4]; + u8 reserved_4[0x4]; +}; + +struct mlx5_ifc_modify_tis_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_modify_tis_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 tisn[0x18]; + + u8 reserved_3[0x20]; + + u8 modify_bitmask[0x40]; + + u8 reserved_4[0x40]; + + struct mlx5_ifc_tisc_bits ctx; +}; + +struct mlx5_ifc_modify_tir_bitmask_bits { + u8 reserved_0[0x20]; + + u8 reserved_1[0x1b]; + u8 self_lb_en[0x1]; + u8 reserved_2[0x3]; + u8 lro[0x1]; +}; + +struct mlx5_ifc_modify_tir_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_modify_tir_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 tirn[0x18]; + + u8 reserved_3[0x20]; + + struct mlx5_ifc_modify_tir_bitmask_bits bitmask; + + u8 reserved_4[0x40]; + + struct mlx5_ifc_tirc_bits ctx; +}; + +struct mlx5_ifc_modify_sq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_modify_sq_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 sq_state[0x4]; + u8 reserved_2[0x4]; + u8 sqn[0x18]; + + u8 reserved_3[0x20]; + + u8 modify_bitmask[0x40]; + + u8 reserved_4[0x40]; + + struct mlx5_ifc_sqc_bits ctx; +}; + +struct mlx5_ifc_modify_rqt_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_rqt_bitmask_bits { + u8 reserved[0x20]; + + u8 reserved1[0x1f]; + u8 rqn_list[0x1]; +}; + +struct mlx5_ifc_modify_rqt_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 rqtn[0x18]; + + u8 reserved_3[0x20]; + + struct mlx5_ifc_rqt_bitmask_bits bitmask; + + u8 reserved_4[0x40]; + + struct mlx5_ifc_rqtc_bits ctx; +}; + +struct mlx5_ifc_modify_rq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_modify_rq_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 rq_state[0x4]; + u8 reserved_2[0x4]; + u8 rqn[0x18]; + + u8 reserved_3[0x20]; + + u8 modify_bitmask[0x40]; + + u8 reserved_4[0x40]; + + struct mlx5_ifc_rqc_bits ctx; +}; + +struct mlx5_ifc_modify_rmp_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_rmp_bitmask_bits { + u8 reserved[0x20]; + + u8 reserved1[0x1f]; + u8 lwm[0x1]; +}; + +struct mlx5_ifc_modify_rmp_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 rmp_state[0x4]; + u8 reserved_2[0x4]; + u8 rmpn[0x18]; + + u8 reserved_3[0x20]; + + struct mlx5_ifc_rmp_bitmask_bits bitmask; + + u8 reserved_4[0x40]; + + struct mlx5_ifc_rmpc_bits ctx; +}; + +struct mlx5_ifc_modify_nic_vport_context_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_modify_nic_vport_field_select_bits { + u8 reserved_0[0x1c]; + u8 permanent_address[0x1]; + u8 addresses_list[0x1]; + u8 roce_en[0x1]; + u8 reserved_1[0x1]; +}; + +struct mlx5_ifc_modify_nic_vport_context_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 other_vport[0x1]; + u8 reserved_2[0xf]; + u8 vport_number[0x10]; + + struct mlx5_ifc_modify_nic_vport_field_select_bits field_select; + + u8 reserved_3[0x780]; + + struct mlx5_ifc_nic_vport_context_bits nic_vport_context; +}; + +struct mlx5_ifc_modify_hca_vport_context_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_modify_hca_vport_context_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 other_vport[0x1]; + u8 reserved_2[0xb]; + u8 port_num[0x4]; + u8 vport_number[0x10]; + + u8 reserved_3[0x20]; + + struct mlx5_ifc_hca_vport_context_bits hca_vport_context; +}; + +struct mlx5_ifc_modify_cq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +enum { + MLX5_MODIFY_CQ_IN_OP_MOD_MODIFY_CQ = 0x0, + MLX5_MODIFY_CQ_IN_OP_MOD_RESIZE_CQ = 0x1, +}; + +struct mlx5_ifc_modify_cq_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 cqn[0x18]; + + union mlx5_ifc_modify_field_select_resize_field_select_auto_bits modify_field_select_resize_field_select; + + struct mlx5_ifc_cqc_bits cq_context; + + u8 reserved_3[0x600]; + + u8 pas[0][0x40]; +}; + +struct mlx5_ifc_modify_cong_status_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_modify_cong_status_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x18]; + u8 priority[0x4]; + u8 cong_protocol[0x4]; + + u8 enable[0x1]; + u8 tag_enable[0x1]; + u8 reserved_3[0x1e]; +}; + +struct mlx5_ifc_modify_cong_params_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_modify_cong_params_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x1c]; + u8 cong_protocol[0x4]; + + union mlx5_ifc_field_select_802_1_r_roce_auto_bits field_select; + + u8 reserved_3[0x80]; + + union mlx5_ifc_cong_control_roce_ecn_auto_bits congestion_parameters; +}; + +struct mlx5_ifc_manage_pages_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 output_num_entries[0x20]; + + u8 reserved_1[0x20]; + + u8 pas[0][0x40]; +}; + +enum { + MLX5_MANAGE_PAGES_IN_OP_MOD_ALLOCATION_FAIL = 0x0, + MLX5_MANAGE_PAGES_IN_OP_MOD_ALLOCATION_SUCCESS = 0x1, + MLX5_MANAGE_PAGES_IN_OP_MOD_HCA_RETURN_PAGES = 0x2, +}; + +struct mlx5_ifc_manage_pages_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x10]; + u8 function_id[0x10]; + + u8 input_num_entries[0x20]; + + u8 pas[0][0x40]; +}; + +struct mlx5_ifc_mad_ifc_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; + + u8 response_mad_packet[256][0x8]; +}; + +struct mlx5_ifc_mad_ifc_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 remote_lid[0x10]; + u8 reserved_2[0x8]; + u8 port[0x8]; + + u8 reserved_3[0x20]; + + u8 mad[256][0x8]; +}; + +struct mlx5_ifc_init_hca_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_init_hca_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; +}; + +struct mlx5_ifc_init2rtr_qp_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_init2rtr_qp_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 qpn[0x18]; + + u8 reserved_3[0x20]; + + u8 opt_param_mask[0x20]; + + u8 reserved_4[0x20]; + + struct mlx5_ifc_qpc_bits qpc; + + u8 reserved_5[0x80]; +}; + +struct mlx5_ifc_init2init_qp_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_init2init_qp_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 qpn[0x18]; + + u8 reserved_3[0x20]; + + u8 opt_param_mask[0x20]; + + u8 reserved_4[0x20]; + + struct mlx5_ifc_qpc_bits qpc; + + u8 reserved_5[0x80]; +}; + +struct mlx5_ifc_get_dropped_packet_log_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; + + u8 packet_headers_log[128][0x8]; + + u8 packet_syndrome[64][0x8]; +}; + +struct mlx5_ifc_get_dropped_packet_log_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; +}; + +struct mlx5_ifc_gen_eqe_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x18]; + u8 eq_number[0x8]; + + u8 reserved_3[0x20]; + + u8 eqe[64][0x8]; +}; + +struct mlx5_ifc_gen_eq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_enable_hca_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x20]; +}; + +struct mlx5_ifc_enable_hca_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x10]; + u8 function_id[0x10]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_drain_dct_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_drain_dct_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 dctn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_disable_hca_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x20]; +}; + +struct mlx5_ifc_disable_hca_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x10]; + u8 function_id[0x10]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_detach_from_mcg_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_detach_from_mcg_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 qpn[0x18]; + + u8 reserved_3[0x20]; + + u8 multicast_gid[16][0x8]; +}; + +struct mlx5_ifc_destroy_xrc_srq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_destroy_xrc_srq_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 xrc_srqn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_destroy_tis_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_destroy_tis_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 tisn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_destroy_tir_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_destroy_tir_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 tirn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_destroy_srq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_destroy_srq_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 srqn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_destroy_sq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_destroy_sq_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 sqn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_destroy_rqt_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_destroy_rqt_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 rqtn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_destroy_rq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_destroy_rq_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 rqn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_destroy_rmp_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_destroy_rmp_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 rmpn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_destroy_qp_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_destroy_qp_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 qpn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_destroy_psv_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_destroy_psv_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 psvn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_destroy_mkey_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_destroy_mkey_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 mkey_index[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_destroy_flow_table_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_destroy_flow_table_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; + + u8 table_type[0x8]; + u8 reserved_3[0x18]; + + u8 reserved_4[0x8]; + u8 table_id[0x18]; + + u8 reserved_5[0x140]; +}; + +struct mlx5_ifc_destroy_flow_group_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_destroy_flow_group_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; + + u8 table_type[0x8]; + u8 reserved_3[0x18]; + + u8 reserved_4[0x8]; + u8 table_id[0x18]; + + u8 group_id[0x20]; + + u8 reserved_5[0x120]; +}; + +struct mlx5_ifc_destroy_eq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_destroy_eq_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x18]; + u8 eq_number[0x8]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_destroy_dct_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_destroy_dct_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 dctn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_destroy_cq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_destroy_cq_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 cqn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_delete_vxlan_udp_dport_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_delete_vxlan_udp_dport_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x20]; + + u8 reserved_3[0x10]; + u8 vxlan_udp_port[0x10]; +}; + +struct mlx5_ifc_delete_l2_table_entry_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_delete_l2_table_entry_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x60]; + + u8 reserved_3[0x8]; + u8 table_index[0x18]; + + u8 reserved_4[0x140]; +}; + +struct mlx5_ifc_delete_fte_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_delete_fte_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; + + u8 table_type[0x8]; + u8 reserved_3[0x18]; + + u8 reserved_4[0x8]; + u8 table_id[0x18]; + + u8 reserved_5[0x40]; + + u8 flow_index[0x20]; + + u8 reserved_6[0xe0]; +}; + +struct mlx5_ifc_dealloc_xrcd_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_dealloc_xrcd_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 xrcd[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_dealloc_uar_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_dealloc_uar_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 uar[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_dealloc_transport_domain_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_dealloc_transport_domain_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 transport_domain[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_dealloc_q_counter_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_dealloc_q_counter_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x18]; + u8 counter_set_id[0x8]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_dealloc_pd_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_dealloc_pd_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 pd[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_create_xrc_srq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x8]; + u8 xrc_srqn[0x18]; + + u8 reserved_2[0x20]; +}; + +struct mlx5_ifc_create_xrc_srq_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; + + struct mlx5_ifc_xrc_srqc_bits xrc_srq_context_entry; + + u8 reserved_3[0x600]; + + u8 pas[0][0x40]; +}; + +struct mlx5_ifc_create_tis_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x8]; + u8 tisn[0x18]; + + u8 reserved_2[0x20]; +}; + +struct mlx5_ifc_create_tis_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0xc0]; + + struct mlx5_ifc_tisc_bits ctx; +}; + +struct mlx5_ifc_create_tir_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x8]; + u8 tirn[0x18]; + + u8 reserved_2[0x20]; +}; + +struct mlx5_ifc_create_tir_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0xc0]; + + struct mlx5_ifc_tirc_bits ctx; +}; + +struct mlx5_ifc_create_srq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x8]; + u8 srqn[0x18]; + + u8 reserved_2[0x20]; +}; + +struct mlx5_ifc_create_srq_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; + + struct mlx5_ifc_srqc_bits srq_context_entry; + + u8 reserved_3[0x600]; + + u8 pas[0][0x40]; +}; + +struct mlx5_ifc_create_sq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x8]; + u8 sqn[0x18]; + + u8 reserved_2[0x20]; +}; + +struct mlx5_ifc_create_sq_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0xc0]; + + struct mlx5_ifc_sqc_bits ctx; +}; + +struct mlx5_ifc_create_rqt_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x8]; + u8 rqtn[0x18]; + + u8 reserved_2[0x20]; +}; + +struct mlx5_ifc_create_rqt_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0xc0]; + + struct mlx5_ifc_rqtc_bits rqt_context; +}; + +struct mlx5_ifc_create_rq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x8]; + u8 rqn[0x18]; + + u8 reserved_2[0x20]; +}; + +struct mlx5_ifc_create_rq_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0xc0]; + + struct mlx5_ifc_rqc_bits ctx; +}; + +struct mlx5_ifc_create_rmp_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x8]; + u8 rmpn[0x18]; + + u8 reserved_2[0x20]; +}; + +struct mlx5_ifc_create_rmp_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0xc0]; + + struct mlx5_ifc_rmpc_bits ctx; +}; + +struct mlx5_ifc_create_qp_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x8]; + u8 qpn[0x18]; + + u8 reserved_2[0x20]; +}; + +struct mlx5_ifc_create_qp_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; + + u8 opt_param_mask[0x20]; + + u8 reserved_3[0x20]; + + struct mlx5_ifc_qpc_bits qpc; + + u8 reserved_4[0x80]; + + u8 pas[0][0x40]; +}; + +struct mlx5_ifc_create_psv_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; + + u8 reserved_2[0x8]; + u8 psv0_index[0x18]; + + u8 reserved_3[0x8]; + u8 psv1_index[0x18]; + + u8 reserved_4[0x8]; + u8 psv2_index[0x18]; + + u8 reserved_5[0x8]; + u8 psv3_index[0x18]; +}; + +struct mlx5_ifc_create_psv_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 num_psv[0x4]; + u8 reserved_2[0x4]; + u8 pd[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_create_mkey_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x8]; + u8 mkey_index[0x18]; + + u8 reserved_2[0x20]; +}; + +struct mlx5_ifc_create_mkey_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x20]; + + u8 pg_access[0x1]; + u8 reserved_3[0x1f]; + + struct mlx5_ifc_mkc_bits memory_key_mkey_entry; + + u8 reserved_4[0x80]; + + u8 translations_octword_actual_size[0x20]; + + u8 reserved_5[0x560]; + + u8 klm_pas_mtt[0][0x20]; +}; + +struct mlx5_ifc_create_flow_table_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x8]; + u8 table_id[0x18]; + + u8 reserved_2[0x20]; +}; + +struct mlx5_ifc_create_flow_table_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; + + u8 table_type[0x8]; + u8 reserved_3[0x18]; + + u8 reserved_4[0x20]; + + u8 reserved_5[0x8]; + u8 level[0x8]; + u8 reserved_6[0x8]; + u8 log_size[0x8]; + + u8 reserved_7[0x120]; +}; + +struct mlx5_ifc_create_flow_group_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x8]; + u8 group_id[0x18]; + + u8 reserved_2[0x20]; +}; + +enum { + MLX5_CREATE_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_OUTER_HEADERS = 0x0, + MLX5_CREATE_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_MISC_PARAMETERS = 0x1, + MLX5_CREATE_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_INNER_HEADERS = 0x2, +}; + +struct mlx5_ifc_create_flow_group_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; + + u8 table_type[0x8]; + u8 reserved_3[0x18]; + + u8 reserved_4[0x8]; + u8 table_id[0x18]; + + u8 reserved_5[0x20]; + + u8 start_flow_index[0x20]; + + u8 reserved_6[0x20]; + + u8 end_flow_index[0x20]; + + u8 reserved_7[0xa0]; + + u8 reserved_8[0x18]; + u8 match_criteria_enable[0x8]; + + struct mlx5_ifc_fte_match_param_bits match_criteria; + + u8 reserved_9[0xe00]; +}; + +struct mlx5_ifc_create_eq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x18]; + u8 eq_number[0x8]; + + u8 reserved_2[0x20]; +}; + +struct mlx5_ifc_create_eq_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; + + struct mlx5_ifc_eqc_bits eq_context_entry; + + u8 reserved_3[0x40]; + + u8 event_bitmask[0x40]; + + u8 reserved_4[0x580]; + + u8 pas[0][0x40]; +}; + +struct mlx5_ifc_create_dct_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x8]; + u8 dctn[0x18]; + + u8 reserved_2[0x20]; +}; + +struct mlx5_ifc_create_dct_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; + + struct mlx5_ifc_dctc_bits dct_context_entry; + + u8 reserved_3[0x180]; +}; + +struct mlx5_ifc_create_cq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x8]; + u8 cqn[0x18]; + + u8 reserved_2[0x20]; +}; + +struct mlx5_ifc_create_cq_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; + + struct mlx5_ifc_cqc_bits cq_context; + + u8 reserved_3[0x600]; + + u8 pas[0][0x40]; +}; + +struct mlx5_ifc_config_int_moderation_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x4]; + u8 min_delay[0xc]; + u8 int_vector[0x10]; + + u8 reserved_2[0x20]; +}; + +enum { + MLX5_CONFIG_INT_MODERATION_IN_OP_MOD_WRITE = 0x0, + MLX5_CONFIG_INT_MODERATION_IN_OP_MOD_READ = 0x1, +}; + +struct mlx5_ifc_config_int_moderation_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x4]; + u8 min_delay[0xc]; + u8 int_vector[0x10]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_attach_to_mcg_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_attach_to_mcg_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 qpn[0x18]; + + u8 reserved_3[0x20]; + + u8 multicast_gid[16][0x8]; +}; + +struct mlx5_ifc_arm_xrc_srq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +enum { + MLX5_ARM_XRC_SRQ_IN_OP_MOD_XRC_SRQ = 0x1, +}; + +struct mlx5_ifc_arm_xrc_srq_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 xrc_srqn[0x18]; + + u8 reserved_3[0x10]; + u8 lwm[0x10]; +}; + +struct mlx5_ifc_arm_rq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +enum { + MLX5_ARM_RQ_IN_OP_MOD_SRQ_ = 0x1, +}; + +struct mlx5_ifc_arm_rq_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 srq_number[0x18]; + + u8 reserved_3[0x10]; + u8 lwm[0x10]; +}; + +struct mlx5_ifc_arm_dct_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_arm_dct_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 dct_number[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_alloc_xrcd_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x8]; + u8 xrcd[0x18]; + + u8 reserved_2[0x20]; +}; + +struct mlx5_ifc_alloc_xrcd_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; +}; + +struct mlx5_ifc_alloc_uar_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x8]; + u8 uar[0x18]; + + u8 reserved_2[0x20]; +}; + +struct mlx5_ifc_alloc_uar_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; +}; + +struct mlx5_ifc_alloc_transport_domain_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x8]; + u8 transport_domain[0x18]; + + u8 reserved_2[0x20]; +}; + +struct mlx5_ifc_alloc_transport_domain_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; +}; + +struct mlx5_ifc_alloc_q_counter_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x18]; + u8 counter_set_id[0x8]; + + u8 reserved_2[0x20]; +}; + +struct mlx5_ifc_alloc_q_counter_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; +}; + +struct mlx5_ifc_alloc_pd_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x8]; + u8 pd[0x18]; + + u8 reserved_2[0x20]; +}; + +struct mlx5_ifc_alloc_pd_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; +}; + +struct mlx5_ifc_add_vxlan_udp_dport_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_add_vxlan_udp_dport_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x20]; + + u8 reserved_3[0x10]; + u8 vxlan_udp_port[0x10]; +}; + +struct mlx5_ifc_access_register_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; + + u8 register_data[0][0x20]; +}; + +enum { + MLX5_ACCESS_REGISTER_IN_OP_MOD_WRITE = 0x0, + MLX5_ACCESS_REGISTER_IN_OP_MOD_READ = 0x1, +}; + +struct mlx5_ifc_access_register_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x10]; + u8 register_id[0x10]; + + u8 argument[0x20]; + + u8 register_data[0][0x20]; +}; + +struct mlx5_ifc_sltp_reg_bits { + u8 status[0x4]; + u8 version[0x4]; + u8 local_port[0x8]; + u8 pnat[0x2]; + u8 reserved_0[0x2]; + u8 lane[0x4]; + u8 reserved_1[0x8]; + + u8 reserved_2[0x20]; + + u8 reserved_3[0x7]; + u8 polarity[0x1]; + u8 ob_tap0[0x8]; + u8 ob_tap1[0x8]; + u8 ob_tap2[0x8]; + + u8 reserved_4[0xc]; + u8 ob_preemp_mode[0x4]; + u8 ob_reg[0x8]; + u8 ob_bias[0x8]; + + u8 reserved_5[0x20]; +}; + +struct mlx5_ifc_slrg_reg_bits { + u8 status[0x4]; + u8 version[0x4]; + u8 local_port[0x8]; + u8 pnat[0x2]; + u8 reserved_0[0x2]; + u8 lane[0x4]; + u8 reserved_1[0x8]; + + u8 time_to_link_up[0x10]; + u8 reserved_2[0xc]; + u8 grade_lane_speed[0x4]; + + u8 grade_version[0x8]; + u8 grade[0x18]; + + u8 reserved_3[0x4]; + u8 height_grade_type[0x4]; + u8 height_grade[0x18]; + + u8 height_dz[0x10]; + u8 height_dv[0x10]; + + u8 reserved_4[0x10]; + u8 height_sigma[0x10]; + + u8 reserved_5[0x20]; + + u8 reserved_6[0x4]; + u8 phase_grade_type[0x4]; + u8 phase_grade[0x18]; + + u8 reserved_7[0x8]; + u8 phase_eo_pos[0x8]; + u8 reserved_8[0x8]; + u8 phase_eo_neg[0x8]; + + u8 ffe_set_tested[0x10]; + u8 test_errors_per_lane[0x10]; +}; + +struct mlx5_ifc_pvlc_reg_bits { + u8 reserved_0[0x8]; + u8 local_port[0x8]; + u8 reserved_1[0x10]; + + u8 reserved_2[0x1c]; + u8 vl_hw_cap[0x4]; + + u8 reserved_3[0x1c]; + u8 vl_admin[0x4]; + + u8 reserved_4[0x1c]; + u8 vl_operational[0x4]; +}; + +struct mlx5_ifc_pude_reg_bits { + u8 swid[0x8]; + u8 local_port[0x8]; + u8 reserved_0[0x4]; + u8 admin_status[0x4]; + u8 reserved_1[0x4]; + u8 oper_status[0x4]; + + u8 reserved_2[0x60]; +}; + +struct mlx5_ifc_ptys_reg_bits { + u8 reserved_0[0x8]; + u8 local_port[0x8]; + u8 reserved_1[0xd]; + u8 proto_mask[0x3]; + + u8 reserved_2[0x40]; + + u8 eth_proto_capability[0x20]; + + u8 ib_link_width_capability[0x10]; + u8 ib_proto_capability[0x10]; + + u8 reserved_3[0x20]; + + u8 eth_proto_admin[0x20]; + + u8 ib_link_width_admin[0x10]; + u8 ib_proto_admin[0x10]; + + u8 reserved_4[0x20]; + + u8 eth_proto_oper[0x20]; + + u8 ib_link_width_oper[0x10]; + u8 ib_proto_oper[0x10]; + + u8 reserved_5[0x20]; + + u8 eth_proto_lp_advertise[0x20]; + + u8 reserved_6[0x60]; +}; + +struct mlx5_ifc_ptas_reg_bits { + u8 reserved_0[0x20]; + + u8 algorithm_options[0x10]; + u8 reserved_1[0x4]; + u8 repetitions_mode[0x4]; + u8 num_of_repetitions[0x8]; + + u8 grade_version[0x8]; + u8 height_grade_type[0x4]; + u8 phase_grade_type[0x4]; + u8 height_grade_weight[0x8]; + u8 phase_grade_weight[0x8]; + + u8 gisim_measure_bits[0x10]; + u8 adaptive_tap_measure_bits[0x10]; + + u8 ber_bath_high_error_threshold[0x10]; + u8 ber_bath_mid_error_threshold[0x10]; + + u8 ber_bath_low_error_threshold[0x10]; + u8 one_ratio_high_threshold[0x10]; + + u8 one_ratio_high_mid_threshold[0x10]; + u8 one_ratio_low_mid_threshold[0x10]; + + u8 one_ratio_low_threshold[0x10]; + u8 ndeo_error_threshold[0x10]; + + u8 mixer_offset_step_size[0x10]; + u8 reserved_2[0x8]; + u8 mix90_phase_for_voltage_bath[0x8]; + + u8 mixer_offset_start[0x10]; + u8 mixer_offset_end[0x10]; + + u8 reserved_3[0x15]; + u8 ber_test_time[0xb]; +}; + +struct mlx5_ifc_pspa_reg_bits { + u8 swid[0x8]; + u8 local_port[0x8]; + u8 sub_port[0x8]; + u8 reserved_0[0x8]; + + u8 reserved_1[0x20]; +}; + +struct mlx5_ifc_pqdr_reg_bits { + u8 reserved_0[0x8]; + u8 local_port[0x8]; + u8 reserved_1[0x5]; + u8 prio[0x3]; + u8 reserved_2[0x6]; + u8 mode[0x2]; + + u8 reserved_3[0x20]; + + u8 reserved_4[0x10]; + u8 min_threshold[0x10]; + + u8 reserved_5[0x10]; + u8 max_threshold[0x10]; + + u8 reserved_6[0x10]; + u8 mark_probability_denominator[0x10]; + + u8 reserved_7[0x60]; +}; + +struct mlx5_ifc_ppsc_reg_bits { + u8 reserved_0[0x8]; + u8 local_port[0x8]; + u8 reserved_1[0x10]; + + u8 reserved_2[0x60]; + + u8 reserved_3[0x1c]; + u8 wrps_admin[0x4]; + + u8 reserved_4[0x1c]; + u8 wrps_status[0x4]; + + u8 reserved_5[0x8]; + u8 up_threshold[0x8]; + u8 reserved_6[0x8]; + u8 down_threshold[0x8]; + + u8 reserved_7[0x20]; + + u8 reserved_8[0x1c]; + u8 srps_admin[0x4]; + + u8 reserved_9[0x1c]; + u8 srps_status[0x4]; + + u8 reserved_10[0x40]; +}; + +struct mlx5_ifc_pplr_reg_bits { + u8 reserved_0[0x8]; + u8 local_port[0x8]; + u8 reserved_1[0x10]; + + u8 reserved_2[0x8]; + u8 lb_cap[0x8]; + u8 reserved_3[0x8]; + u8 lb_en[0x8]; +}; + +struct mlx5_ifc_pplm_reg_bits { + u8 reserved_0[0x8]; + u8 local_port[0x8]; + u8 reserved_1[0x10]; + + u8 reserved_2[0x20]; + + u8 port_profile_mode[0x8]; + u8 static_port_profile[0x8]; + u8 active_port_profile[0x8]; + u8 reserved_3[0x8]; + + u8 retransmission_active[0x8]; + u8 fec_mode_active[0x18]; + + u8 reserved_4[0x20]; +}; + +struct mlx5_ifc_ppcnt_reg_bits { + u8 swid[0x8]; + u8 local_port[0x8]; + u8 pnat[0x2]; + u8 reserved_0[0x8]; + u8 grp[0x6]; + + u8 clr[0x1]; + u8 reserved_1[0x1c]; + u8 prio_tc[0x3]; + + union mlx5_ifc_eth_cntrs_grp_data_layout_auto_bits counter_set; +}; + +struct mlx5_ifc_ppad_reg_bits { + u8 reserved_0[0x3]; + u8 single_mac[0x1]; + u8 reserved_1[0x4]; + u8 local_port[0x8]; + u8 mac_47_32[0x10]; + + u8 mac_31_0[0x20]; + + u8 reserved_2[0x40]; +}; + +struct mlx5_ifc_pmtu_reg_bits { + u8 reserved_0[0x8]; + u8 local_port[0x8]; + u8 reserved_1[0x10]; + + u8 max_mtu[0x10]; + u8 reserved_2[0x10]; + + u8 admin_mtu[0x10]; + u8 reserved_3[0x10]; + + u8 oper_mtu[0x10]; + u8 reserved_4[0x10]; +}; + +struct mlx5_ifc_pmpr_reg_bits { + u8 reserved_0[0x8]; + u8 module[0x8]; + u8 reserved_1[0x10]; + + u8 reserved_2[0x18]; + u8 attenuation_5g[0x8]; + + u8 reserved_3[0x18]; + u8 attenuation_7g[0x8]; + + u8 reserved_4[0x18]; + u8 attenuation_12g[0x8]; +}; + +struct mlx5_ifc_pmpe_reg_bits { + u8 reserved_0[0x8]; + u8 module[0x8]; + u8 reserved_1[0xc]; + u8 module_status[0x4]; + + u8 reserved_2[0x60]; +}; + +struct mlx5_ifc_pmpc_reg_bits { + u8 module_state_updated[32][0x8]; +}; + +struct mlx5_ifc_pmlpn_reg_bits { + u8 reserved_0[0x4]; + u8 mlpn_status[0x4]; + u8 local_port[0x8]; + u8 reserved_1[0x10]; + + u8 e[0x1]; + u8 reserved_2[0x1f]; +}; + +struct mlx5_ifc_pmlp_reg_bits { + u8 rxtx[0x1]; + u8 reserved_0[0x7]; + u8 local_port[0x8]; + u8 reserved_1[0x8]; + u8 width[0x8]; + + u8 lane0_module_mapping[0x20]; + + u8 lane1_module_mapping[0x20]; + + u8 lane2_module_mapping[0x20]; + + u8 lane3_module_mapping[0x20]; + + u8 reserved_2[0x160]; +}; + +struct mlx5_ifc_pmaos_reg_bits { + u8 reserved_0[0x8]; + u8 module[0x8]; + u8 reserved_1[0x4]; + u8 admin_status[0x4]; + u8 reserved_2[0x4]; + u8 oper_status[0x4]; + + u8 ase[0x1]; + u8 ee[0x1]; + u8 reserved_3[0x1c]; + u8 e[0x2]; + + u8 reserved_4[0x40]; +}; + +struct mlx5_ifc_plpc_reg_bits { + u8 reserved_0[0x4]; + u8 profile_id[0xc]; + u8 reserved_1[0x4]; + u8 proto_mask[0x4]; + u8 reserved_2[0x8]; + + u8 reserved_3[0x10]; + u8 lane_speed[0x10]; + + u8 reserved_4[0x17]; + u8 lpbf[0x1]; + u8 fec_mode_policy[0x8]; + + u8 retransmission_capability[0x8]; + u8 fec_mode_capability[0x18]; + + u8 retransmission_support_admin[0x8]; + u8 fec_mode_support_admin[0x18]; + + u8 retransmission_request_admin[0x8]; + u8 fec_mode_request_admin[0x18]; + + u8 reserved_5[0x80]; +}; + +struct mlx5_ifc_plib_reg_bits { + u8 reserved_0[0x8]; + u8 local_port[0x8]; + u8 reserved_1[0x8]; + u8 ib_port[0x8]; + + u8 reserved_2[0x60]; +}; + +struct mlx5_ifc_plbf_reg_bits { + u8 reserved_0[0x8]; + u8 local_port[0x8]; + u8 reserved_1[0xd]; + u8 lbf_mode[0x3]; + + u8 reserved_2[0x20]; +}; + +struct mlx5_ifc_pipg_reg_bits { + u8 reserved_0[0x8]; + u8 local_port[0x8]; + u8 reserved_1[0x10]; + + u8 dic[0x1]; + u8 reserved_2[0x19]; + u8 ipg[0x4]; + u8 reserved_3[0x2]; +}; + +struct mlx5_ifc_pifr_reg_bits { + u8 reserved_0[0x8]; + u8 local_port[0x8]; + u8 reserved_1[0x10]; + + u8 reserved_2[0xe0]; + + u8 port_filter[8][0x20]; + + u8 port_filter_update_en[8][0x20]; +}; + +struct mlx5_ifc_pfcc_reg_bits { + u8 reserved_0[0x8]; + u8 local_port[0x8]; + u8 reserved_1[0x10]; + + u8 ppan[0x4]; + u8 reserved_2[0x4]; + u8 prio_mask_tx[0x8]; + u8 reserved_3[0x8]; + u8 prio_mask_rx[0x8]; + + u8 pptx[0x1]; + u8 aptx[0x1]; + u8 reserved_4[0x6]; + u8 pfctx[0x8]; + u8 reserved_5[0x10]; + + u8 pprx[0x1]; + u8 aprx[0x1]; + u8 reserved_6[0x6]; + u8 pfcrx[0x8]; + u8 reserved_7[0x10]; + + u8 reserved_8[0x80]; +}; + +struct mlx5_ifc_pelc_reg_bits { + u8 op[0x4]; + u8 reserved_0[0x4]; + u8 local_port[0x8]; + u8 reserved_1[0x10]; + + u8 op_admin[0x8]; + u8 op_capability[0x8]; + u8 op_request[0x8]; + u8 op_active[0x8]; + + u8 admin[0x40]; + + u8 capability[0x40]; + + u8 request[0x40]; + + u8 active[0x40]; + + u8 reserved_2[0x80]; +}; + +struct mlx5_ifc_peir_reg_bits { + u8 reserved_0[0x8]; + u8 local_port[0x8]; + u8 reserved_1[0x10]; + + u8 reserved_2[0xc]; + u8 error_count[0x4]; + u8 reserved_3[0x10]; + + u8 reserved_4[0xc]; + u8 lane[0x4]; + u8 reserved_5[0x8]; + u8 error_type[0x8]; +}; + +struct mlx5_ifc_pcap_reg_bits { + u8 reserved_0[0x8]; + u8 local_port[0x8]; + u8 reserved_1[0x10]; + + u8 port_capability_mask[4][0x20]; +}; + +struct mlx5_ifc_paos_reg_bits { + u8 swid[0x8]; + u8 local_port[0x8]; + u8 reserved_0[0x4]; + u8 admin_status[0x4]; + u8 reserved_1[0x4]; + u8 oper_status[0x4]; + + u8 ase[0x1]; + u8 ee[0x1]; + u8 reserved_2[0x1c]; + u8 e[0x2]; + + u8 reserved_3[0x40]; +}; + +struct mlx5_ifc_pamp_reg_bits { + u8 reserved_0[0x8]; + u8 opamp_group[0x8]; + u8 reserved_1[0xc]; + u8 opamp_group_type[0x4]; + + u8 start_index[0x10]; + u8 reserved_2[0x4]; + u8 num_of_indices[0xc]; + + u8 index_data[18][0x10]; +}; + +struct mlx5_ifc_lane_2_module_mapping_bits { + u8 reserved_0[0x6]; + u8 rx_lane[0x2]; + u8 reserved_1[0x6]; + u8 tx_lane[0x2]; + u8 reserved_2[0x8]; + u8 module[0x8]; +}; + +struct mlx5_ifc_bufferx_reg_bits { + u8 reserved_0[0x6]; + u8 lossy[0x1]; + u8 epsb[0x1]; + u8 reserved_1[0xc]; + u8 size[0xc]; + + u8 xoff_threshold[0x10]; + u8 xon_threshold[0x10]; +}; + +struct mlx5_ifc_set_node_in_bits { + u8 node_description[64][0x8]; +}; + +struct mlx5_ifc_register_power_settings_bits { + u8 reserved_0[0x18]; + u8 power_settings_level[0x8]; + + u8 reserved_1[0x60]; +}; + +struct mlx5_ifc_register_host_endianness_bits { + u8 he[0x1]; + u8 reserved_0[0x1f]; + + u8 reserved_1[0x60]; +}; + +struct mlx5_ifc_umr_pointer_desc_argument_bits { + u8 reserved_0[0x20]; + + u8 mkey[0x20]; + + u8 addressh_63_32[0x20]; + + u8 addressl_31_0[0x20]; +}; + +struct mlx5_ifc_ud_adrs_vector_bits { + u8 dc_key[0x40]; + + u8 ext[0x1]; + u8 reserved_0[0x7]; + u8 destination_qp_dct[0x18]; + + u8 static_rate[0x4]; + u8 sl_eth_prio[0x4]; + u8 fl[0x1]; + u8 mlid[0x7]; + u8 rlid_udp_sport[0x10]; + + u8 reserved_1[0x20]; + + u8 rmac_47_16[0x20]; + + u8 rmac_15_0[0x10]; + u8 tclass[0x8]; + u8 hop_limit[0x8]; + + u8 reserved_2[0x1]; + u8 grh[0x1]; + u8 reserved_3[0x2]; + u8 src_addr_index[0x8]; + u8 flow_label[0x14]; + + u8 rgid_rip[16][0x8]; +}; + +struct mlx5_ifc_pages_req_event_bits { + u8 reserved_0[0x10]; + u8 function_id[0x10]; + + u8 num_pages[0x20]; + + u8 reserved_1[0xa0]; +}; + +struct mlx5_ifc_eqe_bits { + u8 reserved_0[0x8]; + u8 event_type[0x8]; + u8 reserved_1[0x8]; + u8 event_sub_type[0x8]; + + u8 reserved_2[0xe0]; + + union mlx5_ifc_event_auto_bits event_data; + + u8 reserved_3[0x10]; + u8 signature[0x8]; + u8 reserved_4[0x7]; + u8 owner[0x1]; +}; + +enum { + MLX5_CMD_QUEUE_ENTRY_TYPE_PCIE_CMD_IF_TRANSPORT = 0x7, +}; + +struct mlx5_ifc_cmd_queue_entry_bits { + u8 type[0x8]; + u8 reserved_0[0x18]; + + u8 input_length[0x20]; + + u8 input_mailbox_pointer_63_32[0x20]; + + u8 input_mailbox_pointer_31_9[0x17]; + u8 reserved_1[0x9]; + + u8 command_input_inline_data[16][0x8]; + + u8 command_output_inline_data[16][0x8]; + + u8 output_mailbox_pointer_63_32[0x20]; + + u8 output_mailbox_pointer_31_9[0x17]; + u8 reserved_2[0x9]; + + u8 output_length[0x20]; + + u8 token[0x8]; + u8 signature[0x8]; + u8 reserved_3[0x8]; + u8 status[0x7]; + u8 ownership[0x1]; +}; + +struct mlx5_ifc_cmd_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 command_output[0x20]; +}; + +struct mlx5_ifc_cmd_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 command[0][0x20]; +}; + +struct mlx5_ifc_cmd_if_box_bits { + u8 mailbox_data[512][0x8]; + + u8 reserved_0[0x180]; + + u8 next_pointer_63_32[0x20]; + + u8 next_pointer_31_10[0x16]; + u8 reserved_1[0xa]; + + u8 block_number[0x20]; + + u8 reserved_2[0x8]; + u8 token[0x8]; + u8 ctrl_signature[0x8]; + u8 signature[0x8]; +}; + +struct mlx5_ifc_mtt_bits { + u8 ptag_63_32[0x20]; + + u8 ptag_31_8[0x18]; + u8 reserved_0[0x6]; + u8 wr_en[0x1]; + u8 rd_en[0x1]; +}; + +enum { + MLX5_INITIAL_SEG_NIC_INTERFACE_FULL_DRIVER = 0x0, + MLX5_INITIAL_SEG_NIC_INTERFACE_DISABLED = 0x1, + MLX5_INITIAL_SEG_NIC_INTERFACE_NO_DRAM_NIC = 0x2, +}; + +enum { + MLX5_INITIAL_SEG_NIC_INTERFACE_SUPPORTED_FULL_DRIVER = 0x0, + MLX5_INITIAL_SEG_NIC_INTERFACE_SUPPORTED_DISABLED = 0x1, + MLX5_INITIAL_SEG_NIC_INTERFACE_SUPPORTED_NO_DRAM_NIC = 0x2, +}; + +enum { + MLX5_INITIAL_SEG_HEALTH_SYNDROME_FW_INTERNAL_ERR = 0x1, + MLX5_INITIAL_SEG_HEALTH_SYNDROME_DEAD_IRISC = 0x7, + MLX5_INITIAL_SEG_HEALTH_SYNDROME_HW_FATAL_ERR = 0x8, + MLX5_INITIAL_SEG_HEALTH_SYNDROME_FW_CRC_ERR = 0x9, + MLX5_INITIAL_SEG_HEALTH_SYNDROME_ICM_FETCH_PCI_ERR = 0xa, + MLX5_INITIAL_SEG_HEALTH_SYNDROME_ICM_PAGE_ERR = 0xb, + MLX5_INITIAL_SEG_HEALTH_SYNDROME_ASYNCHRONOUS_EQ_BUF_OVERRUN = 0xc, + MLX5_INITIAL_SEG_HEALTH_SYNDROME_EQ_IN_ERR = 0xd, + MLX5_INITIAL_SEG_HEALTH_SYNDROME_EQ_INV = 0xe, + MLX5_INITIAL_SEG_HEALTH_SYNDROME_FFSER_ERR = 0xf, + MLX5_INITIAL_SEG_HEALTH_SYNDROME_HIGH_TEMP_ERR = 0x10, +}; + +struct mlx5_ifc_initial_seg_bits { + u8 fw_rev_minor[0x10]; + u8 fw_rev_major[0x10]; + + u8 cmd_interface_rev[0x10]; + u8 fw_rev_subminor[0x10]; + + u8 reserved_0[0x40]; + + u8 cmdq_phy_addr_63_32[0x20]; + + u8 cmdq_phy_addr_31_12[0x14]; + u8 reserved_1[0x2]; + u8 nic_interface[0x2]; + u8 log_cmdq_size[0x4]; + u8 log_cmdq_stride[0x4]; + + u8 command_doorbell_vector[0x20]; + + u8 reserved_2[0xf00]; + + u8 initializing[0x1]; + u8 reserved_3[0x4]; + u8 nic_interface_supported[0x3]; + u8 reserved_4[0x18]; + + struct mlx5_ifc_health_buffer_bits health_buffer; + + u8 no_dram_nic_offset[0x20]; + + u8 reserved_5[0x6e40]; + + u8 reserved_6[0x1f]; + u8 clear_int[0x1]; + + u8 health_syndrome[0x8]; + u8 health_counter[0x18]; + + u8 reserved_7[0x17fc0]; +}; + +union mlx5_ifc_ports_control_registers_document_bits { + struct mlx5_ifc_bufferx_reg_bits bufferx_reg; + struct mlx5_ifc_eth_2819_cntrs_grp_data_layout_bits eth_2819_cntrs_grp_data_layout; + struct mlx5_ifc_eth_2863_cntrs_grp_data_layout_bits eth_2863_cntrs_grp_data_layout; + struct mlx5_ifc_eth_3635_cntrs_grp_data_layout_bits eth_3635_cntrs_grp_data_layout; + struct mlx5_ifc_eth_802_3_cntrs_grp_data_layout_bits eth_802_3_cntrs_grp_data_layout; + struct mlx5_ifc_eth_extended_cntrs_grp_data_layout_bits eth_extended_cntrs_grp_data_layout; + struct mlx5_ifc_eth_per_prio_grp_data_layout_bits eth_per_prio_grp_data_layout; + struct mlx5_ifc_eth_per_traffic_grp_data_layout_bits eth_per_traffic_grp_data_layout; + struct mlx5_ifc_lane_2_module_mapping_bits lane_2_module_mapping; + struct mlx5_ifc_pamp_reg_bits pamp_reg; + struct mlx5_ifc_paos_reg_bits paos_reg; + struct mlx5_ifc_pcap_reg_bits pcap_reg; + struct mlx5_ifc_peir_reg_bits peir_reg; + struct mlx5_ifc_pelc_reg_bits pelc_reg; + struct mlx5_ifc_pfcc_reg_bits pfcc_reg; + struct mlx5_ifc_phys_layer_cntrs_bits phys_layer_cntrs; + struct mlx5_ifc_pifr_reg_bits pifr_reg; + struct mlx5_ifc_pipg_reg_bits pipg_reg; + struct mlx5_ifc_plbf_reg_bits plbf_reg; + struct mlx5_ifc_plib_reg_bits plib_reg; + struct mlx5_ifc_plpc_reg_bits plpc_reg; + struct mlx5_ifc_pmaos_reg_bits pmaos_reg; + struct mlx5_ifc_pmlp_reg_bits pmlp_reg; + struct mlx5_ifc_pmlpn_reg_bits pmlpn_reg; + struct mlx5_ifc_pmpc_reg_bits pmpc_reg; + struct mlx5_ifc_pmpe_reg_bits pmpe_reg; + struct mlx5_ifc_pmpr_reg_bits pmpr_reg; + struct mlx5_ifc_pmtu_reg_bits pmtu_reg; + struct mlx5_ifc_ppad_reg_bits ppad_reg; + struct mlx5_ifc_ppcnt_reg_bits ppcnt_reg; + struct mlx5_ifc_pplm_reg_bits pplm_reg; + struct mlx5_ifc_pplr_reg_bits pplr_reg; + struct mlx5_ifc_ppsc_reg_bits ppsc_reg; + struct mlx5_ifc_pqdr_reg_bits pqdr_reg; + struct mlx5_ifc_pspa_reg_bits pspa_reg; + struct mlx5_ifc_ptas_reg_bits ptas_reg; + struct mlx5_ifc_ptys_reg_bits ptys_reg; + struct mlx5_ifc_pude_reg_bits pude_reg; + struct mlx5_ifc_pvlc_reg_bits pvlc_reg; + struct mlx5_ifc_slrg_reg_bits slrg_reg; + struct mlx5_ifc_sltp_reg_bits sltp_reg; + u8 reserved_0[0x60e0]; +}; + +union mlx5_ifc_debug_enhancements_document_bits { + struct mlx5_ifc_health_buffer_bits health_buffer; + u8 reserved_0[0x200]; +}; + +union mlx5_ifc_uplink_pci_interface_document_bits { + struct mlx5_ifc_initial_seg_bits initial_seg; + u8 reserved_0[0x20060]; }; #endif /* MLX5_IFC_H */ diff --git a/kernel/include/linux/mlx5/qp.h b/kernel/include/linux/mlx5/qp.h index 310b5f7fd..f079fb1a3 100644 --- a/kernel/include/linux/mlx5/qp.h +++ b/kernel/include/linux/mlx5/qp.h @@ -134,13 +134,21 @@ enum { enum { MLX5_WQE_CTRL_CQ_UPDATE = 2 << 2, + MLX5_WQE_CTRL_CQ_UPDATE_AND_EQE = 3 << 2, MLX5_WQE_CTRL_SOLICITED = 1 << 1, }; enum { + MLX5_SEND_WQE_DS = 16, MLX5_SEND_WQE_BB = 64, }; +#define MLX5_SEND_WQEBB_NUM_DS (MLX5_SEND_WQE_BB / MLX5_SEND_WQE_DS) + +enum { + MLX5_SEND_WQE_MAX_WQEBBS = 16, +}; + enum { MLX5_WQE_FMR_PERM_LOCAL_READ = 1 << 27, MLX5_WQE_FMR_PERM_LOCAL_WRITE = 1 << 28, @@ -200,6 +208,23 @@ struct mlx5_wqe_ctrl_seg { #define MLX5_WQE_CTRL_WQE_INDEX_MASK 0x00ffff00 #define MLX5_WQE_CTRL_WQE_INDEX_SHIFT 8 +enum { + MLX5_ETH_WQE_L3_INNER_CSUM = 1 << 4, + MLX5_ETH_WQE_L4_INNER_CSUM = 1 << 5, + MLX5_ETH_WQE_L3_CSUM = 1 << 6, + MLX5_ETH_WQE_L4_CSUM = 1 << 7, +}; + +struct mlx5_wqe_eth_seg { + u8 rsvd0[4]; + u8 cs_flags; + u8 rsvd1; + __be16 mss; + __be32 rsvd2; + __be16 inline_hdr_sz; + u8 inline_hdr_start[2]; +}; + struct mlx5_wqe_xrc_seg { __be32 xrc_srqn; u8 rsvd[12]; diff --git a/kernel/include/linux/mlx5/vport.h b/kernel/include/linux/mlx5/vport.h new file mode 100644 index 000000000..967e0fd06 --- /dev/null +++ b/kernel/include/linux/mlx5/vport.h @@ -0,0 +1,55 @@ +/* + * Copyright (c) 2013-2015, Mellanox Technologies, Ltd. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#ifndef __MLX5_VPORT_H__ +#define __MLX5_VPORT_H__ + +#include <linux/mlx5/driver.h> + +u8 mlx5_query_vport_state(struct mlx5_core_dev *mdev, u8 opmod); +void mlx5_query_nic_vport_mac_address(struct mlx5_core_dev *mdev, u8 *addr); +int mlx5_query_hca_vport_gid(struct mlx5_core_dev *dev, u8 other_vport, + u8 port_num, u16 vf_num, u16 gid_index, + union ib_gid *gid); +int mlx5_query_hca_vport_pkey(struct mlx5_core_dev *dev, u8 other_vport, + u8 port_num, u16 vf_num, u16 pkey_index, + u16 *pkey); +int mlx5_query_hca_vport_context(struct mlx5_core_dev *dev, + u8 other_vport, u8 port_num, + u16 vf_num, + struct mlx5_hca_vport_context *rep); +int mlx5_query_hca_vport_system_image_guid(struct mlx5_core_dev *dev, + u64 *sys_image_guid); +int mlx5_query_hca_vport_node_guid(struct mlx5_core_dev *dev, + u64 *node_guid); + +#endif /* __MLX5_VPORT_H__ */ diff --git a/kernel/include/linux/mm-arch-hooks.h b/kernel/include/linux/mm-arch-hooks.h new file mode 100644 index 000000000..4efc3f56e --- /dev/null +++ b/kernel/include/linux/mm-arch-hooks.h @@ -0,0 +1,25 @@ +/* + * Generic mm no-op hooks. + * + * Copyright (C) 2015, IBM Corporation + * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#ifndef _LINUX_MM_ARCH_HOOKS_H +#define _LINUX_MM_ARCH_HOOKS_H + +#include <asm/mm-arch-hooks.h> + +#ifndef arch_remap +static inline void arch_remap(struct mm_struct *mm, + unsigned long old_start, unsigned long old_end, + unsigned long new_start, unsigned long new_end) +{ +} +#define arch_remap arch_remap +#endif + +#endif /* _LINUX_MM_ARCH_HOOKS_H */ diff --git a/kernel/include/linux/mm.h b/kernel/include/linux/mm.h index b2085582d..00bad7793 100644 --- a/kernel/include/linux/mm.h +++ b/kernel/include/linux/mm.h @@ -20,6 +20,7 @@ #include <linux/shrinker.h> #include <linux/resource.h> #include <linux/page_ext.h> +#include <linux/err.h> struct mempolicy; struct anon_vma; @@ -27,6 +28,7 @@ struct anon_vma_chain; struct file_ra_state; struct user_struct; struct writeback_control; +struct bdi_writeback; #ifndef CONFIG_NEED_MULTIPLE_NODES /* Don't use mapnrs, do it properly */ extern unsigned long max_mapnr; @@ -123,8 +125,10 @@ extern unsigned int kobjsize(const void *objp); #define VM_MAYSHARE 0x00000080 #define VM_GROWSDOWN 0x00000100 /* general info on the segment */ +#define VM_UFFD_MISSING 0x00000200 /* missing pages tracking */ #define VM_PFNMAP 0x00000400 /* Page-ranges managed without "struct page", just pure PFN */ #define VM_DENYWRITE 0x00000800 /* ETXTBSY on write attempts.. */ +#define VM_UFFD_WP 0x00001000 /* wrprotect pages tracking */ #define VM_LOCKED 0x00002000 #define VM_IO 0x00004000 /* Memory mapped I/O or similar */ @@ -135,6 +139,7 @@ extern unsigned int kobjsize(const void *objp); #define VM_DONTCOPY 0x00020000 /* Do not copy this vma on fork */ #define VM_DONTEXPAND 0x00040000 /* Cannot expand with mremap() */ +#define VM_LOCKONFAULT 0x00080000 /* Lock the pages covered when they are faulted in */ #define VM_ACCOUNT 0x00100000 /* Is a VM accounted object */ #define VM_NORESERVE 0x00200000 /* should the VM suppress accounting */ #define VM_HUGETLB 0x00400000 /* Huge TLB Page VM */ @@ -198,6 +203,9 @@ extern unsigned int kobjsize(const void *objp); /* This mask defines which mm->def_flags a process can inherit its parent */ #define VM_INIT_DEF_MASK VM_NOHUGEPAGE +/* This mask is used to clear all the VMA flags used by mlock */ +#define VM_LOCKED_CLEAR_MASK (~(VM_LOCKED | VM_LOCKONFAULT)) + /* * mapping from the currently active vm_flags protection bits (the * low four bits) to a page protection mask.. @@ -244,7 +252,10 @@ struct vm_fault { struct vm_operations_struct { void (*open)(struct vm_area_struct * area); void (*close)(struct vm_area_struct * area); + int (*mremap)(struct vm_area_struct * area); int (*fault)(struct vm_area_struct *vma, struct vm_fault *vmf); + int (*pmd_fault)(struct vm_area_struct *, unsigned long address, + pmd_t *, unsigned int flags); void (*map_pages)(struct vm_area_struct *vma, struct vm_fault *vmf); /* notification that a previously read-only page is about to become @@ -303,18 +314,6 @@ struct inode; #define page_private(page) ((page)->private) #define set_page_private(page, v) ((page)->private = (v)) -/* It's valid only if the page is free path or free_list */ -static inline void set_freepage_migratetype(struct page *page, int migratetype) -{ - page->index = migratetype; -} - -/* It's valid only if the page is free path or free_list */ -static inline int get_freepage_migratetype(struct page *page) -{ - return page->index; -} - /* * FIXME: take this include out, include page-flags.h in * files which need it (119 of them) @@ -355,20 +354,15 @@ static inline int get_page_unless_zero(struct page *page) return atomic_inc_not_zero(&page->_count); } -/* - * Try to drop a ref unless the page has a refcount of one, return false if - * that is the case. - * This is to make sure that the refcount won't become zero after this drop. - * This can be called when MMU is off so it must not access - * any of the virtual mappings. - */ -static inline int put_page_unless_one(struct page *page) -{ - return atomic_add_unless(&page->_count, -1, 1); -} - extern int page_is_ram(unsigned long pfn); -extern int region_is_ram(resource_size_t phys_addr, unsigned long size); + +enum { + REGION_INTERSECTS, + REGION_DISJOINT, + REGION_MIXED, +}; + +int region_intersects(resource_size_t offset, size_t size, const char *type); /* Support for virtually mapped pages */ struct page *vmalloc_to_page(const void *addr); @@ -436,46 +430,6 @@ static inline void compound_unlock_irqrestore(struct page *page, #endif } -static inline struct page *compound_head_by_tail(struct page *tail) -{ - struct page *head = tail->first_page; - - /* - * page->first_page may be a dangling pointer to an old - * compound page, so recheck that it is still a tail - * page before returning. - */ - smp_rmb(); - if (likely(PageTail(tail))) - return head; - return tail; -} - -/* - * Since either compound page could be dismantled asynchronously in THP - * or we access asynchronously arbitrary positioned struct page, there - * would be tail flag race. To handle this race, we should call - * smp_rmb() before checking tail flag. compound_head_by_tail() did it. - */ -static inline struct page *compound_head(struct page *page) -{ - if (unlikely(PageTail(page))) - return compound_head_by_tail(page); - return page; -} - -/* - * If we access compound page synchronously such as access to - * allocated page, there is no need to handle tail flag race, so we can - * check tail flag directly without any synchronization primitive. - */ -static inline struct page *compound_head_fast(struct page *page) -{ - if (unlikely(PageTail(page))) - return page->first_page; - return page; -} - /* * The atomic page->_mapcount, starts from -1: so that transitions * both from it and to it can be tracked, using atomic_inc_and_test @@ -499,7 +453,7 @@ static inline int page_count(struct page *page) static inline bool __compound_tail_refcounted(struct page *page) { - return !PageSlab(page) && !PageHeadHuge(page); + return PageAnon(page) && !PageSlab(page) && !PageHeadHuge(page); } /* @@ -524,7 +478,7 @@ static inline void get_huge_page_tail(struct page *page) VM_BUG_ON_PAGE(!PageTail(page), page); VM_BUG_ON_PAGE(page_mapcount(page) < 0, page); VM_BUG_ON_PAGE(atomic_read(&page->_count) != 0, page); - if (compound_tail_refcounted(page->first_page)) + if (compound_tail_refcounted(compound_head(page))) atomic_inc(&page->_mapcount); } @@ -547,13 +501,7 @@ static inline struct page *virt_to_head_page(const void *x) { struct page *page = virt_to_page(x); - /* - * We don't need to worry about synchronization of tail flag - * when we call virt_to_head_page() since it is only called for - * already allocated page and this page won't be freed until - * this virt_to_head_page() is finished. So use _fast variant. - */ - return compound_head_fast(page); + return compound_head(page); } /* @@ -574,28 +522,42 @@ int split_free_page(struct page *page); /* * Compound pages have a destructor function. Provide a * prototype for that function and accessor functions. - * These are _only_ valid on the head of a PG_compound page. + * These are _only_ valid on the head of a compound page. */ +typedef void compound_page_dtor(struct page *); + +/* Keep the enum in sync with compound_page_dtors array in mm/page_alloc.c */ +enum compound_dtor_id { + NULL_COMPOUND_DTOR, + COMPOUND_PAGE_DTOR, +#ifdef CONFIG_HUGETLB_PAGE + HUGETLB_PAGE_DTOR, +#endif + NR_COMPOUND_DTORS, +}; +extern compound_page_dtor * const compound_page_dtors[]; static inline void set_compound_page_dtor(struct page *page, - compound_page_dtor *dtor) + enum compound_dtor_id compound_dtor) { - page[1].compound_dtor = dtor; + VM_BUG_ON_PAGE(compound_dtor >= NR_COMPOUND_DTORS, page); + page[1].compound_dtor = compound_dtor; } static inline compound_page_dtor *get_compound_page_dtor(struct page *page) { - return page[1].compound_dtor; + VM_BUG_ON_PAGE(page[1].compound_dtor >= NR_COMPOUND_DTORS, page); + return compound_page_dtors[page[1].compound_dtor]; } -static inline int compound_order(struct page *page) +static inline unsigned int compound_order(struct page *page) { if (!PageHead(page)) return 0; return page[1].compound_order; } -static inline void set_compound_order(struct page *page, unsigned long order) +static inline void set_compound_order(struct page *page, unsigned int order) { page[1].compound_order = order; } @@ -915,6 +877,27 @@ static inline void set_page_links(struct page *page, enum zone_type zone, #endif } +#ifdef CONFIG_MEMCG +static inline struct mem_cgroup *page_memcg(struct page *page) +{ + return page->mem_cgroup; +} + +static inline void set_page_memcg(struct page *page, struct mem_cgroup *memcg) +{ + page->mem_cgroup = memcg; +} +#else +static inline struct mem_cgroup *page_memcg(struct page *page) +{ + return NULL; +} + +static inline void set_page_memcg(struct page *page, struct mem_cgroup *memcg) +{ +} +#endif + /* * Some inline functions in vmstat.h depend on page_zone() */ @@ -1225,6 +1208,49 @@ long get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm, int write, int force, struct page **pages); int get_user_pages_fast(unsigned long start, int nr_pages, int write, struct page **pages); + +/* Container for pinned pfns / pages */ +struct frame_vector { + unsigned int nr_allocated; /* Number of frames we have space for */ + unsigned int nr_frames; /* Number of frames stored in ptrs array */ + bool got_ref; /* Did we pin pages by getting page ref? */ + bool is_pfns; /* Does array contain pages or pfns? */ + void *ptrs[0]; /* Array of pinned pfns / pages. Use + * pfns_vector_pages() or pfns_vector_pfns() + * for access */ +}; + +struct frame_vector *frame_vector_create(unsigned int nr_frames); +void frame_vector_destroy(struct frame_vector *vec); +int get_vaddr_frames(unsigned long start, unsigned int nr_pfns, + bool write, bool force, struct frame_vector *vec); +void put_vaddr_frames(struct frame_vector *vec); +int frame_vector_to_pages(struct frame_vector *vec); +void frame_vector_to_pfns(struct frame_vector *vec); + +static inline unsigned int frame_vector_count(struct frame_vector *vec) +{ + return vec->nr_frames; +} + +static inline struct page **frame_vector_pages(struct frame_vector *vec) +{ + if (vec->is_pfns) { + int err = frame_vector_to_pages(vec); + + if (err) + return ERR_PTR(err); + } + return (struct page **)(vec->ptrs); +} + +static inline unsigned long *frame_vector_pfns(struct frame_vector *vec) +{ + if (!vec->is_pfns) + frame_vector_to_pfns(vec); + return (unsigned long *)(vec->ptrs); +} + struct kvec; int get_kernel_pages(const struct kvec *iov, int nr_pages, int write, struct page **pages); @@ -1239,10 +1265,13 @@ int __set_page_dirty_nobuffers(struct page *page); int __set_page_dirty_no_writeback(struct page *page); int redirty_page_for_writepage(struct writeback_control *wbc, struct page *page); -void account_page_dirtied(struct page *page, struct address_space *mapping); -void account_page_cleaned(struct page *page, struct address_space *mapping); +void account_page_dirtied(struct page *page, struct address_space *mapping, + struct mem_cgroup *memcg); +void account_page_cleaned(struct page *page, struct address_space *mapping, + struct mem_cgroup *memcg, struct bdi_writeback *wb); int set_page_dirty(struct page *page); int set_page_dirty_lock(struct page *page); +void cancel_dirty_page(struct page *page); int clear_page_dirty_for_io(struct page *page); int get_cmdline(struct task_struct *task, char *buffer, int buflen); @@ -1253,6 +1282,11 @@ static inline int vma_growsdown(struct vm_area_struct *vma, unsigned long addr) return vma && (vma->vm_end == addr) && (vma->vm_flags & VM_GROWSDOWN); } +static inline bool vma_is_anonymous(struct vm_area_struct *vma) +{ + return !vma->vm_ops; +} + static inline int stack_guard_page_start(struct vm_area_struct *vma, unsigned long addr) { @@ -1506,8 +1540,7 @@ static inline bool ptlock_init(struct page *page) * with 0. Make sure nobody took it in use in between. * * It can happen if arch try to use slab for page table allocation: - * slab code uses page->slab_cache and page->first_page (for tail - * pages), which share storage with page->ptl. + * slab code uses page->slab_cache, which share storage with page->ptl. */ VM_BUG_ON_PAGE(*(unsigned long *)&page->ptl, page); if (!ptlock_alloc(page)) @@ -1544,8 +1577,10 @@ static inline void pgtable_init(void) static inline bool pgtable_page_ctor(struct page *page) { + if (!ptlock_init(page)) + return false; inc_zone_page_state(page, NR_PAGETABLE); - return ptlock_init(page); + return true; } static inline void pgtable_page_dtor(struct page *page) @@ -1659,6 +1694,8 @@ extern void free_highmem_page(struct page *page); extern void adjust_managed_page_count(struct page *page, long count); extern void mem_init_print_info(const char *str); +extern void reserve_bootmem_region(unsigned long start, unsigned long end); + /* Free the reserved page into the buddy system, so it gets managed. */ static inline void __free_reserved_page(struct page *page) { @@ -1748,7 +1785,8 @@ extern void sparse_memory_present_with_active_regions(int nid); #if !defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP) && \ !defined(CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID) -static inline int __early_pfn_to_nid(unsigned long pfn) +static inline int __early_pfn_to_nid(unsigned long pfn, + struct mminit_pfnnid_cache *state) { return 0; } @@ -1756,7 +1794,8 @@ static inline int __early_pfn_to_nid(unsigned long pfn) /* please see mm/page_alloc.c */ extern int __meminit early_pfn_to_nid(unsigned long pfn); /* there is a per-arch backend function. */ -extern int __meminit __early_pfn_to_nid(unsigned long pfn); +extern int __meminit __early_pfn_to_nid(unsigned long pfn, + struct mminit_pfnnid_cache *state); #endif extern void set_dma_reserve(unsigned long new_dma_reserve); @@ -1771,7 +1810,8 @@ extern void si_meminfo(struct sysinfo * val); extern void si_meminfo_node(struct sysinfo *val, int nid); extern __printf(3, 4) -void warn_alloc_failed(gfp_t gfp_mask, int order, const char *fmt, ...); +void warn_alloc_failed(gfp_t gfp_mask, unsigned int order, + const char *fmt, ...); extern void setup_per_cpu_pageset(void); @@ -1825,7 +1865,7 @@ extern int vma_adjust(struct vm_area_struct *vma, unsigned long start, extern struct vm_area_struct *vma_merge(struct mm_struct *, struct vm_area_struct *prev, unsigned long addr, unsigned long end, unsigned long vm_flags, struct anon_vma *, struct file *, pgoff_t, - struct mempolicy *); + struct mempolicy *, struct vm_userfaultfd_ctx); extern struct anon_vma *find_mergeable_anon_vma(struct vm_area_struct *); extern int split_vma(struct mm_struct *, struct vm_area_struct *, unsigned long addr, int new_below); @@ -1872,11 +1912,19 @@ extern unsigned long get_unmapped_area(struct file *, unsigned long, unsigned lo extern unsigned long mmap_region(struct file *file, unsigned long addr, unsigned long len, vm_flags_t vm_flags, unsigned long pgoff); -extern unsigned long do_mmap_pgoff(struct file *file, unsigned long addr, +extern unsigned long do_mmap(struct file *file, unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, - unsigned long pgoff, unsigned long *populate); + vm_flags_t vm_flags, unsigned long pgoff, unsigned long *populate); extern int do_munmap(struct mm_struct *, unsigned long, size_t); +static inline unsigned long +do_mmap_pgoff(struct file *file, unsigned long addr, + unsigned long len, unsigned long prot, unsigned long flags, + unsigned long pgoff, unsigned long *populate) +{ + return do_mmap(file, addr, len, prot, flags, 0, pgoff, populate); +} + #ifdef CONFIG_MMU extern int __mm_populate(unsigned long addr, unsigned long len, int ignore_errors); @@ -1962,8 +2010,6 @@ void page_cache_async_readahead(struct address_space *mapping, pgoff_t offset, unsigned long size); -unsigned long max_sane_readahead(unsigned long nr); - /* Generic expand stack which grows the stack according to GROWS{UP,DOWN} */ extern int expand_stack(struct vm_area_struct *vma, unsigned long address); @@ -2063,6 +2109,7 @@ static inline struct page *follow_page(struct vm_area_struct *vma, #define FOLL_NUMA 0x200 /* force NUMA hinting page fault */ #define FOLL_MIGRATION 0x400 /* wait for page to replace migration entry */ #define FOLL_TRIED 0x800 /* a retry, previous pass started an IO */ +#define FOLL_MLOCK 0x1000 /* lock present pages */ typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr, void *data); @@ -2174,12 +2221,48 @@ enum mf_flags { extern int memory_failure(unsigned long pfn, int trapno, int flags); extern void memory_failure_queue(unsigned long pfn, int trapno, int flags); extern int unpoison_memory(unsigned long pfn); +extern int get_hwpoison_page(struct page *page); +extern void put_hwpoison_page(struct page *page); extern int sysctl_memory_failure_early_kill; extern int sysctl_memory_failure_recovery; extern void shake_page(struct page *p, int access); extern atomic_long_t num_poisoned_pages; extern int soft_offline_page(struct page *page, int flags); + +/* + * Error handlers for various types of pages. + */ +enum mf_result { + MF_IGNORED, /* Error: cannot be handled */ + MF_FAILED, /* Error: handling failed */ + MF_DELAYED, /* Will be handled later */ + MF_RECOVERED, /* Successfully recovered */ +}; + +enum mf_action_page_type { + MF_MSG_KERNEL, + MF_MSG_KERNEL_HIGH_ORDER, + MF_MSG_SLAB, + MF_MSG_DIFFERENT_COMPOUND, + MF_MSG_POISONED_HUGE, + MF_MSG_HUGE, + MF_MSG_FREE_HUGE, + MF_MSG_UNMAP_FAILED, + MF_MSG_DIRTY_SWAPCACHE, + MF_MSG_CLEAN_SWAPCACHE, + MF_MSG_DIRTY_MLOCKED_LRU, + MF_MSG_CLEAN_MLOCKED_LRU, + MF_MSG_DIRTY_UNEVICTABLE_LRU, + MF_MSG_CLEAN_UNEVICTABLE_LRU, + MF_MSG_DIRTY_LRU, + MF_MSG_CLEAN_LRU, + MF_MSG_TRUNCATED_LRU, + MF_MSG_BUDDY, + MF_MSG_BUDDY_2ND, + MF_MSG_UNKNOWN, +}; + #if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLBFS) extern void clear_huge_page(struct page *page, unsigned long addr, diff --git a/kernel/include/linux/mm_types.h b/kernel/include/linux/mm_types.h index 89c047144..b238ebfbb 100644 --- a/kernel/include/linux/mm_types.h +++ b/kernel/include/linux/mm_types.h @@ -29,8 +29,6 @@ struct mem_cgroup; IS_ENABLED(CONFIG_ARCH_ENABLE_SPLIT_PMD_PTLOCK)) #define ALLOC_SPLIT_PTLOCKS (SPINLOCK_SIZE > BITS_PER_LONG/8) -typedef void compound_page_dtor(struct page *); - /* * Each physical page in the system has a struct page associated with * it to keep track of whatever it is we are using the page for at the @@ -114,7 +112,13 @@ struct page { }; }; - /* Third double word block */ + /* + * Third double word block + * + * WARNING: bit 0 of the first word encode PageTail(). That means + * the rest users of the storage space MUST NOT use the bit to + * avoid collision and false-positive PageTail(). + */ union { struct list_head lru; /* Pageout list, eg. active_list * protected by zone->lru_lock ! @@ -132,18 +136,37 @@ struct page { #endif }; - struct slab *slab_page; /* slab fields */ struct rcu_head rcu_head; /* Used by SLAB * when destroying via RCU */ - /* First tail page of compound page */ + /* Tail pages of compound page */ struct { - compound_page_dtor *compound_dtor; - unsigned long compound_order; + unsigned long compound_head; /* If bit zero is set */ + + /* First tail page only */ +#ifdef CONFIG_64BIT + /* + * On 64 bit system we have enough space in struct page + * to encode compound_dtor and compound_order with + * unsigned int. It can help compiler generate better or + * smaller code on some archtectures. + */ + unsigned int compound_dtor; + unsigned int compound_order; +#else + unsigned short int compound_dtor; + unsigned short int compound_order; +#endif }; #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && USE_SPLIT_PMD_PTLOCKS - pgtable_t pmd_huge_pte; /* protected by page->ptl */ + struct { + unsigned long __pad; /* do not overlay pmd_huge_pte + * with compound_head to avoid + * possible bit 0 collision. + */ + pgtable_t pmd_huge_pte; /* protected by page->ptl */ + }; #endif }; @@ -164,7 +187,6 @@ struct page { #endif #endif struct kmem_cache *slab_cache; /* SL[AU]B: Pointer to slab */ - struct page *first_page; /* Compound tail pages */ }; #ifdef CONFIG_MEMCG @@ -218,7 +240,25 @@ struct page_frag { #endif }; -typedef unsigned long __nocast vm_flags_t; +#define PAGE_FRAG_CACHE_MAX_SIZE __ALIGN_MASK(32768, ~PAGE_MASK) +#define PAGE_FRAG_CACHE_MAX_ORDER get_order(PAGE_FRAG_CACHE_MAX_SIZE) + +struct page_frag_cache { + void * va; +#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) + __u16 offset; + __u16 size; +#else + __u32 offset; +#endif + /* we maintain a pagecount bias, so that we dont dirty cache line + * containing page->_count every time we allocate a fragment. + */ + unsigned int pagecnt_bias; + bool pfmemalloc; +}; + +typedef unsigned long vm_flags_t; /* * A region containing a mapping of a non-memory backed file under NOMMU @@ -239,6 +279,16 @@ struct vm_region { * this region */ }; +#ifdef CONFIG_USERFAULTFD +#define NULL_VM_UFFD_CTX ((struct vm_userfaultfd_ctx) { NULL, }) +struct vm_userfaultfd_ctx { + struct userfaultfd_ctx *ctx; +}; +#else /* CONFIG_USERFAULTFD */ +#define NULL_VM_UFFD_CTX ((struct vm_userfaultfd_ctx) {}) +struct vm_userfaultfd_ctx {}; +#endif /* CONFIG_USERFAULTFD */ + /* * This struct defines a memory VMM memory area. There is one of these * per VM-area/task. A VM area is any part of the process virtual memory @@ -305,6 +355,7 @@ struct vm_area_struct { #ifdef CONFIG_NUMA struct mempolicy *vm_policy; /* NUMA policy for the VMA */ #endif + struct vm_userfaultfd_ctx vm_userfaultfd_ctx; }; struct core_thread { @@ -461,6 +512,9 @@ struct mm_struct { /* address of the bounds directory */ void __user *bd_addr; #endif +#ifdef CONFIG_HUGETLB_PAGE + atomic_long_t hugetlb_usage; +#endif }; static inline void mm_init_cpumask(struct mm_struct *mm) @@ -529,6 +583,7 @@ enum tlb_flush_reason { TLB_REMOTE_SHOOTDOWN, TLB_LOCAL_SHOOTDOWN, TLB_LOCAL_MM_SHOOTDOWN, + TLB_REMOTE_SEND_IPI, NR_TLB_FLUSH_REASONS, }; diff --git a/kernel/include/linux/mmc/card.h b/kernel/include/linux/mmc/card.h index 19f0175c0..eb0151bac 100644 --- a/kernel/include/linux/mmc/card.h +++ b/kernel/include/linux/mmc/card.h @@ -97,6 +97,7 @@ struct mmc_ext_csd { u8 raw_erased_mem_count; /* 181 */ u8 raw_ext_csd_structure; /* 194 */ u8 raw_card_type; /* 196 */ + u8 raw_driver_strength; /* 197 */ u8 out_of_int_time; /* 198 */ u8 raw_pwr_cl_52_195; /* 200 */ u8 raw_pwr_cl_26_195; /* 201 */ @@ -268,7 +269,6 @@ struct mmc_card { /* for byte mode */ #define MMC_QUIRK_NONSTD_SDIO (1<<2) /* non-standard SDIO card attached */ /* (missing CIA registers) */ -#define MMC_QUIRK_BROKEN_CLK_GATING (1<<3) /* clock gating the sdio bus will make card fail */ #define MMC_QUIRK_NONSTD_FUNC_IF (1<<4) /* SDIO card has nonstd function interfaces */ #define MMC_QUIRK_DISABLE_CD (1<<5) /* disconnect CD/DAT[3] resistor */ #define MMC_QUIRK_INAND_CMD38 (1<<6) /* iNAND devices have broken CMD38 */ @@ -278,10 +278,13 @@ struct mmc_card { #define MMC_QUIRK_LONG_READ_TIME (1<<9) /* Data read time > CSD says */ #define MMC_QUIRK_SEC_ERASE_TRIM_BROKEN (1<<10) /* Skip secure for erase/trim */ #define MMC_QUIRK_BROKEN_IRQ_POLLING (1<<11) /* Polling SDIO_CCCR_INTx could create a fake interrupt */ +#define MMC_QUIRK_TRIM_BROKEN (1<<12) /* Skip trim */ + unsigned int erase_size; /* erase size in sectors */ unsigned int erase_shift; /* if erase unit is power 2 */ unsigned int pref_erase; /* in sectors */ + unsigned int eg_boundary; /* don't cross erase-group boundaries */ u8 erased_byte; /* value of erased bytes */ u32 raw_cid[4]; /* raw card CID */ @@ -305,6 +308,7 @@ struct mmc_card { unsigned int sd_bus_speed; /* Bus Speed Mode set for the card */ unsigned int mmc_avail_type; /* supported device type by both host and card */ + unsigned int drive_strength; /* for UHS-I, HS200 or HS400 */ struct dentry *debugfs_root; struct mmc_part part[MMC_NUM_PHY_PARTITION]; /* physical partitions */ diff --git a/kernel/include/linux/mmc/core.h b/kernel/include/linux/mmc/core.h index de722d4e9..37967b6da 100644 --- a/kernel/include/linux/mmc/core.h +++ b/kernel/include/linux/mmc/core.h @@ -121,6 +121,7 @@ struct mmc_data { struct mmc_request *mrq; /* associated request */ unsigned int sg_len; /* size of scatter list */ + int sg_count; /* mapped sg entries */ struct scatterlist *sg; /* I/O scatter list */ s32 host_cookie; /* host private data */ }; @@ -151,10 +152,8 @@ extern int mmc_app_cmd(struct mmc_host *, struct mmc_card *); extern int mmc_wait_for_app_cmd(struct mmc_host *, struct mmc_card *, struct mmc_command *, int); extern void mmc_start_bkops(struct mmc_card *card, bool from_exception); -extern int __mmc_switch(struct mmc_card *, u8, u8, u8, unsigned int, bool, - bool, bool); extern int mmc_switch(struct mmc_card *, u8, u8, u8, unsigned int); -extern int mmc_send_tuning(struct mmc_host *host); +extern int mmc_send_tuning(struct mmc_host *host, u32 opcode, int *cmd_error); extern int mmc_get_ext_csd(struct mmc_card *card, u8 **new_ext_csd); #define MMC_ERASE_ARG 0x00000000 diff --git a/kernel/include/linux/mmc/dw_mmc.h b/kernel/include/linux/mmc/dw_mmc.h index 12111993a..f67b2ec18 100644 --- a/kernel/include/linux/mmc/dw_mmc.h +++ b/kernel/include/linux/mmc/dw_mmc.h @@ -16,6 +16,7 @@ #include <linux/scatterlist.h> #include <linux/mmc/core.h> +#include <linux/dmaengine.h> #define MAX_MCI_SLOTS 2 @@ -40,6 +41,17 @@ enum { struct mmc_data; +enum { + TRANS_MODE_PIO = 0, + TRANS_MODE_IDMAC, + TRANS_MODE_EDMAC +}; + +struct dw_mci_dma_slave { + struct dma_chan *ch; + enum dma_transfer_direction direction; +}; + /** * struct dw_mci - MMC controller state shared between all slots * @lock: Spinlock protecting the queue and associated data. @@ -98,6 +110,7 @@ struct mmc_data; * @irq_flags: The flags to be passed to request_irq. * @irq: The irq value to be passed to request_irq. * @sdio_id0: Number of slot0 in the SDIO interrupt registers. + * @dto_timer: Timer for broken data transfer over scheme. * * Locking * ======= @@ -153,11 +166,14 @@ struct dw_mci { dma_addr_t sg_dma; void *sg_cpu; const struct dw_mci_dma_ops *dma_ops; -#ifdef CONFIG_MMC_DW_IDMAC + /* For idmac */ unsigned int ring_size; -#else - struct dw_mci_dma_data *dma_data; -#endif + + /* For edmac */ + struct dw_mci_dma_slave *dms; + /* Registers's physical base address */ + void *phy_regs; + u32 cmd_status; u32 data_status; u32 stop_cmdr; @@ -204,14 +220,15 @@ struct dw_mci { int sdio_id0; struct timer_list cmd11_timer; + struct timer_list dto_timer; }; /* DMA ops for Internal/External DMAC interface */ struct dw_mci_dma_ops { /* DMA Ops */ int (*init)(struct dw_mci *host); - void (*start)(struct dw_mci *host, unsigned int sg_len); - void (*complete)(struct dw_mci *host); + int (*start)(struct dw_mci *host, unsigned int sg_len); + void (*complete)(void *host); void (*stop)(struct dw_mci *host); void (*cleanup)(struct dw_mci *host); void (*exit)(struct dw_mci *host); @@ -226,12 +243,8 @@ struct dw_mci_dma_ops { #define DW_MCI_QUIRK_HIGHSPEED BIT(2) /* Unreliable card detection */ #define DW_MCI_QUIRK_BROKEN_CARD_DETECTION BIT(3) -/* No write protect */ -#define DW_MCI_QUIRK_NO_WRITE_PROTECT BIT(4) - -/* Slot level quirks */ -/* This slot has no write protect */ -#define DW_MCI_SLOT_QUIRK_NO_WRITE_PROTECT BIT(0) +/* Timer for broken data transfer over scheme */ +#define DW_MCI_QUIRK_BROKEN_DTO BIT(4) struct dma_pdata; @@ -265,7 +278,6 @@ struct dw_mci_board { struct dw_mci_dma_ops *dma_ops; struct dma_pdata *data; - struct block_settings *blk_settings; }; #endif /* LINUX_MMC_DW_MMC_H */ diff --git a/kernel/include/linux/mmc/host.h b/kernel/include/linux/mmc/host.h index b5bedaec6..8673ffe3d 100644 --- a/kernel/include/linux/mmc/host.h +++ b/kernel/include/linux/mmc/host.h @@ -12,6 +12,7 @@ #include <linux/leds.h> #include <linux/mutex.h> +#include <linux/timer.h> #include <linux/sched.h> #include <linux/device.h> #include <linux/fault-inject.h> @@ -131,7 +132,9 @@ struct mmc_host_ops { /* Prepare HS400 target operating frequency depending host driver */ int (*prepare_hs400_tuning)(struct mmc_host *host, struct mmc_ios *ios); - int (*select_drive_strength)(unsigned int max_dtr, int host_drv, int card_drv); + int (*select_drive_strength)(struct mmc_card *card, + unsigned int max_dtr, int host_drv, + int card_drv, int *drv_type); void (*hw_reset)(struct mmc_host *host); void (*card_event)(struct mmc_host *host); @@ -285,21 +288,10 @@ struct mmc_host { MMC_CAP2_HS400_1_2V) #define MMC_CAP2_HSX00_1_2V (MMC_CAP2_HS200_1_2V_SDR | MMC_CAP2_HS400_1_2V) #define MMC_CAP2_SDIO_IRQ_NOTHREAD (1 << 17) +#define MMC_CAP2_NO_WRITE_PROTECT (1 << 18) /* No physical write protect pin, assume that card is always read-write */ mmc_pm_flag_t pm_caps; /* supported pm features */ -#ifdef CONFIG_MMC_CLKGATE - int clk_requests; /* internal reference counter */ - unsigned int clk_delay; /* number of MCI clk hold cycles */ - bool clk_gated; /* clock gated */ - struct delayed_work clk_gate_work; /* delayed clock gate */ - unsigned int clk_old; /* old clock value cache */ - spinlock_t clk_lock; /* lock for clk fields */ - struct mutex clk_gate_mutex; /* mutex for clock gating */ - struct device_attribute clkgate_delay_attr; - unsigned long clkgate_delay; -#endif - /* host specific block data */ unsigned int max_seg_size; /* see blk_queue_max_segment_size */ unsigned short max_segs; /* see blk_queue_max_segments */ @@ -321,10 +313,18 @@ struct mmc_host { #ifdef CONFIG_MMC_DEBUG unsigned int removed:1; /* host is being removed */ #endif + unsigned int can_retune:1; /* re-tuning can be used */ + unsigned int doing_retune:1; /* re-tuning in progress */ + unsigned int retune_now:1; /* do re-tuning at next req */ int rescan_disable; /* disable card detection */ int rescan_entered; /* used with nonremovable devices */ + int need_retune; /* re-tuning is needed */ + int hold_retune; /* hold off re-tuning */ + unsigned int retune_period; /* re-tuning period in secs */ + struct timer_list retune_timer; /* for periodic re-tuning */ + bool trigger_card_event; /* card_event necessary */ struct mmc_card *card; /* device attached to this host */ @@ -400,7 +400,8 @@ static inline void mmc_signal_sdio_irq(struct mmc_host *host) { host->ops->enable_sdio_irq(host, 0); host->sdio_irq_pending = true; - wake_up_process(host->sdio_irq_thread); + if (host->sdio_irq_thread) + wake_up_process(host->sdio_irq_thread); } void sdio_run_irqs(struct mmc_host *host); @@ -410,6 +411,7 @@ int mmc_regulator_get_ocrmask(struct regulator *supply); int mmc_regulator_set_ocr(struct mmc_host *mmc, struct regulator *supply, unsigned short vdd_bit); +int mmc_regulator_set_vqmmc(struct mmc_host *mmc, struct mmc_ios *ios); #else static inline int mmc_regulator_get_ocrmask(struct regulator *supply) { @@ -422,6 +424,12 @@ static inline int mmc_regulator_set_ocr(struct mmc_host *mmc, { return 0; } + +static inline int mmc_regulator_set_vqmmc(struct mmc_host *mmc, + struct mmc_ios *ios) +{ + return -EINVAL; +} #endif int mmc_regulator_get_supply(struct mmc_host *mmc); @@ -466,26 +474,6 @@ static inline int mmc_host_packed_wr(struct mmc_host *host) return host->caps2 & MMC_CAP2_PACKED_WR; } -#ifdef CONFIG_MMC_CLKGATE -void mmc_host_clk_hold(struct mmc_host *host); -void mmc_host_clk_release(struct mmc_host *host); -unsigned int mmc_host_clk_rate(struct mmc_host *host); - -#else -static inline void mmc_host_clk_hold(struct mmc_host *host) -{ -} - -static inline void mmc_host_clk_release(struct mmc_host *host) -{ -} - -static inline unsigned int mmc_host_clk_rate(struct mmc_host *host) -{ - return host->ios.clock; -} -#endif - static inline int mmc_card_hs(struct mmc_card *card) { return card->host->ios.timing == MMC_TIMING_SD_HS || @@ -513,4 +501,18 @@ static inline bool mmc_card_hs400(struct mmc_card *card) return card->host->ios.timing == MMC_TIMING_MMC_HS400; } +void mmc_retune_timer_stop(struct mmc_host *host); + +static inline void mmc_retune_needed(struct mmc_host *host) +{ + if (host->can_retune) + host->need_retune = 1; +} + +static inline void mmc_retune_recheck(struct mmc_host *host) +{ + if (host->hold_retune <= 1) + host->retune_now = 1; +} + #endif /* LINUX_MMC_HOST_H */ diff --git a/kernel/include/linux/mmc/mmc.h b/kernel/include/linux/mmc/mmc.h index 124f56211..15f2c4a0a 100644 --- a/kernel/include/linux/mmc/mmc.h +++ b/kernel/include/linux/mmc/mmc.h @@ -302,6 +302,7 @@ struct _mmc_csd { #define EXT_CSD_REV 192 /* RO */ #define EXT_CSD_STRUCTURE 194 /* RO */ #define EXT_CSD_CARD_TYPE 196 /* RO */ +#define EXT_CSD_DRIVER_STRENGTH 197 /* RO */ #define EXT_CSD_OUT_OF_INTERRUPT_TIME 198 /* RO */ #define EXT_CSD_PART_SWITCH_TIME 199 /* RO */ #define EXT_CSD_PWR_CL_52_195 200 /* RO */ @@ -390,6 +391,7 @@ struct _mmc_csd { #define EXT_CSD_TIMING_HS 1 /* High speed */ #define EXT_CSD_TIMING_HS200 2 /* HS200 */ #define EXT_CSD_TIMING_HS400 3 /* HS400 */ +#define EXT_CSD_DRV_STR_SHIFT 4 /* Driver Strength shift */ #define EXT_CSD_SEC_ER_EN BIT(0) #define EXT_CSD_SEC_BD_BLK_EN BIT(2) @@ -441,4 +443,6 @@ struct _mmc_csd { #define MMC_SWITCH_MODE_CLEAR_BITS 0x02 /* Clear bits which are 1 in value */ #define MMC_SWITCH_MODE_WRITE_BYTE 0x03 /* Set target to value */ +#define mmc_driver_type_mask(n) (1 << (n)) + #endif /* LINUX_MMC_MMC_H */ diff --git a/kernel/include/linux/mmc/sdhci-pci-data.h b/kernel/include/linux/mmc/sdhci-pci-data.h index 8959604a1..fda15b6d4 100644 --- a/kernel/include/linux/mmc/sdhci-pci-data.h +++ b/kernel/include/linux/mmc/sdhci-pci-data.h @@ -15,4 +15,6 @@ struct sdhci_pci_data { extern struct sdhci_pci_data *(*sdhci_pci_get_data)(struct pci_dev *pdev, int slotno); +extern int sdhci_pci_spt_drive_strength; + #endif diff --git a/kernel/include/linux/mmdebug.h b/kernel/include/linux/mmdebug.h index 877ef226f..772362adf 100644 --- a/kernel/include/linux/mmdebug.h +++ b/kernel/include/linux/mmdebug.h @@ -1,6 +1,7 @@ #ifndef LINUX_MM_DEBUG_H #define LINUX_MM_DEBUG_H 1 +#include <linux/bug.h> #include <linux/stringify.h> struct page; diff --git a/kernel/include/linux/mmiotrace.h b/kernel/include/linux/mmiotrace.h index c5d52780d..3ba327af0 100644 --- a/kernel/include/linux/mmiotrace.h +++ b/kernel/include/linux/mmiotrace.h @@ -106,6 +106,6 @@ extern void enable_mmiotrace(void); extern void disable_mmiotrace(void); extern void mmio_trace_rw(struct mmiotrace_rw *rw); extern void mmio_trace_mapping(struct mmiotrace_map *map); -extern int mmio_trace_printk(const char *fmt, va_list args); +extern __printf(1, 0) int mmio_trace_printk(const char *fmt, va_list args); #endif /* _LINUX_MMIOTRACE_H */ diff --git a/kernel/include/linux/mmu_notifier.h b/kernel/include/linux/mmu_notifier.h index 95243d28a..a1a210d59 100644 --- a/kernel/include/linux/mmu_notifier.h +++ b/kernel/include/linux/mmu_notifier.h @@ -66,6 +66,16 @@ struct mmu_notifier_ops { unsigned long end); /* + * clear_young is a lightweight version of clear_flush_young. Like the + * latter, it is supposed to test-and-clear the young/accessed bitflag + * in the secondary pte, but it may omit flushing the secondary tlb. + */ + int (*clear_young)(struct mmu_notifier *mn, + struct mm_struct *mm, + unsigned long start, + unsigned long end); + + /* * test_young is called to check the young/accessed bitflag in * the secondary pte. This is used to know if the page is * frequently used without actually clearing the flag or tearing @@ -203,6 +213,9 @@ extern void __mmu_notifier_release(struct mm_struct *mm); extern int __mmu_notifier_clear_flush_young(struct mm_struct *mm, unsigned long start, unsigned long end); +extern int __mmu_notifier_clear_young(struct mm_struct *mm, + unsigned long start, + unsigned long end); extern int __mmu_notifier_test_young(struct mm_struct *mm, unsigned long address); extern void __mmu_notifier_change_pte(struct mm_struct *mm, @@ -231,6 +244,15 @@ static inline int mmu_notifier_clear_flush_young(struct mm_struct *mm, return 0; } +static inline int mmu_notifier_clear_young(struct mm_struct *mm, + unsigned long start, + unsigned long end) +{ + if (mm_has_notifiers(mm)) + return __mmu_notifier_clear_young(mm, start, end); + return 0; +} + static inline int mmu_notifier_test_young(struct mm_struct *mm, unsigned long address) { @@ -311,6 +333,28 @@ static inline void mmu_notifier_mm_destroy(struct mm_struct *mm) __young; \ }) +#define ptep_clear_young_notify(__vma, __address, __ptep) \ +({ \ + int __young; \ + struct vm_area_struct *___vma = __vma; \ + unsigned long ___address = __address; \ + __young = ptep_test_and_clear_young(___vma, ___address, __ptep);\ + __young |= mmu_notifier_clear_young(___vma->vm_mm, ___address, \ + ___address + PAGE_SIZE); \ + __young; \ +}) + +#define pmdp_clear_young_notify(__vma, __address, __pmdp) \ +({ \ + int __young; \ + struct vm_area_struct *___vma = __vma; \ + unsigned long ___address = __address; \ + __young = pmdp_test_and_clear_young(___vma, ___address, __pmdp);\ + __young |= mmu_notifier_clear_young(___vma->vm_mm, ___address, \ + ___address + PMD_SIZE); \ + __young; \ +}) + #define ptep_clear_flush_notify(__vma, __address, __ptep) \ ({ \ unsigned long ___addr = __address & PAGE_MASK; \ @@ -324,25 +368,25 @@ static inline void mmu_notifier_mm_destroy(struct mm_struct *mm) ___pte; \ }) -#define pmdp_clear_flush_notify(__vma, __haddr, __pmd) \ +#define pmdp_huge_clear_flush_notify(__vma, __haddr, __pmd) \ ({ \ unsigned long ___haddr = __haddr & HPAGE_PMD_MASK; \ struct mm_struct *___mm = (__vma)->vm_mm; \ pmd_t ___pmd; \ \ - ___pmd = pmdp_clear_flush(__vma, __haddr, __pmd); \ + ___pmd = pmdp_huge_clear_flush(__vma, __haddr, __pmd); \ mmu_notifier_invalidate_range(___mm, ___haddr, \ ___haddr + HPAGE_PMD_SIZE); \ \ ___pmd; \ }) -#define pmdp_get_and_clear_notify(__mm, __haddr, __pmd) \ +#define pmdp_huge_get_and_clear_notify(__mm, __haddr, __pmd) \ ({ \ unsigned long ___haddr = __haddr & HPAGE_PMD_MASK; \ pmd_t ___pmd; \ \ - ___pmd = pmdp_get_and_clear(__mm, __haddr, __pmd); \ + ___pmd = pmdp_huge_get_and_clear(__mm, __haddr, __pmd); \ mmu_notifier_invalidate_range(__mm, ___haddr, \ ___haddr + HPAGE_PMD_SIZE); \ \ @@ -427,9 +471,11 @@ static inline void mmu_notifier_mm_destroy(struct mm_struct *mm) #define ptep_clear_flush_young_notify ptep_clear_flush_young #define pmdp_clear_flush_young_notify pmdp_clear_flush_young +#define ptep_clear_young_notify ptep_test_and_clear_young +#define pmdp_clear_young_notify pmdp_test_and_clear_young #define ptep_clear_flush_notify ptep_clear_flush -#define pmdp_clear_flush_notify pmdp_clear_flush -#define pmdp_get_and_clear_notify pmdp_get_and_clear +#define pmdp_huge_clear_flush_notify pmdp_huge_clear_flush +#define pmdp_huge_get_and_clear_notify pmdp_huge_get_and_clear #define set_pte_at_notify set_pte_at #endif /* CONFIG_MMU_NOTIFIER */ diff --git a/kernel/include/linux/mmzone.h b/kernel/include/linux/mmzone.h index 54d74f6eb..e23a9e704 100644 --- a/kernel/include/linux/mmzone.h +++ b/kernel/include/linux/mmzone.h @@ -37,10 +37,10 @@ enum { MIGRATE_UNMOVABLE, - MIGRATE_RECLAIMABLE, MIGRATE_MOVABLE, + MIGRATE_RECLAIMABLE, MIGRATE_PCPTYPES, /* the number of types on the pcp lists */ - MIGRATE_RESERVE = MIGRATE_PCPTYPES, + MIGRATE_HIGHATOMIC = MIGRATE_PCPTYPES, #ifdef CONFIG_CMA /* * MIGRATE_CMA migration type is designed to mimic the way @@ -319,7 +319,11 @@ enum zone_type { ZONE_HIGHMEM, #endif ZONE_MOVABLE, +#ifdef CONFIG_ZONE_DEVICE + ZONE_DEVICE, +#endif __MAX_NR_ZONES + }; #ifndef __GENERATING_BOUNDS_H @@ -330,13 +334,16 @@ struct zone { /* zone watermarks, access with *_wmark_pages(zone) macros */ unsigned long watermark[NR_WMARK]; + unsigned long nr_reserved_highatomic; + /* - * We don't know if the memory that we're going to allocate will be freeable - * or/and it will be released eventually, so to avoid totally wasting several - * GB of ram we must reserve some of the lower zone memory (otherwise we risk - * to run OOM on the lower zones despite there's tons of freeable ram - * on the higher zones). This array is recalculated at runtime if the - * sysctl_lowmem_reserve_ratio sysctl changes. + * We don't know if the memory that we're going to allocate will be + * freeable or/and it will be released eventually, so to avoid totally + * wasting several GB of ram we must reserve some of the lower zone + * memory (otherwise we risk to run OOM on the lower zones despite + * there being tons of freeable ram on the higher zones). This array is + * recalculated at runtime if the sysctl_lowmem_reserve_ratio sysctl + * changes. */ long lowmem_reserve[MAX_NR_ZONES]; @@ -425,12 +432,6 @@ struct zone { const char *name; - /* - * Number of MIGRATE_RESERVE page block. To maintain for just - * optimization. Protected by zone->lock. - */ - int nr_migrate_reserve_block; - #ifdef CONFIG_MEMORY_ISOLATION /* * Number of isolated pageblock. It is used to solve incorrect @@ -585,75 +586,8 @@ static inline bool zone_is_empty(struct zone *zone) * [1] : No fallback (__GFP_THISNODE) */ #define MAX_ZONELISTS 2 - - -/* - * We cache key information from each zonelist for smaller cache - * footprint when scanning for free pages in get_page_from_freelist(). - * - * 1) The BITMAP fullzones tracks which zones in a zonelist have come - * up short of free memory since the last time (last_fullzone_zap) - * we zero'd fullzones. - * 2) The array z_to_n[] maps each zone in the zonelist to its node - * id, so that we can efficiently evaluate whether that node is - * set in the current tasks mems_allowed. - * - * Both fullzones and z_to_n[] are one-to-one with the zonelist, - * indexed by a zones offset in the zonelist zones[] array. - * - * The get_page_from_freelist() routine does two scans. During the - * first scan, we skip zones whose corresponding bit in 'fullzones' - * is set or whose corresponding node in current->mems_allowed (which - * comes from cpusets) is not set. During the second scan, we bypass - * this zonelist_cache, to ensure we look methodically at each zone. - * - * Once per second, we zero out (zap) fullzones, forcing us to - * reconsider nodes that might have regained more free memory. - * The field last_full_zap is the time we last zapped fullzones. - * - * This mechanism reduces the amount of time we waste repeatedly - * reexaming zones for free memory when they just came up low on - * memory momentarilly ago. - * - * The zonelist_cache struct members logically belong in struct - * zonelist. However, the mempolicy zonelists constructed for - * MPOL_BIND are intentionally variable length (and usually much - * shorter). A general purpose mechanism for handling structs with - * multiple variable length members is more mechanism than we want - * here. We resort to some special case hackery instead. - * - * The MPOL_BIND zonelists don't need this zonelist_cache (in good - * part because they are shorter), so we put the fixed length stuff - * at the front of the zonelist struct, ending in a variable length - * zones[], as is needed by MPOL_BIND. - * - * Then we put the optional zonelist cache on the end of the zonelist - * struct. This optional stuff is found by a 'zlcache_ptr' pointer in - * the fixed length portion at the front of the struct. This pointer - * both enables us to find the zonelist cache, and in the case of - * MPOL_BIND zonelists, (which will just set the zlcache_ptr to NULL) - * to know that the zonelist cache is not there. - * - * The end result is that struct zonelists come in two flavors: - * 1) The full, fixed length version, shown below, and - * 2) The custom zonelists for MPOL_BIND. - * The custom MPOL_BIND zonelists have a NULL zlcache_ptr and no zlcache. - * - * Even though there may be multiple CPU cores on a node modifying - * fullzones or last_full_zap in the same zonelist_cache at the same - * time, we don't lock it. This is just hint data - if it is wrong now - * and then, the allocator will still function, perhaps a bit slower. - */ - - -struct zonelist_cache { - unsigned short z_to_n[MAX_ZONES_PER_ZONELIST]; /* zone->nid */ - DECLARE_BITMAP(fullzones, MAX_ZONES_PER_ZONELIST); /* zone full? */ - unsigned long last_full_zap; /* when last zap'd (jiffies) */ -}; #else #define MAX_ZONELISTS 1 -struct zonelist_cache; #endif /* @@ -671,9 +605,6 @@ struct zoneref { * allocation, the other zones are fallback zones, in decreasing * priority. * - * If zlcache_ptr is not NULL, then it is just the address of zlcache, - * as explained above. If zlcache_ptr is NULL, there is no zlcache. - * * * To speed the reading of the zonelist, the zonerefs contain the zone index * of the entry being read. Helper functions to access information given * a struct zoneref are @@ -683,21 +614,9 @@ struct zoneref { * zonelist_node_idx() - Return the index of the node for an entry */ struct zonelist { - struct zonelist_cache *zlcache_ptr; // NULL or &zlcache struct zoneref _zonerefs[MAX_ZONES_PER_ZONELIST + 1]; -#ifdef CONFIG_NUMA - struct zonelist_cache zlcache; // optional ... -#endif }; -#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP -struct node_active_region { - unsigned long start_pfn; - unsigned long end_pfn; - int nid; -}; -#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ - #ifndef CONFIG_DISCONTIGMEM /* The array of struct pages - for discontigmem use pgdat->lmem_map */ extern struct page *mem_map; @@ -762,6 +681,14 @@ typedef struct pglist_data { /* Number of pages migrated during the rate limiting time interval */ unsigned long numabalancing_migrate_nr_pages; #endif + +#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT + /* + * If memory initialisation on large machines is deferred then this + * is the first PFN that needs to be initialised. + */ + unsigned long first_deferred_pfn; +#endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */ } pg_data_t; #define node_present_pages(nid) (NODE_DATA(nid)->node_present_pages) @@ -786,6 +713,25 @@ static inline bool pgdat_is_empty(pg_data_t *pgdat) return !pgdat->node_start_pfn && !pgdat->node_spanned_pages; } +static inline int zone_id(const struct zone *zone) +{ + struct pglist_data *pgdat = zone->zone_pgdat; + + return zone - pgdat->node_zones; +} + +#ifdef CONFIG_ZONE_DEVICE +static inline bool is_dev_zone(const struct zone *zone) +{ + return zone_id(zone) == ZONE_DEVICE; +} +#else +static inline bool is_dev_zone(const struct zone *zone) +{ + return false; +} +#endif + #include <linux/memory_hotplug.h> extern struct mutex zonelists_mutex; @@ -794,14 +740,13 @@ void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx); bool zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, int classzone_idx, int alloc_flags); bool zone_watermark_ok_safe(struct zone *z, unsigned int order, - unsigned long mark, int classzone_idx, int alloc_flags); + unsigned long mark, int classzone_idx); enum memmap_context { MEMMAP_EARLY, MEMMAP_HOTPLUG, }; extern int init_currently_empty_zone(struct zone *zone, unsigned long start_pfn, - unsigned long size, - enum memmap_context context); + unsigned long size); extern void lruvec_init(struct lruvec *lruvec); @@ -1216,11 +1161,16 @@ void sparse_init(void); #define sparse_index_init(_sec, _nid) do {} while (0) #endif /* CONFIG_SPARSEMEM */ -#ifdef CONFIG_NODES_SPAN_OTHER_NODES -bool early_pfn_in_nid(unsigned long pfn, int nid); -#else -#define early_pfn_in_nid(pfn, nid) (1) -#endif +/* + * During memory init memblocks map pfns to nids. The search is expensive and + * this caches recent lookups. The implementation of __early_pfn_to_nid + * may treat start/end as pfns or sections. + */ +struct mminit_pfnnid_cache { + unsigned long last_start; + unsigned long last_end; + int last_nid; +}; #ifndef early_pfn_valid #define early_pfn_valid(pfn) (1) diff --git a/kernel/include/linux/mod_devicetable.h b/kernel/include/linux/mod_devicetable.h index 3bfd56778..64f36e09a 100644 --- a/kernel/include/linux/mod_devicetable.h +++ b/kernel/include/linux/mod_devicetable.h @@ -189,6 +189,8 @@ struct css_device_id { struct acpi_device_id { __u8 id[ACPI_ID_LEN]; kernel_ulong_t driver_data; + __u32 cls; + __u32 cls_msk; }; #define PNP_ID_LEN 8 @@ -217,6 +219,14 @@ struct serio_device_id { __u8 proto; }; +struct hda_device_id { + __u32 vendor_id; + __u32 rev_id; + __u8 api_version; + const char *name; + unsigned long driver_data; +}; + /* * Struct used for matching a device */ @@ -251,7 +261,7 @@ struct pcmcia_device_id { __u32 prod_id_hash[4]; - /* not matched against in kernelspace*/ + /* not matched against in kernelspace */ const char * prod_id[4]; /* not matched against */ @@ -599,9 +609,21 @@ struct ipack_device_id { #define MEI_CL_MODULE_PREFIX "mei:" #define MEI_CL_NAME_SIZE 32 +#define MEI_CL_VERSION_ANY 0xff +/** + * struct mei_cl_device_id - MEI client device identifier + * @name: helper name + * @uuid: client uuid + * @version: client protocol version + * @driver_info: information used by the driver. + * + * identifies mei client device by uuid and name + */ struct mei_cl_device_id { char name[MEI_CL_NAME_SIZE]; + uuid_le uuid; + __u8 version; kernel_ulong_t driver_info; }; @@ -629,4 +651,10 @@ struct mcb_device_id { kernel_ulong_t driver_data; }; +struct ulpi_device_id { + __u16 vendor; + __u16 product; + kernel_ulong_t driver_data; +}; + #endif /* LINUX_MOD_DEVICETABLE_H */ diff --git a/kernel/include/linux/module.h b/kernel/include/linux/module.h index c883b86ea..b229a9961 100644 --- a/kernel/include/linux/module.h +++ b/kernel/include/linux/module.h @@ -11,12 +11,14 @@ #include <linux/compiler.h> #include <linux/cache.h> #include <linux/kmod.h> +#include <linux/init.h> #include <linux/elf.h> #include <linux/stringify.h> #include <linux/kobject.h> #include <linux/moduleparam.h> #include <linux/jump_label.h> #include <linux/export.h> +#include <linux/rbtree_latch.h> #include <linux/percpu.h> #include <asm/module.h> @@ -70,6 +72,89 @@ extern struct module_attribute module_uevent; extern int init_module(void); extern void cleanup_module(void); +#ifndef MODULE +/** + * module_init() - driver initialization entry point + * @x: function to be run at kernel boot time or module insertion + * + * module_init() will either be called during do_initcalls() (if + * builtin) or at module insertion time (if a module). There can only + * be one per module. + */ +#define module_init(x) __initcall(x); + +/** + * module_exit() - driver exit entry point + * @x: function to be run when driver is removed + * + * module_exit() will wrap the driver clean-up code + * with cleanup_module() when used with rmmod when + * the driver is a module. If the driver is statically + * compiled into the kernel, module_exit() has no effect. + * There can only be one per module. + */ +#define module_exit(x) __exitcall(x); + +#else /* MODULE */ + +/* + * In most cases loadable modules do not need custom + * initcall levels. There are still some valid cases where + * a driver may be needed early if built in, and does not + * matter when built as a loadable module. Like bus + * snooping debug drivers. + */ +#define early_initcall(fn) module_init(fn) +#define core_initcall(fn) module_init(fn) +#define core_initcall_sync(fn) module_init(fn) +#define postcore_initcall(fn) module_init(fn) +#define postcore_initcall_sync(fn) module_init(fn) +#define arch_initcall(fn) module_init(fn) +#define subsys_initcall(fn) module_init(fn) +#define subsys_initcall_sync(fn) module_init(fn) +#define fs_initcall(fn) module_init(fn) +#define fs_initcall_sync(fn) module_init(fn) +#define rootfs_initcall(fn) module_init(fn) +#define device_initcall(fn) module_init(fn) +#define device_initcall_sync(fn) module_init(fn) +#define late_initcall(fn) module_init(fn) +#define late_initcall_sync(fn) module_init(fn) + +#define console_initcall(fn) module_init(fn) +#define security_initcall(fn) module_init(fn) + +/* Each module must use one module_init(). */ +#define module_init(initfn) \ + static inline initcall_t __inittest(void) \ + { return initfn; } \ + int init_module(void) __attribute__((alias(#initfn))); + +/* This is only required if you want to be unloadable. */ +#define module_exit(exitfn) \ + static inline exitcall_t __exittest(void) \ + { return exitfn; } \ + void cleanup_module(void) __attribute__((alias(#exitfn))); + +#endif + +/* This means "can be init if no module support, otherwise module load + may call it." */ +#ifdef CONFIG_MODULES +#define __init_or_module +#define __initdata_or_module +#define __initconst_or_module +#define __INIT_OR_MODULE .text +#define __INITDATA_OR_MODULE .data +#define __INITRODATA_OR_MODULE .section ".rodata","a",%progbits +#else +#define __init_or_module __init +#define __initdata_or_module __initdata +#define __initconst_or_module __initconst +#define __INIT_OR_MODULE __INIT +#define __INITDATA_OR_MODULE __INITDATA +#define __INITRODATA_OR_MODULE __INITRODATA +#endif /*CONFIG_MODULES*/ + /* Archs provide a method of finding the correct exception table. */ struct exception_table_entry; @@ -210,6 +295,19 @@ enum module_state { MODULE_STATE_UNFORMED, /* Still setting it up. */ }; +struct module; + +struct mod_tree_node { + struct module *mod; + struct latch_tree_node node; +}; + +struct mod_kallsyms { + Elf_Sym *symtab; + unsigned int num_symtab; + char *strtab; +}; + struct module { enum module_state state; @@ -232,6 +330,9 @@ struct module { unsigned int num_syms; /* Kernel parameters. */ +#ifdef CONFIG_SYSFS + struct mutex param_lock; +#endif struct kernel_param *kp; unsigned int num_kp; @@ -257,6 +358,8 @@ struct module { bool sig_ok; #endif + bool async_probe_requested; + /* symbols that will be GPL-only in the near future. */ const struct kernel_symbol *gpl_future_syms; const unsigned long *gpl_future_crcs; @@ -269,8 +372,15 @@ struct module { /* Startup function. */ int (*init)(void); - /* If this is non-NULL, vfree after init() returns */ - void *module_init; + /* + * If this is non-NULL, vfree() after init() returns. + * + * Cacheline align here, such that: + * module_init, module_core, init_size, core_size, + * init_text_size, core_text_size and mtn_core::{mod,node[0]} + * are on the same cacheline. + */ + void *module_init ____cacheline_aligned; /* Here is the actual code + data, vfree'd on unload. */ void *module_core; @@ -281,6 +391,16 @@ struct module { /* The size of the executable code in each section. */ unsigned int init_text_size, core_text_size; +#ifdef CONFIG_MODULES_TREE_LOOKUP + /* + * We want mtn_core::{mod,node[0]} to be in the same cacheline as the + * above entries such that a regular lookup will only touch one + * cacheline. + */ + struct mod_tree_node mtn_core; + struct mod_tree_node mtn_init; +#endif + /* Size of RO sections of the module (text+rodata) */ unsigned int init_ro_size, core_ro_size; @@ -297,14 +417,9 @@ struct module { #endif #ifdef CONFIG_KALLSYMS - /* - * We keep the symbol and string tables for kallsyms. - * The core_* fields below are temporary, loader-only (they - * could really be discarded after module init). - */ - Elf_Sym *symtab, *core_symtab; - unsigned int num_symtab, core_num_syms; - char *strtab, *core_strtab; + /* Protected by RCU and/or module_mutex: use rcu_dereference() */ + struct mod_kallsyms *kallsyms; + struct mod_kallsyms core_kallsyms; /* Section attributes */ struct module_sect_attrs *sect_attrs; @@ -336,7 +451,7 @@ struct module { const char **trace_bprintk_fmt_start; #endif #ifdef CONFIG_EVENT_TRACING - struct ftrace_event_call **trace_events; + struct trace_event_call **trace_events; unsigned int num_trace_events; struct trace_enum_map **trace_enums; unsigned int num_trace_enums; @@ -367,7 +482,7 @@ struct module { ctor_fn_t *ctors; unsigned int num_ctors; #endif -}; +} ____cacheline_aligned; #ifndef MODULE_ARCH_INIT #define MODULE_ARCH_INIT {} #endif @@ -421,14 +536,22 @@ struct symsearch { bool unused; }; -/* Search for an exported symbol by name. */ +/* + * Search for an exported symbol by name. + * + * Must be called with module_mutex held or preemption disabled. + */ const struct kernel_symbol *find_symbol(const char *name, struct module **owner, const unsigned long **crc, bool gplok, bool warn); -/* Walk the exported symbol table */ +/* + * Walk the exported symbol table + * + * Must be called with module_mutex held or preemption disabled. + */ bool each_symbol_section(bool (*fn)(const struct symsearch *arr, struct module *owner, void *data), void *data); @@ -508,6 +631,11 @@ int unregister_module_notifier(struct notifier_block *nb); extern void print_modules(void); +static inline bool module_requested_async_probing(struct module *module) +{ + return module && module->async_probe_requested; +} + #else /* !CONFIG_MODULES... */ /* Given an address, look for it in the exception tables. */ @@ -618,6 +746,12 @@ static inline int unregister_module_notifier(struct notifier_block *nb) static inline void print_modules(void) { } + +static inline bool module_requested_async_probing(struct module *module) +{ + return false; +} + #endif /* CONFIG_MODULES */ #ifdef CONFIG_SYSFS @@ -655,4 +789,16 @@ static inline void module_bug_finalize(const Elf_Ehdr *hdr, static inline void module_bug_cleanup(struct module *mod) {} #endif /* CONFIG_GENERIC_BUG */ +#ifdef CONFIG_MODULE_SIG +static inline bool module_sig_ok(struct module *module) +{ + return module->sig_ok; +} +#else /* !CONFIG_MODULE_SIG */ +static inline bool module_sig_ok(struct module *module) +{ + return true; +} +#endif /* CONFIG_MODULE_SIG */ + #endif /* _LINUX_MODULE_H */ diff --git a/kernel/include/linux/moduleparam.h b/kernel/include/linux/moduleparam.h index 1c9effa25..52666d90c 100644 --- a/kernel/include/linux/moduleparam.h +++ b/kernel/include/linux/moduleparam.h @@ -67,8 +67,9 @@ enum { struct kernel_param { const char *name; + struct module *mod; const struct kernel_param_ops *ops; - u16 perm; + const u16 perm; s8 level; u8 flags; union { @@ -108,7 +109,7 @@ struct kparam_array * * @perm is 0 if the the variable is not to appear in sysfs, or 0444 * for world-readable, 0644 for root-writable, etc. Note that if it - * is writable, you may need to use kparam_block_sysfs_write() around + * is writable, you may need to use kernel_param_lock() around * accesses (esp. charp, which can be kfreed when it changes). * * The @type is simply pasted to refer to a param_ops_##type and a @@ -216,16 +217,16 @@ struct kparam_array parameters. */ #define __module_param_call(prefix, name, ops, arg, perm, level, flags) \ /* Default value instead of permissions? */ \ - static const char __param_str_##name[] = prefix #name; \ + static const char __param_str_##name[] = prefix #name; \ static struct kernel_param __moduleparam_const __param_##name \ __used \ __attribute__ ((unused,__section__ ("__param"),aligned(sizeof(void *)))) \ - = { __param_str_##name, ops, VERIFY_OCTAL_PERMISSIONS(perm), \ - level, flags, { arg } } + = { __param_str_##name, THIS_MODULE, ops, \ + VERIFY_OCTAL_PERMISSIONS(perm), level, flags, { arg } } /* Obsolete - use module_param_cb() */ #define module_param_call(name, set, get, arg, perm) \ - static struct kernel_param_ops __param_ops_##name = \ + static const struct kernel_param_ops __param_ops_##name = \ { .flags = 0, (void *)set, (void *)get }; \ __module_param_call(MODULE_PARAM_PREFIX, \ name, &__param_ops_##name, arg, \ @@ -238,58 +239,14 @@ __check_old_set_param(int (*oldset)(const char *, struct kernel_param *)) return 0; } -/** - * kparam_block_sysfs_write - make sure a parameter isn't written via sysfs. - * @name: the name of the parameter - * - * There's no point blocking write on a paramter that isn't writable via sysfs! - */ -#define kparam_block_sysfs_write(name) \ - do { \ - BUG_ON(!(__param_##name.perm & 0222)); \ - __kernel_param_lock(); \ - } while (0) - -/** - * kparam_unblock_sysfs_write - allows sysfs to write to a parameter again. - * @name: the name of the parameter - */ -#define kparam_unblock_sysfs_write(name) \ - do { \ - BUG_ON(!(__param_##name.perm & 0222)); \ - __kernel_param_unlock(); \ - } while (0) - -/** - * kparam_block_sysfs_read - make sure a parameter isn't read via sysfs. - * @name: the name of the parameter - * - * This also blocks sysfs writes. - */ -#define kparam_block_sysfs_read(name) \ - do { \ - BUG_ON(!(__param_##name.perm & 0444)); \ - __kernel_param_lock(); \ - } while (0) - -/** - * kparam_unblock_sysfs_read - allows sysfs to read a parameter again. - * @name: the name of the parameter - */ -#define kparam_unblock_sysfs_read(name) \ - do { \ - BUG_ON(!(__param_##name.perm & 0444)); \ - __kernel_param_unlock(); \ - } while (0) - #ifdef CONFIG_SYSFS -extern void __kernel_param_lock(void); -extern void __kernel_param_unlock(void); +extern void kernel_param_lock(struct module *mod); +extern void kernel_param_unlock(struct module *mod); #else -static inline void __kernel_param_lock(void) +static inline void kernel_param_lock(struct module *mod) { } -static inline void __kernel_param_unlock(void) +static inline void kernel_param_unlock(struct module *mod) { } #endif @@ -310,6 +267,15 @@ static inline void __kernel_param_unlock(void) #define core_param(name, var, type, perm) \ param_check_##type(name, &(var)); \ __module_param_call("", name, ¶m_ops_##type, &var, perm, -1, 0) + +/** + * core_param_unsafe - same as core_param but taints kernel + */ +#define core_param_unsafe(name, var, type, perm) \ + param_check_##type(name, &(var)); \ + __module_param_call("", name, ¶m_ops_##type, &var, perm, \ + -1, KERNEL_PARAM_FL_UNSAFE) + #endif /* !MODULE */ /** @@ -357,8 +323,9 @@ extern char *parse_args(const char *name, unsigned num, s16 level_min, s16 level_max, + void *arg, int (*unknown)(char *param, char *val, - const char *doing)); + const char *doing, void *arg)); /* Called by module remove. */ #ifdef CONFIG_SYSFS @@ -376,64 +343,71 @@ static inline void destroy_params(const struct kernel_param *params, #define __param_check(name, p, type) \ static inline type __always_unused *__check_##name(void) { return(p); } -extern struct kernel_param_ops param_ops_byte; +extern const struct kernel_param_ops param_ops_byte; extern int param_set_byte(const char *val, const struct kernel_param *kp); extern int param_get_byte(char *buffer, const struct kernel_param *kp); #define param_check_byte(name, p) __param_check(name, p, unsigned char) -extern struct kernel_param_ops param_ops_short; +extern const struct kernel_param_ops param_ops_short; extern int param_set_short(const char *val, const struct kernel_param *kp); extern int param_get_short(char *buffer, const struct kernel_param *kp); #define param_check_short(name, p) __param_check(name, p, short) -extern struct kernel_param_ops param_ops_ushort; +extern const struct kernel_param_ops param_ops_ushort; extern int param_set_ushort(const char *val, const struct kernel_param *kp); extern int param_get_ushort(char *buffer, const struct kernel_param *kp); #define param_check_ushort(name, p) __param_check(name, p, unsigned short) -extern struct kernel_param_ops param_ops_int; +extern const struct kernel_param_ops param_ops_int; extern int param_set_int(const char *val, const struct kernel_param *kp); extern int param_get_int(char *buffer, const struct kernel_param *kp); #define param_check_int(name, p) __param_check(name, p, int) -extern struct kernel_param_ops param_ops_uint; +extern const struct kernel_param_ops param_ops_uint; extern int param_set_uint(const char *val, const struct kernel_param *kp); extern int param_get_uint(char *buffer, const struct kernel_param *kp); #define param_check_uint(name, p) __param_check(name, p, unsigned int) -extern struct kernel_param_ops param_ops_long; +extern const struct kernel_param_ops param_ops_long; extern int param_set_long(const char *val, const struct kernel_param *kp); extern int param_get_long(char *buffer, const struct kernel_param *kp); #define param_check_long(name, p) __param_check(name, p, long) -extern struct kernel_param_ops param_ops_ulong; +extern const struct kernel_param_ops param_ops_ulong; extern int param_set_ulong(const char *val, const struct kernel_param *kp); extern int param_get_ulong(char *buffer, const struct kernel_param *kp); #define param_check_ulong(name, p) __param_check(name, p, unsigned long) -extern struct kernel_param_ops param_ops_ullong; +extern const struct kernel_param_ops param_ops_ullong; extern int param_set_ullong(const char *val, const struct kernel_param *kp); extern int param_get_ullong(char *buffer, const struct kernel_param *kp); #define param_check_ullong(name, p) __param_check(name, p, unsigned long long) -extern struct kernel_param_ops param_ops_charp; +extern const struct kernel_param_ops param_ops_charp; extern int param_set_charp(const char *val, const struct kernel_param *kp); extern int param_get_charp(char *buffer, const struct kernel_param *kp); +extern void param_free_charp(void *arg); #define param_check_charp(name, p) __param_check(name, p, char *) /* We used to allow int as well as bool. We're taking that away! */ -extern struct kernel_param_ops param_ops_bool; +extern const struct kernel_param_ops param_ops_bool; extern int param_set_bool(const char *val, const struct kernel_param *kp); extern int param_get_bool(char *buffer, const struct kernel_param *kp); #define param_check_bool(name, p) __param_check(name, p, bool) -extern struct kernel_param_ops param_ops_invbool; +extern const struct kernel_param_ops param_ops_bool_enable_only; +extern int param_set_bool_enable_only(const char *val, + const struct kernel_param *kp); +/* getter is the same as for the regular bool */ +#define param_check_bool_enable_only param_check_bool + +extern const struct kernel_param_ops param_ops_invbool; extern int param_set_invbool(const char *val, const struct kernel_param *kp); extern int param_get_invbool(char *buffer, const struct kernel_param *kp); #define param_check_invbool(name, p) __param_check(name, p, bool) /* An int, which can only be set like a bool (though it shows as an int). */ -extern struct kernel_param_ops param_ops_bint; +extern const struct kernel_param_ops param_ops_bint; extern int param_set_bint(const char *val, const struct kernel_param *kp); #define param_get_bint param_get_int #define param_check_bint param_check_int @@ -477,9 +451,9 @@ extern int param_set_bint(const char *val, const struct kernel_param *kp); perm, -1, 0); \ __MODULE_PARM_TYPE(name, "array of " #type) -extern struct kernel_param_ops param_array_ops; +extern const struct kernel_param_ops param_array_ops; -extern struct kernel_param_ops param_ops_string; +extern const struct kernel_param_ops param_ops_string; extern int param_set_copystring(const char *val, const struct kernel_param *); extern int param_get_string(char *buffer, const struct kernel_param *kp); diff --git a/kernel/include/linux/mpi.h b/kernel/include/linux/mpi.h index 5af1b81de..3a5abe95a 100644 --- a/kernel/include/linux/mpi.h +++ b/kernel/include/linux/mpi.h @@ -31,12 +31,7 @@ #define G10_MPI_H #include <linux/types.h> - -/* DSI defines */ - -#define SHA1_DIGEST_LENGTH 20 - -/*end of DSI defines */ +#include <linux/scatterlist.h> #define BYTES_PER_MPI_LIMB (BITS_PER_LONG / 8) #define BITS_PER_MPI_LIMB BITS_PER_LONG @@ -78,11 +73,16 @@ void mpi_swap(MPI a, MPI b); MPI do_encode_md(const void *sha_buffer, unsigned nbits); MPI mpi_read_raw_data(const void *xbuffer, size_t nbytes); MPI mpi_read_from_buffer(const void *buffer, unsigned *ret_nread); +MPI mpi_read_raw_from_sgl(struct scatterlist *sgl, unsigned int len); int mpi_fromstr(MPI val, const char *str); u32 mpi_get_keyid(MPI a, u32 *keyid); void *mpi_get_buffer(MPI a, unsigned *nbytes, int *sign); +int mpi_read_buffer(MPI a, uint8_t *buf, unsigned buf_len, unsigned *nbytes, + int *sign); void *mpi_get_secure_buffer(MPI a, unsigned *nbytes, int *sign); int mpi_set_buffer(MPI a, const void *buffer, unsigned nbytes, int sign); +int mpi_write_to_sgl(MPI a, struct scatterlist *sg, unsigned *nbytes, + int *sign); #define log_mpidump g10_log_mpidump @@ -142,4 +142,17 @@ int mpi_rshift(MPI x, MPI a, unsigned n); /*-- mpi-inv.c --*/ int mpi_invm(MPI x, MPI u, MPI v); +/* inline functions */ + +/** + * mpi_get_size() - returns max size required to store the number + * + * @a: A multi precision integer for which we want to allocate a bufer + * + * Return: size required to store the number + */ +static inline unsigned int mpi_get_size(MPI a) +{ + return a->nlimbs * BYTES_PER_MPI_LIMB; +} #endif /*G10_MPI_H */ diff --git a/kernel/include/linux/mpls_iptunnel.h b/kernel/include/linux/mpls_iptunnel.h new file mode 100644 index 000000000..ef29eb2d6 --- /dev/null +++ b/kernel/include/linux/mpls_iptunnel.h @@ -0,0 +1,6 @@ +#ifndef _LINUX_MPLS_IPTUNNEL_H +#define _LINUX_MPLS_IPTUNNEL_H + +#include <uapi/linux/mpls_iptunnel.h> + +#endif /* _LINUX_MPLS_IPTUNNEL_H */ diff --git a/kernel/include/linux/msi.h b/kernel/include/linux/msi.h index 8ac4a68ff..f71a25e5f 100644 --- a/kernel/include/linux/msi.h +++ b/kernel/include/linux/msi.h @@ -14,38 +14,85 @@ extern int pci_msi_ignore_mask; /* Helper functions */ struct irq_data; struct msi_desc; +struct pci_dev; +struct platform_msi_priv_data; void __get_cached_msi_msg(struct msi_desc *entry, struct msi_msg *msg); void get_cached_msi_msg(unsigned int irq, struct msi_msg *msg); +typedef void (*irq_write_msi_msg_t)(struct msi_desc *desc, + struct msi_msg *msg); + +/** + * platform_msi_desc - Platform device specific msi descriptor data + * @msi_priv_data: Pointer to platform private data + * @msi_index: The index of the MSI descriptor for multi MSI + */ +struct platform_msi_desc { + struct platform_msi_priv_data *msi_priv_data; + u16 msi_index; +}; + +/** + * struct msi_desc - Descriptor structure for MSI based interrupts + * @list: List head for management + * @irq: The base interrupt number + * @nvec_used: The number of vectors used + * @dev: Pointer to the device which uses this descriptor + * @msg: The last set MSI message cached for reuse + * + * @masked: [PCI MSI/X] Mask bits + * @is_msix: [PCI MSI/X] True if MSI-X + * @multiple: [PCI MSI/X] log2 num of messages allocated + * @multi_cap: [PCI MSI/X] log2 num of messages supported + * @maskbit: [PCI MSI/X] Mask-Pending bit supported? + * @is_64: [PCI MSI/X] Address size: 0=32bit 1=64bit + * @entry_nr: [PCI MSI/X] Entry which is described by this descriptor + * @default_irq:[PCI MSI/X] The default pre-assigned non-MSI irq + * @mask_pos: [PCI MSI] Mask register position + * @mask_base: [PCI MSI-X] Mask register base address + * @platform: [platform] Platform device specific msi descriptor data + */ struct msi_desc { - struct { - __u8 is_msix : 1; - __u8 multiple: 3; /* log2 num of messages allocated */ - __u8 multi_cap : 3; /* log2 num of messages supported */ - __u8 maskbit : 1; /* mask-pending bit supported ? */ - __u8 is_64 : 1; /* Address size: 0=32bit 1=64bit */ - __u16 entry_nr; /* specific enabled entry */ - unsigned default_irq; /* default pre-assigned irq */ - } msi_attrib; - - u32 masked; /* mask bits */ - unsigned int irq; - unsigned int nvec_used; /* number of messages */ - struct list_head list; + /* Shared device/bus type independent data */ + struct list_head list; + unsigned int irq; + unsigned int nvec_used; + struct device *dev; + struct msi_msg msg; union { - void __iomem *mask_base; - u8 mask_pos; - }; - struct pci_dev *dev; + /* PCI MSI/X specific data */ + struct { + u32 masked; + struct { + __u8 is_msix : 1; + __u8 multiple : 3; + __u8 multi_cap : 3; + __u8 maskbit : 1; + __u8 is_64 : 1; + __u16 entry_nr; + unsigned default_irq; + } msi_attrib; + union { + u8 mask_pos; + void __iomem *mask_base; + }; + }; - /* Last set MSI message */ - struct msi_msg msg; + /* + * Non PCI variants add their data structure here. New + * entries need to use a named structure. We want + * proper name spaces for this. The PCI part is + * anonymous for now as it would require an immediate + * tree wide cleanup. + */ + struct platform_msi_desc platform; + }; }; /* Helpers to hide struct msi_desc implementation details */ -#define msi_desc_to_dev(desc) (&(desc)->dev.dev) -#define dev_to_msi_list(dev) (&to_pci_dev((dev))->msi_list) +#define msi_desc_to_dev(desc) ((desc)->dev) +#define dev_to_msi_list(dev) (&(dev)->msi_list) #define first_msi_entry(dev) \ list_first_entry(dev_to_msi_list((dev)), struct msi_desc, list) #define for_each_msi_entry(desc, dev) \ @@ -56,12 +103,17 @@ struct msi_desc { #define for_each_pci_msi_entry(desc, pdev) \ for_each_msi_entry((desc), &(pdev)->dev) -static inline struct pci_dev *msi_desc_to_pci_dev(struct msi_desc *desc) +struct pci_dev *msi_desc_to_pci_dev(struct msi_desc *desc); +void *msi_desc_to_pci_sysdata(struct msi_desc *desc); +#else /* CONFIG_PCI_MSI */ +static inline void *msi_desc_to_pci_sysdata(struct msi_desc *desc) { - return desc->dev; + return NULL; } #endif /* CONFIG_PCI_MSI */ +struct msi_desc *alloc_msi_entry(struct device *dev); +void free_msi_entry(struct msi_desc *entry); void __pci_read_msi_msg(struct msi_desc *entry, struct msi_msg *msg); void __pci_write_msi_msg(struct msi_desc *entry, struct msi_msg *msg); void pci_write_msi_msg(unsigned int irq, struct msi_msg *msg); @@ -108,12 +160,11 @@ struct msi_controller { struct device *dev; struct device_node *of_node; struct list_head list; -#ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN - struct irq_domain *domain; -#endif int (*setup_irq)(struct msi_controller *chip, struct pci_dev *dev, struct msi_desc *desc); + int (*setup_irqs)(struct msi_controller *chip, struct pci_dev *dev, + int nvec, int type); void (*teardown_irq)(struct msi_controller *chip, unsigned int irq); }; @@ -125,6 +176,7 @@ struct msi_controller { struct irq_domain; struct irq_chip; struct device_node; +struct fwnode_handle; struct msi_domain_info; /** @@ -213,7 +265,7 @@ enum { int msi_domain_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force); -struct irq_domain *msi_create_irq_domain(struct device_node *of_node, +struct irq_domain *msi_create_irq_domain(struct fwnode_handle *fwnode, struct msi_domain_info *info, struct irq_domain *parent); int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, @@ -221,23 +273,36 @@ int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, void msi_domain_free_irqs(struct irq_domain *domain, struct device *dev); struct msi_domain_info *msi_get_domain_info(struct irq_domain *domain); +struct irq_domain *platform_msi_create_irq_domain(struct fwnode_handle *fwnode, + struct msi_domain_info *info, + struct irq_domain *parent); +int platform_msi_domain_alloc_irqs(struct device *dev, unsigned int nvec, + irq_write_msi_msg_t write_msi_msg); +void platform_msi_domain_free_irqs(struct device *dev); #endif /* CONFIG_GENERIC_MSI_IRQ_DOMAIN */ #ifdef CONFIG_PCI_MSI_IRQ_DOMAIN void pci_msi_domain_write_msg(struct irq_data *irq_data, struct msi_msg *msg); -struct irq_domain *pci_msi_create_irq_domain(struct device_node *node, +struct irq_domain *pci_msi_create_irq_domain(struct fwnode_handle *fwnode, struct msi_domain_info *info, struct irq_domain *parent); int pci_msi_domain_alloc_irqs(struct irq_domain *domain, struct pci_dev *dev, int nvec, int type); void pci_msi_domain_free_irqs(struct irq_domain *domain, struct pci_dev *dev); -struct irq_domain *pci_msi_create_default_irq_domain(struct device_node *node, +struct irq_domain *pci_msi_create_default_irq_domain(struct fwnode_handle *fwnode, struct msi_domain_info *info, struct irq_domain *parent); irq_hw_number_t pci_msi_domain_calc_hwirq(struct pci_dev *dev, struct msi_desc *desc); int pci_msi_domain_check_cap(struct irq_domain *domain, struct msi_domain_info *info, struct device *dev); +u32 pci_msi_domain_get_msi_rid(struct irq_domain *domain, struct pci_dev *pdev); +struct irq_domain *pci_msi_get_device_domain(struct pci_dev *pdev); +#else +static inline struct irq_domain *pci_msi_get_device_domain(struct pci_dev *pdev) +{ + return NULL; +} #endif /* CONFIG_PCI_MSI_IRQ_DOMAIN */ #endif /* LINUX_MSI_H */ diff --git a/kernel/include/linux/msm_mdp.h b/kernel/include/linux/msm_mdp.h deleted file mode 100644 index fe722c1fb..000000000 --- a/kernel/include/linux/msm_mdp.h +++ /dev/null @@ -1,79 +0,0 @@ -/* include/linux/msm_mdp.h - * - * Copyright (C) 2007 Google Incorporated - * - * This software is licensed under the terms of the GNU General Public - * License version 2, as published by the Free Software Foundation, and - * may be copied, distributed, and modified under those terms. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - */ -#ifndef _MSM_MDP_H_ -#define _MSM_MDP_H_ - -#include <linux/types.h> - -#define MSMFB_IOCTL_MAGIC 'm' -#define MSMFB_GRP_DISP _IOW(MSMFB_IOCTL_MAGIC, 1, unsigned int) -#define MSMFB_BLIT _IOW(MSMFB_IOCTL_MAGIC, 2, unsigned int) - -enum { - MDP_RGB_565, /* RGB 565 planar */ - MDP_XRGB_8888, /* RGB 888 padded */ - MDP_Y_CBCR_H2V2, /* Y and CbCr, pseudo planar w/ Cb is in MSB */ - MDP_ARGB_8888, /* ARGB 888 */ - MDP_RGB_888, /* RGB 888 planar */ - MDP_Y_CRCB_H2V2, /* Y and CrCb, pseudo planar w/ Cr is in MSB */ - MDP_YCRYCB_H2V1, /* YCrYCb interleave */ - MDP_Y_CRCB_H2V1, /* Y and CrCb, pseduo planar w/ Cr is in MSB */ - MDP_Y_CBCR_H2V1, /* Y and CrCb, pseduo planar w/ Cr is in MSB */ - MDP_RGBA_8888, /* ARGB 888 */ - MDP_BGRA_8888, /* ABGR 888 */ - MDP_RGBX_8888, /* RGBX 888 */ - MDP_IMGTYPE_LIMIT /* Non valid image type after this enum */ -}; - -enum { - PMEM_IMG, - FB_IMG, -}; - -/* flag values */ -#define MDP_ROT_NOP 0 -#define MDP_FLIP_LR 0x1 -#define MDP_FLIP_UD 0x2 -#define MDP_ROT_90 0x4 -#define MDP_ROT_180 (MDP_FLIP_UD|MDP_FLIP_LR) -#define MDP_ROT_270 (MDP_ROT_90|MDP_FLIP_UD|MDP_FLIP_LR) -#define MDP_DITHER 0x8 -#define MDP_BLUR 0x10 - -#define MDP_TRANSP_NOP 0xffffffff -#define MDP_ALPHA_NOP 0xff - -struct mdp_rect { - u32 x, y, w, h; -}; - -struct mdp_img { - u32 width, height, format, offset; - int memory_id; /* the file descriptor */ -}; - -struct mdp_blit_req { - struct mdp_img src; - struct mdp_img dst; - struct mdp_rect src_rect; - struct mdp_rect dst_rect; - u32 alpha, transp_mask, flags; -}; - -struct mdp_blit_req_list { - u32 count; - struct mdp_blit_req req[]; -}; - -#endif /* _MSM_MDP_H_ */ diff --git a/kernel/include/linux/mtd/cfi.h b/kernel/include/linux/mtd/cfi.h index 299d7d31f..9b57a9b1b 100644 --- a/kernel/include/linux/mtd/cfi.h +++ b/kernel/include/linux/mtd/cfi.h @@ -296,183 +296,19 @@ struct cfi_private { struct flchip chips[0]; /* per-chip data structure for each chip */ }; -/* - * Returns the command address according to the given geometry. - */ -static inline uint32_t cfi_build_cmd_addr(uint32_t cmd_ofs, - struct map_info *map, struct cfi_private *cfi) -{ - unsigned bankwidth = map_bankwidth(map); - unsigned interleave = cfi_interleave(cfi); - unsigned type = cfi->device_type; - uint32_t addr; - - addr = (cmd_ofs * type) * interleave; - - /* Modify the unlock address if we are in compatibility mode. - * For 16bit devices on 8 bit busses - * and 32bit devices on 16 bit busses - * set the low bit of the alternating bit sequence of the address. - */ - if (((type * interleave) > bankwidth) && ((cmd_ofs & 0xff) == 0xaa)) - addr |= (type >> 1)*interleave; - - return addr; -} - -/* - * Transforms the CFI command for the given geometry (bus width & interleave). - * It looks too long to be inline, but in the common case it should almost all - * get optimised away. - */ -static inline map_word cfi_build_cmd(u_long cmd, struct map_info *map, struct cfi_private *cfi) -{ - map_word val = { {0} }; - int wordwidth, words_per_bus, chip_mode, chips_per_word; - unsigned long onecmd; - int i; - - /* We do it this way to give the compiler a fighting chance - of optimising away all the crap for 'bankwidth' larger than - an unsigned long, in the common case where that support is - disabled */ - if (map_bankwidth_is_large(map)) { - wordwidth = sizeof(unsigned long); - words_per_bus = (map_bankwidth(map)) / wordwidth; // i.e. normally 1 - } else { - wordwidth = map_bankwidth(map); - words_per_bus = 1; - } - - chip_mode = map_bankwidth(map) / cfi_interleave(cfi); - chips_per_word = wordwidth * cfi_interleave(cfi) / map_bankwidth(map); - - /* First, determine what the bit-pattern should be for a single - device, according to chip mode and endianness... */ - switch (chip_mode) { - default: BUG(); - case 1: - onecmd = cmd; - break; - case 2: - onecmd = cpu_to_cfi16(map, cmd); - break; - case 4: - onecmd = cpu_to_cfi32(map, cmd); - break; - } - - /* Now replicate it across the size of an unsigned long, or - just to the bus width as appropriate */ - switch (chips_per_word) { - default: BUG(); -#if BITS_PER_LONG >= 64 - case 8: - onecmd |= (onecmd << (chip_mode * 32)); -#endif - case 4: - onecmd |= (onecmd << (chip_mode * 16)); - case 2: - onecmd |= (onecmd << (chip_mode * 8)); - case 1: - ; - } +uint32_t cfi_build_cmd_addr(uint32_t cmd_ofs, + struct map_info *map, struct cfi_private *cfi); - /* And finally, for the multi-word case, replicate it - in all words in the structure */ - for (i=0; i < words_per_bus; i++) { - val.x[i] = onecmd; - } - - return val; -} +map_word cfi_build_cmd(u_long cmd, struct map_info *map, struct cfi_private *cfi); #define CMD(x) cfi_build_cmd((x), map, cfi) - -static inline unsigned long cfi_merge_status(map_word val, struct map_info *map, - struct cfi_private *cfi) -{ - int wordwidth, words_per_bus, chip_mode, chips_per_word; - unsigned long onestat, res = 0; - int i; - - /* We do it this way to give the compiler a fighting chance - of optimising away all the crap for 'bankwidth' larger than - an unsigned long, in the common case where that support is - disabled */ - if (map_bankwidth_is_large(map)) { - wordwidth = sizeof(unsigned long); - words_per_bus = (map_bankwidth(map)) / wordwidth; // i.e. normally 1 - } else { - wordwidth = map_bankwidth(map); - words_per_bus = 1; - } - - chip_mode = map_bankwidth(map) / cfi_interleave(cfi); - chips_per_word = wordwidth * cfi_interleave(cfi) / map_bankwidth(map); - - onestat = val.x[0]; - /* Or all status words together */ - for (i=1; i < words_per_bus; i++) { - onestat |= val.x[i]; - } - - res = onestat; - switch(chips_per_word) { - default: BUG(); -#if BITS_PER_LONG >= 64 - case 8: - res |= (onestat >> (chip_mode * 32)); -#endif - case 4: - res |= (onestat >> (chip_mode * 16)); - case 2: - res |= (onestat >> (chip_mode * 8)); - case 1: - ; - } - - /* Last, determine what the bit-pattern should be for a single - device, according to chip mode and endianness... */ - switch (chip_mode) { - case 1: - break; - case 2: - res = cfi16_to_cpu(map, res); - break; - case 4: - res = cfi32_to_cpu(map, res); - break; - default: BUG(); - } - return res; -} - +unsigned long cfi_merge_status(map_word val, struct map_info *map, + struct cfi_private *cfi); #define MERGESTATUS(x) cfi_merge_status((x), map, cfi) - -/* - * Sends a CFI command to a bank of flash for the given geometry. - * - * Returns the offset in flash where the command was written. - * If prev_val is non-null, it will be set to the value at the command address, - * before the command was written. - */ -static inline uint32_t cfi_send_gen_cmd(u_char cmd, uint32_t cmd_addr, uint32_t base, +uint32_t cfi_send_gen_cmd(u_char cmd, uint32_t cmd_addr, uint32_t base, struct map_info *map, struct cfi_private *cfi, - int type, map_word *prev_val) -{ - map_word val; - uint32_t addr = base + cfi_build_cmd_addr(cmd_addr, map, cfi); - val = cfi_build_cmd(cmd, map, cfi); - - if (prev_val) - *prev_val = map_read(map, addr); - - map_write(map, val, addr); - - return addr - base; -} + int type, map_word *prev_val); static inline uint8_t cfi_read_query(struct map_info *map, uint32_t addr) { @@ -506,15 +342,7 @@ static inline uint16_t cfi_read_query16(struct map_info *map, uint32_t addr) } } -static inline void cfi_udelay(int us) -{ - if (us >= 1000) { - msleep((us+999)/1000); - } else { - udelay(us); - cond_resched(); - } -} +void cfi_udelay(int us); int __xipram cfi_qry_present(struct map_info *map, __u32 base, struct cfi_private *cfi); diff --git a/kernel/include/linux/mtd/map.h b/kernel/include/linux/mtd/map.h index 29975c73a..366cf7795 100644 --- a/kernel/include/linux/mtd/map.h +++ b/kernel/include/linux/mtd/map.h @@ -27,9 +27,9 @@ #include <linux/string.h> #include <linux/bug.h> #include <linux/kernel.h> +#include <linux/io.h> #include <asm/unaligned.h> -#include <asm/io.h> #include <asm/barrier.h> #ifdef CONFIG_MTD_MAP_BANK_WIDTH_1 diff --git a/kernel/include/linux/mtd/nand.h b/kernel/include/linux/mtd/nand.h index 12b75f3ba..5a9d1d4c2 100644 --- a/kernel/include/linux/mtd/nand.h +++ b/kernel/include/linux/mtd/nand.h @@ -26,6 +26,8 @@ struct mtd_info; struct nand_flash_dev; +struct device_node; + /* Scan and identify a NAND device */ extern int nand_scan(struct mtd_info *mtd, int max_chips); /* @@ -502,16 +504,16 @@ struct nand_ecc_ctrl { int (*read_page_raw)(struct mtd_info *mtd, struct nand_chip *chip, uint8_t *buf, int oob_required, int page); int (*write_page_raw)(struct mtd_info *mtd, struct nand_chip *chip, - const uint8_t *buf, int oob_required); + const uint8_t *buf, int oob_required, int page); int (*read_page)(struct mtd_info *mtd, struct nand_chip *chip, uint8_t *buf, int oob_required, int page); int (*read_subpage)(struct mtd_info *mtd, struct nand_chip *chip, uint32_t offs, uint32_t len, uint8_t *buf, int page); int (*write_subpage)(struct mtd_info *mtd, struct nand_chip *chip, uint32_t offset, uint32_t data_len, - const uint8_t *data_buf, int oob_required); + const uint8_t *data_buf, int oob_required, int page); int (*write_page)(struct mtd_info *mtd, struct nand_chip *chip, - const uint8_t *buf, int oob_required); + const uint8_t *buf, int oob_required, int page); int (*write_oob_raw)(struct mtd_info *mtd, struct nand_chip *chip, int page); int (*read_oob_raw)(struct mtd_info *mtd, struct nand_chip *chip, @@ -542,6 +544,7 @@ struct nand_buffers { * flash device * @IO_ADDR_W: [BOARDSPECIFIC] address to write the 8 I/O lines of the * flash device. + * @flash_node: [BOARDSPECIFIC] device node describing this instance * @read_byte: [REPLACEABLE] read one byte from the chip * @read_word: [REPLACEABLE] read one word from the chip * @write_byte: [REPLACEABLE] write a single byte to the chip on the @@ -553,10 +556,6 @@ struct nand_buffers { * @block_markbad: [REPLACEABLE] mark a block bad * @cmd_ctrl: [BOARDSPECIFIC] hardwarespecific function for controlling * ALE/CLE/nCE. Also used to write command and address - * @init_size: [BOARDSPECIFIC] hardwarespecific function for setting - * mtd->oobsize, mtd->writesize and so on. - * @id_data contains the 8 bytes values of NAND_CMD_READID. - * Return with the bus width. * @dev_ready: [BOARDSPECIFIC] hardwarespecific function for accessing * device ready/busy line. If set to NULL no access to * ready/busy is available and the ready/busy information @@ -644,6 +643,8 @@ struct nand_chip { void __iomem *IO_ADDR_R; void __iomem *IO_ADDR_W; + struct device_node *flash_node; + uint8_t (*read_byte)(struct mtd_info *mtd); u16 (*read_word)(struct mtd_info *mtd); void (*write_byte)(struct mtd_info *mtd, uint8_t byte); @@ -653,8 +654,6 @@ struct nand_chip { int (*block_bad)(struct mtd_info *mtd, loff_t ofs, int getchip); int (*block_markbad)(struct mtd_info *mtd, loff_t ofs); void (*cmd_ctrl)(struct mtd_info *mtd, int dat, unsigned int ctrl); - int (*init_size)(struct mtd_info *mtd, struct nand_chip *this, - u8 *id_data); int (*dev_ready)(struct mtd_info *mtd); void (*cmdfunc)(struct mtd_info *mtd, unsigned command, int column, int page_addr); @@ -833,7 +832,6 @@ struct nand_manufacturers { extern struct nand_flash_dev nand_flash_ids[]; extern struct nand_manufacturers nand_manuf_ids[]; -extern int nand_scan_bbt(struct mtd_info *mtd, struct nand_bbt_descr *bd); extern int nand_default_bbt(struct mtd_info *mtd); extern int nand_markbad_bbt(struct mtd_info *mtd, loff_t offs); extern int nand_isreserved_bbt(struct mtd_info *mtd, loff_t offs); @@ -1026,4 +1024,9 @@ struct nand_sdr_timings { /* get timing characteristics from ONFI timing mode. */ const struct nand_sdr_timings *onfi_async_timing_mode_to_sdr_timings(int mode); + +int nand_check_erased_ecc_chunk(void *data, int datalen, + void *ecc, int ecclen, + void *extraoob, int extraooblen, + int threshold); #endif /* __LINUX_MTD_NAND_H */ diff --git a/kernel/include/linux/mtd/spi-nor.h b/kernel/include/linux/mtd/spi-nor.h index e5409524b..bc742dac7 100644 --- a/kernel/include/linux/mtd/spi-nor.h +++ b/kernel/include/linux/mtd/spi-nor.h @@ -10,6 +10,23 @@ #ifndef __LINUX_MTD_SPI_NOR_H #define __LINUX_MTD_SPI_NOR_H +#include <linux/bitops.h> +#include <linux/mtd/cfi.h> + +/* + * Manufacturer IDs + * + * The first byte returned from the flash after sending opcode SPINOR_OP_RDID. + * Sometimes these are the same as CFI IDs, but sometimes they aren't. + */ +#define SNOR_MFR_ATMEL CFI_MFR_ATMEL +#define SNOR_MFR_INTEL CFI_MFR_INTEL +#define SNOR_MFR_MICRON CFI_MFR_ST /* ST Micro <--> Micron */ +#define SNOR_MFR_MACRONIX CFI_MFR_MACRONIX +#define SNOR_MFR_SPANSION CFI_MFR_AMD +#define SNOR_MFR_SST CFI_MFR_SST +#define SNOR_MFR_WINBOND 0xef /* Also used by some Spansion */ + /* * Note on opcode nomenclature: some opcodes have a format like * SPINOR_OP_FUNCTION{4,}_x_y_z. The numbers x, y, and z stand for the number @@ -61,24 +78,24 @@ #define SPINOR_OP_WD_EVCR 0x61 /* Write EVCR register */ /* Status Register bits. */ -#define SR_WIP 1 /* Write in progress */ -#define SR_WEL 2 /* Write enable latch */ +#define SR_WIP BIT(0) /* Write in progress */ +#define SR_WEL BIT(1) /* Write enable latch */ /* meaning of other SR_* bits may differ between vendors */ -#define SR_BP0 4 /* Block protect 0 */ -#define SR_BP1 8 /* Block protect 1 */ -#define SR_BP2 0x10 /* Block protect 2 */ -#define SR_SRWD 0x80 /* SR write protect */ +#define SR_BP0 BIT(2) /* Block protect 0 */ +#define SR_BP1 BIT(3) /* Block protect 1 */ +#define SR_BP2 BIT(4) /* Block protect 2 */ +#define SR_SRWD BIT(7) /* SR write protect */ -#define SR_QUAD_EN_MX 0x40 /* Macronix Quad I/O */ +#define SR_QUAD_EN_MX BIT(6) /* Macronix Quad I/O */ /* Enhanced Volatile Configuration Register bits */ -#define EVCR_QUAD_EN_MICRON 0x80 /* Micron Quad I/O */ +#define EVCR_QUAD_EN_MICRON BIT(7) /* Micron Quad I/O */ /* Flag Status Register bits */ -#define FSR_READY 0x80 +#define FSR_READY BIT(7) /* Configuration Register bits. */ -#define CR_QUAD_EN_SPAN 0x2 /* Spansion Quad I/O */ +#define CR_QUAD_EN_SPAN BIT(1) /* Spansion Quad I/O */ enum read_mode { SPI_NOR_NORMAL = 0, @@ -87,33 +104,6 @@ enum read_mode { SPI_NOR_QUAD, }; -/** - * struct spi_nor_xfer_cfg - Structure for defining a Serial Flash transfer - * @wren: command for "Write Enable", or 0x00 for not required - * @cmd: command for operation - * @cmd_pins: number of pins to send @cmd (1, 2, 4) - * @addr: address for operation - * @addr_pins: number of pins to send @addr (1, 2, 4) - * @addr_width: number of address bytes - * (3,4, or 0 for address not required) - * @mode: mode data - * @mode_pins: number of pins to send @mode (1, 2, 4) - * @mode_cycles: number of mode cycles (0 for mode not required) - * @dummy_cycles: number of dummy cycles (0 for dummy not required) - */ -struct spi_nor_xfer_cfg { - u8 wren; - u8 cmd; - u8 cmd_pins; - u32 addr; - u8 addr_pins; - u8 addr_width; - u8 mode; - u8 mode_pins; - u8 mode_cycles; - u8 dummy_cycles; -}; - #define SPI_NOR_MAX_CMD_SIZE 8 enum spi_nor_ops { SPI_NOR_OPS_READ = 0, @@ -127,11 +117,14 @@ enum spi_nor_option_flags { SNOR_F_USE_FSR = BIT(0), }; +struct mtd_info; + /** * struct spi_nor - Structure for defining a the SPI NOR layer * @mtd: point to a mtd_info structure * @lock: the lock for the read/write/erase/lock/unlock operations * @dev: point to a spi device, or a spi nor controller device. + * @flash_node: point to a device node describing this flash instance. * @page_size: the page size of the SPI NOR * @addr_width: number of address bytes * @erase_opcode: the opcode for erasing a sector @@ -141,28 +134,28 @@ enum spi_nor_option_flags { * @flash_read: the mode of the read * @sst_write_second: used by the SST write operation * @flags: flag options for the current SPI-NOR (SNOR_F_*) - * @cfg: used by the read_xfer/write_xfer * @cmd_buf: used by the write_reg * @prepare: [OPTIONAL] do some preparations for the * read/write/erase/lock/unlock operations * @unprepare: [OPTIONAL] do some post work after the * read/write/erase/lock/unlock operations - * @read_xfer: [OPTIONAL] the read fundamental primitive - * @write_xfer: [OPTIONAL] the writefundamental primitive * @read_reg: [DRIVER-SPECIFIC] read out the register * @write_reg: [DRIVER-SPECIFIC] write data to the register * @read: [DRIVER-SPECIFIC] read data from the SPI NOR * @write: [DRIVER-SPECIFIC] write data to the SPI NOR * @erase: [DRIVER-SPECIFIC] erase a sector of the SPI NOR * at the offset @offs - * @lock: [FLASH-SPECIFIC] lock a region of the SPI NOR - * @unlock: [FLASH-SPECIFIC] unlock a region of the SPI NOR + * @flash_lock: [FLASH-SPECIFIC] lock a region of the SPI NOR + * @flash_unlock: [FLASH-SPECIFIC] unlock a region of the SPI NOR + * @flash_is_locked: [FLASH-SPECIFIC] check if a region of the SPI NOR is + * completely locked * @priv: the private data */ struct spi_nor { - struct mtd_info *mtd; + struct mtd_info mtd; struct mutex lock; struct device *dev; + struct device_node *flash_node; u32 page_size; u8 addr_width; u8 erase_opcode; @@ -172,18 +165,12 @@ struct spi_nor { enum read_mode flash_read; bool sst_write_second; u32 flags; - struct spi_nor_xfer_cfg cfg; u8 cmd_buf[SPI_NOR_MAX_CMD_SIZE]; int (*prepare)(struct spi_nor *nor, enum spi_nor_ops ops); void (*unprepare)(struct spi_nor *nor, enum spi_nor_ops ops); - int (*read_xfer)(struct spi_nor *nor, struct spi_nor_xfer_cfg *cfg, - u8 *buf, size_t len); - int (*write_xfer)(struct spi_nor *nor, struct spi_nor_xfer_cfg *cfg, - u8 *buf, size_t len); int (*read_reg)(struct spi_nor *nor, u8 opcode, u8 *buf, int len); - int (*write_reg)(struct spi_nor *nor, u8 opcode, u8 *buf, int len, - int write_enable); + int (*write_reg)(struct spi_nor *nor, u8 opcode, u8 *buf, int len); int (*read)(struct spi_nor *nor, loff_t from, size_t len, size_t *retlen, u_char *read_buf); @@ -193,6 +180,7 @@ struct spi_nor { int (*flash_lock)(struct spi_nor *nor, loff_t ofs, uint64_t len); int (*flash_unlock)(struct spi_nor *nor, loff_t ofs, uint64_t len); + int (*flash_is_locked)(struct spi_nor *nor, loff_t ofs, uint64_t len); void *priv; }; diff --git a/kernel/include/linux/n_r3964.h b/kernel/include/linux/n_r3964.h index 5d0b2a1de..90a803aa4 100644 --- a/kernel/include/linux/n_r3964.h +++ b/kernel/include/linux/n_r3964.h @@ -152,9 +152,6 @@ struct r3964_info { unsigned char *rx_buf; /* ring buffer */ unsigned char *tx_buf; - wait_queue_head_t read_wait; - //struct wait_queue *read_wait; - struct r3964_block_header *rx_first; struct r3964_block_header *rx_last; struct r3964_block_header *tx_first; @@ -164,8 +161,9 @@ struct r3964_info { unsigned char last_rx; unsigned char bcc; unsigned int blocks_in_rx_queue; - - + + struct mutex read_lock; /* serialize r3964_read */ + struct r3964_client_info *firstClient; unsigned int state; unsigned int flags; diff --git a/kernel/include/linux/namei.h b/kernel/include/linux/namei.h index c8990779f..d8c6334cd 100644 --- a/kernel/include/linux/namei.h +++ b/kernel/include/linux/namei.h @@ -1,16 +1,15 @@ #ifndef _LINUX_NAMEI_H #define _LINUX_NAMEI_H -#include <linux/dcache.h> -#include <linux/errno.h> -#include <linux/linkage.h> +#include <linux/kernel.h> #include <linux/path.h> - -struct vfsmount; -struct nameidata; +#include <linux/fcntl.h> +#include <linux/errno.h> enum { MAX_NESTED_LINKS = 8 }; +#define MAXSYMLINKS 40 + /* * Type of the last component on LOOKUP_PARENT */ @@ -45,13 +44,29 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND}; #define LOOKUP_ROOT 0x2000 #define LOOKUP_EMPTY 0x4000 -extern int user_path_at(int, const char __user *, unsigned, struct path *); extern int user_path_at_empty(int, const char __user *, unsigned, struct path *, int *empty); -#define user_path(name, path) user_path_at(AT_FDCWD, name, LOOKUP_FOLLOW, path) -#define user_lpath(name, path) user_path_at(AT_FDCWD, name, 0, path) -#define user_path_dir(name, path) \ - user_path_at(AT_FDCWD, name, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, path) +static inline int user_path_at(int dfd, const char __user *name, unsigned flags, + struct path *path) +{ + return user_path_at_empty(dfd, name, flags, path, NULL); +} + +static inline int user_path(const char __user *name, struct path *path) +{ + return user_path_at_empty(AT_FDCWD, name, LOOKUP_FOLLOW, path, NULL); +} + +static inline int user_lpath(const char __user *name, struct path *path) +{ + return user_path_at_empty(AT_FDCWD, name, 0, path, NULL); +} + +static inline int user_path_dir(const char __user *name, struct path *path) +{ + return user_path_at_empty(AT_FDCWD, name, + LOOKUP_FOLLOW | LOOKUP_DIRECTORY, path, NULL); +} extern int kern_path(const char *, unsigned, struct path *); @@ -70,9 +85,7 @@ extern int follow_up(struct path *); extern struct dentry *lock_rename(struct dentry *, struct dentry *); extern void unlock_rename(struct dentry *, struct dentry *); -extern void nd_jump_link(struct nameidata *nd, struct path *path); -extern void nd_set_link(struct nameidata *nd, char *path); -extern char *nd_get_link(struct nameidata *nd); +extern void nd_jump_link(struct path *path); static inline void nd_terminate_link(void *name, size_t len, size_t maxlen) { diff --git a/kernel/include/linux/nd.h b/kernel/include/linux/nd.h new file mode 100644 index 000000000..507e47c86 --- /dev/null +++ b/kernel/include/linux/nd.h @@ -0,0 +1,151 @@ +/* + * Copyright(c) 2013-2015 Intel Corporation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public License as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ +#ifndef __LINUX_ND_H__ +#define __LINUX_ND_H__ +#include <linux/fs.h> +#include <linux/ndctl.h> +#include <linux/device.h> + +struct nd_device_driver { + struct device_driver drv; + unsigned long type; + int (*probe)(struct device *dev); + int (*remove)(struct device *dev); +}; + +static inline struct nd_device_driver *to_nd_device_driver( + struct device_driver *drv) +{ + return container_of(drv, struct nd_device_driver, drv); +}; + +/** + * struct nd_namespace_common - core infrastructure of a namespace + * @force_raw: ignore other personalities for the namespace (e.g. btt) + * @dev: device model node + * @claim: when set a another personality has taken ownership of the namespace + * @rw_bytes: access the raw namespace capacity with byte-aligned transfers + */ +struct nd_namespace_common { + int force_raw; + struct device dev; + struct device *claim; + int (*rw_bytes)(struct nd_namespace_common *, resource_size_t offset, + void *buf, size_t size, int rw); +}; + +static inline struct nd_namespace_common *to_ndns(struct device *dev) +{ + return container_of(dev, struct nd_namespace_common, dev); +} + +/** + * struct nd_namespace_io - infrastructure for loading an nd_pmem instance + * @dev: namespace device created by the nd region driver + * @res: struct resource conversion of a NFIT SPA table + */ +struct nd_namespace_io { + struct nd_namespace_common common; + struct resource res; +}; + +/** + * struct nd_namespace_pmem - namespace device for dimm-backed interleaved memory + * @nsio: device and system physical address range to drive + * @alt_name: namespace name supplied in the dimm label + * @uuid: namespace name supplied in the dimm label + */ +struct nd_namespace_pmem { + struct nd_namespace_io nsio; + char *alt_name; + u8 *uuid; +}; + +/** + * struct nd_namespace_blk - namespace for dimm-bounded persistent memory + * @alt_name: namespace name supplied in the dimm label + * @uuid: namespace name supplied in the dimm label + * @id: ida allocated id + * @lbasize: blk namespaces have a native sector size when btt not present + * @num_resources: number of dpa extents to claim + * @res: discontiguous dpa extents for given dimm + */ +struct nd_namespace_blk { + struct nd_namespace_common common; + char *alt_name; + u8 *uuid; + int id; + unsigned long lbasize; + int num_resources; + struct resource **res; +}; + +static inline struct nd_namespace_io *to_nd_namespace_io(struct device *dev) +{ + return container_of(dev, struct nd_namespace_io, common.dev); +} + +static inline struct nd_namespace_pmem *to_nd_namespace_pmem(struct device *dev) +{ + struct nd_namespace_io *nsio = to_nd_namespace_io(dev); + + return container_of(nsio, struct nd_namespace_pmem, nsio); +} + +static inline struct nd_namespace_blk *to_nd_namespace_blk(struct device *dev) +{ + return container_of(dev, struct nd_namespace_blk, common.dev); +} + +/** + * nvdimm_read_bytes() - synchronously read bytes from an nvdimm namespace + * @ndns: device to read + * @offset: namespace-relative starting offset + * @buf: buffer to fill + * @size: transfer length + * + * @buf is up-to-date upon return from this routine. + */ +static inline int nvdimm_read_bytes(struct nd_namespace_common *ndns, + resource_size_t offset, void *buf, size_t size) +{ + return ndns->rw_bytes(ndns, offset, buf, size, READ); +} + +/** + * nvdimm_write_bytes() - synchronously write bytes to an nvdimm namespace + * @ndns: device to read + * @offset: namespace-relative starting offset + * @buf: buffer to drain + * @size: transfer length + * + * NVDIMM Namepaces disks do not implement sectors internally. Depending on + * the @ndns, the contents of @buf may be in cpu cache, platform buffers, + * or on backing memory media upon return from this routine. Flushing + * to media is handled internal to the @ndns driver, if at all. + */ +static inline int nvdimm_write_bytes(struct nd_namespace_common *ndns, + resource_size_t offset, void *buf, size_t size) +{ + return ndns->rw_bytes(ndns, offset, buf, size, WRITE); +} + +#define MODULE_ALIAS_ND_DEVICE(type) \ + MODULE_ALIAS("nd:t" __stringify(type) "*") +#define ND_DEVICE_MODALIAS_FMT "nd:t%d" + +int __must_check __nd_driver_register(struct nd_device_driver *nd_drv, + struct module *module, const char *mod_name); +#define nd_driver_register(driver) \ + __nd_driver_register(driver, THIS_MODULE, KBUILD_MODNAME) +#endif /* __LINUX_ND_H__ */ diff --git a/kernel/include/linux/net.h b/kernel/include/linux/net.h index 738ea48be..0b4ac7da5 100644 --- a/kernel/include/linux/net.h +++ b/kernel/include/linux/net.h @@ -24,7 +24,8 @@ #include <linux/fcntl.h> /* For O_CLOEXEC and O_NONBLOCK */ #include <linux/kmemcheck.h> #include <linux/rcupdate.h> -#include <linux/jump_label.h> +#include <linux/once.h> + #include <uapi/linux/net.h> struct poll_table_struct; @@ -33,12 +34,15 @@ struct inode; struct file; struct net; -#define SOCK_ASYNC_NOSPACE 0 -#define SOCK_ASYNC_WAITDATA 1 +/* Historically, SOCKWQ_ASYNC_NOSPACE & SOCKWQ_ASYNC_WAITDATA were located + * in sock->flags, but moved into sk->sk_wq->flags to be RCU protected. + * Eventually all flags will be in sk->sk_wq_flags. + */ +#define SOCKWQ_ASYNC_NOSPACE 0 +#define SOCKWQ_ASYNC_WAITDATA 1 #define SOCK_NOSPACE 2 #define SOCK_PASSCRED 3 #define SOCK_PASSSEC 4 -#define SOCK_EXTERNALLY_ALLOCATED 5 #ifndef ARCH_HAS_SOCKET_TYPES /** @@ -89,6 +93,7 @@ struct socket_wq { /* Note: wait MUST be first field of socket_wq */ wait_queue_head_t wait; struct fasync_struct *fasync_list; + unsigned long flags; /* %SOCKWQ_ASYNC_NOSPACE, etc */ struct rcu_head rcu; } ____cacheline_aligned_in_smp; @@ -96,7 +101,7 @@ struct socket_wq { * struct socket - general BSD socket * @state: socket state (%SS_CONNECTED, etc) * @type: socket type (%SOCK_STREAM, etc) - * @flags: socket flags (%SOCK_ASYNC_NOSPACE, etc) + * @flags: socket flags (%SOCK_NOSPACE, etc) * @ops: protocol specific socket operations * @file: File back pointer for gc * @sk: internal networking protocol agnostic socket representation @@ -202,13 +207,13 @@ enum { SOCK_WAKE_URG, }; -int sock_wake_async(struct socket *sk, int how, int band); +int sock_wake_async(struct socket_wq *sk_wq, int how, int band); int sock_register(const struct net_proto_family *fam); void sock_unregister(int family); int __sock_create(struct net *net, int family, int type, int proto, struct socket **res, int kern); int sock_create(int family, int type, int proto, struct socket **res); -int sock_create_kern(int family, int type, int proto, struct socket **res); +int sock_create_kern(struct net *net, int family, int type, int proto, struct socket **res); int sock_create_lite(int family, int type, int proto, struct socket **res); void sock_release(struct socket *sock); int sock_sendmsg(struct socket *sock, struct msghdr *msg); @@ -240,25 +245,19 @@ do { \ net_ratelimited_function(pr_warn, fmt, ##__VA_ARGS__) #define net_info_ratelimited(fmt, ...) \ net_ratelimited_function(pr_info, fmt, ##__VA_ARGS__) +#if defined(DEBUG) #define net_dbg_ratelimited(fmt, ...) \ net_ratelimited_function(pr_debug, fmt, ##__VA_ARGS__) +#else +#define net_dbg_ratelimited(fmt, ...) \ + do { \ + if (0) \ + no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__); \ + } while (0) +#endif -bool __net_get_random_once(void *buf, int nbytes, bool *done, - struct static_key *done_key); - -#define net_get_random_once(buf, nbytes) \ - ({ \ - bool ___ret = false; \ - static bool ___done = false; \ - static struct static_key ___once_key = \ - STATIC_KEY_INIT_TRUE; \ - if (static_key_true(&___once_key)) \ - ___ret = __net_get_random_once(buf, \ - nbytes, \ - &___done, \ - &___once_key); \ - ___ret; \ - }) +#define net_get_random_once(buf, nbytes) \ + get_random_once((buf), (nbytes)) int kernel_sendmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t len); diff --git a/kernel/include/linux/netdev_features.h b/kernel/include/linux/netdev_features.h index 7d59dc6ab..f0d87347d 100644 --- a/kernel/include/linux/netdev_features.h +++ b/kernel/include/linux/netdev_features.h @@ -66,7 +66,6 @@ enum { NETIF_F_HW_VLAN_STAG_FILTER_BIT,/* Receive filtering on VLAN STAGs */ NETIF_F_HW_L2FW_DOFFLOAD_BIT, /* Allow L2 Forwarding in Hardware */ NETIF_F_BUSY_POLL_BIT, /* Busy poll */ - NETIF_F_HW_SWITCH_OFFLOAD_BIT, /* HW switch offload */ /* * Add your fresh new feature above and remember to update @@ -125,7 +124,9 @@ enum { #define NETIF_F_HW_VLAN_STAG_TX __NETIF_F(HW_VLAN_STAG_TX) #define NETIF_F_HW_L2FW_DOFFLOAD __NETIF_F(HW_L2FW_DOFFLOAD) #define NETIF_F_BUSY_POLL __NETIF_F(BUSY_POLL) -#define NETIF_F_HW_SWITCH_OFFLOAD __NETIF_F(HW_SWITCH_OFFLOAD) + +#define for_each_netdev_feature(mask_addr, bit) \ + for_each_set_bit(bit, (unsigned long *)mask_addr, NETDEV_FEATURE_COUNT) /* Features valid for ethtool to change */ /* = all defined minus driver/device-class-related */ @@ -161,8 +162,7 @@ enum { */ #define NETIF_F_ONE_FOR_ALL (NETIF_F_GSO_SOFTWARE | NETIF_F_GSO_ROBUST | \ NETIF_F_SG | NETIF_F_HIGHDMA | \ - NETIF_F_FRAGLIST | NETIF_F_VLAN_CHALLENGED | \ - NETIF_F_HW_SWITCH_OFFLOAD) + NETIF_F_FRAGLIST | NETIF_F_VLAN_CHALLENGED) /* * If one device doesn't support one of these features, then disable it @@ -170,6 +170,12 @@ enum { */ #define NETIF_F_ALL_FOR_ALL (NETIF_F_NOCACHE_COPY | NETIF_F_FSO) +/* + * If upper/master device has these features disabled, they must be disabled + * on all lower/slave devices as well. + */ +#define NETIF_F_UPPER_DISABLES NETIF_F_LRO + /* changeable features with no special hardware requirements */ #define NETIF_F_SOFT_FEATURES (NETIF_F_GSO | NETIF_F_GRO) diff --git a/kernel/include/linux/netdevice.h b/kernel/include/linux/netdevice.h index 7a289e802..c0e12f7f0 100644 --- a/kernel/include/linux/netdevice.h +++ b/kernel/include/linux/netdevice.h @@ -507,6 +507,7 @@ static inline void napi_enable(struct napi_struct *n) BUG_ON(!test_bit(NAPI_STATE_SCHED, &n->state)); smp_mb__before_atomic(); clear_bit(NAPI_STATE_SCHED, &n->state); + clear_bit(NAPI_STATE_NPSVC, &n->state); } #ifdef CONFIG_SMP @@ -717,8 +718,8 @@ struct xps_map { u16 queues[0]; }; #define XPS_MAP_SIZE(_num) (sizeof(struct xps_map) + ((_num) * sizeof(u16))) -#define XPS_MIN_MAP_ALLOC ((L1_CACHE_BYTES - sizeof(struct xps_map)) \ - / sizeof(u16)) +#define XPS_MIN_MAP_ALLOC ((L1_CACHE_ALIGN(offsetof(struct xps_map, queues[1])) \ + - sizeof(struct xps_map)) / sizeof(u16)) /* * This structure holds all XPS maps for device. Maps are indexed by CPU. @@ -766,6 +767,13 @@ struct netdev_phys_item_id { unsigned char id_len; }; +static inline bool netdev_phys_item_id_same(struct netdev_phys_item_id *a, + struct netdev_phys_item_id *b) +{ + return a->id_len == b->id_len && + memcmp(a->id, b->id, a->id_len) == 0; +} + typedef u16 (*select_queue_fallback_t)(struct net_device *dev, struct sk_buff *skb); @@ -873,6 +881,7 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev, * int (*ndo_set_vf_rate)(struct net_device *dev, int vf, int min_tx_rate, * int max_tx_rate); * int (*ndo_set_vf_spoofchk)(struct net_device *dev, int vf, bool setting); + * int (*ndo_set_vf_trust)(struct net_device *dev, int vf, bool setting); * int (*ndo_get_vf_config)(struct net_device *dev, * int vf, struct ifla_vf_info *ivf); * int (*ndo_set_vf_link_state)(struct net_device *dev, int vf, int link_state); @@ -1041,6 +1050,16 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev, * TX queue. * int (*ndo_get_iflink)(const struct net_device *dev); * Called to get the iflink value of this device. + * void (*ndo_change_proto_down)(struct net_device *dev, + * bool proto_down); + * This function is used to pass protocol port error state information + * to the switch driver. The switch driver can react to the proto_down + * by doing a phys down on the associated switch port. + * int (*ndo_fill_metadata_dst)(struct net_device *dev, struct sk_buff *skb); + * This function is used to get egress tunnel information for given skb. + * This is useful for retrieving outer tunnel header parameters while + * sampling packet. + * */ struct net_device_ops { int (*ndo_init)(struct net_device *dev); @@ -1095,11 +1114,17 @@ struct net_device_ops { int max_tx_rate); int (*ndo_set_vf_spoofchk)(struct net_device *dev, int vf, bool setting); + int (*ndo_set_vf_trust)(struct net_device *dev, + int vf, bool setting); int (*ndo_get_vf_config)(struct net_device *dev, int vf, struct ifla_vf_info *ivf); int (*ndo_set_vf_link_state)(struct net_device *dev, int vf, int link_state); + int (*ndo_get_vf_stats)(struct net_device *dev, + int vf, + struct ifla_vf_stats + *vf_stats); int (*ndo_set_vf_port)(struct net_device *dev, int vf, struct nlattr *port[]); @@ -1207,6 +1232,10 @@ struct net_device_ops { int queue_index, u32 maxrate); int (*ndo_get_iflink)(const struct net_device *dev); + int (*ndo_change_proto_down)(struct net_device *dev, + bool proto_down); + int (*ndo_fill_metadata_dst)(struct net_device *dev, + struct sk_buff *skb); }; /** @@ -1221,13 +1250,8 @@ struct net_device_ops { * * @IFF_802_1Q_VLAN: 802.1Q VLAN device * @IFF_EBRIDGE: Ethernet bridging device - * @IFF_SLAVE_INACTIVE: bonding slave not the curr. active - * @IFF_MASTER_8023AD: bonding master, 802.3ad - * @IFF_MASTER_ALB: bonding master, balance-alb * @IFF_BONDING: bonding master or slave - * @IFF_SLAVE_NEEDARP: need ARPs for validation * @IFF_ISATAP: ISATAP interface (RFC4214) - * @IFF_MASTER_ARPMON: bonding master, ARP mon in use * @IFF_WAN_HDLC: WAN HDLC device * @IFF_XMIT_DST_RELEASE: dev_hard_start_xmit() is allowed to * release skb->dst @@ -1243,44 +1267,42 @@ struct net_device_ops { * @IFF_LIVE_ADDR_CHANGE: device supports hardware address * change when it's running * @IFF_MACVLAN: Macvlan device + * @IFF_L3MDEV_MASTER: device is an L3 master device + * @IFF_NO_QUEUE: device can run without qdisc attached + * @IFF_OPENVSWITCH: device is a Open vSwitch master + * @IFF_L3MDEV_SLAVE: device is enslaved to an L3 master device */ enum netdev_priv_flags { IFF_802_1Q_VLAN = 1<<0, IFF_EBRIDGE = 1<<1, - IFF_SLAVE_INACTIVE = 1<<2, - IFF_MASTER_8023AD = 1<<3, - IFF_MASTER_ALB = 1<<4, - IFF_BONDING = 1<<5, - IFF_SLAVE_NEEDARP = 1<<6, - IFF_ISATAP = 1<<7, - IFF_MASTER_ARPMON = 1<<8, - IFF_WAN_HDLC = 1<<9, - IFF_XMIT_DST_RELEASE = 1<<10, - IFF_DONT_BRIDGE = 1<<11, - IFF_DISABLE_NETPOLL = 1<<12, - IFF_MACVLAN_PORT = 1<<13, - IFF_BRIDGE_PORT = 1<<14, - IFF_OVS_DATAPATH = 1<<15, - IFF_TX_SKB_SHARING = 1<<16, - IFF_UNICAST_FLT = 1<<17, - IFF_TEAM_PORT = 1<<18, - IFF_SUPP_NOFCS = 1<<19, - IFF_LIVE_ADDR_CHANGE = 1<<20, - IFF_MACVLAN = 1<<21, - IFF_XMIT_DST_RELEASE_PERM = 1<<22, - IFF_IPVLAN_MASTER = 1<<23, - IFF_IPVLAN_SLAVE = 1<<24, + IFF_BONDING = 1<<2, + IFF_ISATAP = 1<<3, + IFF_WAN_HDLC = 1<<4, + IFF_XMIT_DST_RELEASE = 1<<5, + IFF_DONT_BRIDGE = 1<<6, + IFF_DISABLE_NETPOLL = 1<<7, + IFF_MACVLAN_PORT = 1<<8, + IFF_BRIDGE_PORT = 1<<9, + IFF_OVS_DATAPATH = 1<<10, + IFF_TX_SKB_SHARING = 1<<11, + IFF_UNICAST_FLT = 1<<12, + IFF_TEAM_PORT = 1<<13, + IFF_SUPP_NOFCS = 1<<14, + IFF_LIVE_ADDR_CHANGE = 1<<15, + IFF_MACVLAN = 1<<16, + IFF_XMIT_DST_RELEASE_PERM = 1<<17, + IFF_IPVLAN_MASTER = 1<<18, + IFF_IPVLAN_SLAVE = 1<<19, + IFF_L3MDEV_MASTER = 1<<20, + IFF_NO_QUEUE = 1<<21, + IFF_OPENVSWITCH = 1<<22, + IFF_L3MDEV_SLAVE = 1<<23, }; #define IFF_802_1Q_VLAN IFF_802_1Q_VLAN #define IFF_EBRIDGE IFF_EBRIDGE -#define IFF_SLAVE_INACTIVE IFF_SLAVE_INACTIVE -#define IFF_MASTER_8023AD IFF_MASTER_8023AD -#define IFF_MASTER_ALB IFF_MASTER_ALB #define IFF_BONDING IFF_BONDING -#define IFF_SLAVE_NEEDARP IFF_SLAVE_NEEDARP #define IFF_ISATAP IFF_ISATAP -#define IFF_MASTER_ARPMON IFF_MASTER_ARPMON #define IFF_WAN_HDLC IFF_WAN_HDLC #define IFF_XMIT_DST_RELEASE IFF_XMIT_DST_RELEASE #define IFF_DONT_BRIDGE IFF_DONT_BRIDGE @@ -1297,6 +1319,10 @@ enum netdev_priv_flags { #define IFF_XMIT_DST_RELEASE_PERM IFF_XMIT_DST_RELEASE_PERM #define IFF_IPVLAN_MASTER IFF_IPVLAN_MASTER #define IFF_IPVLAN_SLAVE IFF_IPVLAN_SLAVE +#define IFF_L3MDEV_MASTER IFF_L3MDEV_MASTER +#define IFF_NO_QUEUE IFF_NO_QUEUE +#define IFF_OPENVSWITCH IFF_OPENVSWITCH +#define IFF_L3MDEV_SLAVE IFF_L3MDEV_SLAVE /** * struct net_device - The DEVICE structure. @@ -1372,7 +1398,8 @@ enum netdev_priv_flags { * @dma: DMA channel * @mtu: Interface MTU value * @type: Interface hardware type - * @hard_header_len: Hardware header length + * @hard_header_len: Hardware header length, which means that this is the + * minimum size of a packet. * * @needed_headroom: Extra headroom the hardware may need, but not in all * cases can this be guaranteed @@ -1444,6 +1471,8 @@ enum netdev_priv_flags { * * @xps_maps: XXX: need comments on this one * + * @offload_fwd_mark: Offload device fwding mark + * * @trans_start: Time (in jiffies) of last Tx * @watchdog_timeo: Represents the timeout that is used by * the watchdog ( see dev_watchdog() ) @@ -1498,6 +1527,10 @@ enum netdev_priv_flags { * * @qdisc_tx_busylock: XXX: need comments on this one * + * @proto_down: protocol port state information can be sent to the + * switch driver and used to set the phys state of the + * switch port. + * * FIXME: cleanup struct net_device such that network protocol info * moves out. */ @@ -1564,7 +1597,10 @@ struct net_device { const struct net_device_ops *netdev_ops; const struct ethtool_ops *ethtool_ops; #ifdef CONFIG_NET_SWITCHDEV - const struct swdev_ops *swdev_ops; + const struct switchdev_ops *switchdev_ops; +#endif +#ifdef CONFIG_NET_L3_MASTER_DEV + const struct l3mdev_ops *l3mdev_ops; #endif const struct header_ops *header_ops; @@ -1652,7 +1688,14 @@ struct net_device { rx_handler_func_t __rcu *rx_handler; void __rcu *rx_handler_data; +#ifdef CONFIG_NET_CLS_ACT + struct tcf_proto __rcu *ingress_cl_list; +#endif struct netdev_queue __rcu *ingress_queue; +#ifdef CONFIG_NETFILTER_INGRESS + struct list_head nf_hooks_ingress; +#endif + unsigned char broadcast[MAX_ADDR_LEN]; #ifdef CONFIG_RFS_ACCEL struct cpu_rmap *rx_cpu_rmap; @@ -1674,6 +1717,10 @@ struct net_device { struct xps_dev_maps __rcu *xps_maps; #endif +#ifdef CONFIG_NET_SWITCHDEV + u32 offload_fwd_mark; +#endif + /* These may be needed for future network-power-down code. */ /* @@ -1751,6 +1798,7 @@ struct net_device { #endif struct phy_device *phydev; struct lock_class_key *qdisc_tx_busylock; + bool proto_down; }; #define to_net_dev(d) container_of(d, struct net_device, dev) @@ -1990,6 +2038,7 @@ struct offload_callbacks { struct packet_offload { __be16 type; /* This is really htons(ether_type). */ + u16 priority; struct offload_callbacks callbacks; struct list_head list; }; @@ -2020,20 +2069,23 @@ struct pcpu_sw_netstats { struct u64_stats_sync syncp; }; -#define netdev_alloc_pcpu_stats(type) \ -({ \ - typeof(type) __percpu *pcpu_stats = alloc_percpu(type); \ - if (pcpu_stats) { \ - int __cpu; \ - for_each_possible_cpu(__cpu) { \ - typeof(type) *stat; \ - stat = per_cpu_ptr(pcpu_stats, __cpu); \ - u64_stats_init(&stat->syncp); \ - } \ - } \ - pcpu_stats; \ +#define __netdev_alloc_pcpu_stats(type, gfp) \ +({ \ + typeof(type) __percpu *pcpu_stats = alloc_percpu_gfp(type, gfp);\ + if (pcpu_stats) { \ + int __cpu; \ + for_each_possible_cpu(__cpu) { \ + typeof(type) *stat; \ + stat = per_cpu_ptr(pcpu_stats, __cpu); \ + u64_stats_init(&stat->syncp); \ + } \ + } \ + pcpu_stats; \ }) +#define netdev_alloc_pcpu_stats(type) \ + __netdev_alloc_pcpu_stats(type, GFP_KERNEL) + #include <linux/notifier.h> /* netdevice notifier chain. Please remember to update the rtnetlink @@ -2068,6 +2120,7 @@ struct pcpu_sw_netstats { #define NETDEV_PRECHANGEMTU 0x0017 /* notify before mtu change happened */ #define NETDEV_CHANGEINFODATA 0x0018 #define NETDEV_BONDING_INFO 0x0019 +#define NETDEV_PRECHANGEUPPER 0x001A int register_netdevice_notifier(struct notifier_block *nb); int unregister_netdevice_notifier(struct notifier_block *nb); @@ -2081,6 +2134,13 @@ struct netdev_notifier_change_info { unsigned int flags_changed; }; +struct netdev_notifier_changeupper_info { + struct netdev_notifier_info info; /* must be first */ + struct net_device *upper_dev; /* new upper dev */ + bool master; /* is upper dev master */ + bool linking; /* is the nofication for link or unlink */ +}; + static inline void netdev_notifier_info_init(struct netdev_notifier_info *info, struct net_device *dev) { @@ -2161,6 +2221,7 @@ void dev_add_offload(struct packet_offload *po); void dev_remove_offload(struct packet_offload *po); int dev_get_iflink(const struct net_device *dev); +int dev_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb); struct net_device *__dev_get_by_flags(struct net *net, unsigned short flags, unsigned short mask); struct net_device *dev_get_by_name(struct net *net, const char *name); @@ -2171,12 +2232,8 @@ int dev_open(struct net_device *dev); int dev_close(struct net_device *dev); int dev_close_many(struct list_head *head, bool unlink); void dev_disable_lro(struct net_device *dev); -int dev_loopback_xmit(struct sock *sk, struct sk_buff *newskb); -int dev_queue_xmit_sk(struct sock *sk, struct sk_buff *skb); -static inline int dev_queue_xmit(struct sk_buff *skb) -{ - return dev_queue_xmit_sk(skb->sk, skb); -} +int dev_loopback_xmit(struct net *net, struct sock *sk, struct sk_buff *newskb); +int dev_queue_xmit(struct sk_buff *skb); int dev_queue_xmit_accel(struct sk_buff *skb, void *accel_priv); int register_netdevice(struct net_device *dev); void unregister_netdevice_queue(struct net_device *dev, struct list_head *head); @@ -2192,11 +2249,20 @@ void netdev_freemem(struct net_device *dev); void synchronize_net(void); int init_dummy_netdev(struct net_device *dev); +#ifdef CONFIG_PREEMPT_RT_FULL +static inline int dev_recursion_level(void) +{ + return current->xmit_recursion; +} + +#else + DECLARE_PER_CPU(int, xmit_recursion); static inline int dev_recursion_level(void) { return this_cpu_read(xmit_recursion); } +#endif struct net_device *dev_get_by_index(struct net *net, int ifindex); struct net_device *__dev_get_by_index(struct net *net, int ifindex); @@ -2265,8 +2331,7 @@ __sum16 __skb_gro_checksum_complete(struct sk_buff *skb); static inline bool skb_at_gro_remcsum_start(struct sk_buff *skb) { - return (NAPI_GRO_CB(skb)->gro_remcsum_start - skb_headroom(skb) == - skb_gro_offset(skb)); + return (NAPI_GRO_CB(skb)->gro_remcsum_start == skb_gro_offset(skb)); } static inline bool __skb_gro_checksum_validate_needed(struct sk_buff *skb, @@ -2362,37 +2427,58 @@ static inline void skb_gro_remcsum_init(struct gro_remcsum *grc) grc->delta = 0; } -static inline void skb_gro_remcsum_process(struct sk_buff *skb, void *ptr, - int start, int offset, - struct gro_remcsum *grc, - bool nopartial) +static inline void *skb_gro_remcsum_process(struct sk_buff *skb, void *ptr, + unsigned int off, size_t hdrlen, + int start, int offset, + struct gro_remcsum *grc, + bool nopartial) { __wsum delta; + size_t plen = hdrlen + max_t(size_t, offset + sizeof(u16), start); BUG_ON(!NAPI_GRO_CB(skb)->csum_valid); if (!nopartial) { - NAPI_GRO_CB(skb)->gro_remcsum_start = - ((unsigned char *)ptr + start) - skb->head; - return; + NAPI_GRO_CB(skb)->gro_remcsum_start = off + hdrlen + start; + return ptr; + } + + ptr = skb_gro_header_fast(skb, off); + if (skb_gro_header_hard(skb, off + plen)) { + ptr = skb_gro_header_slow(skb, off + plen, off); + if (!ptr) + return NULL; } - delta = remcsum_adjust(ptr, NAPI_GRO_CB(skb)->csum, start, offset); + delta = remcsum_adjust(ptr + hdrlen, NAPI_GRO_CB(skb)->csum, + start, offset); /* Adjust skb->csum since we changed the packet */ NAPI_GRO_CB(skb)->csum = csum_add(NAPI_GRO_CB(skb)->csum, delta); - grc->offset = (ptr + offset) - (void *)skb->head; + grc->offset = off + hdrlen + offset; grc->delta = delta; + + return ptr; } static inline void skb_gro_remcsum_cleanup(struct sk_buff *skb, struct gro_remcsum *grc) { + void *ptr; + size_t plen = grc->offset + sizeof(u16); + if (!grc->delta) return; - remcsum_unadjust((__sum16 *)(skb->head + grc->offset), grc->delta); + ptr = skb_gro_header_fast(skb, grc->offset); + if (skb_gro_header_hard(skb, grc->offset + sizeof(u16))) { + ptr = skb_gro_header_slow(skb, plen, grc->offset); + if (!ptr) + return; + } + + remcsum_unadjust((__sum16 *)ptr, grc->delta); } static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev, @@ -2553,10 +2639,6 @@ static inline void netif_tx_wake_all_queues(struct net_device *dev) static inline void netif_tx_stop_queue(struct netdev_queue *dev_queue) { - if (WARN_ON(!dev_queue)) { - pr_info("netif_stop_queue() cannot be called before register_netdev()\n"); - return; - } set_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state); } @@ -2572,15 +2654,7 @@ static inline void netif_stop_queue(struct net_device *dev) netif_tx_stop_queue(netdev_get_tx_queue(dev, 0)); } -static inline void netif_tx_stop_all_queues(struct net_device *dev) -{ - unsigned int i; - - for (i = 0; i < dev->num_tx_queues; i++) { - struct netdev_queue *txq = netdev_get_tx_queue(dev, i); - netif_tx_stop_queue(txq); - } -} +void netif_tx_stop_all_queues(struct net_device *dev); static inline bool netif_tx_queue_stopped(const struct netdev_queue *dev_queue) { @@ -2841,6 +2915,9 @@ static inline int netif_set_xps_queue(struct net_device *dev, } #endif +u16 __skb_tx_hash(const struct net_device *dev, struct sk_buff *skb, + unsigned int num_tx_queues); + /* * Returns a Tx hash for the given packet when dev->real_num_tx_queues is used * as a distribution range limit for the returned value. @@ -2938,11 +3015,7 @@ static inline void dev_consume_skb_any(struct sk_buff *skb) int netif_rx(struct sk_buff *skb); int netif_rx_ni(struct sk_buff *skb); -int netif_receive_skb_sk(struct sock *sk, struct sk_buff *skb); -static inline int netif_receive_skb(struct sk_buff *skb) -{ - return netif_receive_skb_sk(skb->sk, skb); -} +int netif_receive_skb(struct sk_buff *skb); gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb); void napi_gro_flush(struct napi_struct *napi, bool flush_old); struct sk_buff *napi_get_frags(struct napi_struct *napi); @@ -2980,6 +3053,7 @@ int dev_get_phys_port_id(struct net_device *dev, struct netdev_phys_item_id *ppid); int dev_get_phys_port_name(struct net_device *dev, char *name, size_t len); +int dev_change_proto_down(struct net_device *dev, bool proto_down); struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev); struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq, int *ret); @@ -3779,6 +3853,31 @@ static inline bool netif_supports_nofcs(struct net_device *dev) return dev->priv_flags & IFF_SUPP_NOFCS; } +static inline bool netif_is_l3_master(const struct net_device *dev) +{ + return dev->priv_flags & IFF_L3MDEV_MASTER; +} + +static inline bool netif_is_l3_slave(const struct net_device *dev) +{ + return dev->priv_flags & IFF_L3MDEV_SLAVE; +} + +static inline bool netif_is_bridge_master(const struct net_device *dev) +{ + return dev->priv_flags & IFF_EBRIDGE; +} + +static inline bool netif_is_bridge_port(const struct net_device *dev) +{ + return dev->priv_flags & IFF_BRIDGE_PORT; +} + +static inline bool netif_is_ovs_master(const struct net_device *dev) +{ + return dev->priv_flags & IFF_OPENVSWITCH; +} + /* This device needs to keep skb dst for qdisc enqueue or ndo_start_xmit() */ static inline void netif_keep_dst(struct net_device *dev) { diff --git a/kernel/include/linux/netfilter.h b/kernel/include/linux/netfilter.h index 63560d0a8..0ad556726 100644 --- a/kernel/include/linux/netfilter.h +++ b/kernel/include/linux/netfilter.h @@ -10,7 +10,10 @@ #include <linux/wait.h> #include <linux/list.h> #include <linux/static_key.h> -#include <uapi/linux/netfilter.h> +#include <linux/netfilter_defs.h> +#include <linux/netdevice.h> +#include <net/net_namespace.h> + #ifdef CONFIG_NETFILTER static inline int NF_DROP_GETERR(int verdict) { @@ -38,9 +41,6 @@ static inline void nf_inet_addr_mask(const union nf_inet_addr *a1, int netfilter_init(void); -/* Largest hook number + 1 */ -#define NF_MAX_HOOKS 8 - struct sk_buff; struct nf_hook_ops; @@ -54,16 +54,20 @@ struct nf_hook_state { struct net_device *in; struct net_device *out; struct sock *sk; - int (*okfn)(struct sock *, struct sk_buff *); + struct net *net; + struct list_head *hook_list; + int (*okfn)(struct net *, struct sock *, struct sk_buff *); }; static inline void nf_hook_state_init(struct nf_hook_state *p, + struct list_head *hook_list, unsigned int hook, int thresh, u_int8_t pf, struct net_device *indev, struct net_device *outdev, struct sock *sk, - int (*okfn)(struct sock *, struct sk_buff *)) + struct net *net, + int (*okfn)(struct net *, struct sock *, struct sk_buff *)) { p->hook = hook; p->thresh = thresh; @@ -71,24 +75,26 @@ static inline void nf_hook_state_init(struct nf_hook_state *p, p->in = indev; p->out = outdev; p->sk = sk; + p->net = net; + p->hook_list = hook_list; p->okfn = okfn; } -typedef unsigned int nf_hookfn(const struct nf_hook_ops *ops, +typedef unsigned int nf_hookfn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state); struct nf_hook_ops { - struct list_head list; + struct list_head list; /* User fills in from here down. */ - nf_hookfn *hook; - struct module *owner; - void *priv; - u_int8_t pf; - unsigned int hooknum; + nf_hookfn *hook; + struct net_device *dev; + void *priv; + u_int8_t pf; + unsigned int hooknum; /* Hooks are ordered in ascending priority. */ - int priority; + int priority; }; struct nf_sockopt_ops { @@ -116,6 +122,13 @@ struct nf_sockopt_ops { }; /* Function to register/unregister hook points. */ +int nf_register_net_hook(struct net *net, const struct nf_hook_ops *ops); +void nf_unregister_net_hook(struct net *net, const struct nf_hook_ops *ops); +int nf_register_net_hooks(struct net *net, const struct nf_hook_ops *reg, + unsigned int n); +void nf_unregister_net_hooks(struct net *net, const struct nf_hook_ops *reg, + unsigned int n); + int nf_register_hook(struct nf_hook_ops *reg); void nf_unregister_hook(struct nf_hook_ops *reg); int nf_register_hooks(struct nf_hook_ops *reg, unsigned int n); @@ -126,23 +139,23 @@ void nf_unregister_hooks(struct nf_hook_ops *reg, unsigned int n); int nf_register_sockopt(struct nf_sockopt_ops *reg); void nf_unregister_sockopt(struct nf_sockopt_ops *reg); -extern struct list_head nf_hooks[NFPROTO_NUMPROTO][NF_MAX_HOOKS]; - #ifdef HAVE_JUMP_LABEL extern struct static_key nf_hooks_needed[NFPROTO_NUMPROTO][NF_MAX_HOOKS]; -static inline bool nf_hooks_active(u_int8_t pf, unsigned int hook) +static inline bool nf_hook_list_active(struct list_head *hook_list, + u_int8_t pf, unsigned int hook) { if (__builtin_constant_p(pf) && __builtin_constant_p(hook)) return static_key_false(&nf_hooks_needed[pf][hook]); - return !list_empty(&nf_hooks[pf][hook]); + return !list_empty(hook_list); } #else -static inline bool nf_hooks_active(u_int8_t pf, unsigned int hook) +static inline bool nf_hook_list_active(struct list_head *hook_list, + u_int8_t pf, unsigned int hook) { - return !list_empty(&nf_hooks[pf][hook]); + return !list_empty(hook_list); } #endif @@ -150,35 +163,38 @@ int nf_hook_slow(struct sk_buff *skb, struct nf_hook_state *state); /** * nf_hook_thresh - call a netfilter hook - * + * * Returns 1 if the hook has allowed the packet to pass. The function * okfn must be invoked by the caller in this case. Any other return * value indicates the packet has been consumed by the hook. */ static inline int nf_hook_thresh(u_int8_t pf, unsigned int hook, + struct net *net, struct sock *sk, struct sk_buff *skb, struct net_device *indev, struct net_device *outdev, - int (*okfn)(struct sock *, struct sk_buff *), + int (*okfn)(struct net *, struct sock *, struct sk_buff *), int thresh) { - if (nf_hooks_active(pf, hook)) { + struct list_head *hook_list = &net->nf.hooks[pf][hook]; + + if (nf_hook_list_active(hook_list, pf, hook)) { struct nf_hook_state state; - nf_hook_state_init(&state, hook, thresh, pf, - indev, outdev, sk, okfn); + nf_hook_state_init(&state, hook_list, hook, thresh, + pf, indev, outdev, sk, net, okfn); return nf_hook_slow(skb, &state); } return 1; } -static inline int nf_hook(u_int8_t pf, unsigned int hook, struct sock *sk, - struct sk_buff *skb, struct net_device *indev, - struct net_device *outdev, - int (*okfn)(struct sock *, struct sk_buff *)) +static inline int nf_hook(u_int8_t pf, unsigned int hook, struct net *net, + struct sock *sk, struct sk_buff *skb, + struct net_device *indev, struct net_device *outdev, + int (*okfn)(struct net *, struct sock *, struct sk_buff *)) { - return nf_hook_thresh(pf, hook, sk, skb, indev, outdev, okfn, INT_MIN); + return nf_hook_thresh(pf, hook, net, sk, skb, indev, outdev, okfn, INT_MIN); } /* Activate hook; either okfn or kfree_skb called, unless a hook @@ -199,36 +215,38 @@ static inline int nf_hook(u_int8_t pf, unsigned int hook, struct sock *sk, */ static inline int -NF_HOOK_THRESH(uint8_t pf, unsigned int hook, struct sock *sk, +NF_HOOK_THRESH(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk, struct sk_buff *skb, struct net_device *in, struct net_device *out, - int (*okfn)(struct sock *, struct sk_buff *), int thresh) + int (*okfn)(struct net *, struct sock *, struct sk_buff *), + int thresh) { - int ret = nf_hook_thresh(pf, hook, sk, skb, in, out, okfn, thresh); + int ret = nf_hook_thresh(pf, hook, net, sk, skb, in, out, okfn, thresh); if (ret == 1) - ret = okfn(sk, skb); + ret = okfn(net, sk, skb); return ret; } static inline int -NF_HOOK_COND(uint8_t pf, unsigned int hook, struct sock *sk, +NF_HOOK_COND(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk, struct sk_buff *skb, struct net_device *in, struct net_device *out, - int (*okfn)(struct sock *, struct sk_buff *), bool cond) + int (*okfn)(struct net *, struct sock *, struct sk_buff *), + bool cond) { int ret; if (!cond || - ((ret = nf_hook_thresh(pf, hook, sk, skb, in, out, okfn, INT_MIN)) == 1)) - ret = okfn(sk, skb); + ((ret = nf_hook_thresh(pf, hook, net, sk, skb, in, out, okfn, INT_MIN)) == 1)) + ret = okfn(net, sk, skb); return ret; } static inline int -NF_HOOK(uint8_t pf, unsigned int hook, struct sock *sk, struct sk_buff *skb, +NF_HOOK(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk, struct sk_buff *skb, struct net_device *in, struct net_device *out, - int (*okfn)(struct sock *, struct sk_buff *)) + int (*okfn)(struct net *, struct sock *, struct sk_buff *)) { - return NF_HOOK_THRESH(pf, hook, sk, skb, in, out, okfn, INT_MIN); + return NF_HOOK_THRESH(pf, hook, net, sk, skb, in, out, okfn, INT_MIN); } /* Call setsockopt() */ @@ -264,7 +282,7 @@ struct nf_afinfo { struct flowi *fl, bool strict); void (*saveroute)(const struct sk_buff *skb, struct nf_queue_entry *entry); - int (*reroute)(struct sk_buff *skb, + int (*reroute)(struct net *net, struct sk_buff *skb, const struct nf_queue_entry *entry); int route_key_size; }; @@ -328,21 +346,27 @@ nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl, u_int8_t family) } #else /* !CONFIG_NETFILTER */ -#define NF_HOOK(pf, hook, sk, skb, indev, outdev, okfn) (okfn)(sk, skb) -#define NF_HOOK_COND(pf, hook, sk, skb, indev, outdev, okfn, cond) (okfn)(sk, skb) -static inline int nf_hook_thresh(u_int8_t pf, unsigned int hook, - struct sock *sk, - struct sk_buff *skb, - struct net_device *indev, - struct net_device *outdev, - int (*okfn)(struct sock *sk, struct sk_buff *), int thresh) +static inline int +NF_HOOK_COND(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk, + struct sk_buff *skb, struct net_device *in, struct net_device *out, + int (*okfn)(struct net *, struct sock *, struct sk_buff *), + bool cond) +{ + return okfn(net, sk, skb); +} + +static inline int +NF_HOOK(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk, + struct sk_buff *skb, struct net_device *in, struct net_device *out, + int (*okfn)(struct net *, struct sock *, struct sk_buff *)) { - return okfn(sk, skb); + return okfn(net, sk, skb); } -static inline int nf_hook(u_int8_t pf, unsigned int hook, struct sock *sk, - struct sk_buff *skb, struct net_device *indev, - struct net_device *outdev, - int (*okfn)(struct sock *, struct sk_buff *)) + +static inline int nf_hook(u_int8_t pf, unsigned int hook, struct net *net, + struct sock *sk, struct sk_buff *skb, + struct net_device *indev, struct net_device *outdev, + int (*okfn)(struct net *, struct sock *, struct sk_buff *)) { return 1; } @@ -354,26 +378,43 @@ nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl, u_int8_t family) #endif /*CONFIG_NETFILTER*/ #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) +#include <linux/netfilter/nf_conntrack_zones_common.h> + extern void (*ip_ct_attach)(struct sk_buff *, const struct sk_buff *) __rcu; void nf_ct_attach(struct sk_buff *, const struct sk_buff *); extern void (*nf_ct_destroy)(struct nf_conntrack *) __rcu; +#else +static inline void nf_ct_attach(struct sk_buff *new, struct sk_buff *skb) {} +#endif struct nf_conn; enum ip_conntrack_info; struct nlattr; -struct nfq_ct_hook { +struct nfnl_ct_hook { + struct nf_conn *(*get_ct)(const struct sk_buff *skb, + enum ip_conntrack_info *ctinfo); size_t (*build_size)(const struct nf_conn *ct); - int (*build)(struct sk_buff *skb, struct nf_conn *ct); + int (*build)(struct sk_buff *skb, struct nf_conn *ct, + enum ip_conntrack_info ctinfo, + u_int16_t ct_attr, u_int16_t ct_info_attr); int (*parse)(const struct nlattr *attr, struct nf_conn *ct); int (*attach_expect)(const struct nlattr *attr, struct nf_conn *ct, u32 portid, u32 report); void (*seq_adjust)(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, s32 off); }; -extern struct nfq_ct_hook __rcu *nfq_ct_hook; -#else -static inline void nf_ct_attach(struct sk_buff *new, struct sk_buff *skb) {} -#endif +extern struct nfnl_ct_hook __rcu *nfnl_ct_hook; + +/** + * nf_skb_duplicated - TEE target has sent a packet + * + * When a xtables target sends a packet, the OUTPUT and POSTROUTING + * hooks are traversed again, i.e. nft and xtables are invoked recursively. + * + * This is used by xtables TEE target to prevent the duplicated skb from + * being duplicated again. + */ +DECLARE_PER_CPU(bool, nf_skb_duplicated); #endif /*__LINUX_NETFILTER_H*/ diff --git a/kernel/include/linux/netfilter/ipset/ip_set.h b/kernel/include/linux/netfilter/ipset/ip_set.h index 34b172301..0e1f433cc 100644 --- a/kernel/include/linux/netfilter/ipset/ip_set.h +++ b/kernel/include/linux/netfilter/ipset/ip_set.h @@ -108,8 +108,13 @@ struct ip_set_counter { atomic64_t packets; }; +struct ip_set_comment_rcu { + struct rcu_head rcu; + char str[0]; +}; + struct ip_set_comment { - char *str; + struct ip_set_comment_rcu __rcu *c; }; struct ip_set_skbinfo { @@ -122,13 +127,13 @@ struct ip_set_skbinfo { struct ip_set; #define ext_timeout(e, s) \ -(unsigned long *)(((void *)(e)) + (s)->offset[IPSET_EXT_ID_TIMEOUT]) +((unsigned long *)(((void *)(e)) + (s)->offset[IPSET_EXT_ID_TIMEOUT])) #define ext_counter(e, s) \ -(struct ip_set_counter *)(((void *)(e)) + (s)->offset[IPSET_EXT_ID_COUNTER]) +((struct ip_set_counter *)(((void *)(e)) + (s)->offset[IPSET_EXT_ID_COUNTER])) #define ext_comment(e, s) \ -(struct ip_set_comment *)(((void *)(e)) + (s)->offset[IPSET_EXT_ID_COMMENT]) +((struct ip_set_comment *)(((void *)(e)) + (s)->offset[IPSET_EXT_ID_COMMENT])) #define ext_skbinfo(e, s) \ -(struct ip_set_skbinfo *)(((void *)(e)) + (s)->offset[IPSET_EXT_ID_SKBINFO]) +((struct ip_set_skbinfo *)(((void *)(e)) + (s)->offset[IPSET_EXT_ID_SKBINFO])) typedef int (*ipset_adtfn)(struct ip_set *set, void *value, const struct ip_set_ext *ext, @@ -176,6 +181,9 @@ struct ip_set_type_variant { /* List elements */ int (*list)(const struct ip_set *set, struct sk_buff *skb, struct netlink_callback *cb); + /* Keep listing private when resizing runs parallel */ + void (*uref)(struct ip_set *set, struct netlink_callback *cb, + bool start); /* Return true if "b" set is the same as "a" * according to the create set parameters */ @@ -223,7 +231,7 @@ struct ip_set { /* The name of the set */ char name[IPSET_MAXNAMELEN]; /* Lock protecting the set data */ - rwlock_t lock; + spinlock_t lock; /* References to the set */ u32 ref; /* The core set type */ @@ -341,12 +349,11 @@ ip_set_put_skbinfo(struct sk_buff *skb, struct ip_set_skbinfo *skbinfo) cpu_to_be64((u64)skbinfo->skbmark << 32 | skbinfo->skbmarkmask))) || (skbinfo->skbprio && - nla_put_net32(skb, IPSET_ATTR_SKBPRIO, + nla_put_net32(skb, IPSET_ATTR_SKBPRIO, cpu_to_be32(skbinfo->skbprio))) || (skbinfo->skbqueue && - nla_put_net16(skb, IPSET_ATTR_SKBQUEUE, + nla_put_net16(skb, IPSET_ATTR_SKBQUEUE, cpu_to_be16(skbinfo->skbqueue))); - } static inline void @@ -380,12 +387,12 @@ ip_set_init_counter(struct ip_set_counter *counter, /* Netlink CB args */ enum { - IPSET_CB_NET = 0, - IPSET_CB_DUMP, - IPSET_CB_INDEX, - IPSET_CB_ARG0, + IPSET_CB_NET = 0, /* net namespace */ + IPSET_CB_DUMP, /* dump single set/all sets */ + IPSET_CB_INDEX, /* set index */ + IPSET_CB_PRIVATE, /* set private data */ + IPSET_CB_ARG0, /* type specific */ IPSET_CB_ARG1, - IPSET_CB_ARG2, }; /* register and unregister set references */ @@ -414,7 +421,7 @@ extern void ip_set_free(void *members); extern int ip_set_get_ipaddr4(struct nlattr *nla, __be32 *ipaddr); extern int ip_set_get_ipaddr6(struct nlattr *nla, union nf_inet_addr *ipaddr); extern size_t ip_set_elem_len(struct ip_set *set, struct nlattr *tb[], - size_t len); + size_t len, size_t align); extern int ip_set_get_extensions(struct ip_set *set, struct nlattr *tb[], struct ip_set_ext *ext); @@ -533,29 +540,9 @@ bitmap_bytes(u32 a, u32 b) #include <linux/netfilter/ipset/ip_set_timeout.h> #include <linux/netfilter/ipset/ip_set_comment.h> -static inline int +int ip_set_put_extensions(struct sk_buff *skb, const struct ip_set *set, - const void *e, bool active) -{ - if (SET_WITH_TIMEOUT(set)) { - unsigned long *timeout = ext_timeout(e, set); - - if (nla_put_net32(skb, IPSET_ATTR_TIMEOUT, - htonl(active ? ip_set_timeout_get(timeout) - : *timeout))) - return -EMSGSIZE; - } - if (SET_WITH_COUNTER(set) && - ip_set_put_counter(skb, ext_counter(e, set))) - return -EMSGSIZE; - if (SET_WITH_COMMENT(set) && - ip_set_put_comment(skb, ext_comment(e, set))) - return -EMSGSIZE; - if (SET_WITH_SKBINFO(set) && - ip_set_put_skbinfo(skb, ext_skbinfo(e, set))) - return -EMSGSIZE; - return 0; -} + const void *e, bool active); #define IP_SET_INIT_KEXT(skb, opt, set) \ { .bytes = (skb)->len, .packets = 1, \ @@ -565,8 +552,6 @@ ip_set_put_extensions(struct sk_buff *skb, const struct ip_set *set, { .bytes = ULLONG_MAX, .packets = ULLONG_MAX, \ .timeout = (set)->timeout } -#define IP_SET_INIT_CIDR(a, b) ((a) ? (a) : (b)) - #define IPSET_CONCAT(a, b) a##b #define IPSET_TOKEN(a, b) IPSET_CONCAT(a, b) diff --git a/kernel/include/linux/netfilter/ipset/ip_set_comment.h b/kernel/include/linux/netfilter/ipset/ip_set_comment.h index 21217ea00..8d0248525 100644 --- a/kernel/include/linux/netfilter/ipset/ip_set_comment.h +++ b/kernel/include/linux/netfilter/ipset/ip_set_comment.h @@ -16,41 +16,57 @@ ip_set_comment_uget(struct nlattr *tb) return nla_data(tb); } +/* Called from uadd only, protected by the set spinlock. + * The kadt functions don't use the comment extensions in any way. + */ static inline void ip_set_init_comment(struct ip_set_comment *comment, const struct ip_set_ext *ext) { + struct ip_set_comment_rcu *c = rcu_dereference_protected(comment->c, 1); size_t len = ext->comment ? strlen(ext->comment) : 0; - if (unlikely(comment->str)) { - kfree(comment->str); - comment->str = NULL; + if (unlikely(c)) { + kfree_rcu(c, rcu); + rcu_assign_pointer(comment->c, NULL); } if (!len) return; if (unlikely(len > IPSET_MAX_COMMENT_SIZE)) len = IPSET_MAX_COMMENT_SIZE; - comment->str = kzalloc(len + 1, GFP_ATOMIC); - if (unlikely(!comment->str)) + c = kzalloc(sizeof(*c) + len + 1, GFP_ATOMIC); + if (unlikely(!c)) return; - strlcpy(comment->str, ext->comment, len + 1); + strlcpy(c->str, ext->comment, len + 1); + rcu_assign_pointer(comment->c, c); } +/* Used only when dumping a set, protected by rcu_read_lock_bh() */ static inline int ip_set_put_comment(struct sk_buff *skb, struct ip_set_comment *comment) { - if (!comment->str) + struct ip_set_comment_rcu *c = rcu_dereference_bh(comment->c); + + if (!c) return 0; - return nla_put_string(skb, IPSET_ATTR_COMMENT, comment->str); + return nla_put_string(skb, IPSET_ATTR_COMMENT, c->str); } +/* Called from uadd/udel, flush or the garbage collectors protected + * by the set spinlock. + * Called when the set is destroyed and when there can't be any user + * of the set data anymore. + */ static inline void ip_set_comment_free(struct ip_set_comment *comment) { - if (unlikely(!comment->str)) + struct ip_set_comment_rcu *c; + + c = rcu_dereference_protected(comment->c, 1); + if (unlikely(!c)) return; - kfree(comment->str); - comment->str = NULL; + kfree_rcu(c, rcu); + rcu_assign_pointer(comment->c, NULL); } #endif diff --git a/kernel/include/linux/netfilter/ipset/ip_set_timeout.h b/kernel/include/linux/netfilter/ipset/ip_set_timeout.h index 83c2f9e08..1d6a935c1 100644 --- a/kernel/include/linux/netfilter/ipset/ip_set_timeout.h +++ b/kernel/include/linux/netfilter/ipset/ip_set_timeout.h @@ -40,38 +40,33 @@ ip_set_timeout_uget(struct nlattr *tb) } static inline bool -ip_set_timeout_test(unsigned long timeout) +ip_set_timeout_expired(unsigned long *t) { - return timeout == IPSET_ELEM_PERMANENT || - time_is_after_jiffies(timeout); -} - -static inline bool -ip_set_timeout_expired(unsigned long *timeout) -{ - return *timeout != IPSET_ELEM_PERMANENT && - time_is_before_jiffies(*timeout); + return *t != IPSET_ELEM_PERMANENT && time_is_before_jiffies(*t); } static inline void -ip_set_timeout_set(unsigned long *timeout, u32 t) +ip_set_timeout_set(unsigned long *timeout, u32 value) { - if (!t) { + unsigned long t; + + if (!value) { *timeout = IPSET_ELEM_PERMANENT; return; } - *timeout = msecs_to_jiffies(t * 1000) + jiffies; - if (*timeout == IPSET_ELEM_PERMANENT) + t = msecs_to_jiffies(value * MSEC_PER_SEC) + jiffies; + if (t == IPSET_ELEM_PERMANENT) /* Bingo! :-) */ - (*timeout)--; + t--; + *timeout = t; } static inline u32 ip_set_timeout_get(unsigned long *timeout) { return *timeout == IPSET_ELEM_PERMANENT ? 0 : - jiffies_to_msecs(*timeout - jiffies)/1000; + jiffies_to_msecs(*timeout - jiffies)/MSEC_PER_SEC; } #endif /* __KERNEL__ */ diff --git a/kernel/include/linux/netfilter/nf_conntrack_zones_common.h b/kernel/include/linux/netfilter/nf_conntrack_zones_common.h new file mode 100644 index 000000000..5d7cf36d4 --- /dev/null +++ b/kernel/include/linux/netfilter/nf_conntrack_zones_common.h @@ -0,0 +1,23 @@ +#ifndef _NF_CONNTRACK_ZONES_COMMON_H +#define _NF_CONNTRACK_ZONES_COMMON_H + +#include <uapi/linux/netfilter/nf_conntrack_tuple_common.h> + +#define NF_CT_DEFAULT_ZONE_ID 0 + +#define NF_CT_ZONE_DIR_ORIG (1 << IP_CT_DIR_ORIGINAL) +#define NF_CT_ZONE_DIR_REPL (1 << IP_CT_DIR_REPLY) + +#define NF_CT_DEFAULT_ZONE_DIR (NF_CT_ZONE_DIR_ORIG | NF_CT_ZONE_DIR_REPL) + +#define NF_CT_FLAG_MARK 1 + +struct nf_conntrack_zone { + u16 id; + u8 flags; + u8 dir; +}; + +extern const struct nf_conntrack_zone nf_ct_zone_dflt; + +#endif /* _NF_CONNTRACK_ZONES_COMMON_H */ diff --git a/kernel/include/linux/netfilter/nfnetlink.h b/kernel/include/linux/netfilter/nfnetlink.h index e955d4730..5646b24bf 100644 --- a/kernel/include/linux/netfilter/nfnetlink.h +++ b/kernel/include/linux/netfilter/nfnetlink.h @@ -14,7 +14,7 @@ struct nfnl_callback { int (*call_rcu)(struct sock *nl, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const cda[]); - int (*call_batch)(struct sock *nl, struct sk_buff *skb, + int (*call_batch)(struct net *net, struct sock *nl, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const cda[]); const struct nla_policy *policy; /* netlink attribute policy */ @@ -45,11 +45,11 @@ int nfnetlink_unicast(struct sk_buff *skb, struct net *net, u32 portid, void nfnl_lock(__u8 subsys_id); void nfnl_unlock(__u8 subsys_id); #ifdef CONFIG_PROVE_LOCKING -int lockdep_nfnl_is_held(__u8 subsys_id); +bool lockdep_nfnl_is_held(__u8 subsys_id); #else -static inline int lockdep_nfnl_is_held(__u8 subsys_id) +static inline bool lockdep_nfnl_is_held(__u8 subsys_id) { - return 1; + return true; } #endif /* CONFIG_PROVE_LOCKING */ diff --git a/kernel/include/linux/netfilter/nfnetlink_acct.h b/kernel/include/linux/netfilter/nfnetlink_acct.h index 6ec975748..80ca889b1 100644 --- a/kernel/include/linux/netfilter/nfnetlink_acct.h +++ b/kernel/include/linux/netfilter/nfnetlink_acct.h @@ -2,6 +2,7 @@ #define _NFNL_ACCT_H_ #include <uapi/linux/netfilter/nfnetlink_acct.h> +#include <net/net_namespace.h> enum { NFACCT_NO_QUOTA = -1, @@ -11,7 +12,7 @@ enum { struct nf_acct; -struct nf_acct *nfnl_acct_find_get(const char *filter_name); +struct nf_acct *nfnl_acct_find_get(struct net *net, const char *filter_name); void nfnl_acct_put(struct nf_acct *acct); void nfnl_acct_update(const struct sk_buff *skb, struct nf_acct *nfacct); extern int nfnl_acct_overquota(const struct sk_buff *skb, diff --git a/kernel/include/linux/netfilter/x_tables.h b/kernel/include/linux/netfilter/x_tables.h index f434fc08c..8d8b410f2 100644 --- a/kernel/include/linux/netfilter/x_tables.h +++ b/kernel/include/linux/netfilter/x_tables.h @@ -3,6 +3,7 @@ #include <linux/netdevice.h> +#include <linux/static_key.h> #include <linux/locallock.h> #include <uapi/linux/netfilter/x_tables.h> @@ -13,6 +14,7 @@ * @target: the target extension * @matchinfo: per-match data * @targetinfo: per-target data + * @net network namespace through which the action was invoked * @in: input netdevice * @out: output netdevice * @fragoff: packet is a fragment, this is the data offset @@ -24,7 +26,6 @@ * Fields written to by extensions: * * @hotdrop: drop packet if we had inspection problems - * Network namespace obtainable using dev_net(in/out) */ struct xt_action_param { union { @@ -34,6 +35,7 @@ struct xt_action_param { union { const void *matchinfo, *targinfo; }; + struct net *net; const struct net_device *in, *out; int fragoff; unsigned int thoff; @@ -63,6 +65,7 @@ struct xt_mtchk_param { void *matchinfo; unsigned int hook_mask; u_int8_t family; + bool nft_compat; }; /** @@ -93,6 +96,7 @@ struct xt_tgchk_param { void *targinfo; unsigned int hook_mask; u_int8_t family; + bool nft_compat; }; /* Target destructor parameters */ @@ -221,15 +225,11 @@ struct xt_table_info { * @stacksize jumps (number of user chains) can possibly be made. */ unsigned int stacksize; - unsigned int __percpu *stackptr; void ***jumpstack; - /* ipt_entry tables: one per CPU */ - /* Note : this field MUST be the last one, see XT_TABLE_INFO_SZ */ - void *entries[1]; + + unsigned char entries[0] __aligned(8); }; -#define XT_TABLE_INFO_SZ (offsetof(struct xt_table_info, entries) \ - + nr_cpu_ids * sizeof(char *)) int xt_register_target(struct xt_target *target); void xt_unregister_target(struct xt_target *target); int xt_register_targets(struct xt_target *target, unsigned int n); @@ -285,6 +285,12 @@ DECLARE_PER_CPU(seqcount_t, xt_recseq); DECLARE_LOCAL_IRQ_LOCK(xt_write_lock); +/* xt_tee_enabled - true if x_tables needs to handle reentrancy + * + * Enabled if current ip(6)tables ruleset has at least one -j TEE rule. + */ +extern struct static_key xt_tee_enabled; + /** * xt_write_recseq_begin - start of a write section * @@ -358,6 +364,57 @@ static inline unsigned long ifname_compare_aligned(const char *_a, return ret; } + +/* On SMP, ip(6)t_entry->counters.pcnt holds address of the + * real (percpu) counter. On !SMP, its just the packet count, + * so nothing needs to be done there. + * + * xt_percpu_counter_alloc returns the address of the percpu + * counter, or 0 on !SMP. We force an alignment of 16 bytes + * so that bytes/packets share a common cache line. + * + * Hence caller must use IS_ERR_VALUE to check for error, this + * allows us to return 0 for single core systems without forcing + * callers to deal with SMP vs. NONSMP issues. + */ +static inline u64 xt_percpu_counter_alloc(void) +{ + if (nr_cpu_ids > 1) { + void __percpu *res = __alloc_percpu(sizeof(struct xt_counters), + sizeof(struct xt_counters)); + + if (res == NULL) + return (u64) -ENOMEM; + + return (u64) (__force unsigned long) res; + } + + return 0; +} +static inline void xt_percpu_counter_free(u64 pcnt) +{ + if (nr_cpu_ids > 1) + free_percpu((void __percpu *) (unsigned long) pcnt); +} + +static inline struct xt_counters * +xt_get_this_cpu_counter(struct xt_counters *cnt) +{ + if (nr_cpu_ids > 1) + return this_cpu_ptr((void __percpu *) (unsigned long) cnt->pcnt); + + return cnt; +} + +static inline struct xt_counters * +xt_get_per_cpu_counter(struct xt_counters *cnt, unsigned int cpu) +{ + if (nr_cpu_ids > 1) + return per_cpu_ptr((void __percpu *) (unsigned long) cnt->pcnt, cpu); + + return cnt; +} + struct nf_hook_ops *xt_hook_link(const struct xt_table *, nf_hookfn *); void xt_hook_unlink(const struct xt_table *, struct nf_hook_ops *); diff --git a/kernel/include/linux/netfilter_arp/arp_tables.h b/kernel/include/linux/netfilter_arp/arp_tables.h index c22a7fb8d..6f074db2f 100644 --- a/kernel/include/linux/netfilter_arp/arp_tables.h +++ b/kernel/include/linux/netfilter_arp/arp_tables.h @@ -53,7 +53,6 @@ extern struct xt_table *arpt_register_table(struct net *net, const struct arpt_replace *repl); extern void arpt_unregister_table(struct xt_table *table); extern unsigned int arpt_do_table(struct sk_buff *skb, - unsigned int hook, const struct nf_hook_state *state, struct xt_table *table); diff --git a/kernel/include/linux/netfilter_bridge.h b/kernel/include/linux/netfilter_bridge.h index f2fdb5a52..2ed40c402 100644 --- a/kernel/include/linux/netfilter_bridge.h +++ b/kernel/include/linux/netfilter_bridge.h @@ -17,17 +17,7 @@ enum nf_br_hook_priorities { #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) -#define BRNF_BRIDGED_DNAT 0x02 -#define BRNF_NF_BRIDGE_PREROUTING 0x08 - -static inline unsigned int nf_bridge_mtu_reduction(const struct sk_buff *skb) -{ - if (skb->nf_bridge->orig_proto == BRNF_PROTO_PPPOE) - return PPPOE_SES_HLEN; - return 0; -} - -int br_handle_frame_finish(struct sock *sk, struct sk_buff *skb); +int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb); static inline void br_drop_fake_rtable(struct sk_buff *skb) { @@ -70,8 +60,17 @@ nf_bridge_get_physoutdev(const struct sk_buff *skb) { return skb->nf_bridge ? skb->nf_bridge->physoutdev : NULL; } + +static inline bool nf_bridge_in_prerouting(const struct sk_buff *skb) +{ + return skb->nf_bridge && skb->nf_bridge->in_prerouting; +} #else #define br_drop_fake_rtable(skb) do { } while (0) +static inline bool nf_bridge_in_prerouting(const struct sk_buff *skb) +{ + return false; +} #endif /* CONFIG_BRIDGE_NETFILTER */ #endif diff --git a/kernel/include/linux/netfilter_bridge/ebtables.h b/kernel/include/linux/netfilter_bridge/ebtables.h index f1bd3962e..2ea517c7c 100644 --- a/kernel/include/linux/netfilter_bridge/ebtables.h +++ b/kernel/include/linux/netfilter_bridge/ebtables.h @@ -6,7 +6,7 @@ * * ebtables.c,v 2.0, April, 2002 * - * This code is stongly inspired on the iptables code which is + * This code is strongly inspired by the iptables code which is * Copyright (C) 1999 Paul `Rusty' Russell & Michael J. Neuling */ #ifndef __LINUX_BRIDGE_EFF_H @@ -111,9 +111,9 @@ struct ebt_table { extern struct ebt_table *ebt_register_table(struct net *net, const struct ebt_table *table); extern void ebt_unregister_table(struct net *net, struct ebt_table *table); -extern unsigned int ebt_do_table(unsigned int hook, struct sk_buff *skb, - const struct net_device *in, const struct net_device *out, - struct ebt_table *table); +extern unsigned int ebt_do_table(struct sk_buff *skb, + const struct nf_hook_state *state, + struct ebt_table *table); /* Used in the kernel match() functions */ #define FWINV(bool,invflg) ((bool) ^ !!(info->invflags & invflg)) diff --git a/kernel/include/linux/netfilter_defs.h b/kernel/include/linux/netfilter_defs.h new file mode 100644 index 000000000..d3a7f8597 --- /dev/null +++ b/kernel/include/linux/netfilter_defs.h @@ -0,0 +1,9 @@ +#ifndef __LINUX_NETFILTER_CORE_H_ +#define __LINUX_NETFILTER_CORE_H_ + +#include <uapi/linux/netfilter.h> + +/* Largest hook number + 1, see uapi/linux/netfilter_decnet.h */ +#define NF_MAX_HOOKS 8 + +#endif diff --git a/kernel/include/linux/netfilter_ingress.h b/kernel/include/linux/netfilter_ingress.h new file mode 100644 index 000000000..5fcd375ef --- /dev/null +++ b/kernel/include/linux/netfilter_ingress.h @@ -0,0 +1,44 @@ +#ifndef _NETFILTER_INGRESS_H_ +#define _NETFILTER_INGRESS_H_ + +#include <linux/netfilter.h> +#include <linux/netdevice.h> + +#ifdef CONFIG_NETFILTER_INGRESS +static inline bool nf_hook_ingress_active(const struct sk_buff *skb) +{ +#ifdef HAVE_JUMP_LABEL + if (!static_key_false(&nf_hooks_needed[NFPROTO_NETDEV][NF_NETDEV_INGRESS])) + return false; +#endif + return !list_empty(&skb->dev->nf_hooks_ingress); +} + +static inline int nf_hook_ingress(struct sk_buff *skb) +{ + struct nf_hook_state state; + + nf_hook_state_init(&state, &skb->dev->nf_hooks_ingress, + NF_NETDEV_INGRESS, INT_MIN, NFPROTO_NETDEV, + skb->dev, NULL, NULL, dev_net(skb->dev), NULL); + return nf_hook_slow(skb, &state); +} + +static inline void nf_hook_ingress_init(struct net_device *dev) +{ + INIT_LIST_HEAD(&dev->nf_hooks_ingress); +} +#else /* CONFIG_NETFILTER_INGRESS */ +static inline int nf_hook_ingress_active(struct sk_buff *skb) +{ + return 0; +} + +static inline int nf_hook_ingress(struct sk_buff *skb) +{ + return 0; +} + +static inline void nf_hook_ingress_init(struct net_device *dev) {} +#endif /* CONFIG_NETFILTER_INGRESS */ +#endif /* _NETFILTER_INGRESS_H_ */ diff --git a/kernel/include/linux/netfilter_ipv4.h b/kernel/include/linux/netfilter_ipv4.h index 6e4591bb5..98c03b246 100644 --- a/kernel/include/linux/netfilter_ipv4.h +++ b/kernel/include/linux/netfilter_ipv4.h @@ -6,7 +6,7 @@ #include <uapi/linux/netfilter_ipv4.h> -int ip_route_me_harder(struct sk_buff *skb, unsigned addr_type); +int ip_route_me_harder(struct net *net, struct sk_buff *skb, unsigned addr_type); __sum16 nf_ip_checksum(struct sk_buff *skb, unsigned int hook, unsigned int dataoff, u_int8_t protocol); #endif /*__LINUX_IP_NETFILTER_H*/ diff --git a/kernel/include/linux/netfilter_ipv4/ip_tables.h b/kernel/include/linux/netfilter_ipv4/ip_tables.h index 4073510da..aa598f942 100644 --- a/kernel/include/linux/netfilter_ipv4/ip_tables.h +++ b/kernel/include/linux/netfilter_ipv4/ip_tables.h @@ -64,7 +64,6 @@ struct ipt_error { extern void *ipt_alloc_initial_table(const struct xt_table *); extern unsigned int ipt_do_table(struct sk_buff *skb, - unsigned int hook, const struct nf_hook_state *state, struct xt_table *table); diff --git a/kernel/include/linux/netfilter_ipv6.h b/kernel/include/linux/netfilter_ipv6.h index 64dad1cc1..47c6b04c2 100644 --- a/kernel/include/linux/netfilter_ipv6.h +++ b/kernel/include/linux/netfilter_ipv6.h @@ -9,15 +9,6 @@ #include <uapi/linux/netfilter_ipv6.h> - -#ifdef CONFIG_NETFILTER -int ip6_route_me_harder(struct sk_buff *skb); -__sum16 nf_ip6_checksum(struct sk_buff *skb, unsigned int hook, - unsigned int dataoff, u_int8_t protocol); - -int ipv6_netfilter_init(void); -void ipv6_netfilter_fini(void); - /* * Hook functions for ipv6 to allow xt_* modules to be built-in even * if IPv6 is a module. @@ -25,8 +16,19 @@ void ipv6_netfilter_fini(void); struct nf_ipv6_ops { int (*chk_addr)(struct net *net, const struct in6_addr *addr, const struct net_device *dev, int strict); + void (*route_input)(struct sk_buff *skb); + int (*fragment)(struct net *net, struct sock *sk, struct sk_buff *skb, + int (*output)(struct net *, struct sock *, struct sk_buff *)); }; +#ifdef CONFIG_NETFILTER +int ip6_route_me_harder(struct net *net, struct sk_buff *skb); +__sum16 nf_ip6_checksum(struct sk_buff *skb, unsigned int hook, + unsigned int dataoff, u_int8_t protocol); + +int ipv6_netfilter_init(void); +void ipv6_netfilter_fini(void); + extern const struct nf_ipv6_ops __rcu *nf_ipv6_ops; static inline const struct nf_ipv6_ops *nf_get_ipv6_ops(void) { @@ -36,6 +38,7 @@ static inline const struct nf_ipv6_ops *nf_get_ipv6_ops(void) #else /* CONFIG_NETFILTER */ static inline int ipv6_netfilter_init(void) { return 0; } static inline void ipv6_netfilter_fini(void) { return; } +static inline const struct nf_ipv6_ops *nf_get_ipv6_ops(void) { return NULL; } #endif /* CONFIG_NETFILTER */ #endif /*__LINUX_IP6_NETFILTER_H*/ diff --git a/kernel/include/linux/netfilter_ipv6/ip6_tables.h b/kernel/include/linux/netfilter_ipv6/ip6_tables.h index b40d2b635..0f76e5c67 100644 --- a/kernel/include/linux/netfilter_ipv6/ip6_tables.h +++ b/kernel/include/linux/netfilter_ipv6/ip6_tables.h @@ -30,7 +30,6 @@ extern struct xt_table *ip6t_register_table(struct net *net, const struct ip6t_replace *repl); extern void ip6t_unregister_table(struct net *net, struct xt_table *table); extern unsigned int ip6t_do_table(struct sk_buff *skb, - unsigned int hook, const struct nf_hook_state *state, struct xt_table *table); diff --git a/kernel/include/linux/netlink.h b/kernel/include/linux/netlink.h index 6835c1279..639e9b8b0 100644 --- a/kernel/include/linux/netlink.h +++ b/kernel/include/linux/netlink.h @@ -28,6 +28,8 @@ struct netlink_skb_parms { __u32 dst_group; __u32 flags; struct sock *sk; + bool nsid_is_set; + int nsid; }; #define NETLINK_CB(skb) (*(struct netlink_skb_parms*)&((skb)->cb)) @@ -66,8 +68,17 @@ extern int netlink_change_ngroups(struct sock *sk, unsigned int groups); extern void __netlink_clear_multicast_users(struct sock *sk, unsigned int group); extern void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err); extern int netlink_has_listeners(struct sock *sk, unsigned int group); -extern struct sk_buff *netlink_alloc_skb(struct sock *ssk, unsigned int size, - u32 dst_portid, gfp_t gfp_mask); + +extern struct sk_buff *__netlink_alloc_skb(struct sock *ssk, unsigned int size, + unsigned int ldiff, u32 dst_portid, + gfp_t gfp_mask); +static inline struct sk_buff * +netlink_alloc_skb(struct sock *ssk, unsigned int size, u32 dst_portid, + gfp_t gfp_mask) +{ + return __netlink_alloc_skb(ssk, size, 0, dst_portid, gfp_mask); +} + extern int netlink_unicast(struct sock *ssk, struct sk_buff *skb, __u32 portid, int nonblock); extern int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, __u32 portid, __u32 group, gfp_t allocation); diff --git a/kernel/include/linux/nfs4.h b/kernel/include/linux/nfs4.h index 32201c269..e7e78537a 100644 --- a/kernel/include/linux/nfs4.h +++ b/kernel/include/linux/nfs4.h @@ -130,6 +130,7 @@ enum nfs_opnum4 { OP_READ_PLUS = 68, OP_SEEK = 69, OP_WRITE_SAME = 70, + OP_CLONE = 71, OP_ILLEGAL = 10044, }; @@ -421,6 +422,7 @@ enum lock_type4 { #define FATTR4_WORD2_LAYOUT_TYPES (1UL << 0) #define FATTR4_WORD2_LAYOUT_BLKSIZE (1UL << 1) #define FATTR4_WORD2_MDSTHRESHOLD (1UL << 4) +#define FATTR4_WORD2_CLONE_BLKSIZE (1UL << 13) #define FATTR4_WORD2_SECURITY_LABEL (1UL << 16) /* MDS threshold bitmap bits */ @@ -500,6 +502,8 @@ enum { NFSPROC4_CLNT_SEEK, NFSPROC4_CLNT_ALLOCATE, NFSPROC4_CLNT_DEALLOCATE, + NFSPROC4_CLNT_LAYOUTSTATS, + NFSPROC4_CLNT_CLONE, }; /* nfs41 types */ @@ -546,6 +550,24 @@ enum pnfs_notify_deviceid_type4 { NOTIFY_DEVICEID4_DELETE = 1 << 2, }; +enum pnfs_block_volume_type { + PNFS_BLOCK_VOLUME_SIMPLE = 0, + PNFS_BLOCK_VOLUME_SLICE = 1, + PNFS_BLOCK_VOLUME_CONCAT = 2, + PNFS_BLOCK_VOLUME_STRIPE = 3, +}; + +enum pnfs_block_extent_state { + PNFS_BLOCK_READWRITE_DATA = 0, + PNFS_BLOCK_READ_DATA = 1, + PNFS_BLOCK_INVALID_DATA = 2, + PNFS_BLOCK_NONE_DATA = 3, +}; + +/* on the wire size of a block layout extent */ +#define PNFS_BLOCK_EXTENT_SIZE \ + (7 * sizeof(__be32) + NFS4_DEVICEID4_SIZE) + #define NFL4_UFLG_MASK 0x0000003F #define NFL4_UFLG_DENSE 0x00000001 #define NFL4_UFLG_COMMIT_THRU_MDS 0x00000002 diff --git a/kernel/include/linux/nfs_fs.h b/kernel/include/linux/nfs_fs.h index b95f914ce..5455b660b 100644 --- a/kernel/include/linux/nfs_fs.h +++ b/kernel/include/linux/nfs_fs.h @@ -219,6 +219,7 @@ struct nfs_inode { #define NFS_INO_COMMIT (7) /* inode is committing unstable writes */ #define NFS_INO_LAYOUTCOMMIT (9) /* layoutcommit required */ #define NFS_INO_LAYOUTCOMMITTING (10) /* layoutcommit inflight */ +#define NFS_INO_LAYOUTSTATS (11) /* layoutstats inflight */ static inline struct nfs_inode *NFS_I(const struct inode *inode) { @@ -291,9 +292,12 @@ static inline void nfs_mark_for_revalidate(struct inode *inode) struct nfs_inode *nfsi = NFS_I(inode); spin_lock(&inode->i_lock); - nfsi->cache_validity |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS; + nfsi->cache_validity |= NFS_INO_INVALID_ATTR | + NFS_INO_REVAL_PAGECACHE | + NFS_INO_INVALID_ACCESS | + NFS_INO_INVALID_ACL; if (S_ISDIR(inode->i_mode)) - nfsi->cache_validity |= NFS_INO_REVAL_PAGECACHE|NFS_INO_INVALID_DATA; + nfsi->cache_validity |= NFS_INO_INVALID_DATA; spin_unlock(&inode->i_lock); } @@ -349,7 +353,6 @@ extern void nfs_access_add_cache(struct inode *, struct nfs_access_entry *); extern void nfs_access_set_mask(struct nfs_access_entry *, u32); extern int nfs_permission(struct inode *, int); extern int nfs_open(struct inode *, struct file *); -extern int nfs_release(struct inode *, struct file *); extern int nfs_attribute_timeout(struct inode *inode); extern int nfs_attribute_cache_expired(struct inode *inode); extern int nfs_revalidate_inode(struct nfs_server *server, struct inode *inode); @@ -367,6 +370,7 @@ extern struct nfs_open_context *nfs_find_open_context(struct inode *inode, struc extern struct nfs_open_context *alloc_nfs_open_context(struct dentry *dentry, fmode_t f_mode); extern void nfs_inode_attach_open_context(struct nfs_open_context *ctx); extern void nfs_file_set_open_context(struct file *filp, struct nfs_open_context *ctx); +extern void nfs_file_clear_open_context(struct file *flip); extern struct nfs_lock_context *nfs_get_lock_context(struct nfs_open_context *ctx); extern void nfs_put_lock_context(struct nfs_lock_context *l_ctx); extern u64 nfs_compat_user_ino64(u64 fileid); @@ -540,9 +544,7 @@ extern int nfs_readpage_async(struct nfs_open_context *, struct inode *, static inline loff_t nfs_size_to_loff_t(__u64 size) { - if (size > (__u64) OFFSET_MAX - 1) - return OFFSET_MAX - 1; - return (loff_t) size; + return min_t(u64, size, OFFSET_MAX); } static inline ino_t diff --git a/kernel/include/linux/nfs_fs_sb.h b/kernel/include/linux/nfs_fs_sb.h index 5e1273d4d..2469ab0bb 100644 --- a/kernel/include/linux/nfs_fs_sb.h +++ b/kernel/include/linux/nfs_fs_sb.h @@ -147,6 +147,7 @@ struct nfs_server { unsigned int acdirmax; unsigned int namelen; unsigned int options; /* extra options enabled by mount */ + unsigned int clone_blksize; /* granularity of a CLONE operation */ #define NFS_OPTION_FSCACHE 0x00000001 /* - local caching enabled */ #define NFS_OPTION_MIGRATION 0x00000002 /* - NFSv4 migration enabled */ @@ -173,6 +174,11 @@ struct nfs_server { set of attributes supported on this filesystem excluding the label support bit. */ + u32 exclcreat_bitmask[3]; + /* V4 bitmask representing the + set of attributes supported + on this filesystem for the + exclusive create. */ u32 cache_consistency_bitmask[3]; /* V4 bitmask representing the subset of change attribute, size, ctime @@ -220,7 +226,7 @@ struct nfs_server { #define NFS_CAP_SYMLINKS (1U << 2) #define NFS_CAP_ACLS (1U << 3) #define NFS_CAP_ATOMIC_OPEN (1U << 4) -#define NFS_CAP_CHANGE_ATTR (1U << 5) +/* #define NFS_CAP_CHANGE_ATTR (1U << 5) */ #define NFS_CAP_FILEID (1U << 6) #define NFS_CAP_MODE (1U << 7) #define NFS_CAP_NLINK (1U << 8) @@ -237,5 +243,7 @@ struct nfs_server { #define NFS_CAP_SEEK (1U << 19) #define NFS_CAP_ALLOCATE (1U << 20) #define NFS_CAP_DEALLOCATE (1U << 21) +#define NFS_CAP_LAYOUTSTATS (1U << 22) +#define NFS_CAP_CLONE (1U << 23) #endif diff --git a/kernel/include/linux/nfs_page.h b/kernel/include/linux/nfs_page.h index 3eb072dbc..f2f650f13 100644 --- a/kernel/include/linux/nfs_page.h +++ b/kernel/include/linux/nfs_page.h @@ -67,7 +67,6 @@ struct nfs_rw_ops { const fmode_t rw_mode; struct nfs_pgio_header *(*rw_alloc_header)(void); void (*rw_free_header)(struct nfs_pgio_header *); - void (*rw_release)(struct nfs_pgio_header *); int (*rw_done)(struct rpc_task *, struct nfs_pgio_header *, struct inode *); void (*rw_result)(struct rpc_task *, struct nfs_pgio_header *); diff --git a/kernel/include/linux/nfs_xdr.h b/kernel/include/linux/nfs_xdr.h index e9e9a8dcf..11bbae44f 100644 --- a/kernel/include/linux/nfs_xdr.h +++ b/kernel/include/linux/nfs_xdr.h @@ -141,6 +141,7 @@ struct nfs_fsinfo { __u32 lease_time; /* in seconds */ __u32 layouttype; /* supported pnfs layout driver */ __u32 blksize; /* preferred pnfs io block size */ + __u32 clone_blksize; /* granularity of a CLONE operation */ }; struct nfs_fsstat { @@ -250,6 +251,7 @@ struct nfs4_layoutget { struct nfs4_layoutget_res res; struct rpc_cred *cred; gfp_t gfp_flags; + long timeout; }; struct nfs4_getdeviceinfo_args { @@ -316,6 +318,68 @@ struct nfs4_layoutreturn { int rpc_status; }; +#define PNFS_LAYOUTSTATS_MAXSIZE 256 + +struct nfs42_layoutstat_args; +struct nfs42_layoutstat_devinfo; +typedef void (*layoutstats_encode_t)(struct xdr_stream *, + struct nfs42_layoutstat_args *, + struct nfs42_layoutstat_devinfo *); + +/* Per file per deviceid layoutstats */ +struct nfs42_layoutstat_devinfo { + struct nfs4_deviceid dev_id; + __u64 offset; + __u64 length; + __u64 read_count; + __u64 read_bytes; + __u64 write_count; + __u64 write_bytes; + __u32 layout_type; + layoutstats_encode_t layoutstats_encode; + void *layout_private; +}; + +struct nfs42_layoutstat_args { + struct nfs4_sequence_args seq_args; + struct nfs_fh *fh; + struct inode *inode; + nfs4_stateid stateid; + int num_dev; + struct nfs42_layoutstat_devinfo *devinfo; +}; + +struct nfs42_layoutstat_res { + struct nfs4_sequence_res seq_res; + int num_dev; + int rpc_status; +}; + +struct nfs42_layoutstat_data { + struct inode *inode; + struct nfs42_layoutstat_args args; + struct nfs42_layoutstat_res res; +}; + +struct nfs42_clone_args { + struct nfs4_sequence_args seq_args; + struct nfs_fh *src_fh; + struct nfs_fh *dst_fh; + nfs4_stateid src_stateid; + nfs4_stateid dst_stateid; + __u64 src_offset; + __u64 dst_offset; + __u64 count; + const u32 *dst_bitmask; +}; + +struct nfs42_clone_res { + struct nfs4_sequence_res seq_res; + unsigned int rpc_status; + struct nfs_fattr *dst_fattr; + const struct nfs_server *server; +}; + struct stateowner_id { __u64 create_time; __u32 uniquifier; @@ -336,7 +400,7 @@ struct nfs_openargs { struct stateowner_id id; union { struct { - struct iattr * attrs; /* UNCHECKED, GUARDED */ + struct iattr * attrs; /* UNCHECKED, GUARDED, EXCLUSIVE4_1 */ nfs4_verifier verifier; /* EXCLUSIVE */ }; nfs4_stateid delegation; /* CLAIM_DELEGATE_CUR */ @@ -346,7 +410,7 @@ struct nfs_openargs { const struct nfs_server *server; /* Needed for ID mapping */ const u32 * bitmask; const u32 * open_bitmap; - __u32 claim; + enum open_claim_type4 claim; enum createmode4 createmode; const struct nfs4_label *label; }; @@ -363,8 +427,8 @@ struct nfs_openres { const struct nfs_server *server; fmode_t delegation_type; nfs4_stateid delegation; + unsigned long pagemod_limit; __u32 do_recall; - __u64 maxsize; __u32 attrset[NFS4_BITMAP_SIZE]; struct nfs4_string *owner; struct nfs4_string *group_owner; @@ -485,7 +549,7 @@ struct nfs4_delegreturnargs { struct nfs4_delegreturnres { struct nfs4_sequence_res seq_res; struct nfs_fattr * fattr; - const struct nfs_server *server; + struct nfs_server *server; }; /* @@ -558,7 +622,7 @@ struct nfs_removeargs { struct nfs_removeres { struct nfs4_sequence_res seq_res; - const struct nfs_server *server; + struct nfs_server *server; struct nfs_fattr *dir_attr; struct nfs4_change_info cinfo; }; @@ -576,7 +640,7 @@ struct nfs_renameargs { struct nfs_renameres { struct nfs4_sequence_res seq_res; - const struct nfs_server *server; + struct nfs_server *server; struct nfs4_change_info old_cinfo; struct nfs_fattr *old_fattr; struct nfs4_change_info new_cinfo; @@ -642,7 +706,6 @@ struct nfs_setaclargs { struct nfs4_sequence_args seq_args; struct nfs_fh * fh; size_t acl_len; - unsigned int acl_pgbase; struct page ** acl_pages; }; @@ -654,7 +717,6 @@ struct nfs_getaclargs { struct nfs4_sequence_args seq_args; struct nfs_fh * fh; size_t acl_len; - unsigned int acl_pgbase; struct page ** acl_pages; }; @@ -984,17 +1046,14 @@ struct nfs4_readlink_res { struct nfs4_sequence_res seq_res; }; -#define NFS4_SETCLIENTID_NAMELEN (127) struct nfs4_setclientid { const nfs4_verifier * sc_verifier; - unsigned int sc_name_len; - char sc_name[NFS4_SETCLIENTID_NAMELEN + 1]; u32 sc_prog; unsigned int sc_netid_len; char sc_netid[RPCBIND_MAXNETIDLEN + 1]; unsigned int sc_uaddr_len; char sc_uaddr[RPCBIND_MAXUADDRLEN + 1]; - u32 sc_cb_ident; + struct nfs_client *sc_clnt; struct rpc_cred *sc_cred; }; @@ -1017,11 +1076,13 @@ struct nfs4_statfs_res { struct nfs4_server_caps_arg { struct nfs4_sequence_args seq_args; struct nfs_fh *fhandle; + const u32 * bitmask; }; struct nfs4_server_caps_res { struct nfs4_sequence_res seq_res; u32 attr_bitmask[3]; + u32 exclcreat_bitmask[3]; u32 acl_bitmask; u32 has_links; u32 has_symlinks; @@ -1142,12 +1203,9 @@ struct nfs41_state_protection { struct nfs4_op_map allow; }; -#define NFS4_EXCHANGE_ID_LEN (127) struct nfs41_exchange_id_args { struct nfs_client *client; nfs4_verifier *verifier; - unsigned int id_len; - char id[NFS4_EXCHANGE_ID_LEN]; u32 flags; struct nfs41_state_protection state_protect; }; diff --git a/kernel/include/linux/nmi.h b/kernel/include/linux/nmi.h index 3d46fb470..7ec5b8673 100644 --- a/kernel/include/linux/nmi.h +++ b/kernel/include/linux/nmi.h @@ -27,9 +27,7 @@ static inline void touch_nmi_watchdog(void) #if defined(CONFIG_HARDLOCKUP_DETECTOR) extern void hardlockup_detector_disable(void); #else -static inline void hardlockup_detector_disable(void) -{ -} +static inline void hardlockup_detector_disable(void) {} #endif /* @@ -49,6 +47,12 @@ static inline bool trigger_allbutself_cpu_backtrace(void) arch_trigger_all_cpu_backtrace(false); return true; } + +/* generic implementation */ +void nmi_trigger_all_cpu_backtrace(bool include_self, + void (*raise)(cpumask_t *mask)); +bool nmi_cpu_backtrace(struct pt_regs *regs); + #else static inline bool trigger_all_cpu_backtrace(void) { @@ -67,7 +71,9 @@ extern int nmi_watchdog_enabled; extern int soft_watchdog_enabled; extern int watchdog_user_enabled; extern int watchdog_thresh; +extern unsigned long *watchdog_cpumask_bits; extern int sysctl_softlockup_all_cpu_backtrace; +extern int sysctl_hardlockup_all_cpu_backtrace; struct ctl_table; extern int proc_watchdog(struct ctl_table *, int , void __user *, size_t *, loff_t *); @@ -77,6 +83,19 @@ extern int proc_soft_watchdog(struct ctl_table *, int , void __user *, size_t *, loff_t *); extern int proc_watchdog_thresh(struct ctl_table *, int , void __user *, size_t *, loff_t *); +extern int proc_watchdog_cpumask(struct ctl_table *, int, + void __user *, size_t *, loff_t *); +extern int lockup_detector_suspend(void); +extern void lockup_detector_resume(void); +#else +static inline int lockup_detector_suspend(void) +{ + return 0; +} + +static inline void lockup_detector_resume(void) +{ +} #endif #ifdef CONFIG_HAVE_ACPI_APEI_NMI diff --git a/kernel/include/linux/ntb.h b/kernel/include/linux/ntb.h index 9ac1a62fc..f798e2afb 100644 --- a/kernel/include/linux/ntb.h +++ b/kernel/include/linux/ntb.h @@ -4,15 +4,20 @@ * * GPL LICENSE SUMMARY * - * Copyright(c) 2012 Intel Corporation. All rights reserved. + * Copyright (C) 2015 EMC Corporation. All Rights Reserved. * * This program is free software; you can redistribute it and/or modify * it under the terms of version 2 of the GNU General Public License as * published by the Free Software Foundation. * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * * BSD LICENSE * - * Copyright(c) 2012 Intel Corporation. All rights reserved. + * Copyright (C) 2015 EMC Corporation. All Rights Reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions @@ -40,49 +45,939 @@ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. * - * Intel PCIe NTB Linux driver + * PCIe NTB Linux driver * * Contact Information: - * Jon Mason <jon.mason@intel.com> + * Allen Hubbe <Allen.Hubbe@emc.com> */ -struct ntb_transport_qp; +#ifndef _NTB_H_ +#define _NTB_H_ -struct ntb_client { - struct device_driver driver; - int (*probe)(struct pci_dev *pdev); - void (*remove)(struct pci_dev *pdev); +#include <linux/completion.h> +#include <linux/device.h> + +struct ntb_client; +struct ntb_dev; +struct pci_dev; + +/** + * enum ntb_topo - NTB connection topology + * @NTB_TOPO_NONE: Topology is unknown or invalid. + * @NTB_TOPO_PRI: On primary side of local ntb. + * @NTB_TOPO_SEC: On secondary side of remote ntb. + * @NTB_TOPO_B2B_USD: On primary side of local ntb upstream of remote ntb. + * @NTB_TOPO_B2B_DSD: On primary side of local ntb downstream of remote ntb. + */ +enum ntb_topo { + NTB_TOPO_NONE = -1, + NTB_TOPO_PRI, + NTB_TOPO_SEC, + NTB_TOPO_B2B_USD, + NTB_TOPO_B2B_DSD, +}; + +static inline int ntb_topo_is_b2b(enum ntb_topo topo) +{ + switch ((int)topo) { + case NTB_TOPO_B2B_USD: + case NTB_TOPO_B2B_DSD: + return 1; + } + return 0; +} + +static inline char *ntb_topo_string(enum ntb_topo topo) +{ + switch (topo) { + case NTB_TOPO_NONE: return "NTB_TOPO_NONE"; + case NTB_TOPO_PRI: return "NTB_TOPO_PRI"; + case NTB_TOPO_SEC: return "NTB_TOPO_SEC"; + case NTB_TOPO_B2B_USD: return "NTB_TOPO_B2B_USD"; + case NTB_TOPO_B2B_DSD: return "NTB_TOPO_B2B_DSD"; + } + return "NTB_TOPO_INVALID"; +} + +/** + * enum ntb_speed - NTB link training speed + * @NTB_SPEED_AUTO: Request the max supported speed. + * @NTB_SPEED_NONE: Link is not trained to any speed. + * @NTB_SPEED_GEN1: Link is trained to gen1 speed. + * @NTB_SPEED_GEN2: Link is trained to gen2 speed. + * @NTB_SPEED_GEN3: Link is trained to gen3 speed. + */ +enum ntb_speed { + NTB_SPEED_AUTO = -1, + NTB_SPEED_NONE = 0, + NTB_SPEED_GEN1 = 1, + NTB_SPEED_GEN2 = 2, + NTB_SPEED_GEN3 = 3, +}; + +/** + * enum ntb_width - NTB link training width + * @NTB_WIDTH_AUTO: Request the max supported width. + * @NTB_WIDTH_NONE: Link is not trained to any width. + * @NTB_WIDTH_1: Link is trained to 1 lane width. + * @NTB_WIDTH_2: Link is trained to 2 lane width. + * @NTB_WIDTH_4: Link is trained to 4 lane width. + * @NTB_WIDTH_8: Link is trained to 8 lane width. + * @NTB_WIDTH_12: Link is trained to 12 lane width. + * @NTB_WIDTH_16: Link is trained to 16 lane width. + * @NTB_WIDTH_32: Link is trained to 32 lane width. + */ +enum ntb_width { + NTB_WIDTH_AUTO = -1, + NTB_WIDTH_NONE = 0, + NTB_WIDTH_1 = 1, + NTB_WIDTH_2 = 2, + NTB_WIDTH_4 = 4, + NTB_WIDTH_8 = 8, + NTB_WIDTH_12 = 12, + NTB_WIDTH_16 = 16, + NTB_WIDTH_32 = 32, +}; + +/** + * struct ntb_client_ops - ntb client operations + * @probe: Notify client of a new device. + * @remove: Notify client to remove a device. + */ +struct ntb_client_ops { + int (*probe)(struct ntb_client *client, struct ntb_dev *ntb); + void (*remove)(struct ntb_client *client, struct ntb_dev *ntb); +}; + +static inline int ntb_client_ops_is_valid(const struct ntb_client_ops *ops) +{ + /* commented callbacks are not required: */ + return + ops->probe && + ops->remove && + 1; +} + +/** + * struct ntb_ctx_ops - ntb driver context operations + * @link_event: See ntb_link_event(). + * @db_event: See ntb_db_event(). + */ +struct ntb_ctx_ops { + void (*link_event)(void *ctx); + void (*db_event)(void *ctx, int db_vector); +}; + +static inline int ntb_ctx_ops_is_valid(const struct ntb_ctx_ops *ops) +{ + /* commented callbacks are not required: */ + return + /* ops->link_event && */ + /* ops->db_event && */ + 1; +} + +/** + * struct ntb_ctx_ops - ntb device operations + * @mw_count: See ntb_mw_count(). + * @mw_get_range: See ntb_mw_get_range(). + * @mw_set_trans: See ntb_mw_set_trans(). + * @mw_clear_trans: See ntb_mw_clear_trans(). + * @link_is_up: See ntb_link_is_up(). + * @link_enable: See ntb_link_enable(). + * @link_disable: See ntb_link_disable(). + * @db_is_unsafe: See ntb_db_is_unsafe(). + * @db_valid_mask: See ntb_db_valid_mask(). + * @db_vector_count: See ntb_db_vector_count(). + * @db_vector_mask: See ntb_db_vector_mask(). + * @db_read: See ntb_db_read(). + * @db_set: See ntb_db_set(). + * @db_clear: See ntb_db_clear(). + * @db_read_mask: See ntb_db_read_mask(). + * @db_set_mask: See ntb_db_set_mask(). + * @db_clear_mask: See ntb_db_clear_mask(). + * @peer_db_addr: See ntb_peer_db_addr(). + * @peer_db_read: See ntb_peer_db_read(). + * @peer_db_set: See ntb_peer_db_set(). + * @peer_db_clear: See ntb_peer_db_clear(). + * @peer_db_read_mask: See ntb_peer_db_read_mask(). + * @peer_db_set_mask: See ntb_peer_db_set_mask(). + * @peer_db_clear_mask: See ntb_peer_db_clear_mask(). + * @spad_is_unsafe: See ntb_spad_is_unsafe(). + * @spad_count: See ntb_spad_count(). + * @spad_read: See ntb_spad_read(). + * @spad_write: See ntb_spad_write(). + * @peer_spad_addr: See ntb_peer_spad_addr(). + * @peer_spad_read: See ntb_peer_spad_read(). + * @peer_spad_write: See ntb_peer_spad_write(). + */ +struct ntb_dev_ops { + int (*mw_count)(struct ntb_dev *ntb); + int (*mw_get_range)(struct ntb_dev *ntb, int idx, + phys_addr_t *base, resource_size_t *size, + resource_size_t *align, resource_size_t *align_size); + int (*mw_set_trans)(struct ntb_dev *ntb, int idx, + dma_addr_t addr, resource_size_t size); + int (*mw_clear_trans)(struct ntb_dev *ntb, int idx); + + int (*link_is_up)(struct ntb_dev *ntb, + enum ntb_speed *speed, enum ntb_width *width); + int (*link_enable)(struct ntb_dev *ntb, + enum ntb_speed max_speed, enum ntb_width max_width); + int (*link_disable)(struct ntb_dev *ntb); + + int (*db_is_unsafe)(struct ntb_dev *ntb); + u64 (*db_valid_mask)(struct ntb_dev *ntb); + int (*db_vector_count)(struct ntb_dev *ntb); + u64 (*db_vector_mask)(struct ntb_dev *ntb, int db_vector); + + u64 (*db_read)(struct ntb_dev *ntb); + int (*db_set)(struct ntb_dev *ntb, u64 db_bits); + int (*db_clear)(struct ntb_dev *ntb, u64 db_bits); + + u64 (*db_read_mask)(struct ntb_dev *ntb); + int (*db_set_mask)(struct ntb_dev *ntb, u64 db_bits); + int (*db_clear_mask)(struct ntb_dev *ntb, u64 db_bits); + + int (*peer_db_addr)(struct ntb_dev *ntb, + phys_addr_t *db_addr, resource_size_t *db_size); + u64 (*peer_db_read)(struct ntb_dev *ntb); + int (*peer_db_set)(struct ntb_dev *ntb, u64 db_bits); + int (*peer_db_clear)(struct ntb_dev *ntb, u64 db_bits); + + u64 (*peer_db_read_mask)(struct ntb_dev *ntb); + int (*peer_db_set_mask)(struct ntb_dev *ntb, u64 db_bits); + int (*peer_db_clear_mask)(struct ntb_dev *ntb, u64 db_bits); + + int (*spad_is_unsafe)(struct ntb_dev *ntb); + int (*spad_count)(struct ntb_dev *ntb); + + u32 (*spad_read)(struct ntb_dev *ntb, int idx); + int (*spad_write)(struct ntb_dev *ntb, int idx, u32 val); + + int (*peer_spad_addr)(struct ntb_dev *ntb, int idx, + phys_addr_t *spad_addr); + u32 (*peer_spad_read)(struct ntb_dev *ntb, int idx); + int (*peer_spad_write)(struct ntb_dev *ntb, int idx, u32 val); }; -enum { - NTB_LINK_DOWN = 0, - NTB_LINK_UP, +static inline int ntb_dev_ops_is_valid(const struct ntb_dev_ops *ops) +{ + /* commented callbacks are not required: */ + return + ops->mw_count && + ops->mw_get_range && + ops->mw_set_trans && + /* ops->mw_clear_trans && */ + ops->link_is_up && + ops->link_enable && + ops->link_disable && + /* ops->db_is_unsafe && */ + ops->db_valid_mask && + + /* both set, or both unset */ + (!ops->db_vector_count == !ops->db_vector_mask) && + + ops->db_read && + /* ops->db_set && */ + ops->db_clear && + /* ops->db_read_mask && */ + ops->db_set_mask && + ops->db_clear_mask && + ops->peer_db_addr && + /* ops->peer_db_read && */ + ops->peer_db_set && + /* ops->peer_db_clear && */ + /* ops->peer_db_read_mask && */ + /* ops->peer_db_set_mask && */ + /* ops->peer_db_clear_mask && */ + /* ops->spad_is_unsafe && */ + ops->spad_count && + ops->spad_read && + ops->spad_write && + ops->peer_spad_addr && + /* ops->peer_spad_read && */ + ops->peer_spad_write && + 1; +} + +/** + * struct ntb_client - client interested in ntb devices + * @drv: Linux driver object. + * @ops: See &ntb_client_ops. + */ +struct ntb_client { + struct device_driver drv; + const struct ntb_client_ops ops; }; -int ntb_register_client(struct ntb_client *drvr); -void ntb_unregister_client(struct ntb_client *drvr); -int ntb_register_client_dev(char *device_name); -void ntb_unregister_client_dev(char *device_name); - -struct ntb_queue_handlers { - void (*rx_handler)(struct ntb_transport_qp *qp, void *qp_data, - void *data, int len); - void (*tx_handler)(struct ntb_transport_qp *qp, void *qp_data, - void *data, int len); - void (*event_handler)(void *data, int status); +#define drv_ntb_client(__drv) container_of((__drv), struct ntb_client, drv) + +/** + * struct ntb_device - ntb device + * @dev: Linux device object. + * @pdev: Pci device entry of the ntb. + * @topo: Detected topology of the ntb. + * @ops: See &ntb_dev_ops. + * @ctx: See &ntb_ctx_ops. + * @ctx_ops: See &ntb_ctx_ops. + */ +struct ntb_dev { + struct device dev; + struct pci_dev *pdev; + enum ntb_topo topo; + const struct ntb_dev_ops *ops; + void *ctx; + const struct ntb_ctx_ops *ctx_ops; + + /* private: */ + + /* synchronize setting, clearing, and calling ctx_ops */ + spinlock_t ctx_lock; + /* block unregister until device is fully released */ + struct completion released; }; -unsigned char ntb_transport_qp_num(struct ntb_transport_qp *qp); -unsigned int ntb_transport_max_size(struct ntb_transport_qp *qp); -struct ntb_transport_qp * -ntb_transport_create_queue(void *data, struct pci_dev *pdev, - const struct ntb_queue_handlers *handlers); -void ntb_transport_free_queue(struct ntb_transport_qp *qp); -int ntb_transport_rx_enqueue(struct ntb_transport_qp *qp, void *cb, void *data, - unsigned int len); -int ntb_transport_tx_enqueue(struct ntb_transport_qp *qp, void *cb, void *data, - unsigned int len); -void *ntb_transport_rx_remove(struct ntb_transport_qp *qp, unsigned int *len); -void ntb_transport_link_up(struct ntb_transport_qp *qp); -void ntb_transport_link_down(struct ntb_transport_qp *qp); -bool ntb_transport_link_query(struct ntb_transport_qp *qp); +#define dev_ntb(__dev) container_of((__dev), struct ntb_dev, dev) + +/** + * ntb_register_client() - register a client for interest in ntb devices + * @client: Client context. + * + * The client will be added to the list of clients interested in ntb devices. + * The client will be notified of any ntb devices that are not already + * associated with a client, or if ntb devices are registered later. + * + * Return: Zero if the client is registered, otherwise an error number. + */ +#define ntb_register_client(client) \ + __ntb_register_client((client), THIS_MODULE, KBUILD_MODNAME) + +int __ntb_register_client(struct ntb_client *client, struct module *mod, + const char *mod_name); + +/** + * ntb_unregister_client() - unregister a client for interest in ntb devices + * @client: Client context. + * + * The client will be removed from the list of clients interested in ntb + * devices. If any ntb devices are associated with the client, the client will + * be notified to remove those devices. + */ +void ntb_unregister_client(struct ntb_client *client); + +#define module_ntb_client(__ntb_client) \ + module_driver(__ntb_client, ntb_register_client, \ + ntb_unregister_client) + +/** + * ntb_register_device() - register a ntb device + * @ntb: NTB device context. + * + * The device will be added to the list of ntb devices. If any clients are + * interested in ntb devices, each client will be notified of the ntb device, + * until at most one client accepts the device. + * + * Return: Zero if the device is registered, otherwise an error number. + */ +int ntb_register_device(struct ntb_dev *ntb); + +/** + * ntb_register_device() - unregister a ntb device + * @ntb: NTB device context. + * + * The device will be removed from the list of ntb devices. If the ntb device + * is associated with a client, the client will be notified to remove the + * device. + */ +void ntb_unregister_device(struct ntb_dev *ntb); + +/** + * ntb_set_ctx() - associate a driver context with an ntb device + * @ntb: NTB device context. + * @ctx: Driver context. + * @ctx_ops: Driver context operations. + * + * Associate a driver context and operations with a ntb device. The context is + * provided by the client driver, and the driver may associate a different + * context with each ntb device. + * + * Return: Zero if the context is associated, otherwise an error number. + */ +int ntb_set_ctx(struct ntb_dev *ntb, void *ctx, + const struct ntb_ctx_ops *ctx_ops); + +/** + * ntb_clear_ctx() - disassociate any driver context from an ntb device + * @ntb: NTB device context. + * + * Clear any association that may exist between a driver context and the ntb + * device. + */ +void ntb_clear_ctx(struct ntb_dev *ntb); + +/** + * ntb_link_event() - notify driver context of a change in link status + * @ntb: NTB device context. + * + * Notify the driver context that the link status may have changed. The driver + * should call ntb_link_is_up() to get the current status. + */ +void ntb_link_event(struct ntb_dev *ntb); + +/** + * ntb_db_event() - notify driver context of a doorbell event + * @ntb: NTB device context. + * @vector: Interrupt vector number. + * + * Notify the driver context of a doorbell event. If hardware supports + * multiple interrupt vectors for doorbells, the vector number indicates which + * vector received the interrupt. The vector number is relative to the first + * vector used for doorbells, starting at zero, and must be less than + ** ntb_db_vector_count(). The driver may call ntb_db_read() to check which + * doorbell bits need service, and ntb_db_vector_mask() to determine which of + * those bits are associated with the vector number. + */ +void ntb_db_event(struct ntb_dev *ntb, int vector); + +/** + * ntb_mw_count() - get the number of memory windows + * @ntb: NTB device context. + * + * Hardware and topology may support a different number of memory windows. + * + * Return: the number of memory windows. + */ +static inline int ntb_mw_count(struct ntb_dev *ntb) +{ + return ntb->ops->mw_count(ntb); +} + +/** + * ntb_mw_get_range() - get the range of a memory window + * @ntb: NTB device context. + * @idx: Memory window number. + * @base: OUT - the base address for mapping the memory window + * @size: OUT - the size for mapping the memory window + * @align: OUT - the base alignment for translating the memory window + * @align_size: OUT - the size alignment for translating the memory window + * + * Get the range of a memory window. NULL may be given for any output + * parameter if the value is not needed. The base and size may be used for + * mapping the memory window, to access the peer memory. The alignment and + * size may be used for translating the memory window, for the peer to access + * memory on the local system. + * + * Return: Zero on success, otherwise an error number. + */ +static inline int ntb_mw_get_range(struct ntb_dev *ntb, int idx, + phys_addr_t *base, resource_size_t *size, + resource_size_t *align, resource_size_t *align_size) +{ + return ntb->ops->mw_get_range(ntb, idx, base, size, + align, align_size); +} + +/** + * ntb_mw_set_trans() - set the translation of a memory window + * @ntb: NTB device context. + * @idx: Memory window number. + * @addr: The dma address local memory to expose to the peer. + * @size: The size of the local memory to expose to the peer. + * + * Set the translation of a memory window. The peer may access local memory + * through the window starting at the address, up to the size. The address + * must be aligned to the alignment specified by ntb_mw_get_range(). The size + * must be aligned to the size alignment specified by ntb_mw_get_range(). + * + * Return: Zero on success, otherwise an error number. + */ +static inline int ntb_mw_set_trans(struct ntb_dev *ntb, int idx, + dma_addr_t addr, resource_size_t size) +{ + return ntb->ops->mw_set_trans(ntb, idx, addr, size); +} + +/** + * ntb_mw_clear_trans() - clear the translation of a memory window + * @ntb: NTB device context. + * @idx: Memory window number. + * + * Clear the translation of a memory window. The peer may no longer access + * local memory through the window. + * + * Return: Zero on success, otherwise an error number. + */ +static inline int ntb_mw_clear_trans(struct ntb_dev *ntb, int idx) +{ + if (!ntb->ops->mw_clear_trans) + return ntb->ops->mw_set_trans(ntb, idx, 0, 0); + + return ntb->ops->mw_clear_trans(ntb, idx); +} + +/** + * ntb_link_is_up() - get the current ntb link state + * @ntb: NTB device context. + * @speed: OUT - The link speed expressed as PCIe generation number. + * @width: OUT - The link width expressed as the number of PCIe lanes. + * + * Get the current state of the ntb link. It is recommended to query the link + * state once after every link event. It is safe to query the link state in + * the context of the link event callback. + * + * Return: One if the link is up, zero if the link is down, otherwise a + * negative value indicating the error number. + */ +static inline int ntb_link_is_up(struct ntb_dev *ntb, + enum ntb_speed *speed, enum ntb_width *width) +{ + return ntb->ops->link_is_up(ntb, speed, width); +} + +/** + * ntb_link_enable() - enable the link on the secondary side of the ntb + * @ntb: NTB device context. + * @max_speed: The maximum link speed expressed as PCIe generation number. + * @max_width: The maximum link width expressed as the number of PCIe lanes. + * + * Enable the link on the secondary side of the ntb. This can only be done + * from the primary side of the ntb in primary or b2b topology. The ntb device + * should train the link to its maximum speed and width, or the requested speed + * and width, whichever is smaller, if supported. + * + * Return: Zero on success, otherwise an error number. + */ +static inline int ntb_link_enable(struct ntb_dev *ntb, + enum ntb_speed max_speed, + enum ntb_width max_width) +{ + return ntb->ops->link_enable(ntb, max_speed, max_width); +} + +/** + * ntb_link_disable() - disable the link on the secondary side of the ntb + * @ntb: NTB device context. + * + * Disable the link on the secondary side of the ntb. This can only be + * done from the primary side of the ntb in primary or b2b topology. The ntb + * device should disable the link. Returning from this call must indicate that + * a barrier has passed, though with no more writes may pass in either + * direction across the link, except if this call returns an error number. + * + * Return: Zero on success, otherwise an error number. + */ +static inline int ntb_link_disable(struct ntb_dev *ntb) +{ + return ntb->ops->link_disable(ntb); +} + +/** + * ntb_db_is_unsafe() - check if it is safe to use hardware doorbell + * @ntb: NTB device context. + * + * It is possible for some ntb hardware to be affected by errata. Hardware + * drivers can advise clients to avoid using doorbells. Clients may ignore + * this advice, though caution is recommended. + * + * Return: Zero if it is safe to use doorbells, or One if it is not safe. + */ +static inline int ntb_db_is_unsafe(struct ntb_dev *ntb) +{ + if (!ntb->ops->db_is_unsafe) + return 0; + + return ntb->ops->db_is_unsafe(ntb); +} + +/** + * ntb_db_valid_mask() - get a mask of doorbell bits supported by the ntb + * @ntb: NTB device context. + * + * Hardware may support different number or arrangement of doorbell bits. + * + * Return: A mask of doorbell bits supported by the ntb. + */ +static inline u64 ntb_db_valid_mask(struct ntb_dev *ntb) +{ + return ntb->ops->db_valid_mask(ntb); +} + +/** + * ntb_db_vector_count() - get the number of doorbell interrupt vectors + * @ntb: NTB device context. + * + * Hardware may support different number of interrupt vectors. + * + * Return: The number of doorbell interrupt vectors. + */ +static inline int ntb_db_vector_count(struct ntb_dev *ntb) +{ + if (!ntb->ops->db_vector_count) + return 1; + + return ntb->ops->db_vector_count(ntb); +} + +/** + * ntb_db_vector_mask() - get a mask of doorbell bits serviced by a vector + * @ntb: NTB device context. + * @vector: Doorbell vector number. + * + * Each interrupt vector may have a different number or arrangement of bits. + * + * Return: A mask of doorbell bits serviced by a vector. + */ +static inline u64 ntb_db_vector_mask(struct ntb_dev *ntb, int vector) +{ + if (!ntb->ops->db_vector_mask) + return ntb_db_valid_mask(ntb); + + return ntb->ops->db_vector_mask(ntb, vector); +} + +/** + * ntb_db_read() - read the local doorbell register + * @ntb: NTB device context. + * + * Read the local doorbell register, and return the bits that are set. + * + * Return: The bits currently set in the local doorbell register. + */ +static inline u64 ntb_db_read(struct ntb_dev *ntb) +{ + return ntb->ops->db_read(ntb); +} + +/** + * ntb_db_set() - set bits in the local doorbell register + * @ntb: NTB device context. + * @db_bits: Doorbell bits to set. + * + * Set bits in the local doorbell register, which may generate a local doorbell + * interrupt. Bits that were already set must remain set. + * + * This is unusual, and hardware may not support it. + * + * Return: Zero on success, otherwise an error number. + */ +static inline int ntb_db_set(struct ntb_dev *ntb, u64 db_bits) +{ + if (!ntb->ops->db_set) + return -EINVAL; + + return ntb->ops->db_set(ntb, db_bits); +} + +/** + * ntb_db_clear() - clear bits in the local doorbell register + * @ntb: NTB device context. + * @db_bits: Doorbell bits to clear. + * + * Clear bits in the local doorbell register, arming the bits for the next + * doorbell. + * + * Return: Zero on success, otherwise an error number. + */ +static inline int ntb_db_clear(struct ntb_dev *ntb, u64 db_bits) +{ + return ntb->ops->db_clear(ntb, db_bits); +} + +/** + * ntb_db_read_mask() - read the local doorbell mask + * @ntb: NTB device context. + * + * Read the local doorbell mask register, and return the bits that are set. + * + * This is unusual, though hardware is likely to support it. + * + * Return: The bits currently set in the local doorbell mask register. + */ +static inline u64 ntb_db_read_mask(struct ntb_dev *ntb) +{ + if (!ntb->ops->db_read_mask) + return 0; + + return ntb->ops->db_read_mask(ntb); +} + +/** + * ntb_db_set_mask() - set bits in the local doorbell mask + * @ntb: NTB device context. + * @db_bits: Doorbell mask bits to set. + * + * Set bits in the local doorbell mask register, preventing doorbell interrupts + * from being generated for those doorbell bits. Bits that were already set + * must remain set. + * + * Return: Zero on success, otherwise an error number. + */ +static inline int ntb_db_set_mask(struct ntb_dev *ntb, u64 db_bits) +{ + return ntb->ops->db_set_mask(ntb, db_bits); +} + +/** + * ntb_db_clear_mask() - clear bits in the local doorbell mask + * @ntb: NTB device context. + * @db_bits: Doorbell bits to clear. + * + * Clear bits in the local doorbell mask register, allowing doorbell interrupts + * from being generated for those doorbell bits. If a doorbell bit is already + * set at the time the mask is cleared, and the corresponding mask bit is + * changed from set to clear, then the ntb driver must ensure that + * ntb_db_event() is called. If the hardware does not generate the interrupt + * on clearing the mask bit, then the driver must call ntb_db_event() anyway. + * + * Return: Zero on success, otherwise an error number. + */ +static inline int ntb_db_clear_mask(struct ntb_dev *ntb, u64 db_bits) +{ + return ntb->ops->db_clear_mask(ntb, db_bits); +} + +/** + * ntb_peer_db_addr() - address and size of the peer doorbell register + * @ntb: NTB device context. + * @db_addr: OUT - The address of the peer doorbell register. + * @db_size: OUT - The number of bytes to write the peer doorbell register. + * + * Return the address of the peer doorbell register. This may be used, for + * example, by drivers that offload memory copy operations to a dma engine. + * The drivers may wish to ring the peer doorbell at the completion of memory + * copy operations. For efficiency, and to simplify ordering of operations + * between the dma memory copies and the ringing doorbell, the driver may + * append one additional dma memory copy with the doorbell register as the + * destination, after the memory copy operations. + * + * Return: Zero on success, otherwise an error number. + */ +static inline int ntb_peer_db_addr(struct ntb_dev *ntb, + phys_addr_t *db_addr, + resource_size_t *db_size) +{ + return ntb->ops->peer_db_addr(ntb, db_addr, db_size); +} + +/** + * ntb_peer_db_read() - read the peer doorbell register + * @ntb: NTB device context. + * + * Read the peer doorbell register, and return the bits that are set. + * + * This is unusual, and hardware may not support it. + * + * Return: The bits currently set in the peer doorbell register. + */ +static inline u64 ntb_peer_db_read(struct ntb_dev *ntb) +{ + if (!ntb->ops->peer_db_read) + return 0; + + return ntb->ops->peer_db_read(ntb); +} + +/** + * ntb_peer_db_set() - set bits in the peer doorbell register + * @ntb: NTB device context. + * @db_bits: Doorbell bits to set. + * + * Set bits in the peer doorbell register, which may generate a peer doorbell + * interrupt. Bits that were already set must remain set. + * + * Return: Zero on success, otherwise an error number. + */ +static inline int ntb_peer_db_set(struct ntb_dev *ntb, u64 db_bits) +{ + return ntb->ops->peer_db_set(ntb, db_bits); +} + +/** + * ntb_peer_db_clear() - clear bits in the peer doorbell register + * @ntb: NTB device context. + * @db_bits: Doorbell bits to clear. + * + * Clear bits in the peer doorbell register, arming the bits for the next + * doorbell. + * + * This is unusual, and hardware may not support it. + * + * Return: Zero on success, otherwise an error number. + */ +static inline int ntb_peer_db_clear(struct ntb_dev *ntb, u64 db_bits) +{ + if (!ntb->ops->db_clear) + return -EINVAL; + + return ntb->ops->peer_db_clear(ntb, db_bits); +} + +/** + * ntb_peer_db_read_mask() - read the peer doorbell mask + * @ntb: NTB device context. + * + * Read the peer doorbell mask register, and return the bits that are set. + * + * This is unusual, and hardware may not support it. + * + * Return: The bits currently set in the peer doorbell mask register. + */ +static inline u64 ntb_peer_db_read_mask(struct ntb_dev *ntb) +{ + if (!ntb->ops->db_read_mask) + return 0; + + return ntb->ops->peer_db_read_mask(ntb); +} + +/** + * ntb_peer_db_set_mask() - set bits in the peer doorbell mask + * @ntb: NTB device context. + * @db_bits: Doorbell mask bits to set. + * + * Set bits in the peer doorbell mask register, preventing doorbell interrupts + * from being generated for those doorbell bits. Bits that were already set + * must remain set. + * + * This is unusual, and hardware may not support it. + * + * Return: Zero on success, otherwise an error number. + */ +static inline int ntb_peer_db_set_mask(struct ntb_dev *ntb, u64 db_bits) +{ + if (!ntb->ops->db_set_mask) + return -EINVAL; + + return ntb->ops->peer_db_set_mask(ntb, db_bits); +} + +/** + * ntb_peer_db_clear_mask() - clear bits in the peer doorbell mask + * @ntb: NTB device context. + * @db_bits: Doorbell bits to clear. + * + * Clear bits in the peer doorbell mask register, allowing doorbell interrupts + * from being generated for those doorbell bits. If the hardware does not + * generate the interrupt on clearing the mask bit, then the driver should not + * implement this function! + * + * This is unusual, and hardware may not support it. + * + * Return: Zero on success, otherwise an error number. + */ +static inline int ntb_peer_db_clear_mask(struct ntb_dev *ntb, u64 db_bits) +{ + if (!ntb->ops->db_clear_mask) + return -EINVAL; + + return ntb->ops->peer_db_clear_mask(ntb, db_bits); +} + +/** + * ntb_spad_is_unsafe() - check if it is safe to use the hardware scratchpads + * @ntb: NTB device context. + * + * It is possible for some ntb hardware to be affected by errata. Hardware + * drivers can advise clients to avoid using scratchpads. Clients may ignore + * this advice, though caution is recommended. + * + * Return: Zero if it is safe to use scratchpads, or One if it is not safe. + */ +static inline int ntb_spad_is_unsafe(struct ntb_dev *ntb) +{ + if (!ntb->ops->spad_is_unsafe) + return 0; + + return ntb->ops->spad_is_unsafe(ntb); +} + +/** + * ntb_mw_count() - get the number of scratchpads + * @ntb: NTB device context. + * + * Hardware and topology may support a different number of scratchpads. + * + * Return: the number of scratchpads. + */ +static inline int ntb_spad_count(struct ntb_dev *ntb) +{ + return ntb->ops->spad_count(ntb); +} + +/** + * ntb_spad_read() - read the local scratchpad register + * @ntb: NTB device context. + * @idx: Scratchpad index. + * + * Read the local scratchpad register, and return the value. + * + * Return: The value of the local scratchpad register. + */ +static inline u32 ntb_spad_read(struct ntb_dev *ntb, int idx) +{ + return ntb->ops->spad_read(ntb, idx); +} + +/** + * ntb_spad_write() - write the local scratchpad register + * @ntb: NTB device context. + * @idx: Scratchpad index. + * @val: Scratchpad value. + * + * Write the value to the local scratchpad register. + * + * Return: Zero on success, otherwise an error number. + */ +static inline int ntb_spad_write(struct ntb_dev *ntb, int idx, u32 val) +{ + return ntb->ops->spad_write(ntb, idx, val); +} + +/** + * ntb_peer_spad_addr() - address of the peer scratchpad register + * @ntb: NTB device context. + * @idx: Scratchpad index. + * @spad_addr: OUT - The address of the peer scratchpad register. + * + * Return the address of the peer doorbell register. This may be used, for + * example, by drivers that offload memory copy operations to a dma engine. + * + * Return: Zero on success, otherwise an error number. + */ +static inline int ntb_peer_spad_addr(struct ntb_dev *ntb, int idx, + phys_addr_t *spad_addr) +{ + return ntb->ops->peer_spad_addr(ntb, idx, spad_addr); +} + +/** + * ntb_peer_spad_read() - read the peer scratchpad register + * @ntb: NTB device context. + * @idx: Scratchpad index. + * + * Read the peer scratchpad register, and return the value. + * + * Return: The value of the local scratchpad register. + */ +static inline u32 ntb_peer_spad_read(struct ntb_dev *ntb, int idx) +{ + return ntb->ops->peer_spad_read(ntb, idx); +} + +/** + * ntb_peer_spad_write() - write the peer scratchpad register + * @ntb: NTB device context. + * @idx: Scratchpad index. + * @val: Scratchpad value. + * + * Write the value to the peer scratchpad register. + * + * Return: Zero on success, otherwise an error number. + */ +static inline int ntb_peer_spad_write(struct ntb_dev *ntb, int idx, u32 val) +{ + return ntb->ops->peer_spad_write(ntb, idx, val); +} + +#endif diff --git a/kernel/include/linux/ntb_transport.h b/kernel/include/linux/ntb_transport.h new file mode 100644 index 000000000..7243eb98a --- /dev/null +++ b/kernel/include/linux/ntb_transport.h @@ -0,0 +1,86 @@ +/* + * This file is provided under a dual BSD/GPLv2 license. When using or + * redistributing this file, you may do so under either license. + * + * GPL LICENSE SUMMARY + * + * Copyright(c) 2012 Intel Corporation. All rights reserved. + * Copyright (C) 2015 EMC Corporation. All Rights Reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public License as + * published by the Free Software Foundation. + * + * BSD LICENSE + * + * Copyright(c) 2012 Intel Corporation. All rights reserved. + * Copyright (C) 2015 EMC Corporation. All Rights Reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copy + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * * Neither the name of Intel Corporation nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + * + * PCIe NTB Transport Linux driver + * + * Contact Information: + * Jon Mason <jon.mason@intel.com> + */ + +struct ntb_transport_qp; + +struct ntb_transport_client { + struct device_driver driver; + int (*probe)(struct device *client_dev); + void (*remove)(struct device *client_dev); +}; + +int ntb_transport_register_client(struct ntb_transport_client *drvr); +void ntb_transport_unregister_client(struct ntb_transport_client *drvr); +int ntb_transport_register_client_dev(char *device_name); +void ntb_transport_unregister_client_dev(char *device_name); + +struct ntb_queue_handlers { + void (*rx_handler)(struct ntb_transport_qp *qp, void *qp_data, + void *data, int len); + void (*tx_handler)(struct ntb_transport_qp *qp, void *qp_data, + void *data, int len); + void (*event_handler)(void *data, int status); +}; + +unsigned char ntb_transport_qp_num(struct ntb_transport_qp *qp); +unsigned int ntb_transport_max_size(struct ntb_transport_qp *qp); +struct ntb_transport_qp * +ntb_transport_create_queue(void *data, struct device *client_dev, + const struct ntb_queue_handlers *handlers); +void ntb_transport_free_queue(struct ntb_transport_qp *qp); +int ntb_transport_rx_enqueue(struct ntb_transport_qp *qp, void *cb, void *data, + unsigned int len); +int ntb_transport_tx_enqueue(struct ntb_transport_qp *qp, void *cb, void *data, + unsigned int len); +void *ntb_transport_rx_remove(struct ntb_transport_qp *qp, unsigned int *len); +void ntb_transport_link_up(struct ntb_transport_qp *qp); +void ntb_transport_link_down(struct ntb_transport_qp *qp); +bool ntb_transport_link_query(struct ntb_transport_qp *qp); +unsigned int ntb_transport_tx_free_entry(struct ntb_transport_qp *qp); diff --git a/kernel/include/linux/nvme.h b/kernel/include/linux/nvme.h index 8dbd05e70..3af5f454c 100644 --- a/kernel/include/linux/nvme.h +++ b/kernel/include/linux/nvme.h @@ -15,10 +15,7 @@ #ifndef _LINUX_NVME_H #define _LINUX_NVME_H -#include <uapi/linux/nvme.h> -#include <linux/pci.h> -#include <linux/kref.h> -#include <linux/blk-mq.h> +#include <linux/types.h> struct nvme_bar { __u64 cap; /* Controller Capabilities */ @@ -28,18 +25,32 @@ struct nvme_bar { __u32 cc; /* Controller Configuration */ __u32 rsvd1; /* Reserved */ __u32 csts; /* Controller Status */ - __u32 rsvd2; /* Reserved */ + __u32 nssr; /* Subsystem Reset */ __u32 aqa; /* Admin Queue Attributes */ __u64 asq; /* Admin SQ Base Address */ __u64 acq; /* Admin CQ Base Address */ + __u32 cmbloc; /* Controller Memory Buffer Location */ + __u32 cmbsz; /* Controller Memory Buffer Size */ }; #define NVME_CAP_MQES(cap) ((cap) & 0xffff) #define NVME_CAP_TIMEOUT(cap) (((cap) >> 24) & 0xff) #define NVME_CAP_STRIDE(cap) (((cap) >> 32) & 0xf) +#define NVME_CAP_NSSRC(cap) (((cap) >> 36) & 0x1) #define NVME_CAP_MPSMIN(cap) (((cap) >> 48) & 0xf) #define NVME_CAP_MPSMAX(cap) (((cap) >> 52) & 0xf) +#define NVME_CMB_BIR(cmbloc) ((cmbloc) & 0x7) +#define NVME_CMB_OFST(cmbloc) (((cmbloc) >> 12) & 0xfffff) +#define NVME_CMB_SZ(cmbsz) (((cmbsz) >> 12) & 0xfffff) +#define NVME_CMB_SZU(cmbsz) (((cmbsz) >> 8) & 0xf) + +#define NVME_CMB_WDS(cmbsz) ((cmbsz) & 0x10) +#define NVME_CMB_RDS(cmbsz) ((cmbsz) & 0x8) +#define NVME_CMB_LISTS(cmbsz) ((cmbsz) & 0x4) +#define NVME_CMB_CQS(cmbsz) ((cmbsz) & 0x2) +#define NVME_CMB_SQS(cmbsz) ((cmbsz) & 0x1) + enum { NVME_CC_ENABLE = 1 << 0, NVME_CC_CSS_NVM = 0 << 4, @@ -55,125 +66,535 @@ enum { NVME_CC_IOCQES = 4 << 20, NVME_CSTS_RDY = 1 << 0, NVME_CSTS_CFS = 1 << 1, + NVME_CSTS_NSSRO = 1 << 4, NVME_CSTS_SHST_NORMAL = 0 << 2, NVME_CSTS_SHST_OCCUR = 1 << 2, NVME_CSTS_SHST_CMPLT = 2 << 2, NVME_CSTS_SHST_MASK = 3 << 2, }; -extern unsigned char nvme_io_timeout; -#define NVME_IO_TIMEOUT (nvme_io_timeout * HZ) +struct nvme_id_power_state { + __le16 max_power; /* centiwatts */ + __u8 rsvd2; + __u8 flags; + __le32 entry_lat; /* microseconds */ + __le32 exit_lat; /* microseconds */ + __u8 read_tput; + __u8 read_lat; + __u8 write_tput; + __u8 write_lat; + __le16 idle_power; + __u8 idle_scale; + __u8 rsvd19; + __le16 active_power; + __u8 active_work_scale; + __u8 rsvd23[9]; +}; -/* - * Represents an NVM Express device. Each nvme_dev is a PCI function. - */ -struct nvme_dev { - struct list_head node; - struct nvme_queue **queues; - struct request_queue *admin_q; - struct blk_mq_tag_set tagset; - struct blk_mq_tag_set admin_tagset; - u32 __iomem *dbs; - struct pci_dev *pci_dev; - struct dma_pool *prp_page_pool; - struct dma_pool *prp_small_pool; - int instance; - unsigned queue_count; - unsigned online_queues; - unsigned max_qid; - int q_depth; - u32 db_stride; - u32 ctrl_config; - struct msix_entry *entry; - struct nvme_bar __iomem *bar; - struct list_head namespaces; - struct kref kref; - struct device *device; - work_func_t reset_workfn; - struct work_struct reset_work; - struct work_struct probe_work; - char name[12]; - char serial[20]; - char model[40]; - char firmware_rev[8]; - u32 max_hw_sectors; - u32 stripe_size; - u32 page_size; - u16 oncs; - u16 abort_limit; - u8 event_limit; - u8 vwc; +enum { + NVME_PS_FLAGS_MAX_POWER_SCALE = 1 << 0, + NVME_PS_FLAGS_NON_OP_STATE = 1 << 1, }; -/* - * An NVM Express namespace is equivalent to a SCSI LUN - */ -struct nvme_ns { - struct list_head list; +struct nvme_id_ctrl { + __le16 vid; + __le16 ssvid; + char sn[20]; + char mn[40]; + char fr[8]; + __u8 rab; + __u8 ieee[3]; + __u8 mic; + __u8 mdts; + __le16 cntlid; + __le32 ver; + __u8 rsvd84[172]; + __le16 oacs; + __u8 acl; + __u8 aerl; + __u8 frmw; + __u8 lpa; + __u8 elpe; + __u8 npss; + __u8 avscc; + __u8 apsta; + __le16 wctemp; + __le16 cctemp; + __u8 rsvd270[242]; + __u8 sqes; + __u8 cqes; + __u8 rsvd514[2]; + __le32 nn; + __le16 oncs; + __le16 fuses; + __u8 fna; + __u8 vwc; + __le16 awun; + __le16 awupf; + __u8 nvscc; + __u8 rsvd531; + __le16 acwu; + __u8 rsvd534[2]; + __le32 sgls; + __u8 rsvd540[1508]; + struct nvme_id_power_state psd[32]; + __u8 vs[1024]; +}; - struct nvme_dev *dev; - struct request_queue *queue; - struct gendisk *disk; +enum { + NVME_CTRL_ONCS_COMPARE = 1 << 0, + NVME_CTRL_ONCS_WRITE_UNCORRECTABLE = 1 << 1, + NVME_CTRL_ONCS_DSM = 1 << 2, + NVME_CTRL_VWC_PRESENT = 1 << 0, +}; - unsigned ns_id; - int lba_shift; - u16 ms; - bool ext; - u8 pi_type; - u64 mode_select_num_blocks; - u32 mode_select_block_len; +struct nvme_lbaf { + __le16 ms; + __u8 ds; + __u8 rp; }; -/* - * The nvme_iod describes the data in an I/O, including the list of PRP - * entries. You can't see it in this data structure because C doesn't let - * me express that. Use nvme_alloc_iod to ensure there's enough space - * allocated to store the PRP list. - */ -struct nvme_iod { - unsigned long private; /* For the use of the submitter of the I/O */ - int npages; /* In the PRP list. 0 means small pool in use */ - int offset; /* Of PRP list */ - int nents; /* Used in scatterlist */ - int length; /* Of data, in bytes */ - dma_addr_t first_dma; - struct scatterlist meta_sg[1]; /* metadata requires single contiguous buffer */ - struct scatterlist sg[0]; -}; - -static inline u64 nvme_block_nr(struct nvme_ns *ns, sector_t sector) -{ - return (sector >> (ns->lba_shift - 9)); -} - -/** - * nvme_free_iod - frees an nvme_iod - * @dev: The device that the I/O was submitted to - * @iod: The memory to free - */ -void nvme_free_iod(struct nvme_dev *dev, struct nvme_iod *iod); - -int nvme_setup_prps(struct nvme_dev *, struct nvme_iod *, int, gfp_t); -struct nvme_iod *nvme_map_user_pages(struct nvme_dev *dev, int write, - unsigned long addr, unsigned length); -void nvme_unmap_user_pages(struct nvme_dev *dev, int write, - struct nvme_iod *iod); -int nvme_submit_io_cmd(struct nvme_dev *, struct nvme_ns *, - struct nvme_command *, u32 *); -int nvme_submit_flush_data(struct nvme_queue *nvmeq, struct nvme_ns *ns); -int nvme_submit_admin_cmd(struct nvme_dev *, struct nvme_command *, - u32 *result); -int nvme_identify(struct nvme_dev *, unsigned nsid, unsigned cns, - dma_addr_t dma_addr); -int nvme_get_features(struct nvme_dev *dev, unsigned fid, unsigned nsid, - dma_addr_t dma_addr, u32 *result); -int nvme_set_features(struct nvme_dev *dev, unsigned fid, unsigned dword11, - dma_addr_t dma_addr, u32 *result); - -struct sg_io_hdr; - -int nvme_sg_io(struct nvme_ns *ns, struct sg_io_hdr __user *u_hdr); -int nvme_sg_io32(struct nvme_ns *ns, unsigned long arg); -int nvme_sg_get_version_num(int __user *ip); +struct nvme_id_ns { + __le64 nsze; + __le64 ncap; + __le64 nuse; + __u8 nsfeat; + __u8 nlbaf; + __u8 flbas; + __u8 mc; + __u8 dpc; + __u8 dps; + __u8 nmic; + __u8 rescap; + __u8 fpi; + __u8 rsvd33; + __le16 nawun; + __le16 nawupf; + __le16 nacwu; + __le16 nabsn; + __le16 nabo; + __le16 nabspf; + __u16 rsvd46; + __le64 nvmcap[2]; + __u8 rsvd64[40]; + __u8 nguid[16]; + __u8 eui64[8]; + struct nvme_lbaf lbaf[16]; + __u8 rsvd192[192]; + __u8 vs[3712]; +}; + +enum { + NVME_NS_FEAT_THIN = 1 << 0, + NVME_NS_FLBAS_LBA_MASK = 0xf, + NVME_NS_FLBAS_META_EXT = 0x10, + NVME_LBAF_RP_BEST = 0, + NVME_LBAF_RP_BETTER = 1, + NVME_LBAF_RP_GOOD = 2, + NVME_LBAF_RP_DEGRADED = 3, + NVME_NS_DPC_PI_LAST = 1 << 4, + NVME_NS_DPC_PI_FIRST = 1 << 3, + NVME_NS_DPC_PI_TYPE3 = 1 << 2, + NVME_NS_DPC_PI_TYPE2 = 1 << 1, + NVME_NS_DPC_PI_TYPE1 = 1 << 0, + NVME_NS_DPS_PI_FIRST = 1 << 3, + NVME_NS_DPS_PI_MASK = 0x7, + NVME_NS_DPS_PI_TYPE1 = 1, + NVME_NS_DPS_PI_TYPE2 = 2, + NVME_NS_DPS_PI_TYPE3 = 3, +}; + +struct nvme_smart_log { + __u8 critical_warning; + __u8 temperature[2]; + __u8 avail_spare; + __u8 spare_thresh; + __u8 percent_used; + __u8 rsvd6[26]; + __u8 data_units_read[16]; + __u8 data_units_written[16]; + __u8 host_reads[16]; + __u8 host_writes[16]; + __u8 ctrl_busy_time[16]; + __u8 power_cycles[16]; + __u8 power_on_hours[16]; + __u8 unsafe_shutdowns[16]; + __u8 media_errors[16]; + __u8 num_err_log_entries[16]; + __le32 warning_temp_time; + __le32 critical_comp_time; + __le16 temp_sensor[8]; + __u8 rsvd216[296]; +}; + +enum { + NVME_SMART_CRIT_SPARE = 1 << 0, + NVME_SMART_CRIT_TEMPERATURE = 1 << 1, + NVME_SMART_CRIT_RELIABILITY = 1 << 2, + NVME_SMART_CRIT_MEDIA = 1 << 3, + NVME_SMART_CRIT_VOLATILE_MEMORY = 1 << 4, +}; + +enum { + NVME_AER_NOTICE_NS_CHANGED = 0x0002, +}; + +struct nvme_lba_range_type { + __u8 type; + __u8 attributes; + __u8 rsvd2[14]; + __u64 slba; + __u64 nlb; + __u8 guid[16]; + __u8 rsvd48[16]; +}; + +enum { + NVME_LBART_TYPE_FS = 0x01, + NVME_LBART_TYPE_RAID = 0x02, + NVME_LBART_TYPE_CACHE = 0x03, + NVME_LBART_TYPE_SWAP = 0x04, + + NVME_LBART_ATTRIB_TEMP = 1 << 0, + NVME_LBART_ATTRIB_HIDE = 1 << 1, +}; + +struct nvme_reservation_status { + __le32 gen; + __u8 rtype; + __u8 regctl[2]; + __u8 resv5[2]; + __u8 ptpls; + __u8 resv10[13]; + struct { + __le16 cntlid; + __u8 rcsts; + __u8 resv3[5]; + __le64 hostid; + __le64 rkey; + } regctl_ds[]; +}; + +/* I/O commands */ + +enum nvme_opcode { + nvme_cmd_flush = 0x00, + nvme_cmd_write = 0x01, + nvme_cmd_read = 0x02, + nvme_cmd_write_uncor = 0x04, + nvme_cmd_compare = 0x05, + nvme_cmd_write_zeroes = 0x08, + nvme_cmd_dsm = 0x09, + nvme_cmd_resv_register = 0x0d, + nvme_cmd_resv_report = 0x0e, + nvme_cmd_resv_acquire = 0x11, + nvme_cmd_resv_release = 0x15, +}; + +struct nvme_common_command { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 nsid; + __le32 cdw2[2]; + __le64 metadata; + __le64 prp1; + __le64 prp2; + __le32 cdw10[6]; +}; + +struct nvme_rw_command { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 nsid; + __u64 rsvd2; + __le64 metadata; + __le64 prp1; + __le64 prp2; + __le64 slba; + __le16 length; + __le16 control; + __le32 dsmgmt; + __le32 reftag; + __le16 apptag; + __le16 appmask; +}; + +enum { + NVME_RW_LR = 1 << 15, + NVME_RW_FUA = 1 << 14, + NVME_RW_DSM_FREQ_UNSPEC = 0, + NVME_RW_DSM_FREQ_TYPICAL = 1, + NVME_RW_DSM_FREQ_RARE = 2, + NVME_RW_DSM_FREQ_READS = 3, + NVME_RW_DSM_FREQ_WRITES = 4, + NVME_RW_DSM_FREQ_RW = 5, + NVME_RW_DSM_FREQ_ONCE = 6, + NVME_RW_DSM_FREQ_PREFETCH = 7, + NVME_RW_DSM_FREQ_TEMP = 8, + NVME_RW_DSM_LATENCY_NONE = 0 << 4, + NVME_RW_DSM_LATENCY_IDLE = 1 << 4, + NVME_RW_DSM_LATENCY_NORM = 2 << 4, + NVME_RW_DSM_LATENCY_LOW = 3 << 4, + NVME_RW_DSM_SEQ_REQ = 1 << 6, + NVME_RW_DSM_COMPRESSED = 1 << 7, + NVME_RW_PRINFO_PRCHK_REF = 1 << 10, + NVME_RW_PRINFO_PRCHK_APP = 1 << 11, + NVME_RW_PRINFO_PRCHK_GUARD = 1 << 12, + NVME_RW_PRINFO_PRACT = 1 << 13, +}; + +struct nvme_dsm_cmd { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 nsid; + __u64 rsvd2[2]; + __le64 prp1; + __le64 prp2; + __le32 nr; + __le32 attributes; + __u32 rsvd12[4]; +}; + +enum { + NVME_DSMGMT_IDR = 1 << 0, + NVME_DSMGMT_IDW = 1 << 1, + NVME_DSMGMT_AD = 1 << 2, +}; + +struct nvme_dsm_range { + __le32 cattr; + __le32 nlb; + __le64 slba; +}; + +/* Admin commands */ + +enum nvme_admin_opcode { + nvme_admin_delete_sq = 0x00, + nvme_admin_create_sq = 0x01, + nvme_admin_get_log_page = 0x02, + nvme_admin_delete_cq = 0x04, + nvme_admin_create_cq = 0x05, + nvme_admin_identify = 0x06, + nvme_admin_abort_cmd = 0x08, + nvme_admin_set_features = 0x09, + nvme_admin_get_features = 0x0a, + nvme_admin_async_event = 0x0c, + nvme_admin_activate_fw = 0x10, + nvme_admin_download_fw = 0x11, + nvme_admin_format_nvm = 0x80, + nvme_admin_security_send = 0x81, + nvme_admin_security_recv = 0x82, +}; + +enum { + NVME_QUEUE_PHYS_CONTIG = (1 << 0), + NVME_CQ_IRQ_ENABLED = (1 << 1), + NVME_SQ_PRIO_URGENT = (0 << 1), + NVME_SQ_PRIO_HIGH = (1 << 1), + NVME_SQ_PRIO_MEDIUM = (2 << 1), + NVME_SQ_PRIO_LOW = (3 << 1), + NVME_FEAT_ARBITRATION = 0x01, + NVME_FEAT_POWER_MGMT = 0x02, + NVME_FEAT_LBA_RANGE = 0x03, + NVME_FEAT_TEMP_THRESH = 0x04, + NVME_FEAT_ERR_RECOVERY = 0x05, + NVME_FEAT_VOLATILE_WC = 0x06, + NVME_FEAT_NUM_QUEUES = 0x07, + NVME_FEAT_IRQ_COALESCE = 0x08, + NVME_FEAT_IRQ_CONFIG = 0x09, + NVME_FEAT_WRITE_ATOMIC = 0x0a, + NVME_FEAT_ASYNC_EVENT = 0x0b, + NVME_FEAT_AUTO_PST = 0x0c, + NVME_FEAT_SW_PROGRESS = 0x80, + NVME_FEAT_HOST_ID = 0x81, + NVME_FEAT_RESV_MASK = 0x82, + NVME_FEAT_RESV_PERSIST = 0x83, + NVME_LOG_ERROR = 0x01, + NVME_LOG_SMART = 0x02, + NVME_LOG_FW_SLOT = 0x03, + NVME_LOG_RESERVATION = 0x80, + NVME_FWACT_REPL = (0 << 3), + NVME_FWACT_REPL_ACTV = (1 << 3), + NVME_FWACT_ACTV = (2 << 3), +}; + +struct nvme_identify { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 nsid; + __u64 rsvd2[2]; + __le64 prp1; + __le64 prp2; + __le32 cns; + __u32 rsvd11[5]; +}; + +struct nvme_features { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 nsid; + __u64 rsvd2[2]; + __le64 prp1; + __le64 prp2; + __le32 fid; + __le32 dword11; + __u32 rsvd12[4]; +}; + +struct nvme_create_cq { + __u8 opcode; + __u8 flags; + __u16 command_id; + __u32 rsvd1[5]; + __le64 prp1; + __u64 rsvd8; + __le16 cqid; + __le16 qsize; + __le16 cq_flags; + __le16 irq_vector; + __u32 rsvd12[4]; +}; + +struct nvme_create_sq { + __u8 opcode; + __u8 flags; + __u16 command_id; + __u32 rsvd1[5]; + __le64 prp1; + __u64 rsvd8; + __le16 sqid; + __le16 qsize; + __le16 sq_flags; + __le16 cqid; + __u32 rsvd12[4]; +}; + +struct nvme_delete_queue { + __u8 opcode; + __u8 flags; + __u16 command_id; + __u32 rsvd1[9]; + __le16 qid; + __u16 rsvd10; + __u32 rsvd11[5]; +}; + +struct nvme_abort_cmd { + __u8 opcode; + __u8 flags; + __u16 command_id; + __u32 rsvd1[9]; + __le16 sqid; + __u16 cid; + __u32 rsvd11[5]; +}; + +struct nvme_download_firmware { + __u8 opcode; + __u8 flags; + __u16 command_id; + __u32 rsvd1[5]; + __le64 prp1; + __le64 prp2; + __le32 numd; + __le32 offset; + __u32 rsvd12[4]; +}; + +struct nvme_format_cmd { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 nsid; + __u64 rsvd2[4]; + __le32 cdw10; + __u32 rsvd11[5]; +}; + +struct nvme_command { + union { + struct nvme_common_command common; + struct nvme_rw_command rw; + struct nvme_identify identify; + struct nvme_features features; + struct nvme_create_cq create_cq; + struct nvme_create_sq create_sq; + struct nvme_delete_queue delete_queue; + struct nvme_download_firmware dlfw; + struct nvme_format_cmd format; + struct nvme_dsm_cmd dsm; + struct nvme_abort_cmd abort; + }; +}; + +enum { + NVME_SC_SUCCESS = 0x0, + NVME_SC_INVALID_OPCODE = 0x1, + NVME_SC_INVALID_FIELD = 0x2, + NVME_SC_CMDID_CONFLICT = 0x3, + NVME_SC_DATA_XFER_ERROR = 0x4, + NVME_SC_POWER_LOSS = 0x5, + NVME_SC_INTERNAL = 0x6, + NVME_SC_ABORT_REQ = 0x7, + NVME_SC_ABORT_QUEUE = 0x8, + NVME_SC_FUSED_FAIL = 0x9, + NVME_SC_FUSED_MISSING = 0xa, + NVME_SC_INVALID_NS = 0xb, + NVME_SC_CMD_SEQ_ERROR = 0xc, + NVME_SC_SGL_INVALID_LAST = 0xd, + NVME_SC_SGL_INVALID_COUNT = 0xe, + NVME_SC_SGL_INVALID_DATA = 0xf, + NVME_SC_SGL_INVALID_METADATA = 0x10, + NVME_SC_SGL_INVALID_TYPE = 0x11, + NVME_SC_LBA_RANGE = 0x80, + NVME_SC_CAP_EXCEEDED = 0x81, + NVME_SC_NS_NOT_READY = 0x82, + NVME_SC_RESERVATION_CONFLICT = 0x83, + NVME_SC_CQ_INVALID = 0x100, + NVME_SC_QID_INVALID = 0x101, + NVME_SC_QUEUE_SIZE = 0x102, + NVME_SC_ABORT_LIMIT = 0x103, + NVME_SC_ABORT_MISSING = 0x104, + NVME_SC_ASYNC_LIMIT = 0x105, + NVME_SC_FIRMWARE_SLOT = 0x106, + NVME_SC_FIRMWARE_IMAGE = 0x107, + NVME_SC_INVALID_VECTOR = 0x108, + NVME_SC_INVALID_LOG_PAGE = 0x109, + NVME_SC_INVALID_FORMAT = 0x10a, + NVME_SC_FIRMWARE_NEEDS_RESET = 0x10b, + NVME_SC_INVALID_QUEUE = 0x10c, + NVME_SC_FEATURE_NOT_SAVEABLE = 0x10d, + NVME_SC_FEATURE_NOT_CHANGEABLE = 0x10e, + NVME_SC_FEATURE_NOT_PER_NS = 0x10f, + NVME_SC_FW_NEEDS_RESET_SUBSYS = 0x110, + NVME_SC_BAD_ATTRIBUTES = 0x180, + NVME_SC_INVALID_PI = 0x181, + NVME_SC_READ_ONLY = 0x182, + NVME_SC_WRITE_FAULT = 0x280, + NVME_SC_READ_ERROR = 0x281, + NVME_SC_GUARD_CHECK = 0x282, + NVME_SC_APPTAG_CHECK = 0x283, + NVME_SC_REFTAG_CHECK = 0x284, + NVME_SC_COMPARE_FAILED = 0x285, + NVME_SC_ACCESS_DENIED = 0x286, + NVME_SC_DNR = 0x4000, +}; + +struct nvme_completion { + __le32 result; /* Used by admin commands to return data */ + __u32 rsvd; + __le16 sq_head; /* how much of this queue may be reclaimed */ + __le16 sq_id; /* submission queue that generated this entry */ + __u16 command_id; /* of the command which completed */ + __le16 status; /* did the command fail, and if so, why? */ +}; + +#define NVME_VS(major, minor) (((major) << 16) | ((minor) << 8)) #endif /* _LINUX_NVME_H */ diff --git a/kernel/include/linux/nvmem-consumer.h b/kernel/include/linux/nvmem-consumer.h new file mode 100644 index 000000000..9bb77d3ed --- /dev/null +++ b/kernel/include/linux/nvmem-consumer.h @@ -0,0 +1,157 @@ +/* + * nvmem framework consumer. + * + * Copyright (C) 2015 Srinivas Kandagatla <srinivas.kandagatla@linaro.org> + * Copyright (C) 2013 Maxime Ripard <maxime.ripard@free-electrons.com> + * + * This file is licensed under the terms of the GNU General Public + * License version 2. This program is licensed "as is" without any + * warranty of any kind, whether express or implied. + */ + +#ifndef _LINUX_NVMEM_CONSUMER_H +#define _LINUX_NVMEM_CONSUMER_H + +struct device; +struct device_node; +/* consumer cookie */ +struct nvmem_cell; +struct nvmem_device; + +struct nvmem_cell_info { + const char *name; + unsigned int offset; + unsigned int bytes; + unsigned int bit_offset; + unsigned int nbits; +}; + +#if IS_ENABLED(CONFIG_NVMEM) + +/* Cell based interface */ +struct nvmem_cell *nvmem_cell_get(struct device *dev, const char *name); +struct nvmem_cell *devm_nvmem_cell_get(struct device *dev, const char *name); +void nvmem_cell_put(struct nvmem_cell *cell); +void devm_nvmem_cell_put(struct device *dev, struct nvmem_cell *cell); +void *nvmem_cell_read(struct nvmem_cell *cell, size_t *len); +int nvmem_cell_write(struct nvmem_cell *cell, void *buf, size_t len); + +/* direct nvmem device read/write interface */ +struct nvmem_device *nvmem_device_get(struct device *dev, const char *name); +struct nvmem_device *devm_nvmem_device_get(struct device *dev, + const char *name); +void nvmem_device_put(struct nvmem_device *nvmem); +void devm_nvmem_device_put(struct device *dev, struct nvmem_device *nvmem); +int nvmem_device_read(struct nvmem_device *nvmem, unsigned int offset, + size_t bytes, void *buf); +int nvmem_device_write(struct nvmem_device *nvmem, unsigned int offset, + size_t bytes, void *buf); +ssize_t nvmem_device_cell_read(struct nvmem_device *nvmem, + struct nvmem_cell_info *info, void *buf); +int nvmem_device_cell_write(struct nvmem_device *nvmem, + struct nvmem_cell_info *info, void *buf); + +#else + +static inline struct nvmem_cell *nvmem_cell_get(struct device *dev, + const char *name) +{ + return ERR_PTR(-ENOSYS); +} + +static inline struct nvmem_cell *devm_nvmem_cell_get(struct device *dev, + const char *name) +{ + return ERR_PTR(-ENOSYS); +} + +static inline void devm_nvmem_cell_put(struct device *dev, + struct nvmem_cell *cell) +{ + +} +static inline void nvmem_cell_put(struct nvmem_cell *cell) +{ +} + +static inline char *nvmem_cell_read(struct nvmem_cell *cell, size_t *len) +{ + return ERR_PTR(-ENOSYS); +} + +static inline int nvmem_cell_write(struct nvmem_cell *cell, + const char *buf, size_t len) +{ + return -ENOSYS; +} + +static inline struct nvmem_device *nvmem_device_get(struct device *dev, + const char *name) +{ + return ERR_PTR(-ENOSYS); +} + +static inline struct nvmem_device *devm_nvmem_device_get(struct device *dev, + const char *name) +{ + return ERR_PTR(-ENOSYS); +} + +static inline void nvmem_device_put(struct nvmem_device *nvmem) +{ +} + +static inline void devm_nvmem_device_put(struct device *dev, + struct nvmem_device *nvmem) +{ +} + +static inline ssize_t nvmem_device_cell_read(struct nvmem_device *nvmem, + struct nvmem_cell_info *info, + void *buf) +{ + return -ENOSYS; +} + +static inline int nvmem_device_cell_write(struct nvmem_device *nvmem, + struct nvmem_cell_info *info, + void *buf) +{ + return -ENOSYS; +} + +static inline int nvmem_device_read(struct nvmem_device *nvmem, + unsigned int offset, size_t bytes, + void *buf) +{ + return -ENOSYS; +} + +static inline int nvmem_device_write(struct nvmem_device *nvmem, + unsigned int offset, size_t bytes, + void *buf) +{ + return -ENOSYS; +} +#endif /* CONFIG_NVMEM */ + +#if IS_ENABLED(CONFIG_NVMEM) && IS_ENABLED(CONFIG_OF) +struct nvmem_cell *of_nvmem_cell_get(struct device_node *np, + const char *name); +struct nvmem_device *of_nvmem_device_get(struct device_node *np, + const char *name); +#else +static inline struct nvmem_cell *of_nvmem_cell_get(struct device_node *np, + const char *name) +{ + return ERR_PTR(-ENOSYS); +} + +static inline struct nvmem_device *of_nvmem_device_get(struct device_node *np, + const char *name) +{ + return ERR_PTR(-ENOSYS); +} +#endif /* CONFIG_NVMEM && CONFIG_OF */ + +#endif /* ifndef _LINUX_NVMEM_CONSUMER_H */ diff --git a/kernel/include/linux/nvmem-provider.h b/kernel/include/linux/nvmem-provider.h new file mode 100644 index 000000000..0b68caff1 --- /dev/null +++ b/kernel/include/linux/nvmem-provider.h @@ -0,0 +1,47 @@ +/* + * nvmem framework provider. + * + * Copyright (C) 2015 Srinivas Kandagatla <srinivas.kandagatla@linaro.org> + * Copyright (C) 2013 Maxime Ripard <maxime.ripard@free-electrons.com> + * + * This file is licensed under the terms of the GNU General Public + * License version 2. This program is licensed "as is" without any + * warranty of any kind, whether express or implied. + */ + +#ifndef _LINUX_NVMEM_PROVIDER_H +#define _LINUX_NVMEM_PROVIDER_H + +struct nvmem_device; +struct nvmem_cell_info; + +struct nvmem_config { + struct device *dev; + const char *name; + int id; + struct module *owner; + const struct nvmem_cell_info *cells; + int ncells; + bool read_only; +}; + +#if IS_ENABLED(CONFIG_NVMEM) + +struct nvmem_device *nvmem_register(const struct nvmem_config *cfg); +int nvmem_unregister(struct nvmem_device *nvmem); + +#else + +static inline struct nvmem_device *nvmem_register(const struct nvmem_config *c) +{ + return ERR_PTR(-ENOSYS); +} + +static inline int nvmem_unregister(struct nvmem_device *nvmem) +{ + return -ENOSYS; +} + +#endif /* CONFIG_NVMEM */ + +#endif /* ifndef _LINUX_NVMEM_PROVIDER_H */ diff --git a/kernel/include/linux/nx842.h b/kernel/include/linux/nx842.h deleted file mode 100644 index a4d324c64..000000000 --- a/kernel/include/linux/nx842.h +++ /dev/null @@ -1,11 +0,0 @@ -#ifndef __NX842_H__ -#define __NX842_H__ - -int nx842_get_workmem_size(void); -int nx842_get_workmem_size_aligned(void); -int nx842_compress(const unsigned char *in, unsigned int in_len, - unsigned char *out, unsigned int *out_len, void *wrkmem); -int nx842_decompress(const unsigned char *in, unsigned int in_len, - unsigned char *out, unsigned int *out_len, void *wrkmem); - -#endif diff --git a/kernel/include/linux/of.h b/kernel/include/linux/of.h index 8135d507d..dd10626a6 100644 --- a/kernel/include/linux/of.h +++ b/kernel/include/linux/of.h @@ -120,6 +120,14 @@ extern struct device_node *of_aliases; extern struct device_node *of_stdout; extern raw_spinlock_t devtree_lock; +/* flag descriptions (need to be visible even when !CONFIG_OF) */ +#define OF_DYNAMIC 1 /* node and properties were allocated via kmalloc */ +#define OF_DETACHED 2 /* node has been detached from the device tree */ +#define OF_POPULATED 3 /* device already created for the node */ +#define OF_POPULATED_BUS 4 /* of_platform_populate recursed to children of this node */ + +#define OF_BAD_ADDR ((u64)-1) + #ifdef CONFIG_OF void of_core_init(void); @@ -128,9 +136,10 @@ static inline bool is_of_node(struct fwnode_handle *fwnode) return fwnode && fwnode->type == FWNODE_OF; } -static inline struct device_node *of_node(struct fwnode_handle *fwnode) +static inline struct device_node *to_of_node(struct fwnode_handle *fwnode) { - return fwnode ? container_of(fwnode, struct device_node, fwnode) : NULL; + return is_of_node(fwnode) ? + container_of(fwnode, struct device_node, fwnode) : NULL; } static inline bool of_have_populated_dt(void) @@ -219,17 +228,9 @@ static inline unsigned long of_read_ulong(const __be32 *cell, int size) #define of_node_cmp(s1, s2) strcasecmp((s1), (s2)) #endif -/* flag descriptions */ -#define OF_DYNAMIC 1 /* node and properties were allocated via kmalloc */ -#define OF_DETACHED 2 /* node has been detached from the device tree */ -#define OF_POPULATED 3 /* device already created for the node */ -#define OF_POPULATED_BUS 4 /* of_platform_populate recursed to children of this node */ - #define OF_IS_DYNAMIC(x) test_bit(OF_DYNAMIC, &x->_flags) #define OF_MARK_DYNAMIC(x) set_bit(OF_DYNAMIC, &x->_flags) -#define OF_BAD_ADDR ((u64)-1) - static inline const char *of_node_full_name(const struct device_node *np) { return np ? np->full_name : "<no-node>"; @@ -387,7 +388,7 @@ static inline bool is_of_node(struct fwnode_handle *fwnode) return false; } -static inline struct device_node *of_node(struct fwnode_handle *fwnode) +static inline struct device_node *to_of_node(struct fwnode_handle *fwnode) { return NULL; } @@ -428,6 +429,11 @@ static inline struct device_node *of_find_node_opts_by_path(const char *path, return NULL; } +static inline struct device_node *of_find_node_by_phandle(phandle handle) +{ + return NULL; +} + static inline struct device_node *of_get_parent(const struct device_node *node) { return NULL; @@ -824,7 +830,7 @@ static inline int of_property_read_string_index(struct device_node *np, * @propname: name of the property to be searched. * * Search for a property in a device node. - * Returns true if the property exist false otherwise. + * Returns true if the property exists false otherwise. */ static inline bool of_property_read_bool(const struct device_node *np, const char *propname) diff --git a/kernel/include/linux/of_address.h b/kernel/include/linux/of_address.h index d88e81be6..507daad0b 100644 --- a/kernel/include/linux/of_address.h +++ b/kernel/include/linux/of_address.h @@ -57,6 +57,13 @@ extern int of_dma_get_range(struct device_node *np, u64 *dma_addr, u64 *paddr, u64 *size); extern bool of_dma_is_coherent(struct device_node *np); #else /* CONFIG_OF_ADDRESS */ + +static inline u64 of_translate_address(struct device_node *np, + const __be32 *addr) +{ + return OF_BAD_ADDR; +} + static inline struct device_node *of_find_matching_node_by_address( struct device_node *from, const struct of_device_id *matches, diff --git a/kernel/include/linux/of_device.h b/kernel/include/linux/of_device.h index 22801b10c..cc7dd687a 100644 --- a/kernel/include/linux/of_device.h +++ b/kernel/include/linux/of_device.h @@ -33,6 +33,8 @@ extern int of_device_add(struct platform_device *pdev); extern int of_device_register(struct platform_device *ofdev); extern void of_device_unregister(struct platform_device *ofdev); +extern const void *of_device_get_match_data(const struct device *dev); + extern ssize_t of_device_get_modalias(struct device *dev, char *str, ssize_t len); @@ -57,7 +59,7 @@ void of_dma_configure(struct device *dev, struct device_node *np); #else /* CONFIG_OF */ static inline int of_driver_match_device(struct device *dev, - struct device_driver *drv) + const struct device_driver *drv) { return 0; } @@ -65,6 +67,11 @@ static inline int of_driver_match_device(struct device *dev, static inline void of_device_uevent(struct device *dev, struct kobj_uevent_env *env) { } +static inline const void *of_device_get_match_data(const struct device *dev) +{ + return NULL; +} + static inline int of_device_get_modalias(struct device *dev, char *str, ssize_t len) { diff --git a/kernel/include/linux/of_dma.h b/kernel/include/linux/of_dma.h index 56bc026c1..b90d8ec57 100644 --- a/kernel/include/linux/of_dma.h +++ b/kernel/include/linux/of_dma.h @@ -23,6 +23,9 @@ struct of_dma { struct device_node *of_node; struct dma_chan *(*of_dma_xlate) (struct of_phandle_args *, struct of_dma *); + void *(*of_dma_route_allocate) + (struct of_phandle_args *, struct of_dma *); + struct dma_router *dma_router; void *of_dma_data; }; @@ -31,18 +34,26 @@ struct of_dma_filter_info { dma_filter_fn filter_fn; }; -#ifdef CONFIG_OF +#ifdef CONFIG_DMA_OF extern int of_dma_controller_register(struct device_node *np, struct dma_chan *(*of_dma_xlate) (struct of_phandle_args *, struct of_dma *), void *data); extern void of_dma_controller_free(struct device_node *np); + +extern int of_dma_router_register(struct device_node *np, + void *(*of_dma_route_allocate) + (struct of_phandle_args *, struct of_dma *), + struct dma_router *dma_router); +#define of_dma_router_free of_dma_controller_free + extern struct dma_chan *of_dma_request_slave_channel(struct device_node *np, const char *name); extern struct dma_chan *of_dma_simple_xlate(struct of_phandle_args *dma_spec, struct of_dma *ofdma); extern struct dma_chan *of_dma_xlate_by_chan_id(struct of_phandle_args *dma_spec, struct of_dma *ofdma); + #else static inline int of_dma_controller_register(struct device_node *np, struct dma_chan *(*of_dma_xlate) @@ -56,10 +67,20 @@ static inline void of_dma_controller_free(struct device_node *np) { } +static inline int of_dma_router_register(struct device_node *np, + void *(*of_dma_route_allocate) + (struct of_phandle_args *, struct of_dma *), + struct dma_router *dma_router) +{ + return -ENODEV; +} + +#define of_dma_router_free of_dma_controller_free + static inline struct dma_chan *of_dma_request_slave_channel(struct device_node *np, const char *name) { - return NULL; + return ERR_PTR(-ENODEV); } static inline struct dma_chan *of_dma_simple_xlate(struct of_phandle_args *dma_spec, diff --git a/kernel/include/linux/of_fdt.h b/kernel/include/linux/of_fdt.h index 587ee5079..df9ef3801 100644 --- a/kernel/include/linux/of_fdt.h +++ b/kernel/include/linux/of_fdt.h @@ -37,7 +37,7 @@ extern bool of_fdt_is_big_endian(const void *blob, unsigned long node); extern int of_fdt_match(const void *blob, unsigned long node, const char *const *compat); -extern void of_fdt_unflatten_tree(unsigned long *blob, +extern void of_fdt_unflatten_tree(const unsigned long *blob, struct device_node **mynodes); /* TBD: Temporary export of fdt globals - remove when code fully merged */ @@ -64,6 +64,7 @@ extern int early_init_dt_scan_chosen(unsigned long node, const char *uname, extern int early_init_dt_scan_memory(unsigned long node, const char *uname, int depth, void *data); extern void early_init_fdt_scan_reserved_mem(void); +extern void early_init_fdt_reserve_self(void); extern void early_init_dt_add_memory_arch(u64 base, u64 size); extern int early_init_dt_reserve_memory_arch(phys_addr_t base, phys_addr_t size, bool no_map); @@ -91,6 +92,7 @@ extern u64 fdt_translate_address(const void *blob, int node_offset); extern void of_fdt_limit_memory(int limit); #else /* CONFIG_OF_FLATTREE */ static inline void early_init_fdt_scan_reserved_mem(void) {} +static inline void early_init_fdt_reserve_self(void) {} static inline const char *of_flat_dt_get_machine_name(void) { return NULL; } static inline void unflatten_device_tree(void) {} static inline void unflatten_and_copy_device_tree(void) {} diff --git a/kernel/include/linux/of_gpio.h b/kernel/include/linux/of_gpio.h index 69dbe312b..87d6d1632 100644 --- a/kernel/include/linux/of_gpio.h +++ b/kernel/include/linux/of_gpio.h @@ -29,6 +29,7 @@ struct device_node; */ enum of_gpio_flags { OF_GPIO_ACTIVE_LOW = 0x1, + OF_GPIO_SINGLE_ENDED = 0x2, }; #ifdef CONFIG_OF_GPIO @@ -54,7 +55,7 @@ extern int of_mm_gpiochip_add(struct device_node *np, struct of_mm_gpio_chip *mm_gc); extern void of_mm_gpiochip_remove(struct of_mm_gpio_chip *mm_gc); -extern void of_gpiochip_add(struct gpio_chip *gc); +extern int of_gpiochip_add(struct gpio_chip *gc); extern void of_gpiochip_remove(struct gpio_chip *gc); extern int of_gpio_simple_xlate(struct gpio_chip *gc, const struct of_phandle_args *gpiospec, @@ -76,7 +77,7 @@ static inline int of_gpio_simple_xlate(struct gpio_chip *gc, return -ENOSYS; } -static inline void of_gpiochip_add(struct gpio_chip *gc) { } +static inline int of_gpiochip_add(struct gpio_chip *gc) { return 0; } static inline void of_gpiochip_remove(struct gpio_chip *gc) { } #endif /* CONFIG_OF_GPIO */ diff --git a/kernel/include/linux/of_graph.h b/kernel/include/linux/of_graph.h index 7bc92e050..f8bcd0e21 100644 --- a/kernel/include/linux/of_graph.h +++ b/kernel/include/linux/of_graph.h @@ -45,6 +45,8 @@ int of_graph_parse_endpoint(const struct device_node *node, struct device_node *of_graph_get_port_by_id(struct device_node *node, u32 id); struct device_node *of_graph_get_next_endpoint(const struct device_node *parent, struct device_node *previous); +struct device_node *of_graph_get_endpoint_by_regs( + const struct device_node *parent, int port_reg, int reg); struct device_node *of_graph_get_remote_port_parent( const struct device_node *node); struct device_node *of_graph_get_remote_port(const struct device_node *node); @@ -69,6 +71,12 @@ static inline struct device_node *of_graph_get_next_endpoint( return NULL; } +static inline struct device_node *of_graph_get_endpoint_by_regs( + const struct device_node *parent, int port_reg, int reg) +{ + return NULL; +} + static inline struct device_node *of_graph_get_remote_port_parent( const struct device_node *node) { diff --git a/kernel/include/linux/of_irq.h b/kernel/include/linux/of_irq.h index d884929a7..1e0deb8e8 100644 --- a/kernel/include/linux/of_irq.h +++ b/kernel/include/linux/of_irq.h @@ -46,6 +46,14 @@ extern int of_irq_get(struct device_node *dev, int index); extern int of_irq_get_byname(struct device_node *dev, const char *name); extern int of_irq_to_resource_table(struct device_node *dev, struct resource *res, int nr_irqs); +extern struct device_node *of_irq_find_parent(struct device_node *child); +extern struct irq_domain *of_msi_get_domain(struct device *dev, + struct device_node *np, + enum irq_domain_bus_token token); +extern struct irq_domain *of_msi_map_get_device_domain(struct device *dev, + u32 rid); +extern void of_msi_configure(struct device *dev, struct device_node *np); +u32 of_msi_map_rid(struct device *dev, struct device_node *msi_np, u32 rid_in); #else static inline int of_irq_count(struct device_node *dev) { @@ -64,28 +72,46 @@ static inline int of_irq_to_resource_table(struct device_node *dev, { return 0; } +static inline void *of_irq_find_parent(struct device_node *child) +{ + return NULL; +} + +static inline struct irq_domain *of_msi_get_domain(struct device *dev, + struct device_node *np, + enum irq_domain_bus_token token) +{ + return NULL; +} +static inline struct irq_domain *of_msi_map_get_device_domain(struct device *dev, + u32 rid) +{ + return NULL; +} +static inline void of_msi_configure(struct device *dev, struct device_node *np) +{ +} +static inline u32 of_msi_map_rid(struct device *dev, + struct device_node *msi_np, u32 rid_in) +{ + return rid_in; +} #endif -#if defined(CONFIG_OF) +#if defined(CONFIG_OF_IRQ) || defined(CONFIG_SPARC) /* * irq_of_parse_and_map() is used by all OF enabled platforms; but SPARC * implements it differently. However, the prototype is the same for all, * so declare it here regardless of the CONFIG_OF_IRQ setting. */ extern unsigned int irq_of_parse_and_map(struct device_node *node, int index); -extern struct device_node *of_irq_find_parent(struct device_node *child); -#else /* !CONFIG_OF */ +#else /* !CONFIG_OF && !CONFIG_SPARC */ static inline unsigned int irq_of_parse_and_map(struct device_node *dev, int index) { return 0; } - -static inline void *of_irq_find_parent(struct device_node *child) -{ - return NULL; -} #endif /* !CONFIG_OF */ #endif /* __OF_IRQ_H */ diff --git a/kernel/include/linux/of_pci.h b/kernel/include/linux/of_pci.h index 29fd3fe1c..2c51ee78b 100644 --- a/kernel/include/linux/of_pci.h +++ b/kernel/include/linux/of_pci.h @@ -16,7 +16,7 @@ int of_pci_get_devfn(struct device_node *np); int of_irq_parse_and_map_pci(const struct pci_dev *dev, u8 slot, u8 pin); int of_pci_parse_bus_range(struct device_node *node, struct resource *res); int of_get_pci_domain_nr(struct device_node *node); -void of_pci_dma_configure(struct pci_dev *pci_dev); +void of_pci_check_probe_only(void); #else static inline int of_irq_parse_pci(const struct pci_dev *pdev, struct of_phandle_args *out_irq) { @@ -52,7 +52,7 @@ of_get_pci_domain_nr(struct device_node *node) return -1; } -static inline void of_pci_dma_configure(struct pci_dev *pci_dev) { } +static inline void of_pci_check_probe_only(void) { } #endif #if defined(CONFIG_OF_ADDRESS) diff --git a/kernel/include/linux/of_platform.h b/kernel/include/linux/of_platform.h index 611a69114..956a1006a 100644 --- a/kernel/include/linux/of_platform.h +++ b/kernel/include/linux/of_platform.h @@ -72,6 +72,9 @@ extern int of_platform_populate(struct device_node *root, const struct of_device_id *matches, const struct of_dev_auxdata *lookup, struct device *parent); +extern int of_platform_default_populate(struct device_node *root, + const struct of_dev_auxdata *lookup, + struct device *parent); extern void of_platform_depopulate(struct device *parent); #else static inline int of_platform_populate(struct device_node *root, @@ -81,6 +84,12 @@ static inline int of_platform_populate(struct device_node *root, { return -ENODEV; } +static inline int of_platform_default_populate(struct device_node *root, + const struct of_dev_auxdata *lookup, + struct device *parent) +{ + return -ENODEV; +} static inline void of_platform_depopulate(struct device *parent) { } #endif diff --git a/kernel/include/linux/oid_registry.h b/kernel/include/linux/oid_registry.h index c2bbf672b..d2fa9ca42 100644 --- a/kernel/include/linux/oid_registry.h +++ b/kernel/include/linux/oid_registry.h @@ -41,7 +41,7 @@ enum OID { OID_signed_data, /* 1.2.840.113549.1.7.2 */ /* PKCS#9 {iso(1) member-body(2) us(840) rsadsi(113549) pkcs(1) pkcs-9(9)} */ OID_email_address, /* 1.2.840.113549.1.9.1 */ - OID_content_type, /* 1.2.840.113549.1.9.3 */ + OID_contentType, /* 1.2.840.113549.1.9.3 */ OID_messageDigest, /* 1.2.840.113549.1.9.4 */ OID_signingTime, /* 1.2.840.113549.1.9.5 */ OID_smimeCapabilites, /* 1.2.840.113549.1.9.15 */ @@ -54,6 +54,8 @@ enum OID { /* Microsoft Authenticode & Software Publishing */ OID_msIndirectData, /* 1.3.6.1.4.1.311.2.1.4 */ + OID_msStatementType, /* 1.3.6.1.4.1.311.2.1.11 */ + OID_msSpOpusInfo, /* 1.3.6.1.4.1.311.2.1.12 */ OID_msPeImageDataObjId, /* 1.3.6.1.4.1.311.2.1.15 */ OID_msIndividualSPKeyPurpose, /* 1.3.6.1.4.1.311.2.1.21 */ OID_msOutlookExpress, /* 1.3.6.1.4.1.311.16.4 */ @@ -61,6 +63,9 @@ enum OID { OID_certAuthInfoAccess, /* 1.3.6.1.5.5.7.1.1 */ OID_sha1, /* 1.3.14.3.2.26 */ OID_sha256, /* 2.16.840.1.101.3.4.2.1 */ + OID_sha384, /* 2.16.840.1.101.3.4.2.2 */ + OID_sha512, /* 2.16.840.1.101.3.4.2.3 */ + OID_sha224, /* 2.16.840.1.101.3.4.2.4 */ /* Distinguished Name attribute IDs [RFC 2256] */ OID_commonName, /* 2.5.4.3 */ diff --git a/kernel/include/linux/omap-dma.h b/kernel/include/linux/omap-dma.h index e5a70132a..88fa8af2b 100644 --- a/kernel/include/linux/omap-dma.h +++ b/kernel/include/linux/omap-dma.h @@ -17,7 +17,7 @@ #include <linux/platform_device.h> -#define INT_DMA_LCD 25 +#define INT_DMA_LCD (NR_IRQS_LEGACY + 25) #define OMAP1_DMA_TOUT_IRQ (1 << 0) #define OMAP_DMA_DROP_IRQ (1 << 1) diff --git a/kernel/include/linux/once.h b/kernel/include/linux/once.h new file mode 100644 index 000000000..285f12cb4 --- /dev/null +++ b/kernel/include/linux/once.h @@ -0,0 +1,57 @@ +#ifndef _LINUX_ONCE_H +#define _LINUX_ONCE_H + +#include <linux/types.h> +#include <linux/jump_label.h> + +bool __do_once_start(bool *done, unsigned long *flags); +void __do_once_done(bool *done, struct static_key *once_key, + unsigned long *flags); + +/* Call a function exactly once. The idea of DO_ONCE() is to perform + * a function call such as initialization of random seeds, etc, only + * once, where DO_ONCE() can live in the fast-path. After @func has + * been called with the passed arguments, the static key will patch + * out the condition into a nop. DO_ONCE() guarantees type safety of + * arguments! + * + * Not that the following is not equivalent ... + * + * DO_ONCE(func, arg); + * DO_ONCE(func, arg); + * + * ... to this version: + * + * void foo(void) + * { + * DO_ONCE(func, arg); + * } + * + * foo(); + * foo(); + * + * In case the one-time invocation could be triggered from multiple + * places, then a common helper function must be defined, so that only + * a single static key will be placed there! + */ +#define DO_ONCE(func, ...) \ + ({ \ + bool ___ret = false; \ + static bool ___done = false; \ + static struct static_key ___once_key = STATIC_KEY_INIT_TRUE; \ + if (static_key_true(&___once_key)) { \ + unsigned long ___flags; \ + ___ret = __do_once_start(&___done, &___flags); \ + if (unlikely(___ret)) { \ + func(__VA_ARGS__); \ + __do_once_done(&___done, &___once_key, \ + &___flags); \ + } \ + } \ + ___ret; \ + }) + +#define get_random_once(buf, nbytes) \ + DO_ONCE(get_random_bytes, (buf), (nbytes)) + +#endif /* _LINUX_ONCE_H */ diff --git a/kernel/include/linux/oom.h b/kernel/include/linux/oom.h index 44b2f6f7b..03e625732 100644 --- a/kernel/include/linux/oom.h +++ b/kernel/include/linux/oom.h @@ -13,6 +13,27 @@ struct mem_cgroup; struct task_struct; /* + * Details of the page allocation that triggered the oom killer that are used to + * determine what should be killed. + */ +struct oom_control { + /* Used to determine cpuset */ + struct zonelist *zonelist; + + /* Used to determine mempolicy */ + nodemask_t *nodemask; + + /* Used to determine cpuset and node locality requirement */ + const gfp_t gfp_mask; + + /* + * order == -1 means the oom kill is required by sysrq, otherwise only + * for display purposes. + */ + const int order; +}; + +/* * Types of limitations to the nodes from which allocations may occur */ enum oom_constraint { @@ -32,6 +53,8 @@ enum oom_scan_t { /* Thread is the potential origin of an oom condition; kill first on oom */ #define OOM_FLAG_ORIGIN ((__force oom_flags_t)0x1) +extern struct mutex oom_lock; + static inline void set_current_oom_origin(void) { current->signal->oom_flags |= OOM_FLAG_ORIGIN; @@ -47,9 +70,7 @@ static inline bool oom_task_origin(const struct task_struct *p) return !!(p->signal->oom_flags & OOM_FLAG_ORIGIN); } -extern void mark_tsk_oom_victim(struct task_struct *tsk); - -extern void unmark_oom_victim(void); +extern void mark_oom_victim(struct task_struct *tsk); extern unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg, const nodemask_t *nodemask, @@ -57,24 +78,21 @@ extern unsigned long oom_badness(struct task_struct *p, extern int oom_kills_count(void); extern void note_oom_kill(void); -extern void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, +extern void oom_kill_process(struct oom_control *oc, struct task_struct *p, unsigned int points, unsigned long totalpages, - struct mem_cgroup *memcg, nodemask_t *nodemask, - const char *message); + struct mem_cgroup *memcg, const char *message); -extern bool oom_zonelist_trylock(struct zonelist *zonelist, gfp_t gfp_flags); -extern void oom_zonelist_unlock(struct zonelist *zonelist, gfp_t gfp_flags); - -extern void check_panic_on_oom(enum oom_constraint constraint, gfp_t gfp_mask, - int order, const nodemask_t *nodemask, +extern void check_panic_on_oom(struct oom_control *oc, + enum oom_constraint constraint, struct mem_cgroup *memcg); -extern enum oom_scan_t oom_scan_process_thread(struct task_struct *task, - unsigned long totalpages, const nodemask_t *nodemask, - bool force_kill); +extern enum oom_scan_t oom_scan_process_thread(struct oom_control *oc, + struct task_struct *task, unsigned long totalpages); + +extern bool out_of_memory(struct oom_control *oc); + +extern void exit_oom_victim(void); -extern bool out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, - int order, nodemask_t *mask, bool force_kill); extern int register_oom_notifier(struct notifier_block *nb); extern int unregister_oom_notifier(struct notifier_block *nb); diff --git a/kernel/include/linux/osq_lock.h b/kernel/include/linux/osq_lock.h index 3a6490e81..703ea5c30 100644 --- a/kernel/include/linux/osq_lock.h +++ b/kernel/include/linux/osq_lock.h @@ -32,4 +32,9 @@ static inline void osq_lock_init(struct optimistic_spin_queue *lock) extern bool osq_lock(struct optimistic_spin_queue *lock); extern void osq_unlock(struct optimistic_spin_queue *lock); +static inline bool osq_is_locked(struct optimistic_spin_queue *lock) +{ + return atomic_read(&lock->tail) != OSQ_UNLOCKED_VAL; +} + #endif diff --git a/kernel/include/linux/page-flags.h b/kernel/include/linux/page-flags.h index f34e040b3..bb53c7b86 100644 --- a/kernel/include/linux/page-flags.h +++ b/kernel/include/linux/page-flags.h @@ -86,12 +86,7 @@ enum pageflags { PG_private, /* If pagecache, has fs-private data */ PG_private_2, /* If pagecache, has fs aux data */ PG_writeback, /* Page is under writeback */ -#ifdef CONFIG_PAGEFLAGS_EXTENDED PG_head, /* A head page */ - PG_tail, /* A tail page */ -#else - PG_compound, /* A compound page */ -#endif PG_swapcache, /* Swap page: swp_entry_t in private */ PG_mappedtodisk, /* Has blocks allocated on-disk */ PG_reclaim, /* To be reclaimed asap */ @@ -109,6 +104,10 @@ enum pageflags { #ifdef CONFIG_TRANSPARENT_HUGEPAGE PG_compound_lock, #endif +#if defined(CONFIG_IDLE_PAGE_TRACKING) && defined(CONFIG_64BIT) + PG_young, + PG_idle, +#endif __NR_PAGEFLAGS, /* Filesystems */ @@ -252,7 +251,7 @@ PAGEFLAG(Readahead, reclaim) TESTCLEARFLAG(Readahead, reclaim) * Must use a macro here due to header dependency issues. page_zone() is not * available at this point. */ -#define PageHighMem(__p) is_highmem(page_zone(__p)) +#define PageHighMem(__p) is_highmem_idx(page_zonenum(__p)) #else PAGEFLAG_FALSE(HighMem) #endif @@ -289,6 +288,13 @@ PAGEFLAG_FALSE(HWPoison) #define __PG_HWPOISON 0 #endif +#if defined(CONFIG_IDLE_PAGE_TRACKING) && defined(CONFIG_64BIT) +TESTPAGEFLAG(Young, young) +SETPAGEFLAG(Young, young) +TESTCLEARFLAG(Young, young) +PAGEFLAG(Idle, idle) +#endif + /* * On an anonymous page mapped into a user virtual memory area, * page->mapping points to its anon_vma, not to a struct address_space; @@ -387,85 +393,46 @@ static inline void set_page_writeback_keepwrite(struct page *page) test_set_page_writeback_keepwrite(page); } -#ifdef CONFIG_PAGEFLAGS_EXTENDED -/* - * System with lots of page flags available. This allows separate - * flags for PageHead() and PageTail() checks of compound pages so that bit - * tests can be used in performance sensitive paths. PageCompound is - * generally not used in hot code paths except arch/powerpc/mm/init_64.c - * and arch/powerpc/kvm/book3s_64_vio_hv.c which use it to detect huge pages - * and avoid handling those in real mode. - */ __PAGEFLAG(Head, head) CLEARPAGEFLAG(Head, head) -__PAGEFLAG(Tail, tail) - -static inline int PageCompound(struct page *page) -{ - return page->flags & ((1L << PG_head) | (1L << PG_tail)); -} -#ifdef CONFIG_TRANSPARENT_HUGEPAGE -static inline void ClearPageCompound(struct page *page) +static inline int PageTail(struct page *page) { - BUG_ON(!PageHead(page)); - ClearPageHead(page); + return READ_ONCE(page->compound_head) & 1; } -#endif - -#define PG_head_mask ((1L << PG_head)) - -#else -/* - * Reduce page flag use as much as possible by overlapping - * compound page flags with the flags used for page cache pages. Possible - * because PageCompound is always set for compound pages and not for - * pages on the LRU and/or pagecache. - */ -TESTPAGEFLAG(Compound, compound) -__SETPAGEFLAG(Head, compound) __CLEARPAGEFLAG(Head, compound) - -/* - * PG_reclaim is used in combination with PG_compound to mark the - * head and tail of a compound page. This saves one page flag - * but makes it impossible to use compound pages for the page cache. - * The PG_reclaim bit would have to be used for reclaim or readahead - * if compound pages enter the page cache. - * - * PG_compound & PG_reclaim => Tail page - * PG_compound & ~PG_reclaim => Head page - */ -#define PG_head_mask ((1L << PG_compound)) -#define PG_head_tail_mask ((1L << PG_compound) | (1L << PG_reclaim)) -static inline int PageHead(struct page *page) +static inline void set_compound_head(struct page *page, struct page *head) { - return ((page->flags & PG_head_tail_mask) == PG_head_mask); + WRITE_ONCE(page->compound_head, (unsigned long)head + 1); } -static inline int PageTail(struct page *page) +static inline void clear_compound_head(struct page *page) { - return ((page->flags & PG_head_tail_mask) == PG_head_tail_mask); + WRITE_ONCE(page->compound_head, 0); } -static inline void __SetPageTail(struct page *page) +static inline struct page *compound_head(struct page *page) { - page->flags |= PG_head_tail_mask; + unsigned long head = READ_ONCE(page->compound_head); + + if (unlikely(head & 1)) + return (struct page *) (head - 1); + return page; } -static inline void __ClearPageTail(struct page *page) +static inline int PageCompound(struct page *page) { - page->flags &= ~PG_head_tail_mask; -} + return PageHead(page) || PageTail(page); +} #ifdef CONFIG_TRANSPARENT_HUGEPAGE static inline void ClearPageCompound(struct page *page) { - BUG_ON((page->flags & PG_head_tail_mask) != (1 << PG_compound)); - clear_bit(PG_compound, &page->flags); + BUG_ON(!PageHead(page)); + ClearPageHead(page); } #endif -#endif /* !PAGEFLAGS_EXTENDED */ +#define PG_head_mask ((1L << PG_head)) #ifdef CONFIG_HUGETLB_PAGE int PageHuge(struct page *page); @@ -631,15 +598,19 @@ static inline void ClearPageSlabPfmemalloc(struct page *page) 1 << PG_private | 1 << PG_private_2 | \ 1 << PG_writeback | 1 << PG_reserved | \ 1 << PG_slab | 1 << PG_swapcache | 1 << PG_active | \ - 1 << PG_unevictable | __PG_MLOCKED | __PG_HWPOISON | \ + 1 << PG_unevictable | __PG_MLOCKED | \ __PG_COMPOUND_LOCK) /* * Flags checked when a page is prepped for return by the page allocator. - * Pages being prepped should not have any flags set. It they are set, + * Pages being prepped should not have these flags set. It they are set, * there has been a kernel bug or struct page corruption. + * + * __PG_HWPOISON is exceptional because it needs to be kept beyond page's + * alloc-free cycle to prevent from reusing the page. */ -#define PAGE_FLAGS_CHECK_AT_PREP ((1 << NR_PAGEFLAGS) - 1) +#define PAGE_FLAGS_CHECK_AT_PREP \ + (((1 << NR_PAGEFLAGS) - 1) & ~__PG_HWPOISON) #define PAGE_FLAGS_PRIVATE \ (1 << PG_private | 1 << PG_private_2) diff --git a/kernel/include/linux/page-isolation.h b/kernel/include/linux/page-isolation.h index 2dc1e1697..047d64706 100644 --- a/kernel/include/linux/page-isolation.h +++ b/kernel/include/linux/page-isolation.h @@ -65,11 +65,6 @@ undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn, bool skip_hwpoisoned_pages); -/* - * Internal functions. Changes pageblock's migrate type. - */ -int set_migratetype_isolate(struct page *page, bool skip_hwpoisoned_pages); -void unset_migratetype_isolate(struct page *page, unsigned migratetype); struct page *alloc_migrate_target(struct page *page, unsigned long private, int **resultp); diff --git a/kernel/include/linux/page_counter.h b/kernel/include/linux/page_counter.h index 17fa4f8de..7e62920a3 100644 --- a/kernel/include/linux/page_counter.h +++ b/kernel/include/linux/page_counter.h @@ -36,9 +36,9 @@ static inline unsigned long page_counter_read(struct page_counter *counter) void page_counter_cancel(struct page_counter *counter, unsigned long nr_pages); void page_counter_charge(struct page_counter *counter, unsigned long nr_pages); -int page_counter_try_charge(struct page_counter *counter, - unsigned long nr_pages, - struct page_counter **fail); +bool page_counter_try_charge(struct page_counter *counter, + unsigned long nr_pages, + struct page_counter **fail); void page_counter_uncharge(struct page_counter *counter, unsigned long nr_pages); int page_counter_limit(struct page_counter *counter, unsigned long limit); int page_counter_memparse(const char *buf, const char *max, diff --git a/kernel/include/linux/page_ext.h b/kernel/include/linux/page_ext.h index c42981cd9..17f118a82 100644 --- a/kernel/include/linux/page_ext.h +++ b/kernel/include/linux/page_ext.h @@ -26,6 +26,10 @@ enum page_ext_flags { PAGE_EXT_DEBUG_POISON, /* Page is poisoned */ PAGE_EXT_DEBUG_GUARD, PAGE_EXT_OWNER, +#if defined(CONFIG_IDLE_PAGE_TRACKING) && !defined(CONFIG_64BIT) + PAGE_EXT_YOUNG, + PAGE_EXT_IDLE, +#endif }; /* diff --git a/kernel/include/linux/page_idle.h b/kernel/include/linux/page_idle.h new file mode 100644 index 000000000..bf268fa92 --- /dev/null +++ b/kernel/include/linux/page_idle.h @@ -0,0 +1,110 @@ +#ifndef _LINUX_MM_PAGE_IDLE_H +#define _LINUX_MM_PAGE_IDLE_H + +#include <linux/bitops.h> +#include <linux/page-flags.h> +#include <linux/page_ext.h> + +#ifdef CONFIG_IDLE_PAGE_TRACKING + +#ifdef CONFIG_64BIT +static inline bool page_is_young(struct page *page) +{ + return PageYoung(page); +} + +static inline void set_page_young(struct page *page) +{ + SetPageYoung(page); +} + +static inline bool test_and_clear_page_young(struct page *page) +{ + return TestClearPageYoung(page); +} + +static inline bool page_is_idle(struct page *page) +{ + return PageIdle(page); +} + +static inline void set_page_idle(struct page *page) +{ + SetPageIdle(page); +} + +static inline void clear_page_idle(struct page *page) +{ + ClearPageIdle(page); +} +#else /* !CONFIG_64BIT */ +/* + * If there is not enough space to store Idle and Young bits in page flags, use + * page ext flags instead. + */ +extern struct page_ext_operations page_idle_ops; + +static inline bool page_is_young(struct page *page) +{ + return test_bit(PAGE_EXT_YOUNG, &lookup_page_ext(page)->flags); +} + +static inline void set_page_young(struct page *page) +{ + set_bit(PAGE_EXT_YOUNG, &lookup_page_ext(page)->flags); +} + +static inline bool test_and_clear_page_young(struct page *page) +{ + return test_and_clear_bit(PAGE_EXT_YOUNG, + &lookup_page_ext(page)->flags); +} + +static inline bool page_is_idle(struct page *page) +{ + return test_bit(PAGE_EXT_IDLE, &lookup_page_ext(page)->flags); +} + +static inline void set_page_idle(struct page *page) +{ + set_bit(PAGE_EXT_IDLE, &lookup_page_ext(page)->flags); +} + +static inline void clear_page_idle(struct page *page) +{ + clear_bit(PAGE_EXT_IDLE, &lookup_page_ext(page)->flags); +} +#endif /* CONFIG_64BIT */ + +#else /* !CONFIG_IDLE_PAGE_TRACKING */ + +static inline bool page_is_young(struct page *page) +{ + return false; +} + +static inline void set_page_young(struct page *page) +{ +} + +static inline bool test_and_clear_page_young(struct page *page) +{ + return false; +} + +static inline bool page_is_idle(struct page *page) +{ + return false; +} + +static inline void set_page_idle(struct page *page) +{ +} + +static inline void clear_page_idle(struct page *page) +{ +} + +#endif /* CONFIG_IDLE_PAGE_TRACKING */ + +#endif /* _LINUX_MM_PAGE_IDLE_H */ diff --git a/kernel/include/linux/page_owner.h b/kernel/include/linux/page_owner.h index b48c3471c..cacaabea8 100644 --- a/kernel/include/linux/page_owner.h +++ b/kernel/include/linux/page_owner.h @@ -8,6 +8,7 @@ extern struct page_ext_operations page_owner_ops; extern void __reset_page_owner(struct page *page, unsigned int order); extern void __set_page_owner(struct page *page, unsigned int order, gfp_t gfp_mask); +extern gfp_t __get_page_owner_gfp(struct page *page); static inline void reset_page_owner(struct page *page, unsigned int order) { @@ -25,6 +26,14 @@ static inline void set_page_owner(struct page *page, __set_page_owner(page, order, gfp_mask); } + +static inline gfp_t get_page_owner_gfp(struct page *page) +{ + if (likely(!page_owner_inited)) + return 0; + + return __get_page_owner_gfp(page); +} #else static inline void reset_page_owner(struct page *page, unsigned int order) { @@ -33,6 +42,10 @@ static inline void set_page_owner(struct page *page, unsigned int order, gfp_t gfp_mask) { } +static inline gfp_t get_page_owner_gfp(struct page *page) +{ + return 0; +} #endif /* CONFIG_PAGE_OWNER */ #endif /* __LINUX_PAGE_OWNER_H */ diff --git a/kernel/include/linux/pageblock-flags.h b/kernel/include/linux/pageblock-flags.h index 2baeee12f..e942558b3 100644 --- a/kernel/include/linux/pageblock-flags.h +++ b/kernel/include/linux/pageblock-flags.h @@ -44,7 +44,7 @@ enum pageblock_bits { #ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE /* Huge page sizes are variable */ -extern int pageblock_order; +extern unsigned int pageblock_order; #else /* CONFIG_HUGETLB_PAGE_SIZE_VARIABLE */ diff --git a/kernel/include/linux/pagemap.h b/kernel/include/linux/pagemap.h index 4b3736f70..26eabf5ec 100644 --- a/kernel/include/linux/pagemap.h +++ b/kernel/include/linux/pagemap.h @@ -69,6 +69,13 @@ static inline gfp_t mapping_gfp_mask(struct address_space * mapping) return (__force gfp_t)mapping->flags & __GFP_BITS_MASK; } +/* Restricts the given gfp_mask to what the mapping allows. */ +static inline gfp_t mapping_gfp_constraint(struct address_space *mapping, + gfp_t gfp_mask) +{ + return mapping_gfp_mask(mapping) & gfp_mask; +} + /* * This is non-atomic. Only to be used before the mapping is activated. * Probably needs a barrier... @@ -651,7 +658,8 @@ int add_to_page_cache_locked(struct page *page, struct address_space *mapping, int add_to_page_cache_lru(struct page *page, struct address_space *mapping, pgoff_t index, gfp_t gfp_mask); extern void delete_from_page_cache(struct page *page); -extern void __delete_from_page_cache(struct page *page, void *shadow); +extern void __delete_from_page_cache(struct page *page, void *shadow, + struct mem_cgroup *memcg); int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask); /* @@ -670,4 +678,10 @@ static inline int add_to_page_cache(struct page *page, return error; } +static inline unsigned long dir_pages(struct inode *inode) +{ + return (unsigned long)(inode->i_size + PAGE_CACHE_SIZE - 1) >> + PAGE_CACHE_SHIFT; +} + #endif /* _LINUX_PAGEMAP_H */ diff --git a/kernel/include/linux/parport.h b/kernel/include/linux/parport.h index c22f12547..58e3c64c6 100644 --- a/kernel/include/linux/parport.h +++ b/kernel/include/linux/parport.h @@ -13,6 +13,7 @@ #include <linux/wait.h> #include <linux/irqreturn.h> #include <linux/semaphore.h> +#include <linux/device.h> #include <asm/ptrace.h> #include <uapi/linux/parport.h> @@ -145,6 +146,8 @@ struct pardevice { unsigned int flags; struct pardevice *next; struct pardevice *prev; + struct device dev; + bool devmodel; struct parport_state *state; /* saved status over preemption */ wait_queue_head_t wait_q; unsigned long int time; @@ -156,6 +159,8 @@ struct pardevice { void * sysctl_table; }; +#define to_pardevice(n) container_of(n, struct pardevice, dev) + /* IEEE1284 information */ /* IEEE1284 phases. These are exposed to userland through ppdev IOCTL @@ -195,7 +200,7 @@ struct parport { * This may unfortulately be null if the * port has a legacy driver. */ - + struct device bus_dev; /* to link with the bus */ struct parport *physport; /* If this is a non-default mux parport, i.e. we're a clone of a real @@ -245,15 +250,26 @@ struct parport { struct parport *slaves[3]; }; +#define to_parport_dev(n) container_of(n, struct parport, bus_dev) + #define DEFAULT_SPIN_TIME 500 /* us */ struct parport_driver { const char *name; void (*attach) (struct parport *); void (*detach) (struct parport *); + void (*match_port)(struct parport *); + int (*probe)(struct pardevice *); + struct device_driver driver; + bool devmodel; struct list_head list; }; +#define to_parport_driver(n) container_of(n, struct parport_driver, driver) + +int parport_bus_init(void); +void parport_bus_exit(void); + /* parport_register_port registers a new parallel port at the given address (if one does not already exist) and returns a pointer to it. This entails claiming the I/O region, IRQ and DMA. NULL is returned @@ -272,10 +288,20 @@ void parport_announce_port (struct parport *port); extern void parport_remove_port(struct parport *port); /* Register a new high-level driver. */ -extern int parport_register_driver (struct parport_driver *); + +int __must_check __parport_register_driver(struct parport_driver *, + struct module *, + const char *mod_name); +/* + * parport_register_driver must be a macro so that KBUILD_MODNAME can + * be expanded + */ +#define parport_register_driver(driver) \ + __parport_register_driver(driver, THIS_MODULE, KBUILD_MODNAME) /* Unregister a high-level driver. */ extern void parport_unregister_driver (struct parport_driver *); +void parport_unregister_driver(struct parport_driver *); /* If parport_register_driver doesn't fit your needs, perhaps * parport_find_xxx does. */ @@ -288,6 +314,15 @@ extern irqreturn_t parport_irq_handler(int irq, void *dev_id); /* Reference counting for ports. */ extern struct parport *parport_get_port (struct parport *); extern void parport_put_port (struct parport *); +void parport_del_port(struct parport *); + +struct pardev_cb { + int (*preempt)(void *); + void (*wakeup)(void *); + void *private; + void (*irq_func)(void *); + unsigned int flags; +}; /* parport_register_device declares that a device is connected to a port, and tells the kernel all it needs to know. @@ -301,6 +336,10 @@ struct pardevice *parport_register_device(struct parport *port, void (*irq_func)(void *), int flags, void *handle); +struct pardevice * +parport_register_dev_model(struct parport *port, const char *name, + const struct pardev_cb *par_dev_cb, int cnt); + /* parport_unregister unlinks a device from the chain. */ extern void parport_unregister_device(struct pardevice *dev); diff --git a/kernel/include/linux/pata_arasan_cf_data.h b/kernel/include/linux/pata_arasan_cf_data.h index 3cc21c9cc..9fade5dd2 100644 --- a/kernel/include/linux/pata_arasan_cf_data.h +++ b/kernel/include/linux/pata_arasan_cf_data.h @@ -4,7 +4,7 @@ * Arasan Compact Flash host controller platform data header file * * Copyright (C) 2011 ST Microelectronics - * Viresh Kumar <viresh.linux@gmail.com> + * Viresh Kumar <vireshk@kernel.org> * * This file is licensed under the terms of the GNU General Public * License version 2. This program is licensed "as is" without any diff --git a/kernel/include/linux/pci-acpi.h b/kernel/include/linux/pci-acpi.h index a965efa52..89ab0572d 100644 --- a/kernel/include/linux/pci-acpi.h +++ b/kernel/include/linux/pci-acpi.h @@ -52,6 +52,30 @@ static inline acpi_handle acpi_pci_get_bridge_handle(struct pci_bus *pbus) return ACPI_HANDLE(dev); } +struct acpi_pci_root; +struct acpi_pci_root_ops; + +struct acpi_pci_root_info { + struct acpi_pci_root *root; + struct acpi_device *bridge; + struct acpi_pci_root_ops *ops; + struct list_head resources; + char name[16]; +}; + +struct acpi_pci_root_ops { + struct pci_ops *pci_ops; + int (*init_info)(struct acpi_pci_root_info *info); + void (*release_info)(struct acpi_pci_root_info *info); + int (*prepare_resources)(struct acpi_pci_root_info *info); +}; + +extern int acpi_pci_probe_root_resources(struct acpi_pci_root_info *info); +extern struct pci_bus *acpi_pci_root_create(struct acpi_pci_root *root, + struct acpi_pci_root_ops *ops, + struct acpi_pci_root_info *info, + void *sd); + void acpi_pci_add_bus(struct pci_bus *bus); void acpi_pci_remove_bus(struct pci_bus *bus); diff --git a/kernel/include/linux/pci-ats.h b/kernel/include/linux/pci-ats.h index 72031785f..57e0b8250 100644 --- a/kernel/include/linux/pci-ats.h +++ b/kernel/include/linux/pci-ats.h @@ -3,55 +3,6 @@ #include <linux/pci.h> -/* Address Translation Service */ -struct pci_ats { - int pos; /* capability position */ - int stu; /* Smallest Translation Unit */ - int qdep; /* Invalidate Queue Depth */ - int ref_cnt; /* Physical Function reference count */ - unsigned int is_enabled:1; /* Enable bit is set */ -}; - -#ifdef CONFIG_PCI_ATS - -int pci_enable_ats(struct pci_dev *dev, int ps); -void pci_disable_ats(struct pci_dev *dev); -int pci_ats_queue_depth(struct pci_dev *dev); - -/** - * pci_ats_enabled - query the ATS status - * @dev: the PCI device - * - * Returns 1 if ATS capability is enabled, or 0 if not. - */ -static inline int pci_ats_enabled(struct pci_dev *dev) -{ - return dev->ats && dev->ats->is_enabled; -} - -#else /* CONFIG_PCI_ATS */ - -static inline int pci_enable_ats(struct pci_dev *dev, int ps) -{ - return -ENODEV; -} - -static inline void pci_disable_ats(struct pci_dev *dev) -{ -} - -static inline int pci_ats_queue_depth(struct pci_dev *dev) -{ - return -ENODEV; -} - -static inline int pci_ats_enabled(struct pci_dev *dev) -{ - return 0; -} - -#endif /* CONFIG_PCI_ATS */ - #ifdef CONFIG_PCI_PRI int pci_enable_pri(struct pci_dev *pdev, u32 reqs); diff --git a/kernel/include/linux/pci.h b/kernel/include/linux/pci.h index 6e935e5ea..6ae25aae8 100644 --- a/kernel/include/linux/pci.h +++ b/kernel/include/linux/pci.h @@ -345,6 +345,7 @@ struct pci_dev { unsigned int msi_enabled:1; unsigned int msix_enabled:1; unsigned int ari_enabled:1; /* ARI forwarding */ + unsigned int ats_enabled:1; /* Address Translation Service */ unsigned int is_managed:1; unsigned int needs_freset:1; /* Dev requires fundamental reset */ unsigned int state_saved:1; @@ -357,6 +358,7 @@ struct pci_dev { unsigned int broken_intx_masking:1; unsigned int io_window_1k:1; /* Intel P2P bridge 1K I/O windows */ unsigned int irq_managed:1; + unsigned int has_secondary_link:1; pci_dev_flags_t dev_flags; atomic_t enable_cnt; /* pci_enable_device has been called */ @@ -367,7 +369,6 @@ struct pci_dev { struct bin_attribute *res_attr[DEVICE_COUNT_RESOURCE]; /* sysfs file for resources */ struct bin_attribute *res_attr_wc[DEVICE_COUNT_RESOURCE]; /* sysfs file for WC mapping of resources */ #ifdef CONFIG_PCI_MSI - struct list_head msi_list; const struct attribute_group **msi_irq_groups; #endif struct pci_vpd *vpd; @@ -376,7 +377,9 @@ struct pci_dev { struct pci_sriov *sriov; /* SR-IOV capability related */ struct pci_dev *physfn; /* the PF this VF is associated with */ }; - struct pci_ats *ats; /* Address Translation Service */ + u16 ats_cap; /* ATS Capability offset */ + u8 ats_stu; /* ATS Smallest Translation Unit */ + atomic_t ats_ref_cnt; /* number of VFs with ATS enabled */ #endif phys_addr_t rom; /* Physical address of ROM if it's not from the BAR */ size_t romlen; /* Length of ROM if it's not from the BAR */ @@ -409,9 +412,18 @@ struct pci_host_bridge { void (*release_fn)(struct pci_host_bridge *); void *release_data; unsigned int ignore_reset_delay:1; /* for entire hierarchy */ + /* Resource alignment requirements */ + resource_size_t (*align_resource)(struct pci_dev *dev, + const struct resource *res, + resource_size_t start, + resource_size_t size, + resource_size_t align); }; #define to_pci_host_bridge(n) container_of(n, struct pci_host_bridge, dev) + +struct pci_host_bridge *pci_find_host_bridge(struct pci_bus *bus); + void pci_set_host_bridge_release(struct pci_host_bridge *bridge, void (*release_fn)(struct pci_host_bridge *), void *release_data); @@ -447,7 +459,8 @@ struct pci_bus { struct list_head children; /* list of child buses */ struct list_head devices; /* list of devices on this bus */ struct pci_dev *self; /* bridge device as seen by parent */ - struct list_head slots; /* list of slots on this bus */ + struct list_head slots; /* list of slots on this bus; + protected by pci_slot_mutex */ struct resource *resource[PCI_BRIDGE_RESOURCE_NUM]; struct list_head resources; /* address space routed to this bus */ struct resource busn_res; /* bus numbers routed to this bus */ @@ -739,10 +752,11 @@ struct pci_driver { void pcie_bus_configure_settings(struct pci_bus *bus); enum pcie_bus_config_types { - PCIE_BUS_TUNE_OFF, - PCIE_BUS_SAFE, - PCIE_BUS_PERFORMANCE, - PCIE_BUS_PEER2PEER, + PCIE_BUS_TUNE_OFF, /* don't touch MPS at all */ + PCIE_BUS_DEFAULT, /* ensure MPS matches upstream bridge */ + PCIE_BUS_SAFE, /* use largest MPS boot-time devices support */ + PCIE_BUS_PERFORMANCE, /* use MPS and MRRS for best performance */ + PCIE_BUS_PEER2PEER, /* set MPS = 128 for all devices */ }; extern enum pcie_bus_config_types pcie_bus_config; @@ -781,8 +795,6 @@ void pcibios_bus_to_resource(struct pci_bus *bus, struct resource *res, void pcibios_scan_specific_bus(int busn); struct pci_bus *pci_find_bus(int domain, int busnr); void pci_bus_add_devices(const struct pci_bus *bus); -struct pci_bus *pci_scan_bus_parented(struct device *parent, int bus, - struct pci_ops *ops, void *sysdata); struct pci_bus *pci_scan_bus(int bus, struct pci_ops *ops, void *sysdata); struct pci_bus *pci_create_root_bus(struct device *parent, int bus, struct pci_ops *ops, void *sysdata, @@ -790,6 +802,10 @@ struct pci_bus *pci_create_root_bus(struct device *parent, int bus, int pci_bus_insert_busn_res(struct pci_bus *b, int bus, int busmax); int pci_bus_update_busn_res_end(struct pci_bus *b, int busmax); void pci_bus_release_busn_res(struct pci_bus *b); +struct pci_bus *pci_scan_root_bus_msi(struct device *parent, int bus, + struct pci_ops *ops, void *sysdata, + struct list_head *resources, + struct msi_controller *msi); struct pci_bus *pci_scan_root_bus(struct device *parent, int bus, struct pci_ops *ops, void *sysdata, struct list_head *resources); @@ -800,6 +816,11 @@ struct pci_slot *pci_create_slot(struct pci_bus *parent, int slot_nr, const char *name, struct hotplug_slot *hotplug); void pci_destroy_slot(struct pci_slot *slot); +#ifdef CONFIG_SYSFS +void pci_dev_assign_slot(struct pci_dev *dev); +#else +static inline void pci_dev_assign_slot(struct pci_dev *dev) { } +#endif int pci_scan_slot(struct pci_bus *bus, int devfn); struct pci_dev *pci_scan_single_device(struct pci_bus *bus, int devfn); void pci_device_add(struct pci_dev *dev, struct pci_bus *bus); @@ -808,6 +829,7 @@ void pci_bus_add_device(struct pci_dev *dev); void pci_read_bridge_bases(struct pci_bus *child); struct resource *pci_find_parent_resource(const struct pci_dev *dev, struct resource *res); +struct pci_dev *pci_find_pcie_root_port(struct pci_dev *dev); u8 pci_swizzle_interrupt_pin(const struct pci_dev *dev, u8 pin); int pci_get_interrupt_pin(struct pci_dev *dev, struct pci_dev **bridge); u8 pci_common_swizzle(struct pci_dev *dev, u8 *pinp); @@ -966,6 +988,23 @@ static inline int pci_is_managed(struct pci_dev *pdev) return pdev->is_managed; } +static inline void pci_set_managed_irq(struct pci_dev *pdev, unsigned int irq) +{ + pdev->irq = irq; + pdev->irq_managed = 1; +} + +static inline void pci_reset_managed_irq(struct pci_dev *pdev) +{ + pdev->irq = 0; + pdev->irq_managed = 0; +} + +static inline bool pci_has_managed_irq(struct pci_dev *pdev) +{ + return pdev->irq_managed && pdev->irq > 0; +} + void pci_disable_device(struct pci_dev *dev); extern unsigned int pcibios_max_latency; @@ -982,7 +1021,6 @@ void pci_intx(struct pci_dev *dev, int enable); bool pci_intx_mask_supported(struct pci_dev *dev); bool pci_check_and_mask_intx(struct pci_dev *dev); bool pci_check_and_unmask_intx(struct pci_dev *dev); -void pci_msi_off(struct pci_dev *dev); int pci_set_dma_max_seg_size(struct pci_dev *dev, unsigned int size); int pci_set_dma_seg_boundary(struct pci_dev *dev, unsigned long mask); int pci_wait_for_pending(struct pci_dev *dev, int pos, u16 mask); @@ -1164,6 +1202,17 @@ void pci_unregister_driver(struct pci_driver *dev); module_driver(__pci_driver, pci_register_driver, \ pci_unregister_driver) +/** + * builtin_pci_driver() - Helper macro for registering a PCI driver + * @__pci_driver: pci_driver struct + * + * Helper macro for PCI drivers which do not do anything special in their + * init code. This eliminates a lot of boilerplate. Each driver may only + * use this macro once, and calling it replaces device_initcall(...) + */ +#define builtin_pci_driver(__pci_driver) \ + builtin_driver(__pci_driver, pci_register_driver) + struct pci_driver *pci_dev_driver(const struct pci_dev *dev); int pci_add_dynid(struct pci_driver *drv, unsigned int vendor, unsigned int device, @@ -1199,22 +1248,16 @@ int pci_set_vga_state(struct pci_dev *pdev, bool decode, dma_pool_create(name, &pdev->dev, size, align, allocation) #define pci_pool_destroy(pool) dma_pool_destroy(pool) #define pci_pool_alloc(pool, flags, handle) dma_pool_alloc(pool, flags, handle) +#define pci_pool_zalloc(pool, flags, handle) \ + dma_pool_zalloc(pool, flags, handle) #define pci_pool_free(pool, vaddr, addr) dma_pool_free(pool, vaddr, addr) -enum pci_dma_burst_strategy { - PCI_DMA_BURST_INFINITY, /* make bursts as large as possible, - strategy_parameter is N/A */ - PCI_DMA_BURST_BOUNDARY, /* disconnect at every strategy_parameter - byte boundaries */ - PCI_DMA_BURST_MULTIPLE, /* disconnect at some multiple of - strategy_parameter byte boundaries */ -}; - struct msix_entry { u32 vector; /* kernel uses to write allocated vector */ u16 entry; /* driver uses to specify entry, OS writes */ }; +void pci_msi_setup_pci_dev(struct pci_dev *dev); #ifdef CONFIG_PCI_MSI int pci_msi_vec_count(struct pci_dev *dev); @@ -1307,6 +1350,19 @@ int ht_create_irq(struct pci_dev *dev, int idx); void ht_destroy_irq(unsigned int irq); #endif /* CONFIG_HT_IRQ */ +#ifdef CONFIG_PCI_ATS +/* Address Translation Service */ +void pci_ats_init(struct pci_dev *dev); +int pci_enable_ats(struct pci_dev *dev, int ps); +void pci_disable_ats(struct pci_dev *dev); +int pci_ats_queue_depth(struct pci_dev *dev); +#else +static inline void pci_ats_init(struct pci_dev *d) { } +static inline int pci_enable_ats(struct pci_dev *d, int ps) { return -ENODEV; } +static inline void pci_disable_ats(struct pci_dev *d) { } +static inline int pci_ats_queue_depth(struct pci_dev *d) { return -ENODEV; } +#endif + void pci_cfg_access_lock(struct pci_dev *dev); bool pci_cfg_access_trylock(struct pci_dev *dev); void pci_cfg_access_unlock(struct pci_dev *dev); @@ -1434,8 +1490,6 @@ static inline int pci_request_regions(struct pci_dev *dev, const char *res_name) { return -EIO; } static inline void pci_release_regions(struct pci_dev *dev) { } -#define pci_dma_burst_advice(pdev, strat, strategy_parameter) do { } while (0) - static inline void pci_block_cfg_access(struct pci_dev *dev) { } static inline int pci_block_cfg_access_in_atomic(struct pci_dev *dev) { return 0; } @@ -1660,6 +1714,8 @@ int pcibios_set_pcie_reset_state(struct pci_dev *dev, int pcibios_add_device(struct pci_dev *dev); void pcibios_release_device(struct pci_dev *dev); void pcibios_penalize_isa_irq(int irq, int active); +int pcibios_alloc_irq(struct pci_dev *dev); +void pcibios_free_irq(struct pci_dev *dev); #ifdef CONFIG_HIBERNATE_CALLBACKS extern struct dev_pm_ops pcibios_pm_ops; @@ -1676,6 +1732,7 @@ static inline void pci_mmcfg_late_init(void) { } int pci_ext_cfg_avail(void); void __iomem *pci_ioremap_bar(struct pci_dev *pdev, int bar); +void __iomem *pci_ioremap_wc_bar(struct pci_dev *pdev, int bar); #ifdef CONFIG_PCI_IOV int pci_iov_virtfn_bus(struct pci_dev *dev, int id); @@ -1857,10 +1914,12 @@ int pci_vpd_find_info_keyword(const u8 *buf, unsigned int off, /* PCI <-> OF binding helpers */ #ifdef CONFIG_OF struct device_node; +struct irq_domain; void pci_set_of_node(struct pci_dev *dev); void pci_release_of_node(struct pci_dev *dev); void pci_set_bus_of_node(struct pci_bus *bus); void pci_release_bus_of_node(struct pci_bus *bus); +struct irq_domain *pci_host_bridge_of_msi_domain(struct pci_bus *bus); /* Arch may override this (weak) */ struct device_node *pcibios_get_phb_of_node(struct pci_bus *bus); @@ -1883,6 +1942,8 @@ static inline void pci_set_bus_of_node(struct pci_bus *bus) { } static inline void pci_release_bus_of_node(struct pci_bus *bus) { } static inline struct device_node * pci_device_to_OF_node(const struct pci_dev *pdev) { return NULL; } +static inline struct irq_domain * +pci_host_bridge_of_msi_domain(struct pci_bus *bus) { return NULL; } #endif /* CONFIG_OF */ #ifdef CONFIG_EEH @@ -1909,4 +1970,15 @@ static inline bool pci_is_dev_assigned(struct pci_dev *pdev) { return (pdev->dev_flags & PCI_DEV_FLAGS_ASSIGNED) == PCI_DEV_FLAGS_ASSIGNED; } + +/** + * pci_ari_enabled - query ARI forwarding status + * @bus: the PCI bus + * + * Returns true if ARI forwarding is enabled. + */ +static inline bool pci_ari_enabled(struct pci_bus *bus) +{ + return bus->self && bus->self->ari_enabled; +} #endif /* LINUX_PCI_H */ diff --git a/kernel/include/linux/pci_ids.h b/kernel/include/linux/pci_ids.h index 2f7b9a40f..d9ba49ced 100644 --- a/kernel/include/linux/pci_ids.h +++ b/kernel/include/linux/pci_ids.h @@ -579,6 +579,7 @@ #define PCI_DEVICE_ID_AMD_HUDSON2_SATA_IDE 0x7800 #define PCI_DEVICE_ID_AMD_HUDSON2_SMBUS 0x780b #define PCI_DEVICE_ID_AMD_HUDSON2_IDE 0x780c +#define PCI_DEVICE_ID_AMD_KERNCZ_SMBUS 0x790b #define PCI_VENDOR_ID_TRIDENT 0x1023 #define PCI_DEVICE_ID_TRIDENT_4DWAVE_DX 0x2000 @@ -2329,6 +2330,17 @@ #define PCI_DEVICE_ID_ALTIMA_AC9100 0x03ea #define PCI_DEVICE_ID_ALTIMA_AC1003 0x03eb +#define PCI_VENDOR_ID_CAVIUM 0x177d + +#define PCI_VENDOR_ID_TECHWELL 0x1797 +#define PCI_DEVICE_ID_TECHWELL_6800 0x6800 +#define PCI_DEVICE_ID_TECHWELL_6801 0x6801 +#define PCI_DEVICE_ID_TECHWELL_6804 0x6804 +#define PCI_DEVICE_ID_TECHWELL_6816_1 0x6810 +#define PCI_DEVICE_ID_TECHWELL_6816_2 0x6811 +#define PCI_DEVICE_ID_TECHWELL_6816_3 0x6812 +#define PCI_DEVICE_ID_TECHWELL_6816_4 0x6813 + #define PCI_VENDOR_ID_BELKIN 0x1799 #define PCI_DEVICE_ID_BELKIN_F5D7010V7 0x701f diff --git a/kernel/include/linux/percpu-defs.h b/kernel/include/linux/percpu-defs.h index 57f3a1c55..8f16299ca 100644 --- a/kernel/include/linux/percpu-defs.h +++ b/kernel/include/linux/percpu-defs.h @@ -488,10 +488,8 @@ do { \ #define __this_cpu_dec_return(pcp) __this_cpu_add_return(pcp, -1) /* - * Operations with implied preemption protection. These operations can be - * used without worrying about preemption. Note that interrupts may still - * occur while an operation is in progress and if the interrupt modifies - * the variable too then RMW actions may not be reliable. + * Operations with implied preemption/interrupt protection. These + * operations can be used without worrying about preemption or interrupt. */ #define this_cpu_read(pcp) __pcpu_size_call_return(this_cpu_read_, pcp) #define this_cpu_write(pcp, val) __pcpu_size_call(this_cpu_write_, pcp, val) diff --git a/kernel/include/linux/percpu-rwsem.h b/kernel/include/linux/percpu-rwsem.h index 3e88c9a7d..c2fa3ecb0 100644 --- a/kernel/include/linux/percpu-rwsem.h +++ b/kernel/include/linux/percpu-rwsem.h @@ -5,17 +5,19 @@ #include <linux/rwsem.h> #include <linux/percpu.h> #include <linux/wait.h> +#include <linux/rcu_sync.h> #include <linux/lockdep.h> struct percpu_rw_semaphore { + struct rcu_sync rss; unsigned int __percpu *fast_read_ctr; - atomic_t write_ctr; struct rw_semaphore rw_sem; atomic_t slow_read_ctr; wait_queue_head_t write_waitq; }; extern void percpu_down_read(struct percpu_rw_semaphore *); +extern int percpu_down_read_trylock(struct percpu_rw_semaphore *); extern void percpu_up_read(struct percpu_rw_semaphore *); extern void percpu_down_write(struct percpu_rw_semaphore *); @@ -31,4 +33,23 @@ extern void percpu_free_rwsem(struct percpu_rw_semaphore *); __percpu_init_rwsem(brw, #brw, &rwsem_key); \ }) + +#define percpu_rwsem_is_held(sem) lockdep_is_held(&(sem)->rw_sem) + +static inline void percpu_rwsem_release(struct percpu_rw_semaphore *sem, + bool read, unsigned long ip) +{ + lock_release(&sem->rw_sem.dep_map, 1, ip); +#ifdef CONFIG_RWSEM_SPIN_ON_OWNER + if (!read) + sem->rw_sem.owner = NULL; +#endif +} + +static inline void percpu_rwsem_acquire(struct percpu_rw_semaphore *sem, + bool read, unsigned long ip) +{ + lock_acquire(&sem->rw_sem.dep_map, 0, 1, read, 1, NULL, ip); +} + #endif diff --git a/kernel/include/linux/perf/arm_pmu.h b/kernel/include/linux/perf/arm_pmu.h new file mode 100644 index 000000000..bfa673bb8 --- /dev/null +++ b/kernel/include/linux/perf/arm_pmu.h @@ -0,0 +1,154 @@ +/* + * linux/arch/arm/include/asm/pmu.h + * + * Copyright (C) 2009 picoChip Designs Ltd, Jamie Iles + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + */ + +#ifndef __ARM_PMU_H__ +#define __ARM_PMU_H__ + +#include <linux/interrupt.h> +#include <linux/perf_event.h> + +#include <asm/cputype.h> + +/* + * struct arm_pmu_platdata - ARM PMU platform data + * + * @handle_irq: an optional handler which will be called from the + * interrupt and passed the address of the low level handler, + * and can be used to implement any platform specific handling + * before or after calling it. + */ +struct arm_pmu_platdata { + irqreturn_t (*handle_irq)(int irq, void *dev, + irq_handler_t pmu_handler); +}; + +#ifdef CONFIG_ARM_PMU + +/* + * The ARMv7 CPU PMU supports up to 32 event counters. + */ +#define ARMPMU_MAX_HWEVENTS 32 + +#define HW_OP_UNSUPPORTED 0xFFFF +#define C(_x) PERF_COUNT_HW_CACHE_##_x +#define CACHE_OP_UNSUPPORTED 0xFFFF + +#define PERF_MAP_ALL_UNSUPPORTED \ + [0 ... PERF_COUNT_HW_MAX - 1] = HW_OP_UNSUPPORTED + +#define PERF_CACHE_MAP_ALL_UNSUPPORTED \ +[0 ... C(MAX) - 1] = { \ + [0 ... C(OP_MAX) - 1] = { \ + [0 ... C(RESULT_MAX) - 1] = CACHE_OP_UNSUPPORTED, \ + }, \ +} + +/* The events for a given PMU register set. */ +struct pmu_hw_events { + /* + * The events that are active on the PMU for the given index. + */ + struct perf_event *events[ARMPMU_MAX_HWEVENTS]; + + /* + * A 1 bit for an index indicates that the counter is being used for + * an event. A 0 means that the counter can be used. + */ + DECLARE_BITMAP(used_mask, ARMPMU_MAX_HWEVENTS); + + /* + * Hardware lock to serialize accesses to PMU registers. Needed for the + * read/modify/write sequences. + */ + raw_spinlock_t pmu_lock; + + /* + * When using percpu IRQs, we need a percpu dev_id. Place it here as we + * already have to allocate this struct per cpu. + */ + struct arm_pmu *percpu_pmu; +}; + +struct arm_pmu { + struct pmu pmu; + cpumask_t active_irqs; + cpumask_t supported_cpus; + int *irq_affinity; + char *name; + irqreturn_t (*handle_irq)(int irq_num, void *dev); + void (*enable)(struct perf_event *event); + void (*disable)(struct perf_event *event); + int (*get_event_idx)(struct pmu_hw_events *hw_events, + struct perf_event *event); + void (*clear_event_idx)(struct pmu_hw_events *hw_events, + struct perf_event *event); + int (*set_event_filter)(struct hw_perf_event *evt, + struct perf_event_attr *attr); + u32 (*read_counter)(struct perf_event *event); + void (*write_counter)(struct perf_event *event, u32 val); + void (*start)(struct arm_pmu *); + void (*stop)(struct arm_pmu *); + void (*reset)(void *); + int (*request_irq)(struct arm_pmu *, irq_handler_t handler); + void (*free_irq)(struct arm_pmu *); + int (*map_event)(struct perf_event *event); + int num_events; + atomic_t active_events; + struct mutex reserve_mutex; + u64 max_period; + struct platform_device *plat_device; + struct pmu_hw_events __percpu *hw_events; + struct notifier_block hotplug_nb; +}; + +#define to_arm_pmu(p) (container_of(p, struct arm_pmu, pmu)) + +int armpmu_register(struct arm_pmu *armpmu, int type); + +u64 armpmu_event_update(struct perf_event *event); + +int armpmu_event_set_period(struct perf_event *event); + +int armpmu_map_event(struct perf_event *event, + const unsigned (*event_map)[PERF_COUNT_HW_MAX], + const unsigned (*cache_map)[PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX], + u32 raw_event_mask); + +struct pmu_probe_info { + unsigned int cpuid; + unsigned int mask; + int (*init)(struct arm_pmu *); +}; + +#define PMU_PROBE(_cpuid, _mask, _fn) \ +{ \ + .cpuid = (_cpuid), \ + .mask = (_mask), \ + .init = (_fn), \ +} + +#define ARM_PMU_PROBE(_cpuid, _fn) \ + PMU_PROBE(_cpuid, ARM_CPU_PART_MASK, _fn) + +#define ARM_PMU_XSCALE_MASK ((0xff << 24) | ARM_CPU_XSCALE_ARCH_MASK) + +#define XSCALE_PMU_PROBE(_version, _fn) \ + PMU_PROBE(ARM_CPU_IMP_INTEL << 24 | _version, ARM_PMU_XSCALE_MASK, _fn) + +int arm_pmu_device_probe(struct platform_device *pdev, + const struct of_device_id *of_table, + const struct pmu_probe_info *probe_table); + +#endif /* CONFIG_ARM_PMU */ + +#endif /* __ARM_PMU_H__ */ diff --git a/kernel/include/linux/perf_event.h b/kernel/include/linux/perf_event.h index d8a82a89f..f9828a48f 100644 --- a/kernel/include/linux/perf_event.h +++ b/kernel/include/linux/perf_event.h @@ -120,7 +120,7 @@ struct hw_perf_event { }; struct { /* intel_cqm */ int cqm_state; - int cqm_rmid; + u32 cqm_rmid; struct list_head cqm_events_entry; struct list_head cqm_groups_entry; struct list_head cqm_group_entry; @@ -140,33 +140,67 @@ struct hw_perf_event { }; #endif }; + /* + * If the event is a per task event, this will point to the task in + * question. See the comment in perf_event_alloc(). + */ struct task_struct *target; + +/* + * hw_perf_event::state flags; used to track the PERF_EF_* state. + */ +#define PERF_HES_STOPPED 0x01 /* the counter is stopped */ +#define PERF_HES_UPTODATE 0x02 /* event->count up-to-date */ +#define PERF_HES_ARCH 0x04 + int state; + + /* + * The last observed hardware counter value, updated with a + * local64_cmpxchg() such that pmu::read() can be called nested. + */ local64_t prev_count; + + /* + * The period to start the next sample with. + */ u64 sample_period; + + /* + * The period we started this sample with. + */ u64 last_period; + + /* + * However much is left of the current period; note that this is + * a full 64bit value and allows for generation of periods longer + * than hardware might allow. + */ local64_t period_left; + + /* + * State for throttling the event, see __perf_event_overflow() and + * perf_adjust_freq_unthr_context(). + */ u64 interrupts_seq; u64 interrupts; + /* + * State for freq target events, see __perf_event_overflow() and + * perf_adjust_freq_unthr_context(). + */ u64 freq_time_stamp; u64 freq_count_stamp; #endif }; -/* - * hw_perf_event::state flags - */ -#define PERF_HES_STOPPED 0x01 /* the counter is stopped */ -#define PERF_HES_UPTODATE 0x02 /* event->count up-to-date */ -#define PERF_HES_ARCH 0x04 - struct perf_event; /* * Common implementation detail of pmu::{start,commit,cancel}_txn */ -#define PERF_EVENT_TXN 0x1 +#define PERF_PMU_TXN_ADD 0x1 /* txn to add/schedule event on PMU */ +#define PERF_PMU_TXN_READ 0x2 /* txn to read event group from PMU */ /** * pmu::capabilities flags @@ -210,7 +244,19 @@ struct pmu { /* * Try and initialize the event for this PMU. - * Should return -ENOENT when the @event doesn't match this PMU. + * + * Returns: + * -ENOENT -- @event is not for this PMU + * + * -ENODEV -- @event is for this PMU but PMU not present + * -EBUSY -- @event is for this PMU but PMU temporarily unavailable + * -EINVAL -- @event is for this PMU but @event is not valid + * -EOPNOTSUPP -- @event is for this PMU, @event is valid, but not supported + * -EACCESS -- @event is for this PMU, @event is valid, but no privilidges + * + * 0 -- @event is for this PMU and valid + * + * Other error return values are allowed. */ int (*event_init) (struct perf_event *event); @@ -221,27 +267,61 @@ struct pmu { void (*event_mapped) (struct perf_event *event); /*optional*/ void (*event_unmapped) (struct perf_event *event); /*optional*/ + /* + * Flags for ->add()/->del()/ ->start()/->stop(). There are + * matching hw_perf_event::state flags. + */ #define PERF_EF_START 0x01 /* start the counter when adding */ #define PERF_EF_RELOAD 0x02 /* reload the counter when starting */ #define PERF_EF_UPDATE 0x04 /* update the counter when stopping */ /* - * Adds/Removes a counter to/from the PMU, can be done inside - * a transaction, see the ->*_txn() methods. + * Adds/Removes a counter to/from the PMU, can be done inside a + * transaction, see the ->*_txn() methods. + * + * The add/del callbacks will reserve all hardware resources required + * to service the event, this includes any counter constraint + * scheduling etc. + * + * Called with IRQs disabled and the PMU disabled on the CPU the event + * is on. + * + * ->add() called without PERF_EF_START should result in the same state + * as ->add() followed by ->stop(). + * + * ->del() must always PERF_EF_UPDATE stop an event. If it calls + * ->stop() that must deal with already being stopped without + * PERF_EF_UPDATE. */ int (*add) (struct perf_event *event, int flags); void (*del) (struct perf_event *event, int flags); /* - * Starts/Stops a counter present on the PMU. The PMI handler - * should stop the counter when perf_event_overflow() returns - * !0. ->start() will be used to continue. + * Starts/Stops a counter present on the PMU. + * + * The PMI handler should stop the counter when perf_event_overflow() + * returns !0. ->start() will be used to continue. + * + * Also used to change the sample period. + * + * Called with IRQs disabled and the PMU disabled on the CPU the event + * is on -- will be called from NMI context with the PMU generates + * NMIs. + * + * ->stop() with PERF_EF_UPDATE will read the counter and update + * period/count values like ->read() would. + * + * ->start() with PERF_EF_RELOAD will reprogram the the counter + * value, must be preceded by a ->stop() with PERF_EF_UPDATE. */ void (*start) (struct perf_event *event, int flags); void (*stop) (struct perf_event *event, int flags); /* * Updates the counter value of the event. + * + * For sampling capable PMUs this will also update the software period + * hw_perf_event::period_left field. */ void (*read) (struct perf_event *event); @@ -252,20 +332,26 @@ struct pmu { * * Start the transaction, after this ->add() doesn't need to * do schedulability tests. + * + * Optional. */ - void (*start_txn) (struct pmu *pmu); /* optional */ + void (*start_txn) (struct pmu *pmu, unsigned int txn_flags); /* * If ->start_txn() disabled the ->add() schedulability test * then ->commit_txn() is required to perform one. On success * the transaction is closed. On error the transaction is kept * open until ->cancel_txn() is called. + * + * Optional. */ - int (*commit_txn) (struct pmu *pmu); /* optional */ + int (*commit_txn) (struct pmu *pmu); /* * Will cancel the transaction, assumes ->del() is called * for each successful ->add() during the transaction. + * + * Optional. */ - void (*cancel_txn) (struct pmu *pmu); /* optional */ + void (*cancel_txn) (struct pmu *pmu); /* * Will return the value for perf_event_mmap_page::index for this event, @@ -300,6 +386,11 @@ struct pmu { * Free pmu-private AUX data structures */ void (*free_aux) (void *aux); /* optional */ + + /* + * Filter events for PMU-specific reasons. + */ + int (*filter_match) (struct perf_event *event); /* optional */ }; /** @@ -479,7 +570,7 @@ struct perf_event { void *overflow_handler_context; #ifdef CONFIG_EVENT_TRACING - struct ftrace_event_call *tp_event; + struct trace_event_call *tp_event; struct event_filter *filter; #ifdef CONFIG_FUNCTION_TRACER struct ftrace_ops ftrace_ops; @@ -562,8 +653,12 @@ struct perf_cpu_context { struct perf_event_context *task_ctx; int active_oncpu; int exclusive; + + raw_spinlock_t hrtimer_lock; struct hrtimer hrtimer; ktime_t hrtimer_interval; + unsigned int hrtimer_active; + struct pmu *unique_pmu; struct perf_cgroup *cgrp; }; @@ -602,9 +697,11 @@ struct perf_cgroup { * if there is no cgroup event for the current CPU context. */ static inline struct perf_cgroup * -perf_cgroup_from_task(struct task_struct *task) +perf_cgroup_from_task(struct task_struct *task, struct perf_event_context *ctx) { - return container_of(task_css(task, perf_event_cgrp_id), + return container_of(task_css_check(task, perf_event_cgrp_id, + ctx ? lockdep_is_held(&ctx->lock) + : true), struct perf_cgroup, css); } #endif /* CONFIG_CGROUP_PERF */ @@ -632,6 +729,8 @@ extern int perf_event_init_task(struct task_struct *child); extern void perf_event_exit_task(struct task_struct *child); extern void perf_event_free_task(struct task_struct *task); extern void perf_event_delayed_put(struct task_struct *task); +extern struct perf_event *perf_event_get(unsigned int fd); +extern const struct perf_event_attr *perf_event_attrs(struct perf_event *event); extern void perf_event_print_debug(void); extern void perf_pmu_disable(struct pmu *pmu); extern void perf_pmu_enable(struct pmu *pmu); @@ -650,6 +749,7 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, void *context); extern void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu); +extern u64 perf_event_read_local(struct perf_event *event); extern u64 perf_event_read_value(struct perf_event *event, u64 *enabled, u64 *running); @@ -730,6 +830,22 @@ extern int perf_event_overflow(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs); +extern void perf_event_output(struct perf_event *event, + struct perf_sample_data *data, + struct pt_regs *regs); + +extern void +perf_event_header__init_id(struct perf_event_header *header, + struct perf_sample_data *data, + struct perf_event *event); +extern void +perf_event__output_id_sample(struct perf_event *event, + struct perf_output_handle *handle, + struct perf_sample_data *sample); + +extern void +perf_log_lost_samples(struct perf_event *event, u64 lost); + static inline bool is_sampling_event(struct perf_event *event) { return event->attr.sample_period != 0; @@ -794,11 +910,33 @@ perf_sw_event_sched(u32 event_id, u64 nr, u64 addr) extern struct static_key_deferred perf_sched_events; +static __always_inline bool +perf_sw_migrate_enabled(void) +{ + if (static_key_false(&perf_swevent_enabled[PERF_COUNT_SW_CPU_MIGRATIONS])) + return true; + return false; +} + +static inline void perf_event_task_migrate(struct task_struct *task) +{ + if (perf_sw_migrate_enabled()) + task->sched_migrated = 1; +} + static inline void perf_event_task_sched_in(struct task_struct *prev, struct task_struct *task) { if (static_key_false(&perf_sched_events.key)) __perf_event_task_sched_in(prev, task); + + if (perf_sw_migrate_enabled() && task->sched_migrated) { + struct pt_regs *regs = this_cpu_ptr(&__perf_regs[0]); + + perf_fetch_caller_regs(regs); + ___perf_sw_event(PERF_COUNT_SW_CPU_MIGRATIONS, 1, regs, 0); + task->sched_migrated = 0; + } } static inline void perf_event_task_sched_out(struct task_struct *prev, @@ -921,6 +1059,8 @@ perf_aux_output_skip(struct perf_output_handle *handle, static inline void * perf_get_aux(struct perf_output_handle *handle) { return NULL; } static inline void +perf_event_task_migrate(struct task_struct *task) { } +static inline void perf_event_task_sched_in(struct task_struct *prev, struct task_struct *task) { } static inline void @@ -930,6 +1070,12 @@ static inline int perf_event_init_task(struct task_struct *child) { return 0; } static inline void perf_event_exit_task(struct task_struct *child) { } static inline void perf_event_free_task(struct task_struct *task) { } static inline void perf_event_delayed_put(struct task_struct *task) { } +static inline struct perf_event *perf_event_get(unsigned int fd) { return ERR_PTR(-EINVAL); } +static inline const struct perf_event_attr *perf_event_attrs(struct perf_event *event) +{ + return ERR_PTR(-EINVAL); +} +static inline u64 perf_event_read_local(struct perf_event *event) { return -EINVAL; } static inline void perf_event_print_debug(void) { } static inline int perf_event_task_disable(void) { return -EINVAL; } static inline int perf_event_task_enable(void) { return -EINVAL; } @@ -962,6 +1108,7 @@ static inline void perf_event_enable(struct perf_event *event) { } static inline void perf_event_disable(struct perf_event *event) { } static inline int __perf_event_disable(void *info) { return -1; } static inline void perf_event_task_tick(void) { } +static inline int perf_event_release_kernel(struct perf_event *event) { return 0; } #endif #if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_NO_HZ_FULL) diff --git a/kernel/include/linux/phy.h b/kernel/include/linux/phy.h index 685809835..05fde31b6 100644 --- a/kernel/include/linux/phy.h +++ b/kernel/include/linux/phy.h @@ -19,6 +19,7 @@ #include <linux/spinlock.h> #include <linux/ethtool.h> #include <linux/mii.h> +#include <linux/module.h> #include <linux/timer.h> #include <linux/workqueue.h> #include <linux/mod_devicetable.h> @@ -153,6 +154,7 @@ struct sk_buff; * PHYs should register using this structure */ struct mii_bus { + struct module *owner; const char *name; char id[MII_BUS_ID_SIZE]; void *priv; @@ -181,6 +183,9 @@ struct mii_bus { /* PHY addresses to be ignored when probing */ u32 phy_mask; + /* PHY addresses to ignore the TA/read failure */ + u32 phy_ignore_ta_mask; + /* * Pointer to an array of interrupts, each PHY's * interrupt at the index matching its address @@ -195,7 +200,8 @@ static inline struct mii_bus *mdiobus_alloc(void) return mdiobus_alloc_size(0); } -int mdiobus_register(struct mii_bus *bus); +int __mdiobus_register(struct mii_bus *bus, struct module *owner); +#define mdiobus_register(bus) __mdiobus_register(bus, THIS_MODULE) void mdiobus_unregister(struct mii_bus *bus); void mdiobus_free(struct mii_bus *bus); struct mii_bus *devm_mdiobus_alloc_size(struct device *dev, int sizeof_priv); @@ -207,7 +213,9 @@ static inline struct mii_bus *devm_mdiobus_alloc(struct device *dev) void devm_mdiobus_free(struct device *dev, struct mii_bus *bus); struct phy_device *mdiobus_scan(struct mii_bus *bus, int addr); int mdiobus_read(struct mii_bus *bus, int addr, u32 regnum); +int mdiobus_read_nested(struct mii_bus *bus, int addr, u32 regnum); int mdiobus_write(struct mii_bus *bus, int addr, u32 regnum, u16 val); +int mdiobus_write_nested(struct mii_bus *bus, int addr, u32 regnum, u16 val); #define PHY_INTERRUPT_DISABLED 0x0 @@ -327,6 +335,7 @@ struct phy_c45_device_ids { * c45_ids: 802.3-c45 Device Identifers if is_c45. * is_c45: Set to true if this phy uses clause 45 addressing. * is_internal: Set to true if this phy is internal to a MAC. + * is_pseudo_fixed_link: Set to true if this phy is an Ethernet switch, etc. * has_fixups: Set to true if this phy has fixups/quirks. * suspended: Set to true if this phy has been suspended successfully. * state: state of the PHY for management purposes @@ -365,6 +374,7 @@ struct phy_device { struct phy_c45_device_ids c45_ids; bool is_c45; bool is_internal; + bool is_pseudo_fixed_link; bool has_fixups; bool suspended; @@ -421,6 +431,8 @@ struct phy_device { struct net_device *attached_dev; + u8 mdix; + void (*adjust_link)(struct net_device *dev); }; #define to_phy_device(d) container_of(d, struct phy_device, dev) @@ -675,6 +687,27 @@ static inline bool phy_is_internal(struct phy_device *phydev) } /** + * phy_interface_is_rgmii - Convenience function for testing if a PHY interface + * is RGMII (all variants) + * @phydev: the phy_device struct + */ +static inline bool phy_interface_is_rgmii(struct phy_device *phydev) +{ + return phydev->interface >= PHY_INTERFACE_MODE_RGMII && + phydev->interface <= PHY_INTERFACE_MODE_RGMII_TXID; +}; + +/* + * phy_is_pseudo_fixed_link - Convenience function for testing if this + * PHY is the CPU port facing side of an Ethernet switch, or similar. + * @phydev: the phy_device struct + */ +static inline bool phy_is_pseudo_fixed_link(struct phy_device *phydev) +{ + return phydev->is_pseudo_fixed_link; +} + +/** * phy_write_mmd - Convenience function for writing a register * on an MMD on a given PHY. * @phydev: The phy_device struct @@ -714,6 +747,7 @@ struct phy_device *phy_device_create(struct mii_bus *bus, int addr, int phy_id, struct phy_c45_device_ids *c45_ids); struct phy_device *get_phy_device(struct mii_bus *bus, int addr, bool is_c45); int phy_device_register(struct phy_device *phy); +void phy_device_remove(struct phy_device *phydev); int phy_init_hw(struct phy_device *phydev); int phy_suspend(struct phy_device *phydev); int phy_resume(struct phy_device *phydev); @@ -766,6 +800,7 @@ int phy_mii_ioctl(struct phy_device *phydev, struct ifreq *ifr, int cmd); int phy_start_interrupts(struct phy_device *phydev); void phy_print_status(struct phy_device *phydev); void phy_device_free(struct phy_device *phydev); +int phy_set_max_speed(struct phy_device *phydev, u32 max_speed); int phy_register_fixup(const char *bus_id, u32 phy_uid, u32 phy_uid_mask, int (*run)(struct phy_device *)); diff --git a/kernel/include/linux/phy/phy-sun4i-usb.h b/kernel/include/linux/phy/phy-sun4i-usb.h new file mode 100644 index 000000000..50aed92ea --- /dev/null +++ b/kernel/include/linux/phy/phy-sun4i-usb.h @@ -0,0 +1,26 @@ +/* + * Copyright (c) 2015 Hans de Goede <hdegoede@redhat.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef PHY_SUN4I_USB_H_ +#define PHY_SUN4I_USB_H_ + +#include "phy.h" + +/** + * sun4i_usb_phy_set_squelch_detect() - Enable/disable squelch detect + * @phy: reference to a sun4i usb phy + * @enabled: wether to enable or disable squelch detect + */ +void sun4i_usb_phy_set_squelch_detect(struct phy *phy, bool enabled); + +#endif diff --git a/kernel/include/linux/phy/phy.h b/kernel/include/linux/phy/phy.h index a0197fa1b..8cf05e341 100644 --- a/kernel/include/linux/phy/phy.h +++ b/kernel/include/linux/phy/phy.h @@ -133,6 +133,8 @@ struct phy *devm_phy_get(struct device *dev, const char *string); struct phy *devm_phy_optional_get(struct device *dev, const char *string); struct phy *devm_of_phy_get(struct device *dev, struct device_node *np, const char *con_id); +struct phy *devm_of_phy_get_by_index(struct device *dev, struct device_node *np, + int index); void phy_put(struct phy *phy); void devm_phy_put(struct device *dev, struct phy *phy); struct phy *of_phy_get(struct device_node *np, const char *con_id); @@ -261,6 +263,13 @@ static inline struct phy *devm_of_phy_get(struct device *dev, return ERR_PTR(-ENOSYS); } +static inline struct phy *devm_of_phy_get_by_index(struct device *dev, + struct device_node *np, + int index) +{ + return ERR_PTR(-ENOSYS); +} + static inline void phy_put(struct phy *phy) { } diff --git a/kernel/include/linux/phy_fixed.h b/kernel/include/linux/phy_fixed.h index fe5732d53..2400d2ea4 100644 --- a/kernel/include/linux/phy_fixed.h +++ b/kernel/include/linux/phy_fixed.h @@ -13,9 +13,11 @@ struct device_node; #if IS_ENABLED(CONFIG_FIXED_PHY) extern int fixed_phy_add(unsigned int irq, int phy_id, - struct fixed_phy_status *status); + struct fixed_phy_status *status, + int link_gpio); extern struct phy_device *fixed_phy_register(unsigned int irq, struct fixed_phy_status *status, + int link_gpio, struct device_node *np); extern void fixed_phy_del(int phy_addr); extern int fixed_phy_set_link_update(struct phy_device *phydev, @@ -26,12 +28,14 @@ extern int fixed_phy_update_state(struct phy_device *phydev, const struct fixed_phy_status *changed); #else static inline int fixed_phy_add(unsigned int irq, int phy_id, - struct fixed_phy_status *status) + struct fixed_phy_status *status, + int link_gpio) { return -ENODEV; } static inline struct phy_device *fixed_phy_register(unsigned int irq, struct fixed_phy_status *status, + int gpio_link, struct device_node *np) { return ERR_PTR(-ENODEV); diff --git a/kernel/include/linux/pinctrl/consumer.h b/kernel/include/linux/pinctrl/consumer.h index 18eccefea..d7e5d608f 100644 --- a/kernel/include/linux/pinctrl/consumer.h +++ b/kernel/include/linux/pinctrl/consumer.h @@ -142,7 +142,7 @@ static inline struct pinctrl * __must_check pinctrl_get_select( s = pinctrl_lookup_state(p, name); if (IS_ERR(s)) { pinctrl_put(p); - return ERR_PTR(PTR_ERR(s)); + return ERR_CAST(s); } ret = pinctrl_select_state(p, s); diff --git a/kernel/include/linux/pinctrl/devinfo.h b/kernel/include/linux/pinctrl/devinfo.h index 281cb91dd..05082e407 100644 --- a/kernel/include/linux/pinctrl/devinfo.h +++ b/kernel/include/linux/pinctrl/devinfo.h @@ -24,10 +24,14 @@ * struct dev_pin_info - pin state container for devices * @p: pinctrl handle for the containing device * @default_state: the default state for the handle, if found + * @init_state: the state at probe time, if found + * @sleep_state: the state at suspend time, if found + * @idle_state: the state at idle (runtime suspend) time, if found */ struct dev_pin_info { struct pinctrl *p; struct pinctrl_state *default_state; + struct pinctrl_state *init_state; #ifdef CONFIG_PM struct pinctrl_state *sleep_state; struct pinctrl_state *idle_state; @@ -35,6 +39,7 @@ struct dev_pin_info { }; extern int pinctrl_bind_pins(struct device *dev); +extern int pinctrl_init_done(struct device *dev); #else @@ -45,5 +50,10 @@ static inline int pinctrl_bind_pins(struct device *dev) return 0; } +static inline int pinctrl_init_done(struct device *dev) +{ + return 0; +} + #endif /* CONFIG_PINCTRL */ #endif /* PINCTRL_DEVINFO_H */ diff --git a/kernel/include/linux/pinctrl/pinconf-generic.h b/kernel/include/linux/pinctrl/pinconf-generic.h index fe65962b2..d921afd5f 100644 --- a/kernel/include/linux/pinctrl/pinconf-generic.h +++ b/kernel/include/linux/pinctrl/pinconf-generic.h @@ -20,6 +20,11 @@ /** * enum pin_config_param - possible pin configuration parameters + * @PIN_CONFIG_BIAS_BUS_HOLD: the pin will be set to weakly latch so that it + * weakly drives the last value on a tristate bus, also known as a "bus + * holder", "bus keeper" or "repeater". This allows another device on the + * bus to change the value by driving the bus high or low and switching to + * tristate. The argument is ignored. * @PIN_CONFIG_BIAS_DISABLE: disable any pin bias on the pin, a * transition from say pull-up to pull-down implies that you disable * pull-up in the process, this setting disables all biasing. @@ -29,14 +34,6 @@ * if for example some other pin is going to drive the signal connected * to it for a while. Pins used for input are usually always high * impedance. - * @PIN_CONFIG_BIAS_BUS_HOLD: the pin will be set to weakly latch so that it - * weakly drives the last value on a tristate bus, also known as a "bus - * holder", "bus keeper" or "repeater". This allows another device on the - * bus to change the value by driving the bus high or low and switching to - * tristate. The argument is ignored. - * @PIN_CONFIG_BIAS_PULL_UP: the pin will be pulled up (usually with high - * impedance to VDD). If the argument is != 0 pull-up is enabled, - * if it is 0, pull-up is total, i.e. the pin is connected to VDD. * @PIN_CONFIG_BIAS_PULL_DOWN: the pin will be pulled down (usually with high * impedance to GROUND). If the argument is != 0 pull-down is enabled, * if it is 0, pull-down is total, i.e. the pin is connected to GROUND. @@ -48,10 +45,9 @@ * If the argument is != 0 pull up/down is enabled, if it is 0, the * configuration is ignored. The proper way to disable it is to use * @PIN_CONFIG_BIAS_DISABLE. - * @PIN_CONFIG_DRIVE_PUSH_PULL: the pin will be driven actively high and - * low, this is the most typical case and is typically achieved with two - * active transistors on the output. Setting this config will enable - * push-pull mode, the argument is ignored. + * @PIN_CONFIG_BIAS_PULL_UP: the pin will be pulled up (usually with high + * impedance to VDD). If the argument is != 0 pull-up is enabled, + * if it is 0, pull-up is total, i.e. the pin is connected to VDD. * @PIN_CONFIG_DRIVE_OPEN_DRAIN: the pin will be driven with open drain (open * collector) which means it is usually wired with other output ports * which are then pulled up with an external resistor. Setting this @@ -59,28 +55,26 @@ * @PIN_CONFIG_DRIVE_OPEN_SOURCE: the pin will be driven with open source * (open emitter). Setting this config will enable open source mode, the * argument is ignored. + * @PIN_CONFIG_DRIVE_PUSH_PULL: the pin will be driven actively high and + * low, this is the most typical case and is typically achieved with two + * active transistors on the output. Setting this config will enable + * push-pull mode, the argument is ignored. * @PIN_CONFIG_DRIVE_STRENGTH: the pin will sink or source at most the current * passed as argument. The argument is in mA. + * @PIN_CONFIG_INPUT_DEBOUNCE: this will configure the pin to debounce mode, + * which means it will wait for signals to settle when reading inputs. The + * argument gives the debounce time in usecs. Setting the + * argument to zero turns debouncing off. * @PIN_CONFIG_INPUT_ENABLE: enable the pin's input. Note that this does not * affect the pin's ability to drive output. 1 enables input, 0 disables * input. - * @PIN_CONFIG_INPUT_SCHMITT_ENABLE: control schmitt-trigger mode on the pin. - * If the argument != 0, schmitt-trigger mode is enabled. If it's 0, - * schmitt-trigger mode is disabled. * @PIN_CONFIG_INPUT_SCHMITT: this will configure an input pin to run in * schmitt-trigger mode. If the schmitt-trigger has adjustable hysteresis, * the threshold value is given on a custom format as argument when * setting pins to this mode. - * @PIN_CONFIG_INPUT_DEBOUNCE: this will configure the pin to debounce mode, - * which means it will wait for signals to settle when reading inputs. The - * argument gives the debounce time in usecs. Setting the - * argument to zero turns debouncing off. - * @PIN_CONFIG_POWER_SOURCE: if the pin can select between different power - * supplies, the argument to this parameter (on a custom format) tells - * the driver which alternative power source to use. - * @PIN_CONFIG_SLEW_RATE: if the pin can select slew rate, the argument to - * this parameter (on a custom format) tells the driver which alternative - * slew rate to use. + * @PIN_CONFIG_INPUT_SCHMITT_ENABLE: control schmitt-trigger mode on the pin. + * If the argument != 0, schmitt-trigger mode is enabled. If it's 0, + * schmitt-trigger mode is disabled. * @PIN_CONFIG_LOW_POWER_MODE: this will configure the pin for low power * operation, if several modes of operation are supported these can be * passed in the argument on a custom form, else just use argument 1 @@ -89,29 +83,35 @@ * 1 to indicate high level, argument 0 to indicate low level. (Please * see Documentation/pinctrl.txt, section "GPIO mode pitfalls" for a * discussion around this parameter.) + * @PIN_CONFIG_POWER_SOURCE: if the pin can select between different power + * supplies, the argument to this parameter (on a custom format) tells + * the driver which alternative power source to use. + * @PIN_CONFIG_SLEW_RATE: if the pin can select slew rate, the argument to + * this parameter (on a custom format) tells the driver which alternative + * slew rate to use. * @PIN_CONFIG_END: this is the last enumerator for pin configurations, if * you need to pass in custom configurations to the pin controller, use * PIN_CONFIG_END+1 as the base offset. */ enum pin_config_param { + PIN_CONFIG_BIAS_BUS_HOLD, PIN_CONFIG_BIAS_DISABLE, PIN_CONFIG_BIAS_HIGH_IMPEDANCE, - PIN_CONFIG_BIAS_BUS_HOLD, - PIN_CONFIG_BIAS_PULL_UP, PIN_CONFIG_BIAS_PULL_DOWN, PIN_CONFIG_BIAS_PULL_PIN_DEFAULT, - PIN_CONFIG_DRIVE_PUSH_PULL, + PIN_CONFIG_BIAS_PULL_UP, PIN_CONFIG_DRIVE_OPEN_DRAIN, PIN_CONFIG_DRIVE_OPEN_SOURCE, + PIN_CONFIG_DRIVE_PUSH_PULL, PIN_CONFIG_DRIVE_STRENGTH, + PIN_CONFIG_INPUT_DEBOUNCE, PIN_CONFIG_INPUT_ENABLE, - PIN_CONFIG_INPUT_SCHMITT_ENABLE, PIN_CONFIG_INPUT_SCHMITT, - PIN_CONFIG_INPUT_DEBOUNCE, - PIN_CONFIG_POWER_SOURCE, - PIN_CONFIG_SLEW_RATE, + PIN_CONFIG_INPUT_SCHMITT_ENABLE, PIN_CONFIG_LOW_POWER_MODE, PIN_CONFIG_OUTPUT, + PIN_CONFIG_POWER_SOURCE, + PIN_CONFIG_SLEW_RATE, PIN_CONFIG_END = 0x7FFF, }; diff --git a/kernel/include/linux/pinctrl/pinctrl-state.h b/kernel/include/linux/pinctrl/pinctrl-state.h index b5919f8e6..230735193 100644 --- a/kernel/include/linux/pinctrl/pinctrl-state.h +++ b/kernel/include/linux/pinctrl/pinctrl-state.h @@ -9,6 +9,13 @@ * hogs to configure muxing and pins at boot, and also as a state * to go into when returning from sleep and idle in * .pm_runtime_resume() or ordinary .resume() for example. + * @PINCTRL_STATE_INIT: normally the pinctrl will be set to "default" + * before the driver's probe() function is called. There are some + * drivers where that is not appropriate becausing doing so would + * glitch the pins. In those cases you can add an "init" pinctrl + * which is the state of the pins before drive probe. After probe + * if the pins are still in "init" state they'll be moved to + * "default". * @PINCTRL_STATE_IDLE: the state the pinctrl handle shall be put into * when the pins are idle. This is a state where the system is relaxed * but not fully sleeping - some power may be on but clocks gated for @@ -20,5 +27,6 @@ * ordinary .suspend() function. */ #define PINCTRL_STATE_DEFAULT "default" +#define PINCTRL_STATE_INIT "init" #define PINCTRL_STATE_IDLE "idle" #define PINCTRL_STATE_SLEEP "sleep" diff --git a/kernel/include/linux/pinctrl/pinctrl.h b/kernel/include/linux/pinctrl/pinctrl.h index 66e469751..9ba59fcba 100644 --- a/kernel/include/linux/pinctrl/pinctrl.h +++ b/kernel/include/linux/pinctrl/pinctrl.h @@ -127,7 +127,7 @@ struct pinctrl_ops { */ struct pinctrl_desc { const char *name; - struct pinctrl_pin_desc const *pins; + const struct pinctrl_pin_desc *pins; unsigned int npins; const struct pinctrl_ops *pctlops; const struct pinmux_ops *pmxops; diff --git a/kernel/include/linux/pinctrl/pinmux.h b/kernel/include/linux/pinctrl/pinmux.h index 511bda9ed..ace60d775 100644 --- a/kernel/include/linux/pinctrl/pinmux.h +++ b/kernel/include/linux/pinctrl/pinmux.h @@ -56,6 +56,9 @@ struct pinctrl_dev; * depending on whether the GPIO is configured as input or output, * a direction selector function may be implemented as a backing * to the GPIO controllers that need pin muxing. + * @strict: do not allow simultaneous use of the same pin for GPIO and another + * function. Check both gpio_owner and mux_owner strictly before approving + * the pin request. */ struct pinmux_ops { int (*request) (struct pinctrl_dev *pctldev, unsigned offset); @@ -66,7 +69,7 @@ struct pinmux_ops { int (*get_function_groups) (struct pinctrl_dev *pctldev, unsigned selector, const char * const **groups, - unsigned * const num_groups); + unsigned *num_groups); int (*set_mux) (struct pinctrl_dev *pctldev, unsigned func_selector, unsigned group_selector); int (*gpio_request_enable) (struct pinctrl_dev *pctldev, @@ -79,6 +82,7 @@ struct pinmux_ops { struct pinctrl_gpio_range *range, unsigned offset, bool input); + bool strict; }; #endif /* CONFIG_PINMUX */ diff --git a/kernel/include/linux/platform_data/atmel.h b/kernel/include/linux/platform_data/atmel.h index 4b452c6a2..3c8825b67 100644 --- a/kernel/include/linux/platform_data/atmel.h +++ b/kernel/include/linux/platform_data/atmel.h @@ -9,30 +9,7 @@ #include <linux/mtd/nand.h> #include <linux/mtd/partitions.h> -#include <linux/device.h> -#include <linux/i2c.h> -#include <linux/leds.h> -#include <linux/spi/spi.h> -#include <linux/usb/atmel_usba_udc.h> -#include <linux/atmel-mci.h> -#include <sound/atmel-ac97c.h> #include <linux/serial.h> -#include <linux/platform_data/macb.h> - -/* - * at91: 6 USARTs and one DBGU port (SAM9260) - * avr32: 4 - */ -#define ATMEL_MAX_UART 7 - - /* USB Device */ -struct at91_udc_data { - int vbus_pin; /* high == host powering us */ - u8 vbus_active_low; /* vbus polarity */ - u8 vbus_polled; /* Use polling, not interrupt */ - int pullup_pin; /* active == D+ pulled up */ - u8 pullup_active_low; /* true == pullup_pin is active low */ -}; /* Compact Flash */ struct at91_cf_data { @@ -46,18 +23,6 @@ struct at91_cf_data { #define AT91_IDE_SWAP_A0_A2 0x02 }; - /* USB Host */ -#define AT91_MAX_USBH_PORTS 3 -struct at91_usbh_data { - int vbus_pin[AT91_MAX_USBH_PORTS]; /* port power-control pin */ - int overcurrent_pin[AT91_MAX_USBH_PORTS]; - u8 ports; /* number of ports on root hub */ - u8 overcurrent_supported; - u8 vbus_pin_active_low[AT91_MAX_USBH_PORTS]; - u8 overcurrent_status[AT91_MAX_USBH_PORTS]; - u8 overcurrent_changed[AT91_MAX_USBH_PORTS]; -}; - /* NAND / SmartMedia */ struct atmel_nand_data { int enable_pin; /* chip enable */ @@ -86,11 +51,6 @@ struct atmel_uart_data { struct serial_rs485 rs485; /* rs485 settings */ }; -/* CAN */ -struct at91_can_data { - void (*transceiver_switch)(int on); -}; - /* FIXME: this needs a better location, but gets stuff building again */ extern int at91_suspend_entering_slow_clock(void); diff --git a/kernel/include/linux/i2c/atmel_mxt_ts.h b/kernel/include/linux/platform_data/atmel_mxt_ts.h index 02bf6ea31..695035a8d 100644 --- a/kernel/include/linux/i2c/atmel_mxt_ts.h +++ b/kernel/include/linux/platform_data/atmel_mxt_ts.h @@ -10,16 +10,22 @@ * option) any later version. */ -#ifndef __LINUX_ATMEL_MXT_TS_H -#define __LINUX_ATMEL_MXT_TS_H +#ifndef __LINUX_PLATFORM_DATA_ATMEL_MXT_TS_H +#define __LINUX_PLATFORM_DATA_ATMEL_MXT_TS_H #include <linux/types.h> +enum mxt_suspend_mode { + MXT_SUSPEND_DEEP_SLEEP = 0, + MXT_SUSPEND_T9_CTRL = 1, +}; + /* The platform data for the Atmel maXTouch touchscreen driver */ struct mxt_platform_data { unsigned long irqflags; u8 t19_num_keys; const unsigned int *t19_keymap; + enum mxt_suspend_mode suspend_mode; }; -#endif /* __LINUX_ATMEL_MXT_TS_H */ +#endif /* __LINUX_PLATFORM_DATA_ATMEL_MXT_TS_H */ diff --git a/kernel/include/linux/platform_data/clk-ux500.h b/kernel/include/linux/platform_data/clk-ux500.h index 97baf831e..3af0da1f3 100644 --- a/kernel/include/linux/platform_data/clk-ux500.h +++ b/kernel/include/linux/platform_data/clk-ux500.h @@ -10,14 +10,8 @@ #ifndef __CLK_UX500_H #define __CLK_UX500_H -void u8500_of_clk_init(u32 clkrst1_base, u32 clkrst2_base, u32 clkrst3_base, - u32 clkrst5_base, u32 clkrst6_base); - -void u8500_clk_init(u32 clkrst1_base, u32 clkrst2_base, u32 clkrst3_base, - u32 clkrst5_base, u32 clkrst6_base); -void u9540_clk_init(u32 clkrst1_base, u32 clkrst2_base, u32 clkrst3_base, - u32 clkrst5_base, u32 clkrst6_base); -void u8540_clk_init(u32 clkrst1_base, u32 clkrst2_base, u32 clkrst3_base, - u32 clkrst5_base, u32 clkrst6_base); +void u8500_clk_init(void); +void u9540_clk_init(void); +void u8540_clk_init(void); #endif /* __CLK_UX500_H */ diff --git a/kernel/include/linux/platform_data/dma-dw.h b/kernel/include/linux/platform_data/dma-dw.h index 87ac14c58..03b6095d3 100644 --- a/kernel/include/linux/platform_data/dma-dw.h +++ b/kernel/include/linux/platform_data/dma-dw.h @@ -37,6 +37,7 @@ struct dw_dma_slave { * @nr_channels: Number of channels supported by hardware (max 8) * @is_private: The device channels should be marked as private and not for * by the general purpose DMA channel allocator. + * @is_memcpy: The device channels do support memory-to-memory transfers. * @chan_allocation_order: Allocate channels starting from 0 or 7 * @chan_priority: Set channel priority increasing from 0 to 7 or 7 to 0. * @block_size: Maximum block size supported by the controller @@ -47,6 +48,7 @@ struct dw_dma_slave { struct dw_dma_platform_data { unsigned int nr_channels; bool is_private; + bool is_memcpy; #define CHAN_ALLOCATION_ASCENDING 0 /* zero to seven */ #define CHAN_ALLOCATION_DESCENDING 1 /* seven to zero */ unsigned char chan_allocation_order; diff --git a/kernel/include/linux/platform_data/dma-hsu.h b/kernel/include/linux/platform_data/dma-hsu.h index 8a1f6a492..3453fa655 100644 --- a/kernel/include/linux/platform_data/dma-hsu.h +++ b/kernel/include/linux/platform_data/dma-hsu.h @@ -18,8 +18,4 @@ struct hsu_dma_slave { int chan_id; }; -struct hsu_dma_platform_data { - unsigned short nr_channels; -}; - #endif /* _PLATFORM_DATA_DMA_HSU_H */ diff --git a/kernel/include/linux/platform_data/dma-rcar-audmapp.h b/kernel/include/linux/platform_data/dma-rcar-audmapp.h deleted file mode 100644 index 471fffebb..000000000 --- a/kernel/include/linux/platform_data/dma-rcar-audmapp.h +++ /dev/null @@ -1,34 +0,0 @@ -/* - * This is for Renesas R-Car Audio-DMAC-peri-peri. - * - * Copyright (C) 2014 Renesas Electronics Corporation - * Copyright (C) 2014 Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> - * - * This file is based on the include/linux/sh_dma.h - * - * Header for the new SH dmaengine driver - * - * Copyright (C) 2010 Guennadi Liakhovetski <g.liakhovetski@gmx.de> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ -#ifndef SH_AUDMAPP_H -#define SH_AUDMAPP_H - -#include <linux/dmaengine.h> - -struct audmapp_slave_config { - int slave_id; - dma_addr_t src; - dma_addr_t dst; - u32 chcr; -}; - -struct audmapp_pdata { - struct audmapp_slave_config *slave; - int slave_num; -}; - -#endif /* SH_AUDMAPP_H */ diff --git a/kernel/include/linux/platform_data/edma.h b/kernel/include/linux/platform_data/edma.h index bdb2710e2..4299f4ba0 100644 --- a/kernel/include/linux/platform_data/edma.h +++ b/kernel/include/linux/platform_data/edma.h @@ -41,51 +41,6 @@ #ifndef EDMA_H_ #define EDMA_H_ -/* PaRAM slots are laid out like this */ -struct edmacc_param { - u32 opt; - u32 src; - u32 a_b_cnt; - u32 dst; - u32 src_dst_bidx; - u32 link_bcntrld; - u32 src_dst_cidx; - u32 ccnt; -} __packed; - -/* fields in edmacc_param.opt */ -#define SAM BIT(0) -#define DAM BIT(1) -#define SYNCDIM BIT(2) -#define STATIC BIT(3) -#define EDMA_FWID (0x07 << 8) -#define TCCMODE BIT(11) -#define EDMA_TCC(t) ((t) << 12) -#define TCINTEN BIT(20) -#define ITCINTEN BIT(21) -#define TCCHEN BIT(22) -#define ITCCHEN BIT(23) - -/*ch_status paramater of callback function possible values*/ -#define EDMA_DMA_COMPLETE 1 -#define EDMA_DMA_CC_ERROR 2 -#define EDMA_DMA_TC1_ERROR 3 -#define EDMA_DMA_TC2_ERROR 4 - -enum address_mode { - INCR = 0, - FIFO = 1 -}; - -enum fifo_width { - W8BIT = 0, - W16BIT = 1, - W32BIT = 2, - W64BIT = 3, - W128BIT = 4, - W256BIT = 5 -}; - enum dma_event_q { EVENTQ_0 = 0, EVENTQ_1 = 1, @@ -94,64 +49,10 @@ enum dma_event_q { EVENTQ_DEFAULT = -1 }; -enum sync_dimension { - ASYNC = 0, - ABSYNC = 1 -}; - #define EDMA_CTLR_CHAN(ctlr, chan) (((ctlr) << 16) | (chan)) #define EDMA_CTLR(i) ((i) >> 16) #define EDMA_CHAN_SLOT(i) ((i) & 0xffff) -#define EDMA_CHANNEL_ANY -1 /* for edma_alloc_channel() */ -#define EDMA_SLOT_ANY -1 /* for edma_alloc_slot() */ -#define EDMA_CONT_PARAMS_ANY 1001 -#define EDMA_CONT_PARAMS_FIXED_EXACT 1002 -#define EDMA_CONT_PARAMS_FIXED_NOT_EXACT 1003 - -#define EDMA_MAX_CC 2 - -/* alloc/free DMA channels and their dedicated parameter RAM slots */ -int edma_alloc_channel(int channel, - void (*callback)(unsigned channel, u16 ch_status, void *data), - void *data, enum dma_event_q); -void edma_free_channel(unsigned channel); - -/* alloc/free parameter RAM slots */ -int edma_alloc_slot(unsigned ctlr, int slot); -void edma_free_slot(unsigned slot); - -/* alloc/free a set of contiguous parameter RAM slots */ -int edma_alloc_cont_slots(unsigned ctlr, unsigned int id, int slot, int count); -int edma_free_cont_slots(unsigned slot, int count); - -/* calls that operate on part of a parameter RAM slot */ -void edma_set_src(unsigned slot, dma_addr_t src_port, - enum address_mode mode, enum fifo_width); -void edma_set_dest(unsigned slot, dma_addr_t dest_port, - enum address_mode mode, enum fifo_width); -dma_addr_t edma_get_position(unsigned slot, bool dst); -void edma_set_src_index(unsigned slot, s16 src_bidx, s16 src_cidx); -void edma_set_dest_index(unsigned slot, s16 dest_bidx, s16 dest_cidx); -void edma_set_transfer_params(unsigned slot, u16 acnt, u16 bcnt, u16 ccnt, - u16 bcnt_rld, enum sync_dimension sync_mode); -void edma_link(unsigned from, unsigned to); -void edma_unlink(unsigned from); - -/* calls that operate on an entire parameter RAM slot */ -void edma_write_slot(unsigned slot, const struct edmacc_param *params); -void edma_read_slot(unsigned slot, struct edmacc_param *params); - -/* channel control operations */ -int edma_start(unsigned channel); -void edma_stop(unsigned channel); -void edma_clean_channel(unsigned channel); -void edma_clear_event(unsigned channel); -void edma_pause(unsigned channel); -void edma_resume(unsigned channel); - -void edma_assign_channel_eventq(unsigned channel, enum dma_event_q eventq_no); - struct edma_rsv_info { const s16 (*rsv_chans)[2]; @@ -170,10 +71,11 @@ struct edma_soc_info { /* Resource reservation for other cores */ struct edma_rsv_info *rsv; + /* List of channels allocated for memcpy, terminated with -1 */ + s32 *memcpy_channels; + s8 (*queue_priority_mapping)[2]; const s16 (*xbar_chans)[2]; }; -int edma_trigger_channel(unsigned); - #endif diff --git a/kernel/include/linux/platform_data/gpio-ath79.h b/kernel/include/linux/platform_data/gpio-ath79.h new file mode 100644 index 000000000..88b0db7be --- /dev/null +++ b/kernel/include/linux/platform_data/gpio-ath79.h @@ -0,0 +1,19 @@ +/* + * Atheros AR7XXX/AR9XXX GPIO controller platform data + * + * Copyright (C) 2015 Alban Bedel <albeu@free.fr> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef __LINUX_PLATFORM_DATA_GPIO_ATH79_H +#define __LINUX_PLATFORM_DATA_GPIO_ATH79_H + +struct ath79_gpio_platform_data { + unsigned ngpios; + bool oe_inverted; +}; + +#endif diff --git a/kernel/include/linux/platform_data/gpio-em.h b/kernel/include/linux/platform_data/gpio-em.h deleted file mode 100644 index 7c5a519d2..000000000 --- a/kernel/include/linux/platform_data/gpio-em.h +++ /dev/null @@ -1,11 +0,0 @@ -#ifndef __GPIO_EM_H__ -#define __GPIO_EM_H__ - -struct gpio_em_config { - unsigned int gpio_base; - unsigned int irq_base; - unsigned int number_of_pins; - const char *pctl_name; -}; - -#endif /* __GPIO_EM_H__ */ diff --git a/kernel/include/linux/platform_data/gpio-omap.h b/kernel/include/linux/platform_data/gpio-omap.h index 5d50b25a7..cb2618147 100644 --- a/kernel/include/linux/platform_data/gpio-omap.h +++ b/kernel/include/linux/platform_data/gpio-omap.h @@ -208,9 +208,17 @@ struct omap_gpio_platform_data { int (*get_context_loss_count)(struct device *dev); }; +#if IS_BUILTIN(CONFIG_GPIO_OMAP) extern void omap2_gpio_prepare_for_idle(int off_mode); extern void omap2_gpio_resume_after_idle(void); -extern void omap_set_gpio_debounce(int gpio, int enable); -extern void omap_set_gpio_debounce_time(int gpio, int enable); +#else +static inline void omap2_gpio_prepare_for_idle(int off_mode) +{ +} + +static inline void omap2_gpio_resume_after_idle(void) +{ +} +#endif #endif diff --git a/kernel/include/linux/platform_data/i2c-mux-reg.h b/kernel/include/linux/platform_data/i2c-mux-reg.h new file mode 100644 index 000000000..c68712aad --- /dev/null +++ b/kernel/include/linux/platform_data/i2c-mux-reg.h @@ -0,0 +1,44 @@ +/* + * I2C multiplexer using a single register + * + * Copyright 2015 Freescale Semiconductor + * York Sun <yorksun@freescale.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + */ + +#ifndef __LINUX_PLATFORM_DATA_I2C_MUX_REG_H +#define __LINUX_PLATFORM_DATA_I2C_MUX_REG_H + +/** + * struct i2c_mux_reg_platform_data - Platform-dependent data for i2c-mux-reg + * @parent: Parent I2C bus adapter number + * @base_nr: Base I2C bus number to number adapters from or zero for dynamic + * @values: Array of value for each channel + * @n_values: Number of multiplexer channels + * @little_endian: Indicating if the register is in little endian + * @write_only: Reading the register is not allowed by hardware + * @classes: Optional I2C auto-detection classes + * @idle: Value to write to mux when idle + * @idle_in_use: indicate if idle value is in use + * @reg: Virtual address of the register to switch channel + * @reg_size: register size in bytes + */ +struct i2c_mux_reg_platform_data { + int parent; + int base_nr; + const unsigned int *values; + int n_values; + bool little_endian; + bool write_only; + const unsigned int *classes; + u32 idle; + bool idle_in_use; + void __iomem *reg; + resource_size_t reg_size; +}; + +#endif /* __LINUX_PLATFORM_DATA_I2C_MUX_REG_H */ diff --git a/kernel/include/linux/platform_data/irq-renesas-irqc.h b/kernel/include/linux/platform_data/irq-renesas-irqc.h deleted file mode 100644 index 3ae17b3e0..000000000 --- a/kernel/include/linux/platform_data/irq-renesas-irqc.h +++ /dev/null @@ -1,27 +0,0 @@ -/* - * Renesas IRQC Driver - * - * Copyright (C) 2013 Magnus Damm - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - */ - -#ifndef __IRQ_RENESAS_IRQC_H__ -#define __IRQ_RENESAS_IRQC_H__ - -struct renesas_irqc_config { - unsigned int irq_base; -}; - -#endif /* __IRQ_RENESAS_IRQC_H__ */ diff --git a/kernel/include/linux/platform_data/itco_wdt.h b/kernel/include/linux/platform_data/itco_wdt.h new file mode 100644 index 000000000..f16542c77 --- /dev/null +++ b/kernel/include/linux/platform_data/itco_wdt.h @@ -0,0 +1,19 @@ +/* + * Platform data for the Intel TCO Watchdog + */ + +#ifndef _ITCO_WDT_H_ +#define _ITCO_WDT_H_ + +/* Watchdog resources */ +#define ICH_RES_IO_TCO 0 +#define ICH_RES_IO_SMI 1 +#define ICH_RES_MEM_OFF 2 +#define ICH_RES_MEM_GCS_PMC 0 + +struct itco_wdt_platform_data { + char name[32]; + unsigned int version; +}; + +#endif /* _ITCO_WDT_H_ */ diff --git a/kernel/include/linux/platform_data/keyboard-spear.h b/kernel/include/linux/platform_data/keyboard-spear.h index 9248e3a7e..5e3ff6539 100644 --- a/kernel/include/linux/platform_data/keyboard-spear.h +++ b/kernel/include/linux/platform_data/keyboard-spear.h @@ -1,6 +1,6 @@ /* * Copyright (C) 2010 ST Microelectronics - * Rajeev Kumar<rajeev-dlh.kumar@st.com> + * Rajeev Kumar <rajeevkumar.linux@gmail.com> * * This file is licensed under the terms of the GNU General Public * License version 2. This program is licensed "as is" without any diff --git a/kernel/include/linux/platform_data/leds-kirkwood-netxbig.h b/kernel/include/linux/platform_data/leds-kirkwood-netxbig.h index d2be19a51..3c85a735c 100644 --- a/kernel/include/linux/platform_data/leds-kirkwood-netxbig.h +++ b/kernel/include/linux/platform_data/leds-kirkwood-netxbig.h @@ -40,6 +40,7 @@ struct netxbig_led { int mode_addr; int *mode_val; int bright_addr; + int bright_max; }; struct netxbig_led_platform_data { diff --git a/kernel/include/linux/platform_data/leds-kirkwood-ns2.h b/kernel/include/linux/platform_data/leds-kirkwood-ns2.h index 6a9fed57f..eb8a6860e 100644 --- a/kernel/include/linux/platform_data/leds-kirkwood-ns2.h +++ b/kernel/include/linux/platform_data/leds-kirkwood-ns2.h @@ -9,11 +9,25 @@ #ifndef __LEDS_KIRKWOOD_NS2_H #define __LEDS_KIRKWOOD_NS2_H +enum ns2_led_modes { + NS_V2_LED_OFF, + NS_V2_LED_ON, + NS_V2_LED_SATA, +}; + +struct ns2_led_modval { + enum ns2_led_modes mode; + int cmd_level; + int slow_level; +}; + struct ns2_led { const char *name; const char *default_trigger; unsigned cmd; unsigned slow; + int num_modes; + struct ns2_led_modval *modval; }; struct ns2_led_platform_data { diff --git a/kernel/include/linux/platform_data/lp855x.h b/kernel/include/linux/platform_data/lp855x.h index 9c7fd1efe..1b2ba24e4 100644 --- a/kernel/include/linux/platform_data/lp855x.h +++ b/kernel/include/linux/platform_data/lp855x.h @@ -136,7 +136,6 @@ struct lp855x_rom_data { Only valid when mode is PWM_BASED. * @size_program : total size of lp855x_rom_data * @rom_data : list of new eeprom/eprom registers - * @supply : regulator that supplies 3V input */ struct lp855x_platform_data { const char *name; @@ -145,7 +144,6 @@ struct lp855x_platform_data { unsigned int period_ns; int size_program; struct lp855x_rom_data *rom_data; - struct regulator *supply; }; #endif diff --git a/kernel/include/linux/platform_data/macb.h b/kernel/include/linux/platform_data/macb.h index 044a124bf..21b15f6fe 100644 --- a/kernel/include/linux/platform_data/macb.h +++ b/kernel/include/linux/platform_data/macb.h @@ -8,11 +8,19 @@ #ifndef __MACB_PDATA_H__ #define __MACB_PDATA_H__ +/** + * struct macb_platform_data - platform data for MACB Ethernet + * @phy_mask: phy mask passed when register the MDIO bus + * within the driver + * @phy_irq_pin: PHY IRQ + * @is_rmii: using RMII interface? + * @rev_eth_addr: reverse Ethernet address byte order + */ struct macb_platform_data { u32 phy_mask; - int phy_irq_pin; /* PHY IRQ */ - u8 is_rmii; /* using RMII interface? */ - u8 rev_eth_addr; /* reverse Ethernet address byte order */ + int phy_irq_pin; + u8 is_rmii; + u8 rev_eth_addr; }; #endif /* __MACB_PDATA_H__ */ diff --git a/kernel/include/linux/mdio-gpio.h b/kernel/include/linux/platform_data/mdio-gpio.h index 66c30a763..11f00cdab 100644 --- a/kernel/include/linux/mdio-gpio.h +++ b/kernel/include/linux/platform_data/mdio-gpio.h @@ -23,7 +23,8 @@ struct mdio_gpio_platform_data { bool mdio_active_low; bool mdo_active_low; - unsigned int phy_mask; + u32 phy_mask; + u32 phy_ignore_ta_mask; int irqs[PHY_MAX_ADDR]; /* reset callback */ int (*reset)(struct mii_bus *bus); diff --git a/kernel/include/linux/platform_data/mmc-esdhc-imx.h b/kernel/include/linux/platform_data/mmc-esdhc-imx.h index 75f70f6ac..95ccab3f4 100644 --- a/kernel/include/linux/platform_data/mmc-esdhc-imx.h +++ b/kernel/include/linux/platform_data/mmc-esdhc-imx.h @@ -43,8 +43,8 @@ struct esdhc_platform_data { enum wp_types wp_type; enum cd_types cd_type; int max_bus_width; - unsigned int f_max; bool support_vsel; unsigned int delay_line; + unsigned int tuning_step; /* The delay cell steps in tuning procedure */ }; #endif /* __ASM_ARCH_IMX_ESDHC_H */ diff --git a/kernel/include/linux/platform_data/mtd-nand-pxa3xx.h b/kernel/include/linux/platform_data/mtd-nand-pxa3xx.h index ac4ea2e64..394d15597 100644 --- a/kernel/include/linux/platform_data/mtd-nand-pxa3xx.h +++ b/kernel/include/linux/platform_data/mtd-nand-pxa3xx.h @@ -4,30 +4,6 @@ #include <linux/mtd/mtd.h> #include <linux/mtd/partitions.h> -struct pxa3xx_nand_timing { - unsigned int tCH; /* Enable signal hold time */ - unsigned int tCS; /* Enable signal setup time */ - unsigned int tWH; /* ND_nWE high duration */ - unsigned int tWP; /* ND_nWE pulse time */ - unsigned int tRH; /* ND_nRE high duration */ - unsigned int tRP; /* ND_nRE pulse width */ - unsigned int tR; /* ND_nWE high to ND_nRE low for read */ - unsigned int tWHR; /* ND_nWE high to ND_nRE low for status read */ - unsigned int tAR; /* ND_ALE low to ND_nRE low delay */ -}; - -struct pxa3xx_nand_flash { - char *name; - uint32_t chip_id; - unsigned int page_per_block; /* Pages per block (PG_PER_BLK) */ - unsigned int page_size; /* Page size in bytes (PAGE_SZ) */ - unsigned int flash_width; /* Width of Flash memory (DWIDTH_M) */ - unsigned int dfc_width; /* Width of flash controller(DWIDTH_C) */ - unsigned int num_blocks; /* Number of physical blocks in Flash */ - - struct pxa3xx_nand_timing *timing; /* NAND Flash timing */ -}; - /* * Current pxa3xx_nand controller has two chip select which * both be workable. @@ -63,9 +39,6 @@ struct pxa3xx_nand_platform_data { const struct mtd_partition *parts[NUM_CHIP_SELECT]; unsigned int nr_parts[NUM_CHIP_SELECT]; - - const struct pxa3xx_nand_flash * flash; - size_t num_flash; }; extern void pxa3xx_set_nand_info(struct pxa3xx_nand_platform_data *info); diff --git a/kernel/include/linux/platform_data/nfcmrvl.h b/kernel/include/linux/platform_data/nfcmrvl.h new file mode 100644 index 000000000..a6f9d633f --- /dev/null +++ b/kernel/include/linux/platform_data/nfcmrvl.h @@ -0,0 +1,48 @@ +/* + * Copyright (C) 2015, Marvell International Ltd. + * + * This software file (the "File") is distributed by Marvell International + * Ltd. under the terms of the GNU General Public License Version 2, June 1991 + * (the "License"). You may use, redistribute and/or modify this File in + * accordance with the terms and conditions of the License, a copy of which + * is available on the worldwide web at + * http://www.gnu.org/licenses/old-licenses/gpl-2.0.txt. + * + * THE FILE IS DISTRIBUTED AS-IS, WITHOUT WARRANTY OF ANY KIND, AND THE + * IMPLIED WARRANTIES OF MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE + * ARE EXPRESSLY DISCLAIMED. The License provides additional details about + * this warranty disclaimer. + */ + +#ifndef _NFCMRVL_PTF_H_ +#define _NFCMRVL_PTF_H_ + +struct nfcmrvl_platform_data { + /* + * Generic + */ + + /* GPIO that is wired to RESET_N signal */ + unsigned int reset_n_io; + /* Tell if transport is muxed in HCI one */ + unsigned int hci_muxed; + + /* + * UART specific + */ + + /* Tell if UART needs flow control at init */ + unsigned int flow_control; + /* Tell if firmware supports break control for power management */ + unsigned int break_control; + + + /* + * I2C specific + */ + + unsigned int irq; + unsigned int irq_polarity; +}; + +#endif /* _NFCMRVL_PTF_H_ */ diff --git a/kernel/include/linux/platform_data/ntc_thermistor.h b/kernel/include/linux/platform_data/ntc_thermistor.h index 0a6de4ca4..aed170588 100644 --- a/kernel/include/linux/platform_data/ntc_thermistor.h +++ b/kernel/include/linux/platform_data/ntc_thermistor.h @@ -27,6 +27,7 @@ enum ntc_thermistor_type { TYPE_NCPXXWB473, TYPE_NCPXXWL333, TYPE_B57330V2103, + TYPE_NCPXXWF104, }; struct ntc_thermistor_platform_data { diff --git a/kernel/include/linux/input/pixcir_ts.h b/kernel/include/linux/platform_data/pixcir_i2c_ts.h index 7bae83b7c..646af6f8b 100644 --- a/kernel/include/linux/input/pixcir_ts.h +++ b/kernel/include/linux/platform_data/pixcir_i2c_ts.h @@ -57,7 +57,6 @@ struct pixcir_i2c_chip_data { struct pixcir_ts_platform_data { int x_max; int y_max; - int gpio_attb; /* GPIO connected to ATTB line */ struct pixcir_i2c_chip_data chip; }; diff --git a/kernel/include/linux/platform_data/s3c-hsotg.h b/kernel/include/linux/platform_data/s3c-hsotg.h index 3f1cbf95e..3982586ba 100644 --- a/kernel/include/linux/platform_data/s3c-hsotg.h +++ b/kernel/include/linux/platform_data/s3c-hsotg.h @@ -17,19 +17,19 @@ struct platform_device; -enum s3c_hsotg_dmamode { +enum dwc2_hsotg_dmamode { S3C_HSOTG_DMA_NONE, /* do not use DMA at-all */ S3C_HSOTG_DMA_ONLY, /* always use DMA */ S3C_HSOTG_DMA_DRV, /* DMA is chosen by driver */ }; /** - * struct s3c_hsotg_plat - platform data for high-speed otg/udc + * struct dwc2_hsotg_plat - platform data for high-speed otg/udc * @dma: Whether to use DMA or not. * @is_osc: The clock source is an oscillator, not a crystal */ -struct s3c_hsotg_plat { - enum s3c_hsotg_dmamode dma; +struct dwc2_hsotg_plat { + enum dwc2_hsotg_dmamode dma; unsigned int is_osc:1; int phy_type; @@ -37,6 +37,6 @@ struct s3c_hsotg_plat { int (*phy_exit)(struct platform_device *pdev, int type); }; -extern void s3c_hsotg_set_platdata(struct s3c_hsotg_plat *pd); +extern void dwc2_hsotg_set_platdata(struct dwc2_hsotg_plat *pd); #endif /* __LINUX_USB_S3C_HSOTG_H */ diff --git a/kernel/include/linux/platform_data/spi-davinci.h b/kernel/include/linux/platform_data/spi-davinci.h index 8dc2fa47a..f4edcb03c 100644 --- a/kernel/include/linux/platform_data/spi-davinci.h +++ b/kernel/include/linux/platform_data/spi-davinci.h @@ -49,6 +49,7 @@ struct davinci_spi_platform_data { u8 num_chipselect; u8 intr_line; u8 *chip_sel; + u8 prescaler_limit; bool cshold_bug; enum dma_event_q dma_event_q; }; diff --git a/kernel/include/linux/platform_data/spi-mt65xx.h b/kernel/include/linux/platform_data/spi-mt65xx.h new file mode 100644 index 000000000..54b044839 --- /dev/null +++ b/kernel/include/linux/platform_data/spi-mt65xx.h @@ -0,0 +1,20 @@ +/* + * MTK SPI bus driver definitions + * + * Copyright (c) 2015 MediaTek Inc. + * Author: Leilk Liu <leilk.liu@mediatek.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef ____LINUX_PLATFORM_DATA_SPI_MTK_H +#define ____LINUX_PLATFORM_DATA_SPI_MTK_H + +/* Board specific platform_data */ +struct mtk_chip_config { + u32 tx_mlsb; + u32 rx_mlsb; +}; +#endif diff --git a/kernel/include/linux/platform_data/st21nfcb.h b/kernel/include/linux/platform_data/st-nci.h index b023373d9..f6494b347 100644 --- a/kernel/include/linux/platform_data/st21nfcb.h +++ b/kernel/include/linux/platform_data/st-nci.h @@ -1,7 +1,7 @@ /* - * Driver include for the ST21NFCB NFC chip. + * Driver include for ST NCI NFC chip family. * - * Copyright (C) 2014 STMicroelectronics SAS. All rights reserved. + * Copyright (C) 2014-2015 STMicroelectronics SAS. All rights reserved. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, @@ -16,14 +16,16 @@ * along with this program; if not, see <http://www.gnu.org/licenses/>. */ -#ifndef _ST21NFCB_NCI_H_ -#define _ST21NFCB_NCI_H_ +#ifndef _ST_NCI_H_ +#define _ST_NCI_H_ -#define ST21NFCB_NCI_DRIVER_NAME "st21nfcb_nci" +#define ST_NCI_DRIVER_NAME "st_nci" -struct st21nfcb_nfc_platform_data { +struct st_nci_nfc_platform_data { unsigned int gpio_reset; unsigned int irq_polarity; + bool is_ese_present; + bool is_uicc_present; }; -#endif /* _ST21NFCB_NCI_H_ */ +#endif /* _ST_NCI_H_ */ diff --git a/kernel/include/linux/platform_data/usb-rcar-gen2-phy.h b/kernel/include/linux/platform_data/usb-rcar-gen2-phy.h deleted file mode 100644 index dd3ba46c0..000000000 --- a/kernel/include/linux/platform_data/usb-rcar-gen2-phy.h +++ /dev/null @@ -1,22 +0,0 @@ -/* - * Copyright (C) 2013 Renesas Solutions Corp. - * Copyright (C) 2013 Cogent Embedded, Inc. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#ifndef __USB_RCAR_GEN2_PHY_H -#define __USB_RCAR_GEN2_PHY_H - -#include <linux/types.h> - -struct rcar_gen2_phy_platform_data { - /* USB channel 0 configuration */ - bool chan0_pci:1; /* true: PCI USB host 0, false: USBHS */ - /* USB channel 2 configuration */ - bool chan2_pci:1; /* true: PCI USB host 2, false: USBSS */ -}; - -#endif diff --git a/kernel/include/linux/platform_data/video-ep93xx.h b/kernel/include/linux/platform_data/video-ep93xx.h index 92fc2b223..699ac4109 100644 --- a/kernel/include/linux/platform_data/video-ep93xx.h +++ b/kernel/include/linux/platform_data/video-ep93xx.h @@ -2,11 +2,8 @@ #define __VIDEO_EP93XX_H struct platform_device; -struct fb_videomode; struct fb_info; -#define EP93XXFB_USE_MODEDB 0 - /* VideoAttributes flags */ #define EP93XXFB_STATE_MACHINE_ENABLE (1 << 0) #define EP93XXFB_PIXEL_CLOCK_ENABLE (1 << 1) @@ -38,12 +35,7 @@ struct fb_info; EP93XXFB_PIXEL_DATA_ENABLE) struct ep93xxfb_mach_info { - unsigned int num_modes; - const struct fb_videomode *modes; - const struct fb_videomode *default_mode; - int bpp; unsigned int flags; - int (*setup)(struct platform_device *pdev); void (*teardown)(struct platform_device *pdev); void (*blank)(int blank_mode, struct fb_info *info); diff --git a/kernel/include/linux/platform_data/video-msm_fb.h b/kernel/include/linux/platform_data/video-msm_fb.h deleted file mode 100644 index 31449be3e..000000000 --- a/kernel/include/linux/platform_data/video-msm_fb.h +++ /dev/null @@ -1,146 +0,0 @@ -/* - * Internal shared definitions for various MSM framebuffer parts. - * - * Copyright (C) 2007 Google Incorporated - * - * This software is licensed under the terms of the GNU General Public - * License version 2, as published by the Free Software Foundation, and - * may be copied, distributed, and modified under those terms. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - */ - -#ifndef _MSM_FB_H_ -#define _MSM_FB_H_ - -#include <linux/device.h> - -struct mddi_info; - -struct msm_fb_data { - int xres; /* x resolution in pixels */ - int yres; /* y resolution in pixels */ - int width; /* disply width in mm */ - int height; /* display height in mm */ - unsigned output_format; -}; - -struct msmfb_callback { - void (*func)(struct msmfb_callback *); -}; - -enum { - MSM_MDDI_PMDH_INTERFACE, - MSM_MDDI_EMDH_INTERFACE, - MSM_EBI2_INTERFACE, -}; - -#define MSMFB_CAP_PARTIAL_UPDATES (1 << 0) - -struct msm_panel_data { - /* turns off the fb memory */ - int (*suspend)(struct msm_panel_data *); - /* turns on the fb memory */ - int (*resume)(struct msm_panel_data *); - /* turns off the panel */ - int (*blank)(struct msm_panel_data *); - /* turns on the panel */ - int (*unblank)(struct msm_panel_data *); - void (*wait_vsync)(struct msm_panel_data *); - void (*request_vsync)(struct msm_panel_data *, struct msmfb_callback *); - void (*clear_vsync)(struct msm_panel_data *); - /* from the enum above */ - unsigned interface_type; - /* data to be passed to the fb driver */ - struct msm_fb_data *fb_data; - - /* capabilities supported by the panel */ - uint32_t caps; -}; - -struct msm_mddi_client_data { - void (*suspend)(struct msm_mddi_client_data *); - void (*resume)(struct msm_mddi_client_data *); - void (*activate_link)(struct msm_mddi_client_data *); - void (*remote_write)(struct msm_mddi_client_data *, uint32_t val, - uint32_t reg); - uint32_t (*remote_read)(struct msm_mddi_client_data *, uint32_t reg); - void (*auto_hibernate)(struct msm_mddi_client_data *, int); - /* custom data that needs to be passed from the board file to a - * particular client */ - void *private_client_data; - struct resource *fb_resource; - /* from the list above */ - unsigned interface_type; -}; - -struct msm_mddi_platform_data { - unsigned int clk_rate; - void (*power_client)(struct msm_mddi_client_data *, int on); - - /* fixup the mfr name, product id */ - void (*fixup)(uint16_t *mfr_name, uint16_t *product_id); - - struct resource *fb_resource; /*optional*/ - /* number of clients in the list that follows */ - int num_clients; - /* array of client information of clients */ - struct { - unsigned product_id; /* mfr id in top 16 bits, product id - * in lower 16 bits - */ - char *name; /* the device name will be the platform - * device name registered for the client, - * it should match the name of the associated - * driver - */ - unsigned id; /* id for mddi client device node, will also - * be used as device id of panel devices, if - * the client device will have multiple panels - * space must be left here for them - */ - void *client_data; /* required private client data */ - unsigned int clk_rate; /* optional: if the client requires a - * different mddi clk rate - */ - } client_platform_data[]; -}; - -struct mdp_blit_req; -struct fb_info; -struct mdp_device { - struct device dev; - void (*dma)(struct mdp_device *mpd, uint32_t addr, - uint32_t stride, uint32_t w, uint32_t h, uint32_t x, - uint32_t y, struct msmfb_callback *callback, int interface); - void (*dma_wait)(struct mdp_device *mdp); - int (*blit)(struct mdp_device *mdp, struct fb_info *fb, - struct mdp_blit_req *req); - void (*set_grp_disp)(struct mdp_device *mdp, uint32_t disp_id); -}; - -struct class_interface; -int register_mdp_client(struct class_interface *class_intf); - -/**** private client data structs go below this line ***/ - -struct msm_mddi_bridge_platform_data { - /* from board file */ - int (*init)(struct msm_mddi_bridge_platform_data *, - struct msm_mddi_client_data *); - int (*uninit)(struct msm_mddi_bridge_platform_data *, - struct msm_mddi_client_data *); - /* passed to panel for use by the fb driver */ - int (*blank)(struct msm_mddi_bridge_platform_data *, - struct msm_mddi_client_data *); - int (*unblank)(struct msm_mddi_bridge_platform_data *, - struct msm_mddi_client_data *); - struct msm_fb_data fb_data; -}; - - - -#endif diff --git a/kernel/include/linux/platform_data/wkup_m3.h b/kernel/include/linux/platform_data/wkup_m3.h new file mode 100644 index 000000000..3f1d77eff --- /dev/null +++ b/kernel/include/linux/platform_data/wkup_m3.h @@ -0,0 +1,30 @@ +/* + * TI Wakeup M3 remote processor platform data + * + * Copyright (C) 2014-2015 Texas Instruments, Inc. + * + * Dave Gerlach <d-gerlach@ti.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef _LINUX_PLATFORM_DATA_WKUP_M3_H +#define _LINUX_PLATFORM_DATA_WKUP_M3_H + +struct platform_device; + +struct wkup_m3_platform_data { + const char *reset_name; + + int (*assert_reset)(struct platform_device *pdev, const char *name); + int (*deassert_reset)(struct platform_device *pdev, const char *name); +}; + +#endif /* _LINUX_PLATFORM_DATA_WKUP_M3_H */ diff --git a/kernel/include/linux/platform_data/zforce_ts.h b/kernel/include/linux/platform_data/zforce_ts.h index 0472ab2f6..7bdece8ef 100644 --- a/kernel/include/linux/platform_data/zforce_ts.h +++ b/kernel/include/linux/platform_data/zforce_ts.h @@ -16,9 +16,6 @@ #define _LINUX_INPUT_ZFORCE_TS_H struct zforce_ts_platdata { - int gpio_int; - int gpio_rst; - unsigned int x_max; unsigned int y_max; }; diff --git a/kernel/include/linux/platform_device.h b/kernel/include/linux/platform_device.h index 58f1e75ba..dc777be5f 100644 --- a/kernel/include/linux/platform_device.h +++ b/kernel/include/linux/platform_device.h @@ -222,6 +222,15 @@ static inline void platform_set_drvdata(struct platform_device *pdev, module_driver(__platform_driver, platform_driver_register, \ platform_driver_unregister) +/* builtin_platform_driver() - Helper macro for builtin drivers that + * don't do anything special in driver init. This eliminates some + * boilerplate. Each driver may only use this macro once, and + * calling it replaces device_initcall(). Note this is meant to be + * a parallel of module_platform_driver() above, but w/o _exit stuff. + */ +#define builtin_platform_driver(__platform_driver) \ + builtin_driver(__platform_driver, platform_driver_register) + /* module_platform_driver_probe() - Helper macro for drivers that don't do * anything special in module init/exit. This eliminates a lot of * boilerplate. Each module may only use this macro once, and @@ -240,6 +249,20 @@ static void __exit __platform_driver##_exit(void) \ } \ module_exit(__platform_driver##_exit); +/* builtin_platform_driver_probe() - Helper macro for drivers that don't do + * anything special in device init. This eliminates some boilerplate. Each + * driver may only use this macro once, and using it replaces device_initcall. + * This is meant to be a parallel of module_platform_driver_probe above, but + * without the __exit parts. + */ +#define builtin_platform_driver_probe(__platform_driver, __platform_probe) \ +static int __init __platform_driver##_init(void) \ +{ \ + return platform_driver_probe(&(__platform_driver), \ + __platform_probe); \ +} \ +device_initcall(__platform_driver##_init); \ + #define platform_create_bundle(driver, probe, res, n_res, data, size) \ __platform_create_bundle(driver, probe, res, n_res, data, size, THIS_MODULE) extern struct platform_device *__platform_create_bundle( @@ -247,6 +270,14 @@ extern struct platform_device *__platform_create_bundle( struct resource *res, unsigned int n_res, const void *data, size_t size, struct module *module); +int __platform_register_drivers(struct platform_driver * const *drivers, + unsigned int count, struct module *owner); +void platform_unregister_drivers(struct platform_driver * const *drivers, + unsigned int count); + +#define platform_register_drivers(drivers, count) \ + __platform_register_drivers(drivers, count, THIS_MODULE) + /* early platform driver interface */ struct early_platform_driver { const char *class_str; diff --git a/kernel/include/linux/pm.h b/kernel/include/linux/pm.h index 2d29c64f8..528be6787 100644 --- a/kernel/include/linux/pm.h +++ b/kernel/include/linux/pm.h @@ -342,6 +342,18 @@ struct dev_pm_ops { #define SET_LATE_SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) #endif +#ifdef CONFIG_PM_SLEEP +#define SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ + .suspend_noirq = suspend_fn, \ + .resume_noirq = resume_fn, \ + .freeze_noirq = suspend_fn, \ + .thaw_noirq = resume_fn, \ + .poweroff_noirq = suspend_fn, \ + .restore_noirq = resume_fn, +#else +#define SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) +#endif + #ifdef CONFIG_PM #define SET_RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) \ .runtime_suspend = suspend_fn, \ @@ -529,6 +541,7 @@ enum rpm_request { }; struct wakeup_source; +struct wake_irq; struct pm_domain_data; struct pm_subsys_data { @@ -568,6 +581,7 @@ struct dev_pm_info { unsigned long timer_expires; struct work_struct work; wait_queue_head_t wait_queue; + struct wake_irq *wakeirq; atomic_t usage_count; atomic_t child_count; unsigned int disable_depth:3; @@ -718,6 +732,7 @@ extern int pm_generic_poweroff_noirq(struct device *dev); extern int pm_generic_poweroff_late(struct device *dev); extern int pm_generic_poweroff(struct device *dev); extern void pm_generic_complete(struct device *dev); +extern void pm_complete_with_resume_check(struct device *dev); #else /* !CONFIG_PM_SLEEP */ diff --git a/kernel/include/linux/pm_clock.h b/kernel/include/linux/pm_clock.h index 0b0039634..25266c600 100644 --- a/kernel/include/linux/pm_clock.h +++ b/kernel/include/linux/pm_clock.h @@ -20,6 +20,16 @@ struct pm_clk_notifier_block { struct clk; +#ifdef CONFIG_PM +extern int pm_clk_runtime_suspend(struct device *dev); +extern int pm_clk_runtime_resume(struct device *dev); +#define USE_PM_CLK_RUNTIME_OPS \ + .runtime_suspend = pm_clk_runtime_suspend, \ + .runtime_resume = pm_clk_runtime_resume, +#else +#define USE_PM_CLK_RUNTIME_OPS +#endif + #ifdef CONFIG_PM_CLK static inline bool pm_clk_no_clocks(struct device *dev) { diff --git a/kernel/include/linux/pm_domain.h b/kernel/include/linux/pm_domain.h index 681ccb053..ba4ced38e 100644 --- a/kernel/include/linux/pm_domain.h +++ b/kernel/include/linux/pm_domain.h @@ -15,16 +15,12 @@ #include <linux/err.h> #include <linux/of.h> #include <linux/notifier.h> -#include <linux/cpuidle.h> /* Defines used for the flags field in the struct generic_pm_domain */ #define GENPD_FLAG_PM_CLK (1U << 0) /* PM domain uses PM clk */ enum gpd_status { GPD_STATE_ACTIVE = 0, /* PM domain is active */ - GPD_STATE_WAIT_MASTER, /* PM domain's master is being waited for */ - GPD_STATE_BUSY, /* Something is happening to the PM domain */ - GPD_STATE_REPEAT, /* Power off in progress, to be repeated */ GPD_STATE_POWER_OFF, /* PM domain is off */ }; @@ -41,11 +37,6 @@ struct gpd_dev_ops { bool (*active_wakeup)(struct device *dev); }; -struct gpd_cpuidle_data { - unsigned int saved_exit_latency; - struct cpuidle_state *idle_state; -}; - struct generic_pm_domain { struct dev_pm_domain domain; /* PM domain operations */ struct list_head gpd_list_node; /* Node in the global PM domains list */ @@ -56,12 +47,8 @@ struct generic_pm_domain { struct dev_power_governor *gov; struct work_struct power_off_work; const char *name; - unsigned int in_progress; /* Number of devices being suspended now */ atomic_t sd_count; /* Number of subdomains with power "on" */ enum gpd_status status; /* Current state of the domain */ - wait_queue_head_t status_wait_queue; - struct task_struct *poweroff_task; /* Powering off task */ - unsigned int resume_count; /* Number of devices being resumed */ unsigned int device_count; /* Number of devices */ unsigned int suspended_count; /* System suspend device counter */ unsigned int prepared_count; /* Suspend counter of prepared devices */ @@ -74,7 +61,6 @@ struct generic_pm_domain { s64 max_off_time_ns; /* Maximum allowed "suspended" time. */ bool max_off_time_changed; bool cached_power_down_ok; - struct gpd_cpuidle_data *cpuidle_data; int (*attach_dev)(struct generic_pm_domain *domain, struct device *dev); void (*detach_dev)(struct generic_pm_domain *domain, @@ -95,10 +81,8 @@ struct gpd_link { }; struct gpd_timing_data { - s64 stop_latency_ns; - s64 start_latency_ns; - s64 save_state_latency_ns; - s64 restore_state_latency_ns; + s64 suspend_latency_ns; + s64 resume_latency_ns; s64 effective_constraint_ns; bool constraint_changed; bool cached_stop_ok; @@ -113,7 +97,6 @@ struct generic_pm_domain_data { struct pm_domain_data base; struct gpd_timing_data td; struct notifier_block nb; - int need_restore; }; #ifdef CONFIG_PM_GENERIC_DOMAINS @@ -132,29 +115,15 @@ extern int __pm_genpd_add_device(struct generic_pm_domain *genpd, struct device *dev, struct gpd_timing_data *td); -extern int __pm_genpd_name_add_device(const char *domain_name, - struct device *dev, - struct gpd_timing_data *td); - extern int pm_genpd_remove_device(struct generic_pm_domain *genpd, struct device *dev); extern int pm_genpd_add_subdomain(struct generic_pm_domain *genpd, struct generic_pm_domain *new_subdomain); -extern int pm_genpd_add_subdomain_names(const char *master_name, - const char *subdomain_name); extern int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd, struct generic_pm_domain *target); -extern int pm_genpd_attach_cpuidle(struct generic_pm_domain *genpd, int state); -extern int pm_genpd_name_attach_cpuidle(const char *name, int state); -extern int pm_genpd_detach_cpuidle(struct generic_pm_domain *genpd); -extern int pm_genpd_name_detach_cpuidle(const char *name); extern void pm_genpd_init(struct generic_pm_domain *genpd, struct dev_power_governor *gov, bool is_off); -extern int pm_genpd_poweron(struct generic_pm_domain *genpd); -extern int pm_genpd_name_poweron(const char *domain_name); -extern void pm_genpd_poweroff_unused(void); - extern struct dev_power_governor simple_qos_governor; extern struct dev_power_governor pm_domain_always_on_gov; #else @@ -173,12 +142,6 @@ static inline int __pm_genpd_add_device(struct generic_pm_domain *genpd, { return -ENOSYS; } -static inline int __pm_genpd_name_add_device(const char *domain_name, - struct device *dev, - struct gpd_timing_data *td) -{ - return -ENOSYS; -} static inline int pm_genpd_remove_device(struct generic_pm_domain *genpd, struct device *dev) { @@ -189,47 +152,15 @@ static inline int pm_genpd_add_subdomain(struct generic_pm_domain *genpd, { return -ENOSYS; } -static inline int pm_genpd_add_subdomain_names(const char *master_name, - const char *subdomain_name) -{ - return -ENOSYS; -} static inline int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd, struct generic_pm_domain *target) { return -ENOSYS; } -static inline int pm_genpd_attach_cpuidle(struct generic_pm_domain *genpd, int st) -{ - return -ENOSYS; -} -static inline int pm_genpd_name_attach_cpuidle(const char *name, int state) -{ - return -ENOSYS; -} -static inline int pm_genpd_detach_cpuidle(struct generic_pm_domain *genpd) -{ - return -ENOSYS; -} -static inline int pm_genpd_name_detach_cpuidle(const char *name) -{ - return -ENOSYS; -} static inline void pm_genpd_init(struct generic_pm_domain *genpd, struct dev_power_governor *gov, bool is_off) { } -static inline int pm_genpd_poweron(struct generic_pm_domain *genpd) -{ - return -ENOSYS; -} -static inline int pm_genpd_name_poweron(const char *domain_name) -{ - return -ENOSYS; -} -static inline void pm_genpd_poweroff_unused(void) {} -#define simple_qos_governor NULL -#define pm_domain_always_on_gov NULL #endif static inline int pm_genpd_add_device(struct generic_pm_domain *genpd, @@ -238,12 +169,6 @@ static inline int pm_genpd_add_device(struct generic_pm_domain *genpd, return __pm_genpd_add_device(genpd, dev, NULL); } -static inline int pm_genpd_name_add_device(const char *domain_name, - struct device *dev) -{ - return __pm_genpd_name_add_device(domain_name, dev, NULL); -} - #ifdef CONFIG_PM_GENERIC_DOMAINS_SLEEP extern void pm_genpd_syscore_poweroff(struct device *dev); extern void pm_genpd_syscore_poweron(struct device *dev); diff --git a/kernel/include/linux/pm_opp.h b/kernel/include/linux/pm_opp.h index cec2d4540..9a2e50337 100644 --- a/kernel/include/linux/pm_opp.h +++ b/kernel/include/linux/pm_opp.h @@ -30,7 +30,11 @@ unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp); unsigned long dev_pm_opp_get_freq(struct dev_pm_opp *opp); +bool dev_pm_opp_is_turbo(struct dev_pm_opp *opp); + int dev_pm_opp_get_opp_count(struct device *dev); +unsigned long dev_pm_opp_get_max_clock_latency(struct device *dev); +struct dev_pm_opp *dev_pm_opp_get_suspend_opp(struct device *dev); struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev, unsigned long freq, @@ -62,11 +66,26 @@ static inline unsigned long dev_pm_opp_get_freq(struct dev_pm_opp *opp) return 0; } +static inline bool dev_pm_opp_is_turbo(struct dev_pm_opp *opp) +{ + return false; +} + static inline int dev_pm_opp_get_opp_count(struct device *dev) { return 0; } +static inline unsigned long dev_pm_opp_get_max_clock_latency(struct device *dev) +{ + return 0; +} + +static inline struct dev_pm_opp *dev_pm_opp_get_suspend_opp(struct device *dev) +{ + return NULL; +} + static inline struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev, unsigned long freq, bool available) { @@ -113,16 +132,39 @@ static inline struct srcu_notifier_head *dev_pm_opp_get_notifier( #endif /* CONFIG_PM_OPP */ #if defined(CONFIG_PM_OPP) && defined(CONFIG_OF) -int of_init_opp_table(struct device *dev); -void of_free_opp_table(struct device *dev); +int dev_pm_opp_of_add_table(struct device *dev); +void dev_pm_opp_of_remove_table(struct device *dev); +int dev_pm_opp_of_cpumask_add_table(cpumask_var_t cpumask); +void dev_pm_opp_of_cpumask_remove_table(cpumask_var_t cpumask); +int dev_pm_opp_of_get_sharing_cpus(struct device *cpu_dev, cpumask_var_t cpumask); +int dev_pm_opp_set_sharing_cpus(struct device *cpu_dev, cpumask_var_t cpumask); #else -static inline int of_init_opp_table(struct device *dev) +static inline int dev_pm_opp_of_add_table(struct device *dev) { return -EINVAL; } -static inline void of_free_opp_table(struct device *dev) +static inline void dev_pm_opp_of_remove_table(struct device *dev) +{ +} + +static inline int dev_pm_opp_of_cpumask_add_table(cpumask_var_t cpumask) +{ + return -ENOSYS; +} + +static inline void dev_pm_opp_of_cpumask_remove_table(cpumask_var_t cpumask) +{ +} + +static inline int dev_pm_opp_of_get_sharing_cpus(struct device *cpu_dev, cpumask_var_t cpumask) +{ + return -ENOSYS; +} + +static inline int dev_pm_opp_set_sharing_cpus(struct device *cpu_dev, cpumask_var_t cpumask) { + return -ENOSYS; } #endif diff --git a/kernel/include/linux/pm_qos.h b/kernel/include/linux/pm_qos.h index 7b3ae0cff..0f65d36c2 100644 --- a/kernel/include/linux/pm_qos.h +++ b/kernel/include/linux/pm_qos.h @@ -161,6 +161,8 @@ void dev_pm_qos_hide_flags(struct device *dev); int dev_pm_qos_update_flags(struct device *dev, s32 mask, bool set); s32 dev_pm_qos_get_user_latency_tolerance(struct device *dev); int dev_pm_qos_update_user_latency_tolerance(struct device *dev, s32 val); +int dev_pm_qos_expose_latency_tolerance(struct device *dev); +void dev_pm_qos_hide_latency_tolerance(struct device *dev); static inline s32 dev_pm_qos_requested_resume_latency(struct device *dev) { @@ -229,6 +231,9 @@ static inline s32 dev_pm_qos_get_user_latency_tolerance(struct device *dev) { return PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT; } static inline int dev_pm_qos_update_user_latency_tolerance(struct device *dev, s32 val) { return 0; } +static inline int dev_pm_qos_expose_latency_tolerance(struct device *dev) + { return 0; } +static inline void dev_pm_qos_hide_latency_tolerance(struct device *dev) {} static inline s32 dev_pm_qos_requested_resume_latency(struct device *dev) { return 0; } static inline s32 dev_pm_qos_requested_flags(struct device *dev) { return 0; } diff --git a/kernel/include/linux/pm_runtime.h b/kernel/include/linux/pm_runtime.h index 30e84d48b..3bdbb4189 100644 --- a/kernel/include/linux/pm_runtime.h +++ b/kernel/include/linux/pm_runtime.h @@ -98,11 +98,6 @@ static inline bool pm_runtime_status_suspended(struct device *dev) return dev->power.runtime_status == RPM_SUSPENDED; } -static inline bool pm_runtime_suspended_if_enabled(struct device *dev) -{ - return pm_runtime_status_suspended(dev) && dev->power.disable_depth == 1; -} - static inline bool pm_runtime_enabled(struct device *dev) { return !dev->power.disable_depth; @@ -164,7 +159,6 @@ static inline void device_set_run_wake(struct device *dev, bool enable) {} static inline bool pm_runtime_suspended(struct device *dev) { return false; } static inline bool pm_runtime_active(struct device *dev) { return true; } static inline bool pm_runtime_status_suspended(struct device *dev) { return false; } -static inline bool pm_runtime_suspended_if_enabled(struct device *dev) { return false; } static inline bool pm_runtime_enabled(struct device *dev) { return false; } static inline void pm_runtime_no_callbacks(struct device *dev) {} diff --git a/kernel/include/linux/pm_wakeirq.h b/kernel/include/linux/pm_wakeirq.h new file mode 100644 index 000000000..cd5b62db9 --- /dev/null +++ b/kernel/include/linux/pm_wakeirq.h @@ -0,0 +1,51 @@ +/* + * pm_wakeirq.h - Device wakeirq helper functions + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed "as is" WITHOUT ANY WARRANTY of any + * kind, whether express or implied; without even the implied warranty + * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef _LINUX_PM_WAKEIRQ_H +#define _LINUX_PM_WAKEIRQ_H + +#ifdef CONFIG_PM + +extern int dev_pm_set_wake_irq(struct device *dev, int irq); +extern int dev_pm_set_dedicated_wake_irq(struct device *dev, + int irq); +extern void dev_pm_clear_wake_irq(struct device *dev); +extern void dev_pm_enable_wake_irq(struct device *dev); +extern void dev_pm_disable_wake_irq(struct device *dev); + +#else /* !CONFIG_PM */ + +static inline int dev_pm_set_wake_irq(struct device *dev, int irq) +{ + return 0; +} + +static inline int dev_pm_set_dedicated_wake_irq(struct device *dev, int irq) +{ + return 0; +} + +static inline void dev_pm_clear_wake_irq(struct device *dev) +{ +} + +static inline void dev_pm_enable_wake_irq(struct device *dev) +{ +} + +static inline void dev_pm_disable_wake_irq(struct device *dev) +{ +} + +#endif /* CONFIG_PM */ +#endif /* _LINUX_PM_WAKEIRQ_H */ diff --git a/kernel/include/linux/pm_wakeup.h b/kernel/include/linux/pm_wakeup.h index a0f70808d..a3447932d 100644 --- a/kernel/include/linux/pm_wakeup.h +++ b/kernel/include/linux/pm_wakeup.h @@ -28,9 +28,17 @@ #include <linux/types.h> +struct wake_irq; + /** * struct wakeup_source - Representation of wakeup sources * + * @name: Name of the wakeup source + * @entry: Wakeup source list entry + * @lock: Wakeup source lock + * @wakeirq: Optional device specific wakeirq + * @timer: Wakeup timer list + * @timer_expires: Wakeup timer expiration * @total_time: Total time this wakeup source has been active. * @max_time: Maximum time this wakeup source has been continuously active. * @last_time: Monotonic clock when the wakeup source's was touched last time. @@ -47,6 +55,7 @@ struct wakeup_source { const char *name; struct list_head entry; spinlock_t lock; + struct wake_irq *wakeirq; struct timer_list timer; unsigned long timer_expires; ktime_t total_time; diff --git a/kernel/include/linux/pmem.h b/kernel/include/linux/pmem.h new file mode 100644 index 000000000..acfea8ce4 --- /dev/null +++ b/kernel/include/linux/pmem.h @@ -0,0 +1,181 @@ +/* + * Copyright(c) 2015 Intel Corporation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public License as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ +#ifndef __PMEM_H__ +#define __PMEM_H__ + +#include <linux/io.h> +#include <linux/uio.h> + +#ifdef CONFIG_ARCH_HAS_PMEM_API +#define ARCH_MEMREMAP_PMEM MEMREMAP_WB +#include <asm/pmem.h> +#else +#define ARCH_MEMREMAP_PMEM MEMREMAP_WT +/* + * These are simply here to enable compilation, all call sites gate + * calling these symbols with arch_has_pmem_api() and redirect to the + * implementation in asm/pmem.h. + */ +static inline bool __arch_has_wmb_pmem(void) +{ + return false; +} + +static inline void arch_wmb_pmem(void) +{ + BUG(); +} + +static inline void arch_memcpy_to_pmem(void __pmem *dst, const void *src, + size_t n) +{ + BUG(); +} + +static inline size_t arch_copy_from_iter_pmem(void __pmem *addr, size_t bytes, + struct iov_iter *i) +{ + BUG(); + return 0; +} + +static inline void arch_clear_pmem(void __pmem *addr, size_t size) +{ + BUG(); +} +#endif + +/* + * Architectures that define ARCH_HAS_PMEM_API must provide + * implementations for arch_memcpy_to_pmem(), arch_wmb_pmem(), + * arch_copy_from_iter_pmem(), arch_clear_pmem() and arch_has_wmb_pmem(). + */ +static inline void memcpy_from_pmem(void *dst, void __pmem const *src, size_t size) +{ + memcpy(dst, (void __force const *) src, size); +} + +static inline bool arch_has_pmem_api(void) +{ + return IS_ENABLED(CONFIG_ARCH_HAS_PMEM_API); +} + +/** + * arch_has_wmb_pmem - true if wmb_pmem() ensures durability + * + * For a given cpu implementation within an architecture it is possible + * that wmb_pmem() resolves to a nop. In the case this returns + * false, pmem api users are unable to ensure durability and may want to + * fall back to a different data consistency model, or otherwise notify + * the user. + */ +static inline bool arch_has_wmb_pmem(void) +{ + return arch_has_pmem_api() && __arch_has_wmb_pmem(); +} + +/* + * These defaults seek to offer decent performance and minimize the + * window between i/o completion and writes being durable on media. + * However, it is undefined / architecture specific whether + * ARCH_MEMREMAP_PMEM + default_memcpy_to_pmem is sufficient for + * making data durable relative to i/o completion. + */ +static inline void default_memcpy_to_pmem(void __pmem *dst, const void *src, + size_t size) +{ + memcpy((void __force *) dst, src, size); +} + +static inline size_t default_copy_from_iter_pmem(void __pmem *addr, + size_t bytes, struct iov_iter *i) +{ + return copy_from_iter_nocache((void __force *)addr, bytes, i); +} + +static inline void default_clear_pmem(void __pmem *addr, size_t size) +{ + if (size == PAGE_SIZE && ((unsigned long)addr & ~PAGE_MASK) == 0) + clear_page((void __force *)addr); + else + memset((void __force *)addr, 0, size); +} + +/** + * memcpy_to_pmem - copy data to persistent memory + * @dst: destination buffer for the copy + * @src: source buffer for the copy + * @n: length of the copy in bytes + * + * Perform a memory copy that results in the destination of the copy + * being effectively evicted from, or never written to, the processor + * cache hierarchy after the copy completes. After memcpy_to_pmem() + * data may still reside in cpu or platform buffers, so this operation + * must be followed by a wmb_pmem(). + */ +static inline void memcpy_to_pmem(void __pmem *dst, const void *src, size_t n) +{ + if (arch_has_pmem_api()) + arch_memcpy_to_pmem(dst, src, n); + else + default_memcpy_to_pmem(dst, src, n); +} + +/** + * wmb_pmem - synchronize writes to persistent memory + * + * After a series of memcpy_to_pmem() operations this drains data from + * cpu write buffers and any platform (memory controller) buffers to + * ensure that written data is durable on persistent memory media. + */ +static inline void wmb_pmem(void) +{ + if (arch_has_wmb_pmem()) + arch_wmb_pmem(); + else + wmb(); +} + +/** + * copy_from_iter_pmem - copy data from an iterator to PMEM + * @addr: PMEM destination address + * @bytes: number of bytes to copy + * @i: iterator with source data + * + * Copy data from the iterator 'i' to the PMEM buffer starting at 'addr'. + * This function requires explicit ordering with a wmb_pmem() call. + */ +static inline size_t copy_from_iter_pmem(void __pmem *addr, size_t bytes, + struct iov_iter *i) +{ + if (arch_has_pmem_api()) + return arch_copy_from_iter_pmem(addr, bytes, i); + return default_copy_from_iter_pmem(addr, bytes, i); +} + +/** + * clear_pmem - zero a PMEM memory range + * @addr: virtual start address + * @size: number of bytes to zero + * + * Write zeros into the memory range starting at 'addr' for 'size' bytes. + * This function requires explicit ordering with a wmb_pmem() call. + */ +static inline void clear_pmem(void __pmem *addr, size_t size) +{ + if (arch_has_pmem_api()) + arch_clear_pmem(addr, size); + else + default_clear_pmem(addr, size); +} +#endif /* __PMEM_H__ */ diff --git a/kernel/include/linux/poison.h b/kernel/include/linux/poison.h index 2110a81c5..317e16de0 100644 --- a/kernel/include/linux/poison.h +++ b/kernel/include/linux/poison.h @@ -19,8 +19,8 @@ * under normal circumstances, used to verify that nobody uses * non-initialized list entries. */ -#define LIST_POISON1 ((void *) 0x00100100 + POISON_POINTER_DELTA) -#define LIST_POISON2 ((void *) 0x00200200 + POISON_POINTER_DELTA) +#define LIST_POISON1 ((void *) 0x100 + POISON_POINTER_DELTA) +#define LIST_POISON2 ((void *) 0x200 + POISON_POINTER_DELTA) /********** include/linux/timer.h **********/ /* @@ -69,10 +69,6 @@ #define ATM_POISON_FREE 0x12 #define ATM_POISON 0xdeadbeef -/********** net/ **********/ -#define NEIGHBOR_DEAD 0xdeadbeef -#define NETFILTER_LINK_POISON 0xdead57ac - /********** kernel/mutexes **********/ #define MUTEX_DEBUG_INIT 0x11 #define MUTEX_DEBUG_FREE 0x22 @@ -83,7 +79,4 @@ /********** security/ **********/ #define KEY_DESTROY 0xbd -/********** sound/oss/ **********/ -#define OSS_POISON_FREE 0xAB - #endif diff --git a/kernel/include/linux/power/bq27x00_battery.h b/kernel/include/linux/power/bq27x00_battery.h deleted file mode 100644 index a857f719b..000000000 --- a/kernel/include/linux/power/bq27x00_battery.h +++ /dev/null @@ -1,19 +0,0 @@ -#ifndef __LINUX_BQ27X00_BATTERY_H__ -#define __LINUX_BQ27X00_BATTERY_H__ - -/** - * struct bq27000_plaform_data - Platform data for bq27000 devices - * @name: Name of the battery. If NULL the driver will fallback to "bq27000". - * @read: HDQ read callback. - * This function should provide access to the HDQ bus the battery is - * connected to. - * The first parameter is a pointer to the battery device, the second the - * register to be read. The return value should either be the content of - * the passed register or an error value. - */ -struct bq27000_platform_data { - const char *name; - int (*read)(struct device *dev, unsigned int); -}; - -#endif diff --git a/kernel/include/linux/power/bq27xxx_battery.h b/kernel/include/linux/power/bq27xxx_battery.h new file mode 100644 index 000000000..45f6a7b5b --- /dev/null +++ b/kernel/include/linux/power/bq27xxx_battery.h @@ -0,0 +1,31 @@ +#ifndef __LINUX_BQ27X00_BATTERY_H__ +#define __LINUX_BQ27X00_BATTERY_H__ + +/** + * struct bq27xxx_plaform_data - Platform data for bq27xxx devices + * @name: Name of the battery. + * @chip: Chip class number of this device. + * @read: HDQ read callback. + * This function should provide access to the HDQ bus the battery is + * connected to. + * The first parameter is a pointer to the battery device, the second the + * register to be read. The return value should either be the content of + * the passed register or an error value. + */ +enum bq27xxx_chip { + BQ27000 = 1, /* bq27000, bq27200 */ + BQ27010, /* bq27010, bq27210 */ + BQ27500, /* bq27500, bq27510, bq27520 */ + BQ27530, /* bq27530, bq27531 */ + BQ27541, /* bq27541, bq27542, bq27546, bq27742 */ + BQ27545, /* bq27545 */ + BQ27421, /* bq27421, bq27425, bq27441, bq27621 */ +}; + +struct bq27xxx_platform_data { + const char *name; + enum bq27xxx_chip chip; + int (*read)(struct device *dev, unsigned int); +}; + +#endif diff --git a/kernel/include/linux/power/charger-manager.h b/kernel/include/linux/power/charger-manager.h index eadf28cb2..c4fa907c8 100644 --- a/kernel/include/linux/power/charger-manager.h +++ b/kernel/include/linux/power/charger-manager.h @@ -65,7 +65,7 @@ struct charger_cable { const char *extcon_name; const char *name; - /* The charger-manager use Exton framework*/ + /* The charger-manager use Extcon framework */ struct extcon_specific_cable_nb extcon_dev; struct work_struct wq; struct notifier_block nb; @@ -94,7 +94,7 @@ struct charger_cable { * the charger will be maintained with disabled state. * @cables: * the array of charger cables to enable/disable charger - * and set current limit according to constratint data of + * and set current limit according to constraint data of * struct charger_cable if only charger cable included * in the array of charger cables is attached/detached. * @num_cables: the number of charger cables. @@ -148,7 +148,7 @@ struct charger_regulator { * @polling_interval_ms: interval in millisecond at which * charger manager will monitor battery health * @battery_present: - * Specify where information for existance of battery can be obtained + * Specify where information for existence of battery can be obtained * @psy_charger_stat: the names of power-supply for chargers * @num_charger_regulator: the number of entries in charger_regulators * @charger_regulators: array of charger regulators @@ -156,7 +156,7 @@ struct charger_regulator { * @thermal_zone : the name of thermal zone for battery * @temp_min : Minimum battery temperature for charging. * @temp_max : Maximum battery temperature for charging. - * @temp_diff : Temperature diffential to restart charging. + * @temp_diff : Temperature difference to restart charging. * @measure_battery_temp: * true: measure battery temperature * false: measure ambient temperature diff --git a/kernel/include/linux/power/max17042_battery.h b/kernel/include/linux/power/max17042_battery.h index cf112b407..522757ac9 100644 --- a/kernel/include/linux/power/max17042_battery.h +++ b/kernel/include/linux/power/max17042_battery.h @@ -215,6 +215,10 @@ struct max17042_platform_data { * the datasheet although it can be changed by board designers. */ unsigned int r_sns; + int vmin; /* in millivolts */ + int vmax; /* in millivolts */ + int temp_min; /* in tenths of degree Celsius */ + int temp_max; /* in tenths of degree Celsius */ }; #endif /* __MAX17042_BATTERY_H_ */ diff --git a/kernel/include/linux/power_supply.h b/kernel/include/linux/power_supply.h index a80f1fd01..ef9f15921 100644 --- a/kernel/include/linux/power_supply.h +++ b/kernel/include/linux/power_supply.h @@ -206,6 +206,11 @@ struct power_supply_desc { int (*set_property)(struct power_supply *psy, enum power_supply_property psp, const union power_supply_propval *val); + /* + * property_is_writeable() will be called during registration + * of power supply. If this happens during device probe then it must + * not access internal data of device (because probe did not end). + */ int (*property_is_writeable)(struct power_supply *psy, enum power_supply_property psp); void (*external_power_changed)(struct power_supply *psy); @@ -287,10 +292,15 @@ extern void power_supply_put(struct power_supply *psy); #ifdef CONFIG_OF extern struct power_supply *power_supply_get_by_phandle(struct device_node *np, const char *property); +extern struct power_supply *devm_power_supply_get_by_phandle( + struct device *dev, const char *property); #else /* !CONFIG_OF */ static inline struct power_supply * power_supply_get_by_phandle(struct device_node *np, const char *property) { return NULL; } +static inline struct power_supply * +devm_power_supply_get_by_phandle(struct device *dev, const char *property) +{ return NULL; } #endif /* CONFIG_OF */ extern void power_supply_changed(struct power_supply *psy); extern int power_supply_am_i_supplied(struct power_supply *psy); diff --git a/kernel/include/linux/pps_kernel.h b/kernel/include/linux/pps_kernel.h index 1d2cd2124..54bf1484d 100644 --- a/kernel/include/linux/pps_kernel.h +++ b/kernel/include/linux/pps_kernel.h @@ -48,9 +48,9 @@ struct pps_source_info { struct pps_event_time { #ifdef CONFIG_NTP_PPS - struct timespec ts_raw; + struct timespec64 ts_raw; #endif /* CONFIG_NTP_PPS */ - struct timespec ts_real; + struct timespec64 ts_real; }; /* The main struct */ @@ -105,7 +105,7 @@ extern void pps_event(struct pps_device *pps, struct pps_device *pps_lookup_dev(void const *cookie); static inline void timespec_to_pps_ktime(struct pps_ktime *kt, - struct timespec ts) + struct timespec64 ts) { kt->sec = ts.tv_sec; kt->nsec = ts.tv_nsec; @@ -115,24 +115,24 @@ static inline void timespec_to_pps_ktime(struct pps_ktime *kt, static inline void pps_get_ts(struct pps_event_time *ts) { - getnstime_raw_and_real(&ts->ts_raw, &ts->ts_real); + ktime_get_raw_and_real_ts64(&ts->ts_raw, &ts->ts_real); } #else /* CONFIG_NTP_PPS */ static inline void pps_get_ts(struct pps_event_time *ts) { - getnstimeofday(&ts->ts_real); + ktime_get_real_ts64(&ts->ts_real); } #endif /* CONFIG_NTP_PPS */ /* Subtract known time delay from PPS event time(s) */ -static inline void pps_sub_ts(struct pps_event_time *ts, struct timespec delta) +static inline void pps_sub_ts(struct pps_event_time *ts, struct timespec64 delta) { - ts->ts_real = timespec_sub(ts->ts_real, delta); + ts->ts_real = timespec64_sub(ts->ts_real, delta); #ifdef CONFIG_NTP_PPS - ts->ts_raw = timespec_sub(ts->ts_raw, delta); + ts->ts_raw = timespec64_sub(ts->ts_raw, delta); #endif } diff --git a/kernel/include/linux/pr.h b/kernel/include/linux/pr.h new file mode 100644 index 000000000..65c01c10b --- /dev/null +++ b/kernel/include/linux/pr.h @@ -0,0 +1,18 @@ +#ifndef LINUX_PR_H +#define LINUX_PR_H + +#include <uapi/linux/pr.h> + +struct pr_ops { + int (*pr_register)(struct block_device *bdev, u64 old_key, u64 new_key, + u32 flags); + int (*pr_reserve)(struct block_device *bdev, u64 key, + enum pr_type type, u32 flags); + int (*pr_release)(struct block_device *bdev, u64 key, + enum pr_type type); + int (*pr_preempt)(struct block_device *bdev, u64 old_key, u64 new_key, + enum pr_type type, bool abort); + int (*pr_clear)(struct block_device *bdev, u64 key); +}; + +#endif /* LINUX_PR_H */ diff --git a/kernel/include/linux/preempt.h b/kernel/include/linux/preempt.h index 66587bf45..1cfb1cb72 100644 --- a/kernel/include/linux/preempt.h +++ b/kernel/include/linux/preempt.h @@ -10,17 +10,137 @@ #include <linux/list.h> /* - * We use the MSB mostly because its available; see <linux/preempt_mask.h> for - * the other bits -- can't include that header due to inclusion hell. + * We put the hardirq and softirq counter into the preemption + * counter. The bitmask has the following meaning: + * + * - bits 0-7 are the preemption count (max preemption depth: 256) + * - bits 8-15 are the softirq count (max # of softirqs: 256) + * + * The hardirq count could in theory be the same as the number of + * interrupts in the system, but we run all interrupt handlers with + * interrupts disabled, so we cannot have nesting interrupts. Though + * there are a few palaeontologic drivers which reenable interrupts in + * the handler, so we need more than one bit here. + * + * PREEMPT_MASK: 0x000000ff + * SOFTIRQ_MASK: 0x0000ff00 + * HARDIRQ_MASK: 0x000f0000 + * NMI_MASK: 0x00100000 + * PREEMPT_NEED_RESCHED: 0x80000000 */ +#define PREEMPT_BITS 8 +#define SOFTIRQ_BITS 8 +#define HARDIRQ_BITS 4 +#define NMI_BITS 1 + +#define PREEMPT_SHIFT 0 +#define SOFTIRQ_SHIFT (PREEMPT_SHIFT + PREEMPT_BITS) +#define HARDIRQ_SHIFT (SOFTIRQ_SHIFT + SOFTIRQ_BITS) +#define NMI_SHIFT (HARDIRQ_SHIFT + HARDIRQ_BITS) + +#define __IRQ_MASK(x) ((1UL << (x))-1) + +#define PREEMPT_MASK (__IRQ_MASK(PREEMPT_BITS) << PREEMPT_SHIFT) +#define SOFTIRQ_MASK (__IRQ_MASK(SOFTIRQ_BITS) << SOFTIRQ_SHIFT) +#define HARDIRQ_MASK (__IRQ_MASK(HARDIRQ_BITS) << HARDIRQ_SHIFT) +#define NMI_MASK (__IRQ_MASK(NMI_BITS) << NMI_SHIFT) + +#define PREEMPT_OFFSET (1UL << PREEMPT_SHIFT) +#define SOFTIRQ_OFFSET (1UL << SOFTIRQ_SHIFT) +#define HARDIRQ_OFFSET (1UL << HARDIRQ_SHIFT) +#define NMI_OFFSET (1UL << NMI_SHIFT) + +#ifndef CONFIG_PREEMPT_RT_FULL +# define SOFTIRQ_DISABLE_OFFSET (2 * SOFTIRQ_OFFSET) +#else +# define SOFTIRQ_DISABLE_OFFSET (0) +#endif + +/* We use the MSB mostly because its available */ #define PREEMPT_NEED_RESCHED 0x80000000 +/* preempt_count() and related functions, depends on PREEMPT_NEED_RESCHED */ #include <asm/preempt.h> +#define hardirq_count() (preempt_count() & HARDIRQ_MASK) +#define irq_count() (preempt_count() & (HARDIRQ_MASK | SOFTIRQ_MASK \ + | NMI_MASK)) +#ifndef CONFIG_PREEMPT_RT_FULL +# define softirq_count() (preempt_count() & SOFTIRQ_MASK) +# define in_serving_softirq() (softirq_count() & SOFTIRQ_OFFSET) +#else +# define softirq_count() (0UL) +extern int in_serving_softirq(void); +#endif + +/* + * Are we doing bottom half or hardware interrupt processing? + * Are we in a softirq context? Interrupt context? + * in_softirq - Are we currently processing softirq or have bh disabled? + * in_serving_softirq - Are we currently processing softirq? + */ +#define in_irq() (hardirq_count()) +#define in_softirq() (softirq_count()) +#define in_interrupt() (irq_count()) + +/* + * Are we in NMI context? + */ +#define in_nmi() (preempt_count() & NMI_MASK) + +/* + * The preempt_count offset after preempt_disable(); + */ +#if defined(CONFIG_PREEMPT_COUNT) +# define PREEMPT_DISABLE_OFFSET PREEMPT_OFFSET +#else +# define PREEMPT_DISABLE_OFFSET 0 +#endif + +/* + * The preempt_count offset after spin_lock() + */ +#if !defined(CONFIG_PREEMPT_RT_FULL) +#define PREEMPT_LOCK_OFFSET PREEMPT_DISABLE_OFFSET +#else +#define PREEMPT_LOCK_OFFSET 0 +#endif + +/* + * The preempt_count offset needed for things like: + * + * spin_lock_bh() + * + * Which need to disable both preemption (CONFIG_PREEMPT_COUNT) and + * softirqs, such that unlock sequences of: + * + * spin_unlock(); + * local_bh_enable(); + * + * Work as expected. + */ +#define SOFTIRQ_LOCK_OFFSET (SOFTIRQ_DISABLE_OFFSET + PREEMPT_LOCK_OFFSET) + +/* + * Are we running in atomic context? WARNING: this macro cannot + * always detect atomic context; in particular, it cannot know about + * held spinlocks in non-preemptible kernels. Thus it should not be + * used in the general case to determine whether sleeping is possible. + * Do not use in_atomic() in driver code. + */ +#define in_atomic() (preempt_count() != 0) + +/* + * Check whether we were atomic before we did preempt_disable(): + * (used by the scheduler) + */ +#define in_atomic_preempt_off() (preempt_count() != PREEMPT_DISABLE_OFFSET) + #if defined(CONFIG_DEBUG_PREEMPT) || defined(CONFIG_PREEMPT_TRACER) extern void preempt_count_add(int val); extern void preempt_count_sub(int val); -#define preempt_count_dec_and_test() ({ preempt_count_sub(1); should_resched(); }) +#define preempt_count_dec_and_test() \ + ({ preempt_count_sub(1); should_resched(0); }) #else #define preempt_count_add(val) __preempt_count_add(val) #define preempt_count_sub(val) __preempt_count_sub(val) @@ -75,6 +195,8 @@ do { \ # define preempt_check_resched_rt() barrier(); #endif +#define preemptible() (preempt_count() == 0 && !irqs_disabled()) + #ifdef CONFIG_PREEMPT #define preempt_enable() \ do { \ @@ -83,9 +205,16 @@ do { \ __preempt_schedule(); \ } while (0) +#define preempt_enable_notrace() \ +do { \ + barrier(); \ + if (unlikely(__preempt_count_dec_and_test())) \ + __preempt_schedule_notrace(); \ +} while (0) + #define preempt_check_resched() \ do { \ - if (should_resched()) \ + if (should_resched(0)) \ __preempt_schedule(); \ } while (0) @@ -96,46 +225,33 @@ do { \ preempt_check_resched(); \ } while (0) -#else +#else /* !CONFIG_PREEMPT */ #define preempt_enable() \ do { \ barrier(); \ preempt_count_dec(); \ } while (0) -#define preempt_check_resched() do { } while (0) -#endif - -#define preempt_disable_notrace() \ -do { \ - __preempt_count_inc(); \ - barrier(); \ -} while (0) -#define preempt_enable_no_resched_notrace() \ +#define preempt_enable_notrace() \ do { \ barrier(); \ __preempt_count_dec(); \ } while (0) -#ifdef CONFIG_PREEMPT - -#ifndef CONFIG_CONTEXT_TRACKING -#define __preempt_schedule_context() __preempt_schedule() -#endif +#define preempt_check_resched() do { } while (0) +#endif /* CONFIG_PREEMPT */ -#define preempt_enable_notrace() \ +#define preempt_disable_notrace() \ do { \ + __preempt_count_inc(); \ barrier(); \ - if (unlikely(__preempt_count_dec_and_test())) \ - __preempt_schedule_context(); \ } while (0) -#else -#define preempt_enable_notrace() \ + +#define preempt_enable_no_resched_notrace() \ do { \ barrier(); \ __preempt_count_dec(); \ } while (0) -#endif #else /* !CONFIG_PREEMPT_COUNT */ @@ -155,6 +271,7 @@ do { \ #define preempt_enable_no_resched_notrace() barrier() #define preempt_enable_notrace() barrier() #define preempt_check_resched_rt() barrier() +#define preemptible() 0 #endif /* CONFIG_PREEMPT_COUNT */ @@ -235,6 +352,8 @@ struct preempt_notifier { struct preempt_ops *ops; }; +void preempt_notifier_inc(void); +void preempt_notifier_dec(void); void preempt_notifier_register(struct preempt_notifier *notifier); void preempt_notifier_unregister(struct preempt_notifier *notifier); diff --git a/kernel/include/linux/preempt_mask.h b/kernel/include/linux/preempt_mask.h deleted file mode 100644 index c7e373dc7..000000000 --- a/kernel/include/linux/preempt_mask.h +++ /dev/null @@ -1,126 +0,0 @@ -#ifndef LINUX_PREEMPT_MASK_H -#define LINUX_PREEMPT_MASK_H - -#include <linux/preempt.h> - -/* - * We put the hardirq and softirq counter into the preemption - * counter. The bitmask has the following meaning: - * - * - bits 0-7 are the preemption count (max preemption depth: 256) - * - bits 8-15 are the softirq count (max # of softirqs: 256) - * - * The hardirq count could in theory be the same as the number of - * interrupts in the system, but we run all interrupt handlers with - * interrupts disabled, so we cannot have nesting interrupts. Though - * there are a few palaeontologic drivers which reenable interrupts in - * the handler, so we need more than one bit here. - * - * PREEMPT_MASK: 0x000000ff - * SOFTIRQ_MASK: 0x0000ff00 - * HARDIRQ_MASK: 0x000f0000 - * NMI_MASK: 0x00100000 - * PREEMPT_ACTIVE: 0x00200000 - */ -#define PREEMPT_BITS 8 -#define SOFTIRQ_BITS 8 -#define HARDIRQ_BITS 4 -#define NMI_BITS 1 - -#define PREEMPT_SHIFT 0 -#define SOFTIRQ_SHIFT (PREEMPT_SHIFT + PREEMPT_BITS) -#define HARDIRQ_SHIFT (SOFTIRQ_SHIFT + SOFTIRQ_BITS) -#define NMI_SHIFT (HARDIRQ_SHIFT + HARDIRQ_BITS) - -#define __IRQ_MASK(x) ((1UL << (x))-1) - -#define PREEMPT_MASK (__IRQ_MASK(PREEMPT_BITS) << PREEMPT_SHIFT) -#define SOFTIRQ_MASK (__IRQ_MASK(SOFTIRQ_BITS) << SOFTIRQ_SHIFT) -#define HARDIRQ_MASK (__IRQ_MASK(HARDIRQ_BITS) << HARDIRQ_SHIFT) -#define NMI_MASK (__IRQ_MASK(NMI_BITS) << NMI_SHIFT) - -#define PREEMPT_OFFSET (1UL << PREEMPT_SHIFT) -#define SOFTIRQ_OFFSET (1UL << SOFTIRQ_SHIFT) -#define HARDIRQ_OFFSET (1UL << HARDIRQ_SHIFT) -#define NMI_OFFSET (1UL << NMI_SHIFT) - -#ifndef CONFIG_PREEMPT_RT_FULL -# define SOFTIRQ_DISABLE_OFFSET (2 * SOFTIRQ_OFFSET) -#else -# define SOFTIRQ_DISABLE_OFFSET (0) -#endif - -#define PREEMPT_ACTIVE_BITS 1 -#define PREEMPT_ACTIVE_SHIFT (NMI_SHIFT + NMI_BITS) -#define PREEMPT_ACTIVE (__IRQ_MASK(PREEMPT_ACTIVE_BITS) << PREEMPT_ACTIVE_SHIFT) - -#define hardirq_count() (preempt_count() & HARDIRQ_MASK) -#define irq_count() (preempt_count() & (HARDIRQ_MASK | SOFTIRQ_MASK \ - | NMI_MASK)) -#ifndef CONFIG_PREEMPT_RT_FULL -# define softirq_count() (preempt_count() & SOFTIRQ_MASK) -# define in_serving_softirq() (softirq_count() & SOFTIRQ_OFFSET) -#else -# define softirq_count() (0UL) -extern int in_serving_softirq(void); -#endif - -/* - * Are we doing bottom half or hardware interrupt processing? - * Are we in a softirq context? Interrupt context? - * in_softirq - Are we currently processing softirq or have bh disabled? - * in_serving_softirq - Are we currently processing softirq? - */ -#define in_irq() (hardirq_count()) -#define in_softirq() (softirq_count()) -#define in_interrupt() (irq_count()) - -/* - * Are we in NMI context? - */ -#define in_nmi() (preempt_count() & NMI_MASK) - -#if defined(CONFIG_PREEMPT_COUNT) -# define PREEMPT_CHECK_OFFSET 1 -#else -# define PREEMPT_CHECK_OFFSET 0 -#endif - -/* - * The preempt_count offset needed for things like: - * - * spin_lock_bh() - * - * Which need to disable both preemption (CONFIG_PREEMPT_COUNT) and - * softirqs, such that unlock sequences of: - * - * spin_unlock(); - * local_bh_enable(); - * - * Work as expected. - */ -#define SOFTIRQ_LOCK_OFFSET (SOFTIRQ_DISABLE_OFFSET + PREEMPT_CHECK_OFFSET) - -/* - * Are we running in atomic context? WARNING: this macro cannot - * always detect atomic context; in particular, it cannot know about - * held spinlocks in non-preemptible kernels. Thus it should not be - * used in the general case to determine whether sleeping is possible. - * Do not use in_atomic() in driver code. - */ -#define in_atomic() ((preempt_count() & ~PREEMPT_ACTIVE) != 0) - -/* - * Check whether we were atomic before we did preempt_disable(): - * (used by the scheduler, *after* releasing the kernel lock) - */ -#define in_atomic_preempt_off() \ - ((preempt_count() & ~PREEMPT_ACTIVE) != PREEMPT_CHECK_OFFSET) - -#ifdef CONFIG_PREEMPT_COUNT -# define preemptible() (preempt_count() == 0 && !irqs_disabled()) -#else -# define preemptible() 0 -#endif - -#endif /* LINUX_PREEMPT_MASK_H */ diff --git a/kernel/include/linux/printk.h b/kernel/include/linux/printk.h index 08d0a7574..9cdca696b 100644 --- a/kernel/include/linux/printk.h +++ b/kernel/include/linux/printk.h @@ -30,6 +30,8 @@ static inline const char *printk_skip_level(const char *buffer) return buffer; } +#define CONSOLE_EXT_LOG_MAX 8192 + /* printk's without a loglevel use this.. */ #define MESSAGE_LOGLEVEL_DEFAULT CONFIG_MESSAGE_LOGLEVEL_DEFAULT @@ -122,7 +124,7 @@ void early_printk(const char *s, ...) { } static inline void printk_kill(void) { } #endif -typedef int(*printk_func_t)(const char *fmt, va_list args); +typedef __printf(1, 0) int (*printk_func_t)(const char *fmt, va_list args); #ifdef CONFIG_PRINTK asmlinkage __printf(5, 0) @@ -166,7 +168,7 @@ char *log_buf_addr_get(void); u32 log_buf_len_get(void); void log_buf_kexec_setup(void); void __init setup_log_buf(int early); -void dump_stack_set_arch_desc(const char *fmt, ...); +__printf(1, 2) void dump_stack_set_arch_desc(const char *fmt, ...); void dump_stack_print_info(const char *log_lvl); void show_regs_print_info(const char *log_lvl); #else @@ -217,7 +219,7 @@ static inline void setup_log_buf(int early) { } -static inline void dump_stack_set_arch_desc(const char *fmt, ...) +static inline __printf(1, 2) void dump_stack_set_arch_desc(const char *fmt, ...) { } @@ -404,10 +406,10 @@ do { \ static DEFINE_RATELIMIT_STATE(_rs, \ DEFAULT_RATELIMIT_INTERVAL, \ DEFAULT_RATELIMIT_BURST); \ - DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, fmt); \ + DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, pr_fmt(fmt)); \ if (unlikely(descriptor.flags & _DPRINTK_FLAGS_PRINT) && \ __ratelimit(&_rs)) \ - __dynamic_pr_debug(&descriptor, fmt, ##__VA_ARGS__); \ + __dynamic_pr_debug(&descriptor, pr_fmt(fmt), ##__VA_ARGS__); \ } while (0) #elif defined(DEBUG) #define pr_debug_ratelimited(fmt, ...) \ @@ -456,11 +458,17 @@ static inline void print_hex_dump_bytes(const char *prefix_str, int prefix_type, groupsize, buf, len, ascii) \ dynamic_hex_dump(prefix_str, prefix_type, rowsize, \ groupsize, buf, len, ascii) -#else +#elif defined(DEBUG) #define print_hex_dump_debug(prefix_str, prefix_type, rowsize, \ groupsize, buf, len, ascii) \ print_hex_dump(KERN_DEBUG, prefix_str, prefix_type, rowsize, \ groupsize, buf, len, ascii) -#endif /* defined(CONFIG_DYNAMIC_DEBUG) */ +#else +static inline void print_hex_dump_debug(const char *prefix_str, int prefix_type, + int rowsize, int groupsize, + const void *buf, size_t len, bool ascii) +{ +} +#endif #endif diff --git a/kernel/include/linux/property.h b/kernel/include/linux/property.h index de8bdf417..0a3705a7c 100644 --- a/kernel/include/linux/property.h +++ b/kernel/include/linux/property.h @@ -27,6 +27,12 @@ enum dev_prop_type { DEV_PROP_MAX, }; +enum dev_dma_attr { + DEV_DMA_NOT_SUPPORTED, + DEV_DMA_NON_COHERENT, + DEV_DMA_COHERENT, +}; + bool device_property_present(struct device *dev, const char *propname); int device_property_read_u8_array(struct device *dev, const char *propname, u8 *val, size_t nval); @@ -40,6 +46,8 @@ int device_property_read_string_array(struct device *dev, const char *propname, const char **val, size_t nval); int device_property_read_string(struct device *dev, const char *propname, const char **val); +int device_property_match_string(struct device *dev, + const char *propname, const char *string); bool fwnode_property_present(struct fwnode_handle *fwnode, const char *propname); int fwnode_property_read_u8_array(struct fwnode_handle *fwnode, @@ -59,6 +67,8 @@ int fwnode_property_read_string_array(struct fwnode_handle *fwnode, size_t nval); int fwnode_property_read_string(struct fwnode_handle *fwnode, const char *propname, const char **val); +int fwnode_property_match_string(struct fwnode_handle *fwnode, + const char *propname, const char *string); struct fwnode_handle *device_get_next_child_node(struct device *dev, struct fwnode_handle *child); @@ -164,4 +174,12 @@ struct property_set { void device_add_property_set(struct device *dev, struct property_set *pset); +bool device_dma_supported(struct device *dev); + +enum dev_dma_attr device_get_dma_attr(struct device *dev); + +int device_get_phy_mode(struct device *dev); + +void *device_get_mac_address(struct device *dev, char *addr, int alen); + #endif /* _LINUX_PROPERTY_H_ */ diff --git a/kernel/include/linux/proportions.h b/kernel/include/linux/proportions.h index 00e8e8fa7..21221338a 100644 --- a/kernel/include/linux/proportions.h +++ b/kernel/include/linux/proportions.h @@ -1,7 +1,7 @@ /* * FLoating proportions * - * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com> + * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra * * This file contains the public data structure and API definitions. */ @@ -33,7 +33,7 @@ struct prop_global { /* * global proportion descriptor * - * this is needed to consitently flip prop_global structures. + * this is needed to consistently flip prop_global structures. */ struct prop_descriptor { int index; diff --git a/kernel/include/linux/psci.h b/kernel/include/linux/psci.h new file mode 100644 index 000000000..12c486545 --- /dev/null +++ b/kernel/include/linux/psci.h @@ -0,0 +1,54 @@ +/* + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * Copyright (C) 2015 ARM Limited + */ + +#ifndef __LINUX_PSCI_H +#define __LINUX_PSCI_H + +#include <linux/init.h> +#include <linux/types.h> + +#define PSCI_POWER_STATE_TYPE_STANDBY 0 +#define PSCI_POWER_STATE_TYPE_POWER_DOWN 1 + +bool psci_tos_resident_on(int cpu); +bool psci_power_state_loses_context(u32 state); +bool psci_power_state_is_valid(u32 state); + +struct psci_operations { + int (*cpu_suspend)(u32 state, unsigned long entry_point); + int (*cpu_off)(u32 state); + int (*cpu_on)(unsigned long cpuid, unsigned long entry_point); + int (*migrate)(unsigned long cpuid); + int (*affinity_info)(unsigned long target_affinity, + unsigned long lowest_affinity_level); + int (*migrate_info_type)(void); +}; + +extern struct psci_operations psci_ops; + +#if defined(CONFIG_ARM_PSCI_FW) +int __init psci_dt_init(void); +#else +static inline int psci_dt_init(void) { return 0; } +#endif + +#if defined(CONFIG_ARM_PSCI_FW) && defined(CONFIG_ACPI) +int __init psci_acpi_init(void); +bool __init acpi_psci_present(void); +bool __init acpi_psci_use_hvc(void); +#else +static inline int psci_acpi_init(void) { return 0; } +static inline bool acpi_psci_present(void) { return false; } +#endif + +#endif /* __LINUX_PSCI_H */ diff --git a/kernel/include/linux/pstore.h b/kernel/include/linux/pstore.h index 8e7a25b06..831479f8d 100644 --- a/kernel/include/linux/pstore.h +++ b/kernel/include/linux/pstore.h @@ -75,20 +75,8 @@ struct pstore_info { #define PSTORE_FLAGS_FRAGILE 1 -#ifdef CONFIG_PSTORE extern int pstore_register(struct pstore_info *); +extern void pstore_unregister(struct pstore_info *); extern bool pstore_cannot_block_path(enum kmsg_dump_reason reason); -#else -static inline int -pstore_register(struct pstore_info *psi) -{ - return -ENODEV; -} -static inline bool -pstore_cannot_block_path(enum kmsg_dump_reason reason) -{ - return false; -} -#endif #endif /*_LINUX_PSTORE_H*/ diff --git a/kernel/include/linux/ptp_classify.h b/kernel/include/linux/ptp_classify.h index 159c987b1..a079656b6 100644 --- a/kernel/include/linux/ptp_classify.h +++ b/kernel/include/linux/ptp_classify.h @@ -32,9 +32,9 @@ #define PTP_CLASS_VMASK 0x0f /* max protocol version is 15 */ #define PTP_CLASS_IPV4 0x10 /* event in an IPV4 UDP packet */ #define PTP_CLASS_IPV6 0x20 /* event in an IPV6 UDP packet */ -#define PTP_CLASS_L2 0x30 /* event in a L2 packet */ -#define PTP_CLASS_PMASK 0x30 /* mask for the packet type field */ -#define PTP_CLASS_VLAN 0x40 /* event in a VLAN tagged packet */ +#define PTP_CLASS_L2 0x40 /* event in a L2 packet */ +#define PTP_CLASS_PMASK 0x70 /* mask for the packet type field */ +#define PTP_CLASS_VLAN 0x80 /* event in a VLAN tagged packet */ #define PTP_CLASS_V1_IPV4 (PTP_CLASS_V1 | PTP_CLASS_IPV4) #define PTP_CLASS_V1_IPV6 (PTP_CLASS_V1 | PTP_CLASS_IPV6) /* probably DNE */ @@ -42,6 +42,7 @@ #define PTP_CLASS_V2_IPV6 (PTP_CLASS_V2 | PTP_CLASS_IPV6) #define PTP_CLASS_V2_L2 (PTP_CLASS_V2 | PTP_CLASS_L2) #define PTP_CLASS_V2_VLAN (PTP_CLASS_V2 | PTP_CLASS_VLAN) +#define PTP_CLASS_L4 (PTP_CLASS_IPV4 | PTP_CLASS_IPV6) #define PTP_EV_PORT 319 #define PTP_GEN_BIT 0x08 /* indicates general message, if set in message type */ diff --git a/kernel/include/linux/ptrace.h b/kernel/include/linux/ptrace.h index 987a73a40..504c98a27 100644 --- a/kernel/include/linux/ptrace.h +++ b/kernel/include/linux/ptrace.h @@ -34,6 +34,7 @@ #define PT_TRACE_SECCOMP PT_EVENT_FLAG(PTRACE_EVENT_SECCOMP) #define PT_EXITKILL (PTRACE_O_EXITKILL << PT_OPT_FLAG_SHIFT) +#define PT_SUSPEND_SECCOMP (PTRACE_O_SUSPEND_SECCOMP << PT_OPT_FLAG_SHIFT) /* single stepping state bits (used on ARM and PA-RISC) */ #define PT_SINGLESTEP_BIT 31 @@ -56,7 +57,29 @@ extern void exit_ptrace(struct task_struct *tracer, struct list_head *dead); #define PTRACE_MODE_READ 0x01 #define PTRACE_MODE_ATTACH 0x02 #define PTRACE_MODE_NOAUDIT 0x04 -/* Returns true on success, false on denial. */ +#define PTRACE_MODE_FSCREDS 0x08 +#define PTRACE_MODE_REALCREDS 0x10 + +/* shorthands for READ/ATTACH and FSCREDS/REALCREDS combinations */ +#define PTRACE_MODE_READ_FSCREDS (PTRACE_MODE_READ | PTRACE_MODE_FSCREDS) +#define PTRACE_MODE_READ_REALCREDS (PTRACE_MODE_READ | PTRACE_MODE_REALCREDS) +#define PTRACE_MODE_ATTACH_FSCREDS (PTRACE_MODE_ATTACH | PTRACE_MODE_FSCREDS) +#define PTRACE_MODE_ATTACH_REALCREDS (PTRACE_MODE_ATTACH | PTRACE_MODE_REALCREDS) + +/** + * ptrace_may_access - check whether the caller is permitted to access + * a target task. + * @task: target task + * @mode: selects type of access and caller credentials + * + * Returns true on success, false on denial. + * + * One of the flags PTRACE_MODE_FSCREDS and PTRACE_MODE_REALCREDS must + * be set in @mode to specify whether the access was requested through + * a filesystem syscall (should use effective capabilities and fsuid + * of the caller) or through an explicit syscall such as + * process_vm_writev or ptrace (and should use the real credentials). + */ extern bool ptrace_may_access(struct task_struct *task, unsigned int mode); static inline int ptrace_reparented(struct task_struct *child) diff --git a/kernel/include/linux/pwm.h b/kernel/include/linux/pwm.h index e90628cac..cfc3ed46c 100644 --- a/kernel/include/linux/pwm.h +++ b/kernel/include/linux/pwm.h @@ -2,6 +2,7 @@ #define __LINUX_PWM_H #include <linux/err.h> +#include <linux/mutex.h> #include <linux/of.h> struct pwm_device; @@ -79,26 +80,45 @@ enum { PWMF_EXPORTED = 1 << 2, }; +/** + * struct pwm_device - PWM channel object + * @label: name of the PWM device + * @flags: flags associated with the PWM device + * @hwpwm: per-chip relative index of the PWM device + * @pwm: global index of the PWM device + * @chip: PWM chip providing this PWM device + * @chip_data: chip-private data associated with the PWM device + * @lock: used to serialize accesses to the PWM device where necessary + * @period: period of the PWM signal (in nanoseconds) + * @duty_cycle: duty cycle of the PWM signal (in nanoseconds) + * @polarity: polarity of the PWM signal + */ struct pwm_device { - const char *label; - unsigned long flags; - unsigned int hwpwm; - unsigned int pwm; - struct pwm_chip *chip; - void *chip_data; - - unsigned int period; /* in nanoseconds */ - unsigned int duty_cycle; /* in nanoseconds */ - enum pwm_polarity polarity; + const char *label; + unsigned long flags; + unsigned int hwpwm; + unsigned int pwm; + struct pwm_chip *chip; + void *chip_data; + struct mutex lock; + + unsigned int period; + unsigned int duty_cycle; + enum pwm_polarity polarity; }; +static inline bool pwm_is_enabled(const struct pwm_device *pwm) +{ + return test_bit(PWMF_ENABLED, &pwm->flags); +} + static inline void pwm_set_period(struct pwm_device *pwm, unsigned int period) { if (pwm) pwm->period = period; } -static inline unsigned int pwm_get_period(struct pwm_device *pwm) +static inline unsigned int pwm_get_period(const struct pwm_device *pwm) { return pwm ? pwm->period : 0; } @@ -109,7 +129,7 @@ static inline void pwm_set_duty_cycle(struct pwm_device *pwm, unsigned int duty) pwm->duty_cycle = duty; } -static inline unsigned int pwm_get_duty_cycle(struct pwm_device *pwm) +static inline unsigned int pwm_get_duty_cycle(const struct pwm_device *pwm) { return pwm ? pwm->duty_cycle : 0; } @@ -119,6 +139,11 @@ static inline unsigned int pwm_get_duty_cycle(struct pwm_device *pwm) */ int pwm_set_polarity(struct pwm_device *pwm, enum pwm_polarity polarity); +static inline enum pwm_polarity pwm_get_polarity(const struct pwm_device *pwm) +{ + return pwm ? pwm->polarity : PWM_POLARITY_NORMAL; +} + /** * struct pwm_ops - PWM controller operations * @request: optional hook for requesting a PWM @@ -131,25 +156,18 @@ int pwm_set_polarity(struct pwm_device *pwm, enum pwm_polarity polarity); * @owner: helps prevent removal of modules exporting active PWMs */ struct pwm_ops { - int (*request)(struct pwm_chip *chip, - struct pwm_device *pwm); - void (*free)(struct pwm_chip *chip, - struct pwm_device *pwm); - int (*config)(struct pwm_chip *chip, - struct pwm_device *pwm, - int duty_ns, int period_ns); - int (*set_polarity)(struct pwm_chip *chip, - struct pwm_device *pwm, - enum pwm_polarity polarity); - int (*enable)(struct pwm_chip *chip, - struct pwm_device *pwm); - void (*disable)(struct pwm_chip *chip, - struct pwm_device *pwm); + int (*request)(struct pwm_chip *chip, struct pwm_device *pwm); + void (*free)(struct pwm_chip *chip, struct pwm_device *pwm); + int (*config)(struct pwm_chip *chip, struct pwm_device *pwm, + int duty_ns, int period_ns); + int (*set_polarity)(struct pwm_chip *chip, struct pwm_device *pwm, + enum pwm_polarity polarity); + int (*enable)(struct pwm_chip *chip, struct pwm_device *pwm); + void (*disable)(struct pwm_chip *chip, struct pwm_device *pwm); #ifdef CONFIG_DEBUG_FS - void (*dbg_show)(struct pwm_chip *chip, - struct seq_file *s); + void (*dbg_show)(struct pwm_chip *chip, struct seq_file *s); #endif - struct module *owner; + struct module *owner; }; /** @@ -160,28 +178,32 @@ struct pwm_ops { * @base: number of first PWM controlled by this chip * @npwm: number of PWMs controlled by this chip * @pwms: array of PWM devices allocated by the framework + * @of_xlate: request a PWM device given a device tree PWM specifier + * @of_pwm_n_cells: number of cells expected in the device tree PWM specifier * @can_sleep: must be true if the .config(), .enable() or .disable() * operations may sleep */ struct pwm_chip { - struct device *dev; - struct list_head list; - const struct pwm_ops *ops; - int base; - unsigned int npwm; - - struct pwm_device *pwms; - - struct pwm_device * (*of_xlate)(struct pwm_chip *pc, - const struct of_phandle_args *args); - unsigned int of_pwm_n_cells; - bool can_sleep; + struct device *dev; + struct list_head list; + const struct pwm_ops *ops; + int base; + unsigned int npwm; + + struct pwm_device *pwms; + + struct pwm_device * (*of_xlate)(struct pwm_chip *pc, + const struct of_phandle_args *args); + unsigned int of_pwm_n_cells; + bool can_sleep; }; #if IS_ENABLED(CONFIG_PWM) int pwm_set_chip_data(struct pwm_device *pwm, void *data); void *pwm_get_chip_data(struct pwm_device *pwm); +int pwmchip_add_with_polarity(struct pwm_chip *chip, + enum pwm_polarity polarity); int pwmchip_add(struct pwm_chip *chip); int pwmchip_remove(struct pwm_chip *chip); struct pwm_device *pwm_request_from_chip(struct pwm_chip *chip, @@ -217,6 +239,11 @@ static inline int pwmchip_add(struct pwm_chip *chip) return -EINVAL; } +static inline int pwmchip_add_inversed(struct pwm_chip *chip) +{ + return -EINVAL; +} + static inline int pwmchip_remove(struct pwm_chip *chip) { return -EINVAL; @@ -290,10 +317,15 @@ struct pwm_lookup { #if IS_ENABLED(CONFIG_PWM) void pwm_add_table(struct pwm_lookup *table, size_t num); +void pwm_remove_table(struct pwm_lookup *table, size_t num); #else static inline void pwm_add_table(struct pwm_lookup *table, size_t num) { } + +static inline void pwm_remove_table(struct pwm_lookup *table, size_t num) +{ +} #endif #ifdef CONFIG_PWM_SYSFS diff --git a/kernel/include/linux/pxa2xx_ssp.h b/kernel/include/linux/pxa2xx_ssp.h index dab545bb6..c2f2574ff 100644 --- a/kernel/include/linux/pxa2xx_ssp.h +++ b/kernel/include/linux/pxa2xx_ssp.h @@ -194,8 +194,11 @@ enum pxa_ssp_type { PXA168_SSP, PXA910_SSP, CE4100_SSP, - LPSS_SSP, QUARK_X1000_SSP, + LPSS_LPT_SSP, /* Keep LPSS types sorted with lpss_platforms[] */ + LPSS_BYT_SSP, + LPSS_SPT_SSP, + LPSS_BXT_SSP, }; struct ssp_device { diff --git a/kernel/include/linux/qcom_scm.h b/kernel/include/linux/qcom_scm.h index d7a974d5f..9e1200091 100644 --- a/kernel/include/linux/qcom_scm.h +++ b/kernel/include/linux/qcom_scm.h @@ -1,4 +1,4 @@ -/* Copyright (c) 2010-2014, The Linux Foundation. All rights reserved. +/* Copyright (c) 2010-2015, The Linux Foundation. All rights reserved. * Copyright (C) 2015 Linaro Ltd. * * This program is free software; you can redistribute it and/or modify @@ -16,6 +16,19 @@ extern int qcom_scm_set_cold_boot_addr(void *entry, const cpumask_t *cpus); extern int qcom_scm_set_warm_boot_addr(void *entry, const cpumask_t *cpus); +#define QCOM_SCM_HDCP_MAX_REQ_CNT 5 + +struct qcom_scm_hdcp_req { + u32 addr; + u32 val; +}; + +extern bool qcom_scm_is_available(void); + +extern bool qcom_scm_hdcp_available(void); +extern int qcom_scm_hdcp_req(struct qcom_scm_hdcp_req *req, u32 req_cnt, + u32 *resp); + #define QCOM_SCM_CPU_PWR_DOWN_L2_ON 0x0 #define QCOM_SCM_CPU_PWR_DOWN_L2_OFF 0x1 diff --git a/kernel/include/linux/qed/common_hsi.h b/kernel/include/linux/qed/common_hsi.h new file mode 100644 index 000000000..1d1ba2c5e --- /dev/null +++ b/kernel/include/linux/qed/common_hsi.h @@ -0,0 +1,609 @@ +/* QLogic qed NIC Driver + * Copyright (c) 2015 QLogic Corporation + * + * This software is available under the terms of the GNU General Public License + * (GPL) Version 2, available from the file COPYING in the main directory of + * this source tree. + */ + +#ifndef __COMMON_HSI__ +#define __COMMON_HSI__ + +#define CORE_SPQE_PAGE_SIZE_BYTES 4096 + +#define FW_MAJOR_VERSION 8 +#define FW_MINOR_VERSION 4 +#define FW_REVISION_VERSION 2 +#define FW_ENGINEERING_VERSION 0 + +/***********************/ +/* COMMON HW CONSTANTS */ +/***********************/ + +/* PCI functions */ +#define MAX_NUM_PORTS_K2 (4) +#define MAX_NUM_PORTS_BB (2) +#define MAX_NUM_PORTS (MAX_NUM_PORTS_K2) + +#define MAX_NUM_PFS_K2 (16) +#define MAX_NUM_PFS_BB (8) +#define MAX_NUM_PFS (MAX_NUM_PFS_K2) +#define MAX_NUM_OF_PFS_IN_CHIP (16) /* On both engines */ + +#define MAX_NUM_VFS_K2 (192) +#define MAX_NUM_VFS_BB (120) +#define MAX_NUM_VFS (MAX_NUM_VFS_K2) + +#define MAX_NUM_FUNCTIONS_BB (MAX_NUM_PFS_BB + MAX_NUM_VFS_BB) +#define MAX_NUM_FUNCTIONS (MAX_NUM_PFS + MAX_NUM_VFS) + +#define MAX_FUNCTION_NUMBER_BB (MAX_NUM_PFS + MAX_NUM_VFS_BB) +#define MAX_FUNCTION_NUMBER (MAX_NUM_PFS + MAX_NUM_VFS) + +#define MAX_NUM_VPORTS_K2 (208) +#define MAX_NUM_VPORTS_BB (160) +#define MAX_NUM_VPORTS (MAX_NUM_VPORTS_K2) + +#define MAX_NUM_L2_QUEUES_K2 (320) +#define MAX_NUM_L2_QUEUES_BB (256) +#define MAX_NUM_L2_QUEUES (MAX_NUM_L2_QUEUES_K2) + +/* Traffic classes in network-facing blocks (PBF, BTB, NIG, BRB, PRS and QM) */ +#define NUM_PHYS_TCS_4PORT_K2 (4) +#define NUM_OF_PHYS_TCS (8) + +#define NUM_TCS_4PORT_K2 (NUM_PHYS_TCS_4PORT_K2 + 1) +#define NUM_OF_TCS (NUM_OF_PHYS_TCS + 1) + +#define LB_TC (NUM_OF_PHYS_TCS) + +/* Num of possible traffic priority values */ +#define NUM_OF_PRIO (8) + +#define MAX_NUM_VOQS_K2 (NUM_TCS_4PORT_K2 * MAX_NUM_PORTS_K2) +#define MAX_NUM_VOQS_BB (NUM_OF_TCS * MAX_NUM_PORTS_BB) +#define MAX_NUM_VOQS (MAX_NUM_VOQS_K2) +#define MAX_PHYS_VOQS (NUM_OF_PHYS_TCS * MAX_NUM_PORTS_BB) + +/* CIDs */ +#define NUM_OF_CONNECTION_TYPES (8) +#define NUM_OF_LCIDS (320) +#define NUM_OF_LTIDS (320) + +/*****************/ +/* CDU CONSTANTS */ +/*****************/ + +#define CDU_SEG_TYPE_OFFSET_REG_TYPE_SHIFT (17) +#define CDU_SEG_TYPE_OFFSET_REG_OFFSET_MASK (0x1ffff) + +/*****************/ +/* DQ CONSTANTS */ +/*****************/ + +/* DEMS */ +#define DQ_DEMS_LEGACY 0 + +/* XCM agg val selection */ +#define DQ_XCM_AGG_VAL_SEL_WORD2 0 +#define DQ_XCM_AGG_VAL_SEL_WORD3 1 +#define DQ_XCM_AGG_VAL_SEL_WORD4 2 +#define DQ_XCM_AGG_VAL_SEL_WORD5 3 +#define DQ_XCM_AGG_VAL_SEL_REG3 4 +#define DQ_XCM_AGG_VAL_SEL_REG4 5 +#define DQ_XCM_AGG_VAL_SEL_REG5 6 +#define DQ_XCM_AGG_VAL_SEL_REG6 7 + +/* XCM agg val selection */ +#define DQ_XCM_ETH_EDPM_NUM_BDS_CMD \ + DQ_XCM_AGG_VAL_SEL_WORD2 +#define DQ_XCM_ETH_TX_BD_CONS_CMD \ + DQ_XCM_AGG_VAL_SEL_WORD3 +#define DQ_XCM_CORE_TX_BD_CONS_CMD \ + DQ_XCM_AGG_VAL_SEL_WORD3 +#define DQ_XCM_ETH_TX_BD_PROD_CMD \ + DQ_XCM_AGG_VAL_SEL_WORD4 +#define DQ_XCM_CORE_TX_BD_PROD_CMD \ + DQ_XCM_AGG_VAL_SEL_WORD4 +#define DQ_XCM_CORE_SPQ_PROD_CMD \ + DQ_XCM_AGG_VAL_SEL_WORD4 +#define DQ_XCM_ETH_GO_TO_BD_CONS_CMD DQ_XCM_AGG_VAL_SEL_WORD5 + +/* XCM agg counter flag selection */ +#define DQ_XCM_AGG_FLG_SHIFT_BIT14 0 +#define DQ_XCM_AGG_FLG_SHIFT_BIT15 1 +#define DQ_XCM_AGG_FLG_SHIFT_CF12 2 +#define DQ_XCM_AGG_FLG_SHIFT_CF13 3 +#define DQ_XCM_AGG_FLG_SHIFT_CF18 4 +#define DQ_XCM_AGG_FLG_SHIFT_CF19 5 +#define DQ_XCM_AGG_FLG_SHIFT_CF22 6 +#define DQ_XCM_AGG_FLG_SHIFT_CF23 7 + +/* XCM agg counter flag selection */ +#define DQ_XCM_ETH_DQ_CF_CMD (1 << \ + DQ_XCM_AGG_FLG_SHIFT_CF18) +#define DQ_XCM_CORE_DQ_CF_CMD (1 << \ + DQ_XCM_AGG_FLG_SHIFT_CF18) +#define DQ_XCM_ETH_TERMINATE_CMD (1 << \ + DQ_XCM_AGG_FLG_SHIFT_CF19) +#define DQ_XCM_CORE_TERMINATE_CMD (1 << \ + DQ_XCM_AGG_FLG_SHIFT_CF19) +#define DQ_XCM_ETH_SLOW_PATH_CMD (1 << \ + DQ_XCM_AGG_FLG_SHIFT_CF22) +#define DQ_XCM_CORE_SLOW_PATH_CMD (1 << \ + DQ_XCM_AGG_FLG_SHIFT_CF22) +#define DQ_XCM_ETH_TPH_EN_CMD (1 << \ + DQ_XCM_AGG_FLG_SHIFT_CF23) + +/*****************/ +/* QM CONSTANTS */ +/*****************/ + +/* number of TX queues in the QM */ +#define MAX_QM_TX_QUEUES_K2 512 +#define MAX_QM_TX_QUEUES_BB 448 +#define MAX_QM_TX_QUEUES MAX_QM_TX_QUEUES_K2 + +/* number of Other queues in the QM */ +#define MAX_QM_OTHER_QUEUES_BB 64 +#define MAX_QM_OTHER_QUEUES_K2 128 +#define MAX_QM_OTHER_QUEUES MAX_QM_OTHER_QUEUES_K2 + +/* number of queues in a PF queue group */ +#define QM_PF_QUEUE_GROUP_SIZE 8 + +/* base number of Tx PQs in the CM PQ representation. + * should be used when storing PQ IDs in CM PQ registers and context + */ +#define CM_TX_PQ_BASE 0x200 + +/* QM registers data */ +#define QM_LINE_CRD_REG_WIDTH 16 +#define QM_LINE_CRD_REG_SIGN_BIT (1 << (QM_LINE_CRD_REG_WIDTH - 1)) +#define QM_BYTE_CRD_REG_WIDTH 24 +#define QM_BYTE_CRD_REG_SIGN_BIT (1 << (QM_BYTE_CRD_REG_WIDTH - 1)) +#define QM_WFQ_CRD_REG_WIDTH 32 +#define QM_WFQ_CRD_REG_SIGN_BIT (1 << (QM_WFQ_CRD_REG_WIDTH - 1)) +#define QM_RL_CRD_REG_WIDTH 32 +#define QM_RL_CRD_REG_SIGN_BIT (1 << (QM_RL_CRD_REG_WIDTH - 1)) + +/*****************/ +/* CAU CONSTANTS */ +/*****************/ + +#define CAU_FSM_ETH_RX 0 +#define CAU_FSM_ETH_TX 1 + +/* Number of Protocol Indices per Status Block */ +#define PIS_PER_SB 12 + +#define CAU_HC_STOPPED_STATE 3 +#define CAU_HC_DISABLE_STATE 4 +#define CAU_HC_ENABLE_STATE 0 + +/*****************/ +/* IGU CONSTANTS */ +/*****************/ + +#define MAX_SB_PER_PATH_K2 (368) +#define MAX_SB_PER_PATH_BB (288) +#define MAX_TOT_SB_PER_PATH \ + MAX_SB_PER_PATH_K2 + +#define MAX_SB_PER_PF_MIMD 129 +#define MAX_SB_PER_PF_SIMD 64 +#define MAX_SB_PER_VF 64 + +/* Memory addresses on the BAR for the IGU Sub Block */ +#define IGU_MEM_BASE 0x0000 + +#define IGU_MEM_MSIX_BASE 0x0000 +#define IGU_MEM_MSIX_UPPER 0x0101 +#define IGU_MEM_MSIX_RESERVED_UPPER 0x01ff + +#define IGU_MEM_PBA_MSIX_BASE 0x0200 +#define IGU_MEM_PBA_MSIX_UPPER 0x0202 +#define IGU_MEM_PBA_MSIX_RESERVED_UPPER 0x03ff + +#define IGU_CMD_INT_ACK_BASE 0x0400 +#define IGU_CMD_INT_ACK_UPPER (IGU_CMD_INT_ACK_BASE + \ + MAX_TOT_SB_PER_PATH - \ + 1) +#define IGU_CMD_INT_ACK_RESERVED_UPPER 0x05ff + +#define IGU_CMD_ATTN_BIT_UPD_UPPER 0x05f0 +#define IGU_CMD_ATTN_BIT_SET_UPPER 0x05f1 +#define IGU_CMD_ATTN_BIT_CLR_UPPER 0x05f2 + +#define IGU_REG_SISR_MDPC_WMASK_UPPER 0x05f3 +#define IGU_REG_SISR_MDPC_WMASK_LSB_UPPER 0x05f4 +#define IGU_REG_SISR_MDPC_WMASK_MSB_UPPER 0x05f5 +#define IGU_REG_SISR_MDPC_WOMASK_UPPER 0x05f6 + +#define IGU_CMD_PROD_UPD_BASE 0x0600 +#define IGU_CMD_PROD_UPD_UPPER (IGU_CMD_PROD_UPD_BASE +\ + MAX_TOT_SB_PER_PATH - \ + 1) +#define IGU_CMD_PROD_UPD_RESERVED_UPPER 0x07ff + +/*****************/ +/* PXP CONSTANTS */ +/*****************/ + +/* PTT and GTT */ +#define PXP_NUM_PF_WINDOWS 12 +#define PXP_PER_PF_ENTRY_SIZE 8 +#define PXP_NUM_GLOBAL_WINDOWS 243 +#define PXP_GLOBAL_ENTRY_SIZE 4 +#define PXP_ADMIN_WINDOW_ALLOWED_LENGTH 4 +#define PXP_PF_WINDOW_ADMIN_START 0 +#define PXP_PF_WINDOW_ADMIN_LENGTH 0x1000 +#define PXP_PF_WINDOW_ADMIN_END (PXP_PF_WINDOW_ADMIN_START + \ + PXP_PF_WINDOW_ADMIN_LENGTH - 1) +#define PXP_PF_WINDOW_ADMIN_PER_PF_START 0 +#define PXP_PF_WINDOW_ADMIN_PER_PF_LENGTH (PXP_NUM_PF_WINDOWS * \ + PXP_PER_PF_ENTRY_SIZE) +#define PXP_PF_WINDOW_ADMIN_PER_PF_END (PXP_PF_WINDOW_ADMIN_PER_PF_START + \ + PXP_PF_WINDOW_ADMIN_PER_PF_LENGTH - 1) +#define PXP_PF_WINDOW_ADMIN_GLOBAL_START 0x200 +#define PXP_PF_WINDOW_ADMIN_GLOBAL_LENGTH (PXP_NUM_GLOBAL_WINDOWS * \ + PXP_GLOBAL_ENTRY_SIZE) +#define PXP_PF_WINDOW_ADMIN_GLOBAL_END \ + (PXP_PF_WINDOW_ADMIN_GLOBAL_START + \ + PXP_PF_WINDOW_ADMIN_GLOBAL_LENGTH - 1) +#define PXP_PF_GLOBAL_PRETEND_ADDR 0x1f0 +#define PXP_PF_ME_OPAQUE_MASK_ADDR 0xf4 +#define PXP_PF_ME_OPAQUE_ADDR 0x1f8 +#define PXP_PF_ME_CONCRETE_ADDR 0x1fc + +#define PXP_EXTERNAL_BAR_PF_WINDOW_START 0x1000 +#define PXP_EXTERNAL_BAR_PF_WINDOW_NUM PXP_NUM_PF_WINDOWS +#define PXP_EXTERNAL_BAR_PF_WINDOW_SINGLE_SIZE 0x1000 +#define PXP_EXTERNAL_BAR_PF_WINDOW_LENGTH \ + (PXP_EXTERNAL_BAR_PF_WINDOW_NUM * \ + PXP_EXTERNAL_BAR_PF_WINDOW_SINGLE_SIZE) +#define PXP_EXTERNAL_BAR_PF_WINDOW_END \ + (PXP_EXTERNAL_BAR_PF_WINDOW_START + \ + PXP_EXTERNAL_BAR_PF_WINDOW_LENGTH - 1) + +#define PXP_EXTERNAL_BAR_GLOBAL_WINDOW_START \ + (PXP_EXTERNAL_BAR_PF_WINDOW_END + 1) +#define PXP_EXTERNAL_BAR_GLOBAL_WINDOW_NUM PXP_NUM_GLOBAL_WINDOWS +#define PXP_EXTERNAL_BAR_GLOBAL_WINDOW_SINGLE_SIZE 0x1000 +#define PXP_EXTERNAL_BAR_GLOBAL_WINDOW_LENGTH \ + (PXP_EXTERNAL_BAR_GLOBAL_WINDOW_NUM * \ + PXP_EXTERNAL_BAR_GLOBAL_WINDOW_SINGLE_SIZE) +#define PXP_EXTERNAL_BAR_GLOBAL_WINDOW_END \ + (PXP_EXTERNAL_BAR_GLOBAL_WINDOW_START + \ + PXP_EXTERNAL_BAR_GLOBAL_WINDOW_LENGTH - 1) + +#define PXP_ILT_PAGE_SIZE_NUM_BITS_MIN 12 +#define PXP_ILT_BLOCK_FACTOR_MULTIPLIER 1024 + +/* ILT Records */ +#define PXP_NUM_ILT_RECORDS_BB 7600 +#define PXP_NUM_ILT_RECORDS_K2 11000 +#define MAX_NUM_ILT_RECORDS MAX(PXP_NUM_ILT_RECORDS_BB, PXP_NUM_ILT_RECORDS_K2) + +/******************/ +/* PBF CONSTANTS */ +/******************/ + +/* Number of PBF command queue lines. Each line is 32B. */ +#define PBF_MAX_CMD_LINES 3328 + +/* Number of BTB blocks. Each block is 256B. */ +#define BTB_MAX_BLOCKS 1440 + +/*****************/ +/* PRS CONSTANTS */ +/*****************/ + +/* Async data KCQ CQE */ +struct async_data { + __le32 cid; + __le16 itid; + u8 error_code; + u8 fw_debug_param; +}; + +struct regpair { + __le32 lo; + __le32 hi; +}; + +/* Event Data Union */ +union event_ring_data { + u8 bytes[8]; + struct async_data async_info; +}; + +/* Event Ring Entry */ +struct event_ring_entry { + u8 protocol_id; + u8 opcode; + __le16 reserved0; + __le16 echo; + u8 fw_return_code; + u8 flags; +#define EVENT_RING_ENTRY_ASYNC_MASK 0x1 +#define EVENT_RING_ENTRY_ASYNC_SHIFT 0 +#define EVENT_RING_ENTRY_RESERVED1_MASK 0x7F +#define EVENT_RING_ENTRY_RESERVED1_SHIFT 1 + union event_ring_data data; +}; + +/* Multi function mode */ +enum mf_mode { + SF, + MF_OVLAN, + MF_NPAR, + MAX_MF_MODE +}; + +/* Per-protocol connection types */ +enum protocol_type { + PROTOCOLID_RESERVED1, + PROTOCOLID_RESERVED2, + PROTOCOLID_RESERVED3, + PROTOCOLID_CORE, + PROTOCOLID_ETH, + PROTOCOLID_RESERVED4, + PROTOCOLID_RESERVED5, + PROTOCOLID_PREROCE, + PROTOCOLID_COMMON, + PROTOCOLID_RESERVED6, + MAX_PROTOCOL_TYPE +}; + +/* status block structure */ +struct cau_pi_entry { + u32 prod; +#define CAU_PI_ENTRY_PROD_VAL_MASK 0xFFFF +#define CAU_PI_ENTRY_PROD_VAL_SHIFT 0 +#define CAU_PI_ENTRY_PI_TIMESET_MASK 0x7F +#define CAU_PI_ENTRY_PI_TIMESET_SHIFT 16 +#define CAU_PI_ENTRY_FSM_SEL_MASK 0x1 +#define CAU_PI_ENTRY_FSM_SEL_SHIFT 23 +#define CAU_PI_ENTRY_RESERVED_MASK 0xFF +#define CAU_PI_ENTRY_RESERVED_SHIFT 24 +}; + +/* status block structure */ +struct cau_sb_entry { + u32 data; +#define CAU_SB_ENTRY_SB_PROD_MASK 0xFFFFFF +#define CAU_SB_ENTRY_SB_PROD_SHIFT 0 +#define CAU_SB_ENTRY_STATE0_MASK 0xF +#define CAU_SB_ENTRY_STATE0_SHIFT 24 +#define CAU_SB_ENTRY_STATE1_MASK 0xF +#define CAU_SB_ENTRY_STATE1_SHIFT 28 + u32 params; +#define CAU_SB_ENTRY_SB_TIMESET0_MASK 0x7F +#define CAU_SB_ENTRY_SB_TIMESET0_SHIFT 0 +#define CAU_SB_ENTRY_SB_TIMESET1_MASK 0x7F +#define CAU_SB_ENTRY_SB_TIMESET1_SHIFT 7 +#define CAU_SB_ENTRY_TIMER_RES0_MASK 0x3 +#define CAU_SB_ENTRY_TIMER_RES0_SHIFT 14 +#define CAU_SB_ENTRY_TIMER_RES1_MASK 0x3 +#define CAU_SB_ENTRY_TIMER_RES1_SHIFT 16 +#define CAU_SB_ENTRY_VF_NUMBER_MASK 0xFF +#define CAU_SB_ENTRY_VF_NUMBER_SHIFT 18 +#define CAU_SB_ENTRY_VF_VALID_MASK 0x1 +#define CAU_SB_ENTRY_VF_VALID_SHIFT 26 +#define CAU_SB_ENTRY_PF_NUMBER_MASK 0xF +#define CAU_SB_ENTRY_PF_NUMBER_SHIFT 27 +#define CAU_SB_ENTRY_TPH_MASK 0x1 +#define CAU_SB_ENTRY_TPH_SHIFT 31 +}; + +/* core doorbell data */ +struct core_db_data { + u8 params; +#define CORE_DB_DATA_DEST_MASK 0x3 +#define CORE_DB_DATA_DEST_SHIFT 0 +#define CORE_DB_DATA_AGG_CMD_MASK 0x3 +#define CORE_DB_DATA_AGG_CMD_SHIFT 2 +#define CORE_DB_DATA_BYPASS_EN_MASK 0x1 +#define CORE_DB_DATA_BYPASS_EN_SHIFT 4 +#define CORE_DB_DATA_RESERVED_MASK 0x1 +#define CORE_DB_DATA_RESERVED_SHIFT 5 +#define CORE_DB_DATA_AGG_VAL_SEL_MASK 0x3 +#define CORE_DB_DATA_AGG_VAL_SEL_SHIFT 6 + u8 agg_flags; + __le16 spq_prod; +}; + +/* Enum of doorbell aggregative command selection */ +enum db_agg_cmd_sel { + DB_AGG_CMD_NOP, + DB_AGG_CMD_SET, + DB_AGG_CMD_ADD, + DB_AGG_CMD_MAX, + MAX_DB_AGG_CMD_SEL +}; + +/* Enum of doorbell destination */ +enum db_dest { + DB_DEST_XCM, + DB_DEST_UCM, + DB_DEST_TCM, + DB_NUM_DESTINATIONS, + MAX_DB_DEST +}; + +/* Structure for doorbell address, in legacy mode */ +struct db_legacy_addr { + __le32 addr; +#define DB_LEGACY_ADDR_RESERVED0_MASK 0x3 +#define DB_LEGACY_ADDR_RESERVED0_SHIFT 0 +#define DB_LEGACY_ADDR_DEMS_MASK 0x7 +#define DB_LEGACY_ADDR_DEMS_SHIFT 2 +#define DB_LEGACY_ADDR_ICID_MASK 0x7FFFFFF +#define DB_LEGACY_ADDR_ICID_SHIFT 5 +}; + +/* Igu interrupt command */ +enum igu_int_cmd { + IGU_INT_ENABLE = 0, + IGU_INT_DISABLE = 1, + IGU_INT_NOP = 2, + IGU_INT_NOP2 = 3, + MAX_IGU_INT_CMD +}; + +/* IGU producer or consumer update command */ +struct igu_prod_cons_update { + u32 sb_id_and_flags; +#define IGU_PROD_CONS_UPDATE_SB_INDEX_MASK 0xFFFFFF +#define IGU_PROD_CONS_UPDATE_SB_INDEX_SHIFT 0 +#define IGU_PROD_CONS_UPDATE_UPDATE_FLAG_MASK 0x1 +#define IGU_PROD_CONS_UPDATE_UPDATE_FLAG_SHIFT 24 +#define IGU_PROD_CONS_UPDATE_ENABLE_INT_MASK 0x3 +#define IGU_PROD_CONS_UPDATE_ENABLE_INT_SHIFT 25 +#define IGU_PROD_CONS_UPDATE_SEGMENT_ACCESS_MASK 0x1 +#define IGU_PROD_CONS_UPDATE_SEGMENT_ACCESS_SHIFT 27 +#define IGU_PROD_CONS_UPDATE_TIMER_MASK_MASK 0x1 +#define IGU_PROD_CONS_UPDATE_TIMER_MASK_SHIFT 28 +#define IGU_PROD_CONS_UPDATE_RESERVED0_MASK 0x3 +#define IGU_PROD_CONS_UPDATE_RESERVED0_SHIFT 29 +#define IGU_PROD_CONS_UPDATE_COMMAND_TYPE_MASK 0x1 +#define IGU_PROD_CONS_UPDATE_COMMAND_TYPE_SHIFT 31 + u32 reserved1; +}; + +/* Igu segments access for default status block only */ +enum igu_seg_access { + IGU_SEG_ACCESS_REG = 0, + IGU_SEG_ACCESS_ATTN = 1, + MAX_IGU_SEG_ACCESS +}; + +struct parsing_and_err_flags { + __le16 flags; +#define PARSING_AND_ERR_FLAGS_L3TYPE_MASK 0x3 +#define PARSING_AND_ERR_FLAGS_L3TYPE_SHIFT 0 +#define PARSING_AND_ERR_FLAGS_L4PROTOCOL_MASK 0x3 +#define PARSING_AND_ERR_FLAGS_L4PROTOCOL_SHIFT 2 +#define PARSING_AND_ERR_FLAGS_IPV4FRAG_MASK 0x1 +#define PARSING_AND_ERR_FLAGS_IPV4FRAG_SHIFT 4 +#define PARSING_AND_ERR_FLAGS_TAG8021QEXIST_MASK 0x1 +#define PARSING_AND_ERR_FLAGS_TAG8021QEXIST_SHIFT 5 +#define PARSING_AND_ERR_FLAGS_L4CHKSMWASCALCULATED_MASK 0x1 +#define PARSING_AND_ERR_FLAGS_L4CHKSMWASCALCULATED_SHIFT 6 +#define PARSING_AND_ERR_FLAGS_TIMESYNCPKT_MASK 0x1 +#define PARSING_AND_ERR_FLAGS_TIMESYNCPKT_SHIFT 7 +#define PARSING_AND_ERR_FLAGS_TIMESTAMPRECORDED_MASK 0x1 +#define PARSING_AND_ERR_FLAGS_TIMESTAMPRECORDED_SHIFT 8 +#define PARSING_AND_ERR_FLAGS_IPHDRERROR_MASK 0x1 +#define PARSING_AND_ERR_FLAGS_IPHDRERROR_SHIFT 9 +#define PARSING_AND_ERR_FLAGS_L4CHKSMERROR_MASK 0x1 +#define PARSING_AND_ERR_FLAGS_L4CHKSMERROR_SHIFT 10 +#define PARSING_AND_ERR_FLAGS_TUNNELEXIST_MASK 0x1 +#define PARSING_AND_ERR_FLAGS_TUNNELEXIST_SHIFT 11 +#define PARSING_AND_ERR_FLAGS_TUNNEL8021QTAGEXIST_MASK 0x1 +#define PARSING_AND_ERR_FLAGS_TUNNEL8021QTAGEXIST_SHIFT 12 +#define PARSING_AND_ERR_FLAGS_TUNNELIPHDRERROR_MASK 0x1 +#define PARSING_AND_ERR_FLAGS_TUNNELIPHDRERROR_SHIFT 13 +#define PARSING_AND_ERR_FLAGS_TUNNELL4CHKSMWASCALCULATED_MASK 0x1 +#define PARSING_AND_ERR_FLAGS_TUNNELL4CHKSMWASCALCULATED_SHIFT 14 +#define PARSING_AND_ERR_FLAGS_TUNNELL4CHKSMERROR_MASK 0x1 +#define PARSING_AND_ERR_FLAGS_TUNNELL4CHKSMERROR_SHIFT 15 +}; + +/* Concrete Function ID. */ +struct pxp_concrete_fid { + __le16 fid; +#define PXP_CONCRETE_FID_PFID_MASK 0xF +#define PXP_CONCRETE_FID_PFID_SHIFT 0 +#define PXP_CONCRETE_FID_PORT_MASK 0x3 +#define PXP_CONCRETE_FID_PORT_SHIFT 4 +#define PXP_CONCRETE_FID_PATH_MASK 0x1 +#define PXP_CONCRETE_FID_PATH_SHIFT 6 +#define PXP_CONCRETE_FID_VFVALID_MASK 0x1 +#define PXP_CONCRETE_FID_VFVALID_SHIFT 7 +#define PXP_CONCRETE_FID_VFID_MASK 0xFF +#define PXP_CONCRETE_FID_VFID_SHIFT 8 +}; + +struct pxp_pretend_concrete_fid { + __le16 fid; +#define PXP_PRETEND_CONCRETE_FID_PFID_MASK 0xF +#define PXP_PRETEND_CONCRETE_FID_PFID_SHIFT 0 +#define PXP_PRETEND_CONCRETE_FID_RESERVED_MASK 0x7 +#define PXP_PRETEND_CONCRETE_FID_RESERVED_SHIFT 4 +#define PXP_PRETEND_CONCRETE_FID_VFVALID_MASK 0x1 +#define PXP_PRETEND_CONCRETE_FID_VFVALID_SHIFT 7 +#define PXP_PRETEND_CONCRETE_FID_VFID_MASK 0xFF +#define PXP_PRETEND_CONCRETE_FID_VFID_SHIFT 8 +}; + +union pxp_pretend_fid { + struct pxp_pretend_concrete_fid concrete_fid; + __le16 opaque_fid; +}; + +/* Pxp Pretend Command Register. */ +struct pxp_pretend_cmd { + union pxp_pretend_fid fid; + __le16 control; +#define PXP_PRETEND_CMD_PATH_MASK 0x1 +#define PXP_PRETEND_CMD_PATH_SHIFT 0 +#define PXP_PRETEND_CMD_USE_PORT_MASK 0x1 +#define PXP_PRETEND_CMD_USE_PORT_SHIFT 1 +#define PXP_PRETEND_CMD_PORT_MASK 0x3 +#define PXP_PRETEND_CMD_PORT_SHIFT 2 +#define PXP_PRETEND_CMD_RESERVED0_MASK 0xF +#define PXP_PRETEND_CMD_RESERVED0_SHIFT 4 +#define PXP_PRETEND_CMD_RESERVED1_MASK 0xF +#define PXP_PRETEND_CMD_RESERVED1_SHIFT 8 +#define PXP_PRETEND_CMD_PRETEND_PATH_MASK 0x1 +#define PXP_PRETEND_CMD_PRETEND_PATH_SHIFT 12 +#define PXP_PRETEND_CMD_PRETEND_PORT_MASK 0x1 +#define PXP_PRETEND_CMD_PRETEND_PORT_SHIFT 13 +#define PXP_PRETEND_CMD_PRETEND_FUNCTION_MASK 0x1 +#define PXP_PRETEND_CMD_PRETEND_FUNCTION_SHIFT 14 +#define PXP_PRETEND_CMD_IS_CONCRETE_MASK 0x1 +#define PXP_PRETEND_CMD_IS_CONCRETE_SHIFT 15 +}; + +/* PTT Record in PXP Admin Window. */ +struct pxp_ptt_entry { + __le32 offset; +#define PXP_PTT_ENTRY_OFFSET_MASK 0x7FFFFF +#define PXP_PTT_ENTRY_OFFSET_SHIFT 0 +#define PXP_PTT_ENTRY_RESERVED0_MASK 0x1FF +#define PXP_PTT_ENTRY_RESERVED0_SHIFT 23 + struct pxp_pretend_cmd pretend; +}; + +/* RSS hash type */ +enum rss_hash_type { + RSS_HASH_TYPE_DEFAULT = 0, + RSS_HASH_TYPE_IPV4 = 1, + RSS_HASH_TYPE_TCP_IPV4 = 2, + RSS_HASH_TYPE_IPV6 = 3, + RSS_HASH_TYPE_TCP_IPV6 = 4, + RSS_HASH_TYPE_UDP_IPV4 = 5, + RSS_HASH_TYPE_UDP_IPV6 = 6, + MAX_RSS_HASH_TYPE +}; + +/* status block structure */ +struct status_block { + __le16 pi_array[PIS_PER_SB]; + __le32 sb_num; +#define STATUS_BLOCK_SB_NUM_MASK 0x1FF +#define STATUS_BLOCK_SB_NUM_SHIFT 0 +#define STATUS_BLOCK_ZERO_PAD_MASK 0x7F +#define STATUS_BLOCK_ZERO_PAD_SHIFT 9 +#define STATUS_BLOCK_ZERO_PAD2_MASK 0xFFFF +#define STATUS_BLOCK_ZERO_PAD2_SHIFT 16 + __le32 prod_index; +#define STATUS_BLOCK_PROD_INDEX_MASK 0xFFFFFF +#define STATUS_BLOCK_PROD_INDEX_SHIFT 0 +#define STATUS_BLOCK_ZERO_PAD3_MASK 0xFF +#define STATUS_BLOCK_ZERO_PAD3_SHIFT 24 +}; + +#endif /* __COMMON_HSI__ */ diff --git a/kernel/include/linux/qed/eth_common.h b/kernel/include/linux/qed/eth_common.h new file mode 100644 index 000000000..320b3373a --- /dev/null +++ b/kernel/include/linux/qed/eth_common.h @@ -0,0 +1,279 @@ +/* QLogic qed NIC Driver + * Copyright (c) 2015 QLogic Corporation + * + * This software is available under the terms of the GNU General Public License + * (GPL) Version 2, available from the file COPYING in the main directory of + * this source tree. + */ + +#ifndef __ETH_COMMON__ +#define __ETH_COMMON__ + +/********************/ +/* ETH FW CONSTANTS */ +/********************/ +#define ETH_CACHE_LINE_SIZE 64 + +#define ETH_MAX_RAMROD_PER_CON 8 +#define ETH_TX_BD_PAGE_SIZE_BYTES 4096 +#define ETH_RX_BD_PAGE_SIZE_BYTES 4096 +#define ETH_RX_SGE_PAGE_SIZE_BYTES 4096 +#define ETH_RX_CQE_PAGE_SIZE_BYTES 4096 +#define ETH_RX_NUM_NEXT_PAGE_BDS 2 +#define ETH_RX_NUM_NEXT_PAGE_SGES 2 + +#define ETH_TX_MIN_BDS_PER_NON_LSO_PKT 1 +#define ETH_TX_MAX_BDS_PER_NON_LSO_PACKET 18 +#define ETH_TX_MAX_LSO_HDR_NBD 4 +#define ETH_TX_MIN_BDS_PER_LSO_PKT 3 +#define ETH_TX_MIN_BDS_PER_TUNN_IPV6_WITH_EXT_PKT 3 +#define ETH_TX_MIN_BDS_PER_IPV6_WITH_EXT_PKT 2 +#define ETH_TX_MIN_BDS_PER_PKT_W_LOOPBACK_MODE 2 +#define ETH_TX_MAX_NON_LSO_PKT_LEN (9700 - (4 + 12 + 8)) +#define ETH_TX_MAX_LSO_HDR_BYTES 510 + +#define ETH_NUM_STATISTIC_COUNTERS MAX_NUM_VPORTS + +#define ETH_REG_CQE_PBL_SIZE 3 + +/* num of MAC/VLAN filters */ +#define ETH_NUM_MAC_FILTERS 512 +#define ETH_NUM_VLAN_FILTERS 512 + +/* approx. multicast constants */ +#define ETH_MULTICAST_BIN_FROM_MAC_SEED 0 +#define ETH_MULTICAST_MAC_BINS 256 +#define ETH_MULTICAST_MAC_BINS_IN_REGS (ETH_MULTICAST_MAC_BINS / 32) + +/* ethernet vport update constants */ +#define ETH_FILTER_RULES_COUNT 10 +#define ETH_RSS_IND_TABLE_ENTRIES_NUM 128 +#define ETH_RSS_KEY_SIZE_REGS 10 +#define ETH_RSS_ENGINE_NUM_K2 207 +#define ETH_RSS_ENGINE_NUM_BB 127 + +/* TPA constants */ +#define ETH_TPA_MAX_AGGS_NUM 64 +#define ETH_TPA_CQE_START_SGL_SIZE 3 +#define ETH_TPA_CQE_CONT_SGL_SIZE 6 +#define ETH_TPA_CQE_END_SGL_SIZE 4 + +/* Queue Zone sizes */ +#define TSTORM_QZONE_SIZE 0 +#define MSTORM_QZONE_SIZE sizeof(struct mstorm_eth_queue_zone) +#define USTORM_QZONE_SIZE sizeof(struct ustorm_eth_queue_zone) +#define XSTORM_QZONE_SIZE 0 +#define YSTORM_QZONE_SIZE sizeof(struct ystorm_eth_queue_zone) +#define PSTORM_QZONE_SIZE 0 + +/* Interrupt coalescing TimeSet */ +struct coalescing_timeset { + u8 timeset; + u8 valid; +}; + +struct eth_tx_1st_bd_flags { + u8 bitfields; +#define ETH_TX_1ST_BD_FLAGS_FORCE_VLAN_MODE_MASK 0x1 +#define ETH_TX_1ST_BD_FLAGS_FORCE_VLAN_MODE_SHIFT 0 +#define ETH_TX_1ST_BD_FLAGS_IP_CSUM_MASK 0x1 +#define ETH_TX_1ST_BD_FLAGS_IP_CSUM_SHIFT 1 +#define ETH_TX_1ST_BD_FLAGS_L4_CSUM_MASK 0x1 +#define ETH_TX_1ST_BD_FLAGS_L4_CSUM_SHIFT 2 +#define ETH_TX_1ST_BD_FLAGS_VLAN_INSERTION_MASK 0x1 +#define ETH_TX_1ST_BD_FLAGS_VLAN_INSERTION_SHIFT 3 +#define ETH_TX_1ST_BD_FLAGS_LSO_MASK 0x1 +#define ETH_TX_1ST_BD_FLAGS_LSO_SHIFT 4 +#define ETH_TX_1ST_BD_FLAGS_START_BD_MASK 0x1 +#define ETH_TX_1ST_BD_FLAGS_START_BD_SHIFT 5 +#define ETH_TX_1ST_BD_FLAGS_TUNN_IP_CSUM_MASK 0x1 +#define ETH_TX_1ST_BD_FLAGS_TUNN_IP_CSUM_SHIFT 6 +#define ETH_TX_1ST_BD_FLAGS_TUNN_L4_CSUM_MASK 0x1 +#define ETH_TX_1ST_BD_FLAGS_TUNN_L4_CSUM_SHIFT 7 +}; + +/* The parsing information data fo rthe first tx bd of a given packet. */ +struct eth_tx_data_1st_bd { + __le16 vlan; + u8 nbds; + struct eth_tx_1st_bd_flags bd_flags; + __le16 fw_use_only; +}; + +/* The parsing information data for the second tx bd of a given packet. */ +struct eth_tx_data_2nd_bd { + __le16 tunn_ip_size; + __le16 bitfields; +#define ETH_TX_DATA_2ND_BD_L4_HDR_START_OFFSET_W_MASK 0x1FFF +#define ETH_TX_DATA_2ND_BD_L4_HDR_START_OFFSET_W_SHIFT 0 +#define ETH_TX_DATA_2ND_BD_RESERVED0_MASK 0x7 +#define ETH_TX_DATA_2ND_BD_RESERVED0_SHIFT 13 + __le16 bitfields2; +#define ETH_TX_DATA_2ND_BD_TUNN_INNER_L2_HDR_SIZE_W_MASK 0xF +#define ETH_TX_DATA_2ND_BD_TUNN_INNER_L2_HDR_SIZE_W_SHIFT 0 +#define ETH_TX_DATA_2ND_BD_TUNN_INNER_ETH_TYPE_MASK 0x3 +#define ETH_TX_DATA_2ND_BD_TUNN_INNER_ETH_TYPE_SHIFT 4 +#define ETH_TX_DATA_2ND_BD_DEST_PORT_MODE_MASK 0x3 +#define ETH_TX_DATA_2ND_BD_DEST_PORT_MODE_SHIFT 6 +#define ETH_TX_DATA_2ND_BD_TUNN_TYPE_MASK 0x3 +#define ETH_TX_DATA_2ND_BD_TUNN_TYPE_SHIFT 8 +#define ETH_TX_DATA_2ND_BD_TUNN_INNER_IPV6_MASK 0x1 +#define ETH_TX_DATA_2ND_BD_TUNN_INNER_IPV6_SHIFT 10 +#define ETH_TX_DATA_2ND_BD_IPV6_EXT_MASK 0x1 +#define ETH_TX_DATA_2ND_BD_IPV6_EXT_SHIFT 11 +#define ETH_TX_DATA_2ND_BD_TUNN_IPV6_EXT_MASK 0x1 +#define ETH_TX_DATA_2ND_BD_TUNN_IPV6_EXT_SHIFT 12 +#define ETH_TX_DATA_2ND_BD_L4_UDP_MASK 0x1 +#define ETH_TX_DATA_2ND_BD_L4_UDP_SHIFT 13 +#define ETH_TX_DATA_2ND_BD_L4_PSEUDO_CSUM_MODE_MASK 0x1 +#define ETH_TX_DATA_2ND_BD_L4_PSEUDO_CSUM_MODE_SHIFT 14 +#define ETH_TX_DATA_2ND_BD_RESERVED1_MASK 0x1 +#define ETH_TX_DATA_2ND_BD_RESERVED1_SHIFT 15 +}; + +/* Regular ETH Rx FP CQE. */ +struct eth_fast_path_rx_reg_cqe { + u8 type; + u8 bitfields; +#define ETH_FAST_PATH_RX_REG_CQE_RSS_HASH_TYPE_MASK 0x7 +#define ETH_FAST_PATH_RX_REG_CQE_RSS_HASH_TYPE_SHIFT 0 +#define ETH_FAST_PATH_RX_REG_CQE_TC_MASK 0xF +#define ETH_FAST_PATH_RX_REG_CQE_TC_SHIFT 3 +#define ETH_FAST_PATH_RX_REG_CQE_RESERVED0_MASK 0x1 +#define ETH_FAST_PATH_RX_REG_CQE_RESERVED0_SHIFT 7 + __le16 pkt_len; + struct parsing_and_err_flags pars_flags; + __le16 vlan_tag; + __le32 rss_hash; + __le16 len_on_bd; + u8 placement_offset; + u8 reserved; + __le16 pbl[ETH_REG_CQE_PBL_SIZE]; + u8 reserved1[10]; +}; + +/* The L4 pseudo checksum mode for Ethernet */ +enum eth_l4_pseudo_checksum_mode { + ETH_L4_PSEUDO_CSUM_CORRECT_LENGTH, + ETH_L4_PSEUDO_CSUM_ZERO_LENGTH, + MAX_ETH_L4_PSEUDO_CHECKSUM_MODE +}; + +struct eth_rx_bd { + struct regpair addr; +}; + +/* regular ETH Rx SP CQE */ +struct eth_slow_path_rx_cqe { + u8 type; + u8 ramrod_cmd_id; + u8 error_flag; + u8 reserved[27]; + __le16 echo; +}; + +/* union for all ETH Rx CQE types */ +union eth_rx_cqe { + struct eth_fast_path_rx_reg_cqe fast_path_regular; + struct eth_slow_path_rx_cqe slow_path; +}; + +/* ETH Rx CQE type */ +enum eth_rx_cqe_type { + ETH_RX_CQE_TYPE_UNUSED, + ETH_RX_CQE_TYPE_REGULAR, + ETH_RX_CQE_TYPE_SLOW_PATH, + MAX_ETH_RX_CQE_TYPE +}; + +/* ETH Rx producers data */ +struct eth_rx_prod_data { + __le16 bd_prod; + __le16 sge_prod; + __le16 cqe_prod; + __le16 reserved; +}; + +/* The first tx bd of a given packet */ +struct eth_tx_1st_bd { + struct regpair addr; + __le16 nbytes; + struct eth_tx_data_1st_bd data; +}; + +/* The second tx bd of a given packet */ +struct eth_tx_2nd_bd { + struct regpair addr; + __le16 nbytes; + struct eth_tx_data_2nd_bd data; +}; + +/* The parsing information data for the third tx bd of a given packet. */ +struct eth_tx_data_3rd_bd { + __le16 lso_mss; + u8 bitfields; +#define ETH_TX_DATA_3RD_BD_TCP_HDR_LEN_DW_MASK 0xF +#define ETH_TX_DATA_3RD_BD_TCP_HDR_LEN_DW_SHIFT 0 +#define ETH_TX_DATA_3RD_BD_HDR_NBD_MASK 0xF +#define ETH_TX_DATA_3RD_BD_HDR_NBD_SHIFT 4 + u8 resereved0[3]; +}; + +/* The third tx bd of a given packet */ +struct eth_tx_3rd_bd { + struct regpair addr; + __le16 nbytes; + struct eth_tx_data_3rd_bd data; +}; + +/* The common non-special TX BD ring element */ +struct eth_tx_bd { + struct regpair addr; + __le16 nbytes; + __le16 reserved0; + __le32 reserved1; +}; + +union eth_tx_bd_types { + struct eth_tx_1st_bd first_bd; + struct eth_tx_2nd_bd second_bd; + struct eth_tx_3rd_bd third_bd; + struct eth_tx_bd reg_bd; +}; + +/* Mstorm Queue Zone */ +struct mstorm_eth_queue_zone { + struct eth_rx_prod_data rx_producers; + __le32 reserved[2]; +}; + +/* Ustorm Queue Zone */ +struct ustorm_eth_queue_zone { + struct coalescing_timeset int_coalescing_timeset; + __le16 reserved[3]; +}; + +/* Ystorm Queue Zone */ +struct ystorm_eth_queue_zone { + struct coalescing_timeset int_coalescing_timeset; + __le16 reserved[3]; +}; + +/* ETH doorbell data */ +struct eth_db_data { + u8 params; +#define ETH_DB_DATA_DEST_MASK 0x3 +#define ETH_DB_DATA_DEST_SHIFT 0 +#define ETH_DB_DATA_AGG_CMD_MASK 0x3 +#define ETH_DB_DATA_AGG_CMD_SHIFT 2 +#define ETH_DB_DATA_BYPASS_EN_MASK 0x1 +#define ETH_DB_DATA_BYPASS_EN_SHIFT 4 +#define ETH_DB_DATA_RESERVED_MASK 0x1 +#define ETH_DB_DATA_RESERVED_SHIFT 5 +#define ETH_DB_DATA_AGG_VAL_SEL_MASK 0x3 +#define ETH_DB_DATA_AGG_VAL_SEL_SHIFT 6 + u8 agg_flags; + __le16 bd_prod; +}; + +#endif /* __ETH_COMMON__ */ diff --git a/kernel/include/linux/qed/qed_chain.h b/kernel/include/linux/qed/qed_chain.h new file mode 100644 index 000000000..41b9049b5 --- /dev/null +++ b/kernel/include/linux/qed/qed_chain.h @@ -0,0 +1,540 @@ +/* QLogic qed NIC Driver + * Copyright (c) 2015 QLogic Corporation + * + * This software is available under the terms of the GNU General Public License + * (GPL) Version 2, available from the file COPYING in the main directory of + * this source tree. + */ + +#ifndef _QED_CHAIN_H +#define _QED_CHAIN_H + +#include <linux/types.h> +#include <asm/byteorder.h> +#include <linux/kernel.h> +#include <linux/list.h> +#include <linux/slab.h> +#include <linux/qed/common_hsi.h> + +/* dma_addr_t manip */ +#define DMA_LO_LE(x) cpu_to_le32(lower_32_bits(x)) +#define DMA_HI_LE(x) cpu_to_le32(upper_32_bits(x)) + +#define HILO_GEN(hi, lo, type) ((((type)(hi)) << 32) + (lo)) +#define HILO_DMA(hi, lo) HILO_GEN(hi, lo, dma_addr_t) +#define HILO_64(hi, lo) HILO_GEN((le32_to_cpu(hi)), (le32_to_cpu(lo)), u64) +#define HILO_DMA_REGPAIR(regpair) (HILO_DMA(regpair.hi, regpair.lo)) +#define HILO_64_REGPAIR(regpair) (HILO_64(regpair.hi, regpair.lo)) + +enum qed_chain_mode { + /* Each Page contains a next pointer at its end */ + QED_CHAIN_MODE_NEXT_PTR, + + /* Chain is a single page (next ptr) is unrequired */ + QED_CHAIN_MODE_SINGLE, + + /* Page pointers are located in a side list */ + QED_CHAIN_MODE_PBL, +}; + +enum qed_chain_use_mode { + QED_CHAIN_USE_TO_PRODUCE, /* Chain starts empty */ + QED_CHAIN_USE_TO_CONSUME, /* Chain starts full */ + QED_CHAIN_USE_TO_CONSUME_PRODUCE, /* Chain starts empty */ +}; + +struct qed_chain_next { + struct regpair next_phys; + void *next_virt; +}; + +struct qed_chain_pbl { + dma_addr_t p_phys_table; + void *p_virt_table; + u16 prod_page_idx; + u16 cons_page_idx; +}; + +struct qed_chain { + void *p_virt_addr; + dma_addr_t p_phys_addr; + void *p_prod_elem; + void *p_cons_elem; + u16 page_cnt; + enum qed_chain_mode mode; + enum qed_chain_use_mode intended_use; /* used to produce/consume */ + u16 capacity; /*< number of _usable_ elements */ + u16 size; /* number of elements */ + u16 prod_idx; + u16 cons_idx; + u16 elem_per_page; + u16 elem_per_page_mask; + u16 elem_unusable; + u16 usable_per_page; + u16 elem_size; + u16 next_page_mask; + struct qed_chain_pbl pbl; +}; + +#define QED_CHAIN_PBL_ENTRY_SIZE (8) +#define QED_CHAIN_PAGE_SIZE (0x1000) +#define ELEMS_PER_PAGE(elem_size) (QED_CHAIN_PAGE_SIZE / (elem_size)) + +#define UNUSABLE_ELEMS_PER_PAGE(elem_size, mode) \ + ((mode == QED_CHAIN_MODE_NEXT_PTR) ? \ + (1 + ((sizeof(struct qed_chain_next) - 1) / \ + (elem_size))) : 0) + +#define USABLE_ELEMS_PER_PAGE(elem_size, mode) \ + ((u32)(ELEMS_PER_PAGE(elem_size) - \ + UNUSABLE_ELEMS_PER_PAGE(elem_size, mode))) + +#define QED_CHAIN_PAGE_CNT(elem_cnt, elem_size, mode) \ + DIV_ROUND_UP(elem_cnt, USABLE_ELEMS_PER_PAGE(elem_size, mode)) + +/* Accessors */ +static inline u16 qed_chain_get_prod_idx(struct qed_chain *p_chain) +{ + return p_chain->prod_idx; +} + +static inline u16 qed_chain_get_cons_idx(struct qed_chain *p_chain) +{ + return p_chain->cons_idx; +} + +static inline u16 qed_chain_get_elem_left(struct qed_chain *p_chain) +{ + u16 used; + + /* we don't need to trancate upon assignmet, as we assign u32->u16 */ + used = ((u32)0x10000u + (u32)(p_chain->prod_idx)) - + (u32)p_chain->cons_idx; + if (p_chain->mode == QED_CHAIN_MODE_NEXT_PTR) + used -= p_chain->prod_idx / p_chain->elem_per_page - + p_chain->cons_idx / p_chain->elem_per_page; + + return p_chain->capacity - used; +} + +static inline u8 qed_chain_is_full(struct qed_chain *p_chain) +{ + return qed_chain_get_elem_left(p_chain) == p_chain->capacity; +} + +static inline u8 qed_chain_is_empty(struct qed_chain *p_chain) +{ + return qed_chain_get_elem_left(p_chain) == 0; +} + +static inline u16 qed_chain_get_elem_per_page( + struct qed_chain *p_chain) +{ + return p_chain->elem_per_page; +} + +static inline u16 qed_chain_get_usable_per_page( + struct qed_chain *p_chain) +{ + return p_chain->usable_per_page; +} + +static inline u16 qed_chain_get_unusable_per_page( + struct qed_chain *p_chain) +{ + return p_chain->elem_unusable; +} + +static inline u16 qed_chain_get_size(struct qed_chain *p_chain) +{ + return p_chain->size; +} + +static inline dma_addr_t +qed_chain_get_pbl_phys(struct qed_chain *p_chain) +{ + return p_chain->pbl.p_phys_table; +} + +/** + * @brief qed_chain_advance_page - + * + * Advance the next element accros pages for a linked chain + * + * @param p_chain + * @param p_next_elem + * @param idx_to_inc + * @param page_to_inc + */ +static inline void +qed_chain_advance_page(struct qed_chain *p_chain, + void **p_next_elem, + u16 *idx_to_inc, + u16 *page_to_inc) + +{ + switch (p_chain->mode) { + case QED_CHAIN_MODE_NEXT_PTR: + { + struct qed_chain_next *p_next = *p_next_elem; + *p_next_elem = p_next->next_virt; + *idx_to_inc += p_chain->elem_unusable; + break; + } + case QED_CHAIN_MODE_SINGLE: + *p_next_elem = p_chain->p_virt_addr; + break; + + case QED_CHAIN_MODE_PBL: + /* It is assumed pages are sequential, next element needs + * to change only when passing going back to first from last. + */ + if (++(*page_to_inc) == p_chain->page_cnt) { + *page_to_inc = 0; + *p_next_elem = p_chain->p_virt_addr; + } + } +} + +#define is_unusable_idx(p, idx) \ + (((p)->idx & (p)->elem_per_page_mask) == (p)->usable_per_page) + +#define is_unusable_next_idx(p, idx) \ + ((((p)->idx + 1) & (p)->elem_per_page_mask) == (p)->usable_per_page) + +#define test_ans_skip(p, idx) \ + do { \ + if (is_unusable_idx(p, idx)) { \ + (p)->idx += (p)->elem_unusable; \ + } \ + } while (0) + +/** + * @brief qed_chain_return_multi_produced - + * + * A chain in which the driver "Produces" elements should use this API + * to indicate previous produced elements are now consumed. + * + * @param p_chain + * @param num + */ +static inline void +qed_chain_return_multi_produced(struct qed_chain *p_chain, + u16 num) +{ + p_chain->cons_idx += num; + test_ans_skip(p_chain, cons_idx); +} + +/** + * @brief qed_chain_return_produced - + * + * A chain in which the driver "Produces" elements should use this API + * to indicate previous produced elements are now consumed. + * + * @param p_chain + */ +static inline void qed_chain_return_produced(struct qed_chain *p_chain) +{ + p_chain->cons_idx++; + test_ans_skip(p_chain, cons_idx); +} + +/** + * @brief qed_chain_produce - + * + * A chain in which the driver "Produces" elements should use this to get + * a pointer to the next element which can be "Produced". It's driver + * responsibility to validate that the chain has room for new element. + * + * @param p_chain + * + * @return void*, a pointer to next element + */ +static inline void *qed_chain_produce(struct qed_chain *p_chain) +{ + void *ret = NULL; + + if ((p_chain->prod_idx & p_chain->elem_per_page_mask) == + p_chain->next_page_mask) { + qed_chain_advance_page(p_chain, &p_chain->p_prod_elem, + &p_chain->prod_idx, + &p_chain->pbl.prod_page_idx); + } + + ret = p_chain->p_prod_elem; + p_chain->prod_idx++; + p_chain->p_prod_elem = (void *)(((u8 *)p_chain->p_prod_elem) + + p_chain->elem_size); + + return ret; +} + +/** + * @brief qed_chain_get_capacity - + * + * Get the maximum number of BDs in chain + * + * @param p_chain + * @param num + * + * @return u16, number of unusable BDs + */ +static inline u16 qed_chain_get_capacity(struct qed_chain *p_chain) +{ + return p_chain->capacity; +} + +/** + * @brief qed_chain_recycle_consumed - + * + * Returns an element which was previously consumed; + * Increments producers so they could be written to FW. + * + * @param p_chain + */ +static inline void +qed_chain_recycle_consumed(struct qed_chain *p_chain) +{ + test_ans_skip(p_chain, prod_idx); + p_chain->prod_idx++; +} + +/** + * @brief qed_chain_consume - + * + * A Chain in which the driver utilizes data written by a different source + * (i.e., FW) should use this to access passed buffers. + * + * @param p_chain + * + * @return void*, a pointer to the next buffer written + */ +static inline void *qed_chain_consume(struct qed_chain *p_chain) +{ + void *ret = NULL; + + if ((p_chain->cons_idx & p_chain->elem_per_page_mask) == + p_chain->next_page_mask) { + qed_chain_advance_page(p_chain, &p_chain->p_cons_elem, + &p_chain->cons_idx, + &p_chain->pbl.cons_page_idx); + } + + ret = p_chain->p_cons_elem; + p_chain->cons_idx++; + p_chain->p_cons_elem = (void *)(((u8 *)p_chain->p_cons_elem) + + p_chain->elem_size); + + return ret; +} + +/** + * @brief qed_chain_reset - Resets the chain to its start state + * + * @param p_chain pointer to a previously allocted chain + */ +static inline void qed_chain_reset(struct qed_chain *p_chain) +{ + int i; + + p_chain->prod_idx = 0; + p_chain->cons_idx = 0; + p_chain->p_cons_elem = p_chain->p_virt_addr; + p_chain->p_prod_elem = p_chain->p_virt_addr; + + if (p_chain->mode == QED_CHAIN_MODE_PBL) { + p_chain->pbl.prod_page_idx = p_chain->page_cnt - 1; + p_chain->pbl.cons_page_idx = p_chain->page_cnt - 1; + } + + switch (p_chain->intended_use) { + case QED_CHAIN_USE_TO_CONSUME_PRODUCE: + case QED_CHAIN_USE_TO_PRODUCE: + /* Do nothing */ + break; + + case QED_CHAIN_USE_TO_CONSUME: + /* produce empty elements */ + for (i = 0; i < p_chain->capacity; i++) + qed_chain_recycle_consumed(p_chain); + break; + } +} + +/** + * @brief qed_chain_init - Initalizes a basic chain struct + * + * @param p_chain + * @param p_virt_addr + * @param p_phys_addr physical address of allocated buffer's beginning + * @param page_cnt number of pages in the allocated buffer + * @param elem_size size of each element in the chain + * @param intended_use + * @param mode + */ +static inline void qed_chain_init(struct qed_chain *p_chain, + void *p_virt_addr, + dma_addr_t p_phys_addr, + u16 page_cnt, + u8 elem_size, + enum qed_chain_use_mode intended_use, + enum qed_chain_mode mode) +{ + /* chain fixed parameters */ + p_chain->p_virt_addr = p_virt_addr; + p_chain->p_phys_addr = p_phys_addr; + p_chain->elem_size = elem_size; + p_chain->page_cnt = page_cnt; + p_chain->mode = mode; + + p_chain->intended_use = intended_use; + p_chain->elem_per_page = ELEMS_PER_PAGE(elem_size); + p_chain->usable_per_page = + USABLE_ELEMS_PER_PAGE(elem_size, mode); + p_chain->capacity = p_chain->usable_per_page * page_cnt; + p_chain->size = p_chain->elem_per_page * page_cnt; + p_chain->elem_per_page_mask = p_chain->elem_per_page - 1; + + p_chain->elem_unusable = UNUSABLE_ELEMS_PER_PAGE(elem_size, mode); + + p_chain->next_page_mask = (p_chain->usable_per_page & + p_chain->elem_per_page_mask); + + if (mode == QED_CHAIN_MODE_NEXT_PTR) { + struct qed_chain_next *p_next; + u16 i; + + for (i = 0; i < page_cnt - 1; i++) { + /* Increment mem_phy to the next page. */ + p_phys_addr += QED_CHAIN_PAGE_SIZE; + + /* Initialize the physical address of the next page. */ + p_next = (struct qed_chain_next *)((u8 *)p_virt_addr + + elem_size * + p_chain-> + usable_per_page); + + p_next->next_phys.lo = DMA_LO_LE(p_phys_addr); + p_next->next_phys.hi = DMA_HI_LE(p_phys_addr); + + /* Initialize the virtual address of the next page. */ + p_next->next_virt = (void *)((u8 *)p_virt_addr + + QED_CHAIN_PAGE_SIZE); + + /* Move to the next page. */ + p_virt_addr = p_next->next_virt; + } + + /* Last page's next should point to beginning of the chain */ + p_next = (struct qed_chain_next *)((u8 *)p_virt_addr + + elem_size * + p_chain->usable_per_page); + + p_next->next_phys.lo = DMA_LO_LE(p_chain->p_phys_addr); + p_next->next_phys.hi = DMA_HI_LE(p_chain->p_phys_addr); + p_next->next_virt = p_chain->p_virt_addr; + } + qed_chain_reset(p_chain); +} + +/** + * @brief qed_chain_pbl_init - Initalizes a basic pbl chain + * struct + * @param p_chain + * @param p_virt_addr virtual address of allocated buffer's beginning + * @param p_phys_addr physical address of allocated buffer's beginning + * @param page_cnt number of pages in the allocated buffer + * @param elem_size size of each element in the chain + * @param use_mode + * @param p_phys_pbl pointer to a pre-allocated side table + * which will hold physical page addresses. + * @param p_virt_pbl pointer to a pre allocated side table + * which will hold virtual page addresses. + */ +static inline void +qed_chain_pbl_init(struct qed_chain *p_chain, + void *p_virt_addr, + dma_addr_t p_phys_addr, + u16 page_cnt, + u8 elem_size, + enum qed_chain_use_mode use_mode, + dma_addr_t p_phys_pbl, + dma_addr_t *p_virt_pbl) +{ + dma_addr_t *p_pbl_dma = p_virt_pbl; + int i; + + qed_chain_init(p_chain, p_virt_addr, p_phys_addr, page_cnt, + elem_size, use_mode, QED_CHAIN_MODE_PBL); + + p_chain->pbl.p_phys_table = p_phys_pbl; + p_chain->pbl.p_virt_table = p_virt_pbl; + + /* Fill the PBL with physical addresses*/ + for (i = 0; i < page_cnt; i++) { + *p_pbl_dma = p_phys_addr; + p_phys_addr += QED_CHAIN_PAGE_SIZE; + p_pbl_dma++; + } +} + +/** + * @brief qed_chain_set_prod - sets the prod to the given + * value + * + * @param prod_idx + * @param p_prod_elem + */ +static inline void qed_chain_set_prod(struct qed_chain *p_chain, + u16 prod_idx, + void *p_prod_elem) +{ + p_chain->prod_idx = prod_idx; + p_chain->p_prod_elem = p_prod_elem; +} + +/** + * @brief qed_chain_get_elem - + * + * get a pointer to an element represented by absolute idx + * + * @param p_chain + * @assumption p_chain->size is a power of 2 + * + * @return void*, a pointer to next element + */ +static inline void *qed_chain_sge_get_elem(struct qed_chain *p_chain, + u16 idx) +{ + void *ret = NULL; + + if (idx >= p_chain->size) + return NULL; + + ret = (u8 *)p_chain->p_virt_addr + p_chain->elem_size * idx; + + return ret; +} + +/** + * @brief qed_chain_sge_inc_cons_prod + * + * for sge chains, producer isn't increased serially, the ring + * is expected to be full at all times. Once elements are + * consumed, they are immediately produced. + * + * @param p_chain + * @param cnt + * + * @return inline void + */ +static inline void +qed_chain_sge_inc_cons_prod(struct qed_chain *p_chain, + u16 cnt) +{ + p_chain->prod_idx += cnt; + p_chain->cons_idx += cnt; +} + +#endif diff --git a/kernel/include/linux/qed/qed_eth_if.h b/kernel/include/linux/qed/qed_eth_if.h new file mode 100644 index 000000000..81ab178e3 --- /dev/null +++ b/kernel/include/linux/qed/qed_eth_if.h @@ -0,0 +1,165 @@ +/* QLogic qed NIC Driver + * Copyright (c) 2015 QLogic Corporation + * + * This software is available under the terms of the GNU General Public License + * (GPL) Version 2, available from the file COPYING in the main directory of + * this source tree. + */ + +#ifndef _QED_ETH_IF_H +#define _QED_ETH_IF_H + +#include <linux/list.h> +#include <linux/if_link.h> +#include <linux/qed/eth_common.h> +#include <linux/qed/qed_if.h> + +struct qed_dev_eth_info { + struct qed_dev_info common; + + u8 num_queues; + u8 num_tc; + + u8 port_mac[ETH_ALEN]; + u8 num_vlan_filters; +}; + +struct qed_update_vport_rss_params { + u16 rss_ind_table[128]; + u32 rss_key[10]; +}; + +struct qed_update_vport_params { + u8 vport_id; + u8 update_vport_active_flg; + u8 vport_active_flg; + u8 update_rss_flg; + struct qed_update_vport_rss_params rss_params; +}; + +struct qed_stop_rxq_params { + u8 rss_id; + u8 rx_queue_id; + u8 vport_id; + bool eq_completion_only; +}; + +struct qed_stop_txq_params { + u8 rss_id; + u8 tx_queue_id; +}; + +enum qed_filter_rx_mode_type { + QED_FILTER_RX_MODE_TYPE_REGULAR, + QED_FILTER_RX_MODE_TYPE_MULTI_PROMISC, + QED_FILTER_RX_MODE_TYPE_PROMISC, +}; + +enum qed_filter_xcast_params_type { + QED_FILTER_XCAST_TYPE_ADD, + QED_FILTER_XCAST_TYPE_DEL, + QED_FILTER_XCAST_TYPE_REPLACE, +}; + +struct qed_filter_ucast_params { + enum qed_filter_xcast_params_type type; + u8 vlan_valid; + u16 vlan; + u8 mac_valid; + unsigned char mac[ETH_ALEN]; +}; + +struct qed_filter_mcast_params { + enum qed_filter_xcast_params_type type; + u8 num; + unsigned char mac[64][ETH_ALEN]; +}; + +union qed_filter_type_params { + enum qed_filter_rx_mode_type accept_flags; + struct qed_filter_ucast_params ucast; + struct qed_filter_mcast_params mcast; +}; + +enum qed_filter_type { + QED_FILTER_TYPE_UCAST, + QED_FILTER_TYPE_MCAST, + QED_FILTER_TYPE_RX_MODE, + QED_MAX_FILTER_TYPES, +}; + +struct qed_filter_params { + enum qed_filter_type type; + union qed_filter_type_params filter; +}; + +struct qed_queue_start_common_params { + u8 rss_id; + u8 queue_id; + u8 vport_id; + u16 sb; + u16 sb_idx; +}; + +struct qed_eth_cb_ops { + struct qed_common_cb_ops common; +}; + +struct qed_eth_ops { + const struct qed_common_ops *common; + + int (*fill_dev_info)(struct qed_dev *cdev, + struct qed_dev_eth_info *info); + + void (*register_ops)(struct qed_dev *cdev, + struct qed_eth_cb_ops *ops, + void *cookie); + + int (*vport_start)(struct qed_dev *cdev, + u8 vport_id, u16 mtu, + u8 drop_ttl0_flg, + u8 inner_vlan_removal_en_flg); + + int (*vport_stop)(struct qed_dev *cdev, + u8 vport_id); + + int (*vport_update)(struct qed_dev *cdev, + struct qed_update_vport_params *params); + + int (*q_rx_start)(struct qed_dev *cdev, + struct qed_queue_start_common_params *params, + u16 bd_max_bytes, + dma_addr_t bd_chain_phys_addr, + dma_addr_t cqe_pbl_addr, + u16 cqe_pbl_size, + void __iomem **pp_prod); + + int (*q_rx_stop)(struct qed_dev *cdev, + struct qed_stop_rxq_params *params); + + int (*q_tx_start)(struct qed_dev *cdev, + struct qed_queue_start_common_params *params, + dma_addr_t pbl_addr, + u16 pbl_size, + void __iomem **pp_doorbell); + + int (*q_tx_stop)(struct qed_dev *cdev, + struct qed_stop_txq_params *params); + + int (*filter_config)(struct qed_dev *cdev, + struct qed_filter_params *params); + + int (*fastpath_stop)(struct qed_dev *cdev); + + int (*eth_cqe_completion)(struct qed_dev *cdev, + u8 rss_id, + struct eth_slow_path_rx_cqe *cqe); + + void (*get_vport_stats)(struct qed_dev *cdev, + struct qed_eth_stats *stats); +}; + +const struct qed_eth_ops *qed_get_eth_ops(u32 version); +void qed_put_eth_ops(void); + +#endif diff --git a/kernel/include/linux/qed/qed_if.h b/kernel/include/linux/qed/qed_if.h new file mode 100644 index 000000000..dc9a1353f --- /dev/null +++ b/kernel/include/linux/qed/qed_if.h @@ -0,0 +1,498 @@ +/* QLogic qed NIC Driver + * + * Copyright (c) 2015 QLogic Corporation + * + * This software is available under the terms of the GNU General Public License + * (GPL) Version 2, available from the file COPYING in the main directory of + * this source tree. + */ + +#ifndef _QED_IF_H +#define _QED_IF_H + +#include <linux/types.h> +#include <linux/interrupt.h> +#include <linux/netdevice.h> +#include <linux/pci.h> +#include <linux/skbuff.h> +#include <linux/types.h> +#include <asm/byteorder.h> +#include <linux/io.h> +#include <linux/compiler.h> +#include <linux/kernel.h> +#include <linux/list.h> +#include <linux/slab.h> +#include <linux/qed/common_hsi.h> +#include <linux/qed/qed_chain.h> + +#define DIRECT_REG_WR(reg_addr, val) writel((u32)val, \ + (void __iomem *)(reg_addr)) + +#define DIRECT_REG_RD(reg_addr) readl((void __iomem *)(reg_addr)) + +#define QED_COALESCE_MAX 0xFF + +/* forward */ +struct qed_dev; + +struct qed_eth_pf_params { + /* The following parameters are used during HW-init + * and these parameters need to be passed as arguments + * to update_pf_params routine invoked before slowpath start + */ + u16 num_cons; +}; + +struct qed_pf_params { + struct qed_eth_pf_params eth_pf_params; +}; + +enum qed_int_mode { + QED_INT_MODE_INTA, + QED_INT_MODE_MSIX, + QED_INT_MODE_MSI, + QED_INT_MODE_POLL, +}; + +struct qed_sb_info { + struct status_block *sb_virt; + dma_addr_t sb_phys; + u32 sb_ack; /* Last given ack */ + u16 igu_sb_id; + void __iomem *igu_addr; + u8 flags; +#define QED_SB_INFO_INIT 0x1 +#define QED_SB_INFO_SETUP 0x2 + + struct qed_dev *cdev; +}; + +struct qed_dev_info { + unsigned long pci_mem_start; + unsigned long pci_mem_end; + unsigned int pci_irq; + u8 num_hwfns; + + u8 hw_mac[ETH_ALEN]; + bool is_mf; + + /* FW version */ + u16 fw_major; + u16 fw_minor; + u16 fw_rev; + u16 fw_eng; + + /* MFW version */ + u32 mfw_rev; + + u32 flash_size; + u8 mf_mode; +}; + +enum qed_sb_type { + QED_SB_TYPE_L2_QUEUE, +}; + +enum qed_protocol { + QED_PROTOCOL_ETH, +}; + +struct qed_link_params { + bool link_up; + +#define QED_LINK_OVERRIDE_SPEED_AUTONEG BIT(0) +#define QED_LINK_OVERRIDE_SPEED_ADV_SPEEDS BIT(1) +#define QED_LINK_OVERRIDE_SPEED_FORCED_SPEED BIT(2) +#define QED_LINK_OVERRIDE_PAUSE_CONFIG BIT(3) + u32 override_flags; + bool autoneg; + u32 adv_speeds; + u32 forced_speed; +#define QED_LINK_PAUSE_AUTONEG_ENABLE BIT(0) +#define QED_LINK_PAUSE_RX_ENABLE BIT(1) +#define QED_LINK_PAUSE_TX_ENABLE BIT(2) + u32 pause_config; +}; + +struct qed_link_output { + bool link_up; + + u32 supported_caps; /* In SUPPORTED defs */ + u32 advertised_caps; /* In ADVERTISED defs */ + u32 lp_caps; /* In ADVERTISED defs */ + u32 speed; /* In Mb/s */ + u8 duplex; /* In DUPLEX defs */ + u8 port; /* In PORT defs */ + bool autoneg; + u32 pause_config; +}; + +#define QED_DRV_VER_STR_SIZE 12 +struct qed_slowpath_params { + u32 int_mode; + u8 drv_major; + u8 drv_minor; + u8 drv_rev; + u8 drv_eng; + u8 name[QED_DRV_VER_STR_SIZE]; +}; + +#define ILT_PAGE_SIZE_TCFC 0x8000 /* 32KB */ + +struct qed_int_info { + struct msix_entry *msix; + u8 msix_cnt; + + /* This should be updated by the protocol driver */ + u8 used_cnt; +}; + +struct qed_common_cb_ops { + void (*link_update)(void *dev, + struct qed_link_output *link); +}; + +struct qed_common_ops { + struct qed_dev* (*probe)(struct pci_dev *dev, + enum qed_protocol protocol, + u32 dp_module, u8 dp_level); + + void (*remove)(struct qed_dev *cdev); + + int (*set_power_state)(struct qed_dev *cdev, + pci_power_t state); + + void (*set_id)(struct qed_dev *cdev, + char name[], + char ver_str[]); + + /* Client drivers need to make this call before slowpath_start. + * PF params required for the call before slowpath_start is + * documented within the qed_pf_params structure definition. + */ + void (*update_pf_params)(struct qed_dev *cdev, + struct qed_pf_params *params); + int (*slowpath_start)(struct qed_dev *cdev, + struct qed_slowpath_params *params); + + int (*slowpath_stop)(struct qed_dev *cdev); + + /* Requests to use `cnt' interrupts for fastpath. + * upon success, returns number of interrupts allocated for fastpath. + */ + int (*set_fp_int)(struct qed_dev *cdev, + u16 cnt); + + /* Fills `info' with pointers required for utilizing interrupts */ + int (*get_fp_int)(struct qed_dev *cdev, + struct qed_int_info *info); + + u32 (*sb_init)(struct qed_dev *cdev, + struct qed_sb_info *sb_info, + void *sb_virt_addr, + dma_addr_t sb_phy_addr, + u16 sb_id, + enum qed_sb_type type); + + u32 (*sb_release)(struct qed_dev *cdev, + struct qed_sb_info *sb_info, + u16 sb_id); + + void (*simd_handler_config)(struct qed_dev *cdev, + void *token, + int index, + void (*handler)(void *)); + + void (*simd_handler_clean)(struct qed_dev *cdev, + int index); +/** + * @brief set_link - set links according to params + * + * @param cdev + * @param params - values used to override the default link configuration + * + * @return 0 on success, error otherwise. + */ + int (*set_link)(struct qed_dev *cdev, + struct qed_link_params *params); + +/** + * @brief get_link - returns the current link state. + * + * @param cdev + * @param if_link - structure to be filled with current link configuration. + */ + void (*get_link)(struct qed_dev *cdev, + struct qed_link_output *if_link); + +/** + * @brief - drains chip in case Tx completions fail to arrive due to pause. + * + * @param cdev + */ + int (*drain)(struct qed_dev *cdev); + +/** + * @brief update_msglvl - update module debug level + * + * @param cdev + * @param dp_module + * @param dp_level + */ + void (*update_msglvl)(struct qed_dev *cdev, + u32 dp_module, + u8 dp_level); + + int (*chain_alloc)(struct qed_dev *cdev, + enum qed_chain_use_mode intended_use, + enum qed_chain_mode mode, + u16 num_elems, + size_t elem_size, + struct qed_chain *p_chain); + + void (*chain_free)(struct qed_dev *cdev, + struct qed_chain *p_chain); +}; + +/** + * @brief qed_get_protocol_version + * + * @param protocol + * + * @return version supported by qed for given protocol driver + */ +u32 qed_get_protocol_version(enum qed_protocol protocol); + +#define MASK_FIELD(_name, _value) \ + ((_value) &= (_name ## _MASK)) + +#define FIELD_VALUE(_name, _value) \ + ((_value & _name ## _MASK) << _name ## _SHIFT) + +#define SET_FIELD(value, name, flag) \ + do { \ + (value) &= ~(name ## _MASK << name ## _SHIFT); \ + (value) |= (((u64)flag) << (name ## _SHIFT)); \ + } while (0) + +#define GET_FIELD(value, name) \ + (((value) >> (name ## _SHIFT)) & name ## _MASK) + +/* Debug print definitions */ +#define DP_ERR(cdev, fmt, ...) \ + pr_err("[%s:%d(%s)]" fmt, \ + __func__, __LINE__, \ + DP_NAME(cdev) ? DP_NAME(cdev) : "", \ + ## __VA_ARGS__) \ + +#define DP_NOTICE(cdev, fmt, ...) \ + do { \ + if (unlikely((cdev)->dp_level <= QED_LEVEL_NOTICE)) { \ + pr_notice("[%s:%d(%s)]" fmt, \ + __func__, __LINE__, \ + DP_NAME(cdev) ? DP_NAME(cdev) : "", \ + ## __VA_ARGS__); \ + \ + } \ + } while (0) + +#define DP_INFO(cdev, fmt, ...) \ + do { \ + if (unlikely((cdev)->dp_level <= QED_LEVEL_INFO)) { \ + pr_notice("[%s:%d(%s)]" fmt, \ + __func__, __LINE__, \ + DP_NAME(cdev) ? DP_NAME(cdev) : "", \ + ## __VA_ARGS__); \ + } \ + } while (0) + +#define DP_VERBOSE(cdev, module, fmt, ...) \ + do { \ + if (unlikely(((cdev)->dp_level <= QED_LEVEL_VERBOSE) && \ + ((cdev)->dp_module & module))) { \ + pr_notice("[%s:%d(%s)]" fmt, \ + __func__, __LINE__, \ + DP_NAME(cdev) ? DP_NAME(cdev) : "", \ + ## __VA_ARGS__); \ + } \ + } while (0) + +enum DP_LEVEL { + QED_LEVEL_VERBOSE = 0x0, + QED_LEVEL_INFO = 0x1, + QED_LEVEL_NOTICE = 0x2, + QED_LEVEL_ERR = 0x3, +}; + +#define QED_LOG_LEVEL_SHIFT (30) +#define QED_LOG_VERBOSE_MASK (0x3fffffff) +#define QED_LOG_INFO_MASK (0x40000000) +#define QED_LOG_NOTICE_MASK (0x80000000) + +enum DP_MODULE { + QED_MSG_SPQ = 0x10000, + QED_MSG_STATS = 0x20000, + QED_MSG_DCB = 0x40000, + QED_MSG_IOV = 0x80000, + QED_MSG_SP = 0x100000, + QED_MSG_STORAGE = 0x200000, + QED_MSG_CXT = 0x800000, + QED_MSG_ILT = 0x2000000, + QED_MSG_ROCE = 0x4000000, + QED_MSG_DEBUG = 0x8000000, + /* to be added...up to 0x8000000 */ +}; + +struct qed_eth_stats { + u64 no_buff_discards; + u64 packet_too_big_discard; + u64 ttl0_discard; + u64 rx_ucast_bytes; + u64 rx_mcast_bytes; + u64 rx_bcast_bytes; + u64 rx_ucast_pkts; + u64 rx_mcast_pkts; + u64 rx_bcast_pkts; + u64 mftag_filter_discards; + u64 mac_filter_discards; + u64 tx_ucast_bytes; + u64 tx_mcast_bytes; + u64 tx_bcast_bytes; + u64 tx_ucast_pkts; + u64 tx_mcast_pkts; + u64 tx_bcast_pkts; + u64 tx_err_drop_pkts; + u64 tpa_coalesced_pkts; + u64 tpa_coalesced_events; + u64 tpa_aborts_num; + u64 tpa_not_coalesced_pkts; + u64 tpa_coalesced_bytes; + + /* port */ + u64 rx_64_byte_packets; + u64 rx_127_byte_packets; + u64 rx_255_byte_packets; + u64 rx_511_byte_packets; + u64 rx_1023_byte_packets; + u64 rx_1518_byte_packets; + u64 rx_1522_byte_packets; + u64 rx_2047_byte_packets; + u64 rx_4095_byte_packets; + u64 rx_9216_byte_packets; + u64 rx_16383_byte_packets; + u64 rx_crc_errors; + u64 rx_mac_crtl_frames; + u64 rx_pause_frames; + u64 rx_pfc_frames; + u64 rx_align_errors; + u64 rx_carrier_errors; + u64 rx_oversize_packets; + u64 rx_jabbers; + u64 rx_undersize_packets; + u64 rx_fragments; + u64 tx_64_byte_packets; + u64 tx_65_to_127_byte_packets; + u64 tx_128_to_255_byte_packets; + u64 tx_256_to_511_byte_packets; + u64 tx_512_to_1023_byte_packets; + u64 tx_1024_to_1518_byte_packets; + u64 tx_1519_to_2047_byte_packets; + u64 tx_2048_to_4095_byte_packets; + u64 tx_4096_to_9216_byte_packets; + u64 tx_9217_to_16383_byte_packets; + u64 tx_pause_frames; + u64 tx_pfc_frames; + u64 tx_lpi_entry_count; + u64 tx_total_collisions; + u64 brb_truncates; + u64 brb_discards; + u64 rx_mac_bytes; + u64 rx_mac_uc_packets; + u64 rx_mac_mc_packets; + u64 rx_mac_bc_packets; + u64 rx_mac_frames_ok; + u64 tx_mac_bytes; + u64 tx_mac_uc_packets; + u64 tx_mac_mc_packets; + u64 tx_mac_bc_packets; + u64 tx_mac_ctrl_frames; +}; + +#define QED_SB_IDX 0x0002 + +#define RX_PI 0 +#define TX_PI(tc) (RX_PI + 1 + tc) + +static inline u16 qed_sb_update_sb_idx(struct qed_sb_info *sb_info) +{ + u32 prod = 0; + u16 rc = 0; + + prod = le32_to_cpu(sb_info->sb_virt->prod_index) & + STATUS_BLOCK_PROD_INDEX_MASK; + if (sb_info->sb_ack != prod) { + sb_info->sb_ack = prod; + rc |= QED_SB_IDX; + } + + /* Let SB update */ + mmiowb(); + return rc; +} + +/** + * + * @brief This function creates an update command for interrupts that is + * written to the IGU. + * + * @param sb_info - This is the structure allocated and + * initialized per status block. Assumption is + * that it was initialized using qed_sb_init + * @param int_cmd - Enable/Disable/Nop + * @param upd_flg - whether igu consumer should be + * updated. + * + * @return inline void + */ +static inline void qed_sb_ack(struct qed_sb_info *sb_info, + enum igu_int_cmd int_cmd, + u8 upd_flg) +{ + struct igu_prod_cons_update igu_ack = { 0 }; + + igu_ack.sb_id_and_flags = + ((sb_info->sb_ack << IGU_PROD_CONS_UPDATE_SB_INDEX_SHIFT) | + (upd_flg << IGU_PROD_CONS_UPDATE_UPDATE_FLAG_SHIFT) | + (int_cmd << IGU_PROD_CONS_UPDATE_ENABLE_INT_SHIFT) | + (IGU_SEG_ACCESS_REG << + IGU_PROD_CONS_UPDATE_SEGMENT_ACCESS_SHIFT)); + + DIRECT_REG_WR(sb_info->igu_addr, igu_ack.sb_id_and_flags); + + /* Both segments (interrupts & acks) are written to same place address; + * Need to guarantee all commands will be received (in-order) by HW. + */ + mmiowb(); + barrier(); +} + +static inline void __internal_ram_wr(void *p_hwfn, + void __iomem *addr, + int size, + u32 *data) + +{ + unsigned int i; + + for (i = 0; i < size / sizeof(*data); i++) + DIRECT_REG_WR(&((u32 __iomem *)addr)[i], data[i]); +} + +static inline void internal_ram_wr(void __iomem *addr, + int size, + u32 *data) +{ + __internal_ram_wr(NULL, addr, size, data); +} + +#endif diff --git a/kernel/include/linux/quotaops.h b/kernel/include/linux/quotaops.h index 77ca6601f..7a57c28eb 100644 --- a/kernel/include/linux/quotaops.h +++ b/kernel/include/linux/quotaops.h @@ -43,7 +43,7 @@ void inode_claim_rsv_space(struct inode *inode, qsize_t number); void inode_sub_rsv_space(struct inode *inode, qsize_t number); void inode_reclaim_rsv_space(struct inode *inode, qsize_t number); -void dquot_initialize(struct inode *inode); +int dquot_initialize(struct inode *inode); void dquot_drop(struct inode *inode); struct dquot *dqget(struct super_block *sb, struct kqid qid); static inline struct dquot *dqgrab(struct dquot *dquot) @@ -200,8 +200,9 @@ static inline int sb_has_quota_active(struct super_block *sb, int type) return 0; } -static inline void dquot_initialize(struct inode *inode) +static inline int dquot_initialize(struct inode *inode) { + return 0; } static inline void dquot_drop(struct inode *inode) diff --git a/kernel/include/linux/radix-tree.h b/kernel/include/linux/radix-tree.h index 933ff6977..8ddbd6e15 100644 --- a/kernel/include/linux/radix-tree.h +++ b/kernel/include/linux/radix-tree.h @@ -375,12 +375,28 @@ void **radix_tree_next_chunk(struct radix_tree_root *root, struct radix_tree_iter *iter, unsigned flags); /** + * radix_tree_iter_retry - retry this chunk of the iteration + * @iter: iterator state + * + * If we iterate over a tree protected only by the RCU lock, a race + * against deletion or creation may result in seeing a slot for which + * radix_tree_deref_retry() returns true. If so, call this function + * and continue the iteration. + */ +static inline __must_check +void **radix_tree_iter_retry(struct radix_tree_iter *iter) +{ + iter->next_index = iter->index; + return NULL; +} + +/** * radix_tree_chunk_size - get current chunk size * * @iter: pointer to radix tree iterator * Returns: current chunk size */ -static __always_inline unsigned +static __always_inline long radix_tree_chunk_size(struct radix_tree_iter *iter) { return iter->next_index - iter->index; @@ -414,9 +430,9 @@ radix_tree_next_slot(void **slot, struct radix_tree_iter *iter, unsigned flags) return slot + offset + 1; } } else { - unsigned size = radix_tree_chunk_size(iter) - 1; + long size = radix_tree_chunk_size(iter); - while (size--) { + while (--size > 0) { slot++; iter->index++; if (likely(*slot)) diff --git a/kernel/include/linux/random.h b/kernel/include/linux/random.h index 4a64ad52d..1a8043616 100644 --- a/kernel/include/linux/random.h +++ b/kernel/include/linux/random.h @@ -6,14 +6,25 @@ #ifndef _LINUX_RANDOM_H #define _LINUX_RANDOM_H +#include <linux/list.h> +#include <linux/once.h> + #include <uapi/linux/random.h> +struct random_ready_callback { + struct list_head list; + void (*func)(struct random_ready_callback *rdy); + struct module *owner; +}; + extern void add_device_randomness(const void *, unsigned int); extern void add_input_randomness(unsigned int type, unsigned int code, unsigned int value); extern void add_interrupt_randomness(int irq, int irq_flags, __u64 ip); extern void get_random_bytes(void *buf, int nbytes); +extern int add_random_ready_callback(struct random_ready_callback *rdy); +extern void del_random_ready_callback(struct random_ready_callback *rdy); extern void get_random_bytes_arch(void *buf, int nbytes); void generate_random_uuid(unsigned char uuid_out[16]); extern int random_int_secret_init(void); @@ -36,6 +47,10 @@ struct rnd_state { u32 prandom_u32_state(struct rnd_state *state); void prandom_bytes_state(struct rnd_state *state, void *buf, size_t nbytes); +void prandom_seed_full_state(struct rnd_state __percpu *pcpu_state); + +#define prandom_init_once(pcpu_state) \ + DO_ONCE(prandom_seed_full_state, (pcpu_state)) /** * prandom_u32_max - returns a pseudo-random number in interval [0, ep_ro) diff --git a/kernel/include/linux/rbtree.h b/kernel/include/linux/rbtree.h index fb31765e9..24ddffd25 100644 --- a/kernel/include/linux/rbtree.h +++ b/kernel/include/linux/rbtree.h @@ -73,11 +73,11 @@ extern struct rb_node *rb_first_postorder(const struct rb_root *); extern struct rb_node *rb_next_postorder(const struct rb_node *); /* Fast replacement of a single node without remove/rebalance/add/rebalance */ -extern void rb_replace_node(struct rb_node *victim, struct rb_node *new, +extern void rb_replace_node(struct rb_node *victim, struct rb_node *new, struct rb_root *root); -static inline void rb_link_node(struct rb_node * node, struct rb_node * parent, - struct rb_node ** rb_link) +static inline void rb_link_node(struct rb_node *node, struct rb_node *parent, + struct rb_node **rb_link) { node->__rb_parent_color = (unsigned long)parent; node->rb_left = node->rb_right = NULL; @@ -85,19 +85,30 @@ static inline void rb_link_node(struct rb_node * node, struct rb_node * parent, *rb_link = node; } +void rb_link_node_rcu(struct rb_node *node, struct rb_node *parent, + struct rb_node **rb_link); + #define rb_entry_safe(ptr, type, member) \ ({ typeof(ptr) ____ptr = (ptr); \ ____ptr ? rb_entry(____ptr, type, member) : NULL; \ }) /** - * rbtree_postorder_for_each_entry_safe - iterate over rb_root in post order of - * given type safe against removal of rb_node entry + * rbtree_postorder_for_each_entry_safe - iterate in post-order over rb_root of + * given type allowing the backing memory of @pos to be invalidated * * @pos: the 'type *' to use as a loop cursor. * @n: another 'type *' to use as temporary storage * @root: 'rb_root *' of the rbtree. * @field: the name of the rb_node field within 'type'. + * + * rbtree_postorder_for_each_entry_safe() provides a similar guarantee as + * list_for_each_entry_safe() and allows the iteration to continue independent + * of changes to @pos by the body of the loop. + * + * Note, however, that it cannot handle other modifications that re-order the + * rbtree it is iterating over. This includes calling rb_erase() on @pos, as + * rb_erase() may rebalance the tree, causing us to miss some nodes. */ #define rbtree_postorder_for_each_entry_safe(pos, n, root, field) \ for (pos = rb_entry_safe(rb_first_postorder(root), typeof(*pos), field); \ diff --git a/kernel/include/linux/rbtree_augmented.h b/kernel/include/linux/rbtree_augmented.h index 378c5ee75..14d7b831b 100644 --- a/kernel/include/linux/rbtree_augmented.h +++ b/kernel/include/linux/rbtree_augmented.h @@ -123,11 +123,11 @@ __rb_change_child(struct rb_node *old, struct rb_node *new, { if (parent) { if (parent->rb_left == old) - parent->rb_left = new; + WRITE_ONCE(parent->rb_left, new); else - parent->rb_right = new; + WRITE_ONCE(parent->rb_right, new); } else - root->rb_node = new; + WRITE_ONCE(root->rb_node, new); } extern void __rb_erase_color(struct rb_node *parent, struct rb_root *root, @@ -137,7 +137,8 @@ static __always_inline struct rb_node * __rb_erase_augmented(struct rb_node *node, struct rb_root *root, const struct rb_augment_callbacks *augment) { - struct rb_node *child = node->rb_right, *tmp = node->rb_left; + struct rb_node *child = node->rb_right; + struct rb_node *tmp = node->rb_left; struct rb_node *parent, *rebalance; unsigned long pc; @@ -167,6 +168,7 @@ __rb_erase_augmented(struct rb_node *node, struct rb_root *root, tmp = parent; } else { struct rb_node *successor = child, *child2; + tmp = child->rb_left; if (!tmp) { /* @@ -180,6 +182,7 @@ __rb_erase_augmented(struct rb_node *node, struct rb_root *root, */ parent = successor; child2 = successor->rb_right; + augment->copy(node, successor); } else { /* @@ -201,19 +204,23 @@ __rb_erase_augmented(struct rb_node *node, struct rb_root *root, successor = tmp; tmp = tmp->rb_left; } while (tmp); - parent->rb_left = child2 = successor->rb_right; - successor->rb_right = child; + child2 = successor->rb_right; + WRITE_ONCE(parent->rb_left, child2); + WRITE_ONCE(successor->rb_right, child); rb_set_parent(child, successor); + augment->copy(node, successor); augment->propagate(parent, successor); } - successor->rb_left = tmp = node->rb_left; + tmp = node->rb_left; + WRITE_ONCE(successor->rb_left, tmp); rb_set_parent(tmp, successor); pc = node->__rb_parent_color; tmp = __rb_parent(pc); __rb_change_child(node, successor, tmp, root); + if (child2) { successor->__rb_parent_color = pc; rb_set_parent_color(child2, parent, RB_BLACK); diff --git a/kernel/include/linux/rbtree_latch.h b/kernel/include/linux/rbtree_latch.h new file mode 100644 index 000000000..4f3432c61 --- /dev/null +++ b/kernel/include/linux/rbtree_latch.h @@ -0,0 +1,212 @@ +/* + * Latched RB-trees + * + * Copyright (C) 2015 Intel Corp., Peter Zijlstra <peterz@infradead.org> + * + * Since RB-trees have non-atomic modifications they're not immediately suited + * for RCU/lockless queries. Even though we made RB-tree lookups non-fatal for + * lockless lookups; we cannot guarantee they return a correct result. + * + * The simplest solution is a seqlock + RB-tree, this will allow lockless + * lookups; but has the constraint (inherent to the seqlock) that read sides + * cannot nest in write sides. + * + * If we need to allow unconditional lookups (say as required for NMI context + * usage) we need a more complex setup; this data structure provides this by + * employing the latch technique -- see @raw_write_seqcount_latch -- to + * implement a latched RB-tree which does allow for unconditional lookups by + * virtue of always having (at least) one stable copy of the tree. + * + * However, while we have the guarantee that there is at all times one stable + * copy, this does not guarantee an iteration will not observe modifications. + * What might have been a stable copy at the start of the iteration, need not + * remain so for the duration of the iteration. + * + * Therefore, this does require a lockless RB-tree iteration to be non-fatal; + * see the comment in lib/rbtree.c. Note however that we only require the first + * condition -- not seeing partial stores -- because the latch thing isolates + * us from loops. If we were to interrupt a modification the lookup would be + * pointed at the stable tree and complete while the modification was halted. + */ + +#ifndef RB_TREE_LATCH_H +#define RB_TREE_LATCH_H + +#include <linux/rbtree.h> +#include <linux/seqlock.h> + +struct latch_tree_node { + struct rb_node node[2]; +}; + +struct latch_tree_root { + seqcount_t seq; + struct rb_root tree[2]; +}; + +/** + * latch_tree_ops - operators to define the tree order + * @less: used for insertion; provides the (partial) order between two elements. + * @comp: used for lookups; provides the order between the search key and an element. + * + * The operators are related like: + * + * comp(a->key,b) < 0 := less(a,b) + * comp(a->key,b) > 0 := less(b,a) + * comp(a->key,b) == 0 := !less(a,b) && !less(b,a) + * + * If these operators define a partial order on the elements we make no + * guarantee on which of the elements matching the key is found. See + * latch_tree_find(). + */ +struct latch_tree_ops { + bool (*less)(struct latch_tree_node *a, struct latch_tree_node *b); + int (*comp)(void *key, struct latch_tree_node *b); +}; + +static __always_inline struct latch_tree_node * +__lt_from_rb(struct rb_node *node, int idx) +{ + return container_of(node, struct latch_tree_node, node[idx]); +} + +static __always_inline void +__lt_insert(struct latch_tree_node *ltn, struct latch_tree_root *ltr, int idx, + bool (*less)(struct latch_tree_node *a, struct latch_tree_node *b)) +{ + struct rb_root *root = <r->tree[idx]; + struct rb_node **link = &root->rb_node; + struct rb_node *node = <n->node[idx]; + struct rb_node *parent = NULL; + struct latch_tree_node *ltp; + + while (*link) { + parent = *link; + ltp = __lt_from_rb(parent, idx); + + if (less(ltn, ltp)) + link = &parent->rb_left; + else + link = &parent->rb_right; + } + + rb_link_node_rcu(node, parent, link); + rb_insert_color(node, root); +} + +static __always_inline void +__lt_erase(struct latch_tree_node *ltn, struct latch_tree_root *ltr, int idx) +{ + rb_erase(<n->node[idx], <r->tree[idx]); +} + +static __always_inline struct latch_tree_node * +__lt_find(void *key, struct latch_tree_root *ltr, int idx, + int (*comp)(void *key, struct latch_tree_node *node)) +{ + struct rb_node *node = rcu_dereference_raw(ltr->tree[idx].rb_node); + struct latch_tree_node *ltn; + int c; + + while (node) { + ltn = __lt_from_rb(node, idx); + c = comp(key, ltn); + + if (c < 0) + node = rcu_dereference_raw(node->rb_left); + else if (c > 0) + node = rcu_dereference_raw(node->rb_right); + else + return ltn; + } + + return NULL; +} + +/** + * latch_tree_insert() - insert @node into the trees @root + * @node: nodes to insert + * @root: trees to insert @node into + * @ops: operators defining the node order + * + * It inserts @node into @root in an ordered fashion such that we can always + * observe one complete tree. See the comment for raw_write_seqcount_latch(). + * + * The inserts use rcu_assign_pointer() to publish the element such that the + * tree structure is stored before we can observe the new @node. + * + * All modifications (latch_tree_insert, latch_tree_remove) are assumed to be + * serialized. + */ +static __always_inline void +latch_tree_insert(struct latch_tree_node *node, + struct latch_tree_root *root, + const struct latch_tree_ops *ops) +{ + raw_write_seqcount_latch(&root->seq); + __lt_insert(node, root, 0, ops->less); + raw_write_seqcount_latch(&root->seq); + __lt_insert(node, root, 1, ops->less); +} + +/** + * latch_tree_erase() - removes @node from the trees @root + * @node: nodes to remote + * @root: trees to remove @node from + * @ops: operators defining the node order + * + * Removes @node from the trees @root in an ordered fashion such that we can + * always observe one complete tree. See the comment for + * raw_write_seqcount_latch(). + * + * It is assumed that @node will observe one RCU quiescent state before being + * reused of freed. + * + * All modifications (latch_tree_insert, latch_tree_remove) are assumed to be + * serialized. + */ +static __always_inline void +latch_tree_erase(struct latch_tree_node *node, + struct latch_tree_root *root, + const struct latch_tree_ops *ops) +{ + raw_write_seqcount_latch(&root->seq); + __lt_erase(node, root, 0); + raw_write_seqcount_latch(&root->seq); + __lt_erase(node, root, 1); +} + +/** + * latch_tree_find() - find the node matching @key in the trees @root + * @key: search key + * @root: trees to search for @key + * @ops: operators defining the node order + * + * Does a lockless lookup in the trees @root for the node matching @key. + * + * It is assumed that this is called while holding the appropriate RCU read + * side lock. + * + * If the operators define a partial order on the elements (there are multiple + * elements which have the same key value) it is undefined which of these + * elements will be found. Nor is it possible to iterate the tree to find + * further elements with the same key value. + * + * Returns: a pointer to the node matching @key or NULL. + */ +static __always_inline struct latch_tree_node * +latch_tree_find(void *key, struct latch_tree_root *root, + const struct latch_tree_ops *ops) +{ + struct latch_tree_node *node; + unsigned int seq; + + do { + seq = raw_read_seqcount_latch(&root->seq); + node = __lt_find(key, root, seq & 1, ops->comp); + } while (read_seqcount_retry(&root->seq, seq)); + + return node; +} + +#endif /* RB_TREE_LATCH_H */ diff --git a/kernel/include/linux/rcu_sync.h b/kernel/include/linux/rcu_sync.h new file mode 100644 index 000000000..a63a33e61 --- /dev/null +++ b/kernel/include/linux/rcu_sync.h @@ -0,0 +1,86 @@ +/* + * RCU-based infrastructure for lightweight reader-writer locking + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, you can access it online at + * http://www.gnu.org/licenses/gpl-2.0.html. + * + * Copyright (c) 2015, Red Hat, Inc. + * + * Author: Oleg Nesterov <oleg@redhat.com> + */ + +#ifndef _LINUX_RCU_SYNC_H_ +#define _LINUX_RCU_SYNC_H_ + +#include <linux/wait.h> +#include <linux/rcupdate.h> + +enum rcu_sync_type { RCU_SYNC, RCU_SCHED_SYNC, RCU_BH_SYNC }; + +/* Structure to mediate between updaters and fastpath-using readers. */ +struct rcu_sync { + int gp_state; + int gp_count; + wait_queue_head_t gp_wait; + + int cb_state; + struct rcu_head cb_head; + + enum rcu_sync_type gp_type; +}; + +extern void rcu_sync_lockdep_assert(struct rcu_sync *); + +/** + * rcu_sync_is_idle() - Are readers permitted to use their fastpaths? + * @rsp: Pointer to rcu_sync structure to use for synchronization + * + * Returns true if readers are permitted to use their fastpaths. + * Must be invoked within an RCU read-side critical section whose + * flavor matches that of the rcu_sync struture. + */ +static inline bool rcu_sync_is_idle(struct rcu_sync *rsp) +{ +#ifdef CONFIG_PROVE_RCU + rcu_sync_lockdep_assert(rsp); +#endif + return !rsp->gp_state; /* GP_IDLE */ +} + +extern void rcu_sync_init(struct rcu_sync *, enum rcu_sync_type); +extern void rcu_sync_enter(struct rcu_sync *); +extern void rcu_sync_exit(struct rcu_sync *); +extern void rcu_sync_dtor(struct rcu_sync *); + +#define __RCU_SYNC_INITIALIZER(name, type) { \ + .gp_state = 0, \ + .gp_count = 0, \ + .gp_wait = __WAIT_QUEUE_HEAD_INITIALIZER(name.gp_wait), \ + .cb_state = 0, \ + .gp_type = type, \ + } + +#define __DEFINE_RCU_SYNC(name, type) \ + struct rcu_sync_struct name = __RCU_SYNC_INITIALIZER(name, type) + +#define DEFINE_RCU_SYNC(name) \ + __DEFINE_RCU_SYNC(name, RCU_SYNC) + +#define DEFINE_RCU_SCHED_SYNC(name) \ + __DEFINE_RCU_SYNC(name, RCU_SCHED_SYNC) + +#define DEFINE_RCU_BH_SYNC(name) \ + __DEFINE_RCU_SYNC(name, RCU_BH_SYNC) + +#endif /* _LINUX_RCU_SYNC_H_ */ diff --git a/kernel/include/linux/rculist.h b/kernel/include/linux/rculist.h index a18b16f1d..5ed540986 100644 --- a/kernel/include/linux/rculist.h +++ b/kernel/include/linux/rculist.h @@ -29,8 +29,8 @@ */ static inline void INIT_LIST_HEAD_RCU(struct list_head *list) { - ACCESS_ONCE(list->next) = list; - ACCESS_ONCE(list->prev) = list; + WRITE_ONCE(list->next, list); + WRITE_ONCE(list->prev, list); } /* @@ -247,10 +247,7 @@ static inline void list_splice_init_rcu(struct list_head *list, * primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock(). */ #define list_entry_rcu(ptr, type, member) \ -({ \ - typeof(*ptr) __rcu *__ptr = (typeof(*ptr) __rcu __force *)ptr; \ - container_of((typeof(ptr))rcu_dereference_raw(__ptr), type, member); \ -}) + container_of(lockless_dereference(ptr), type, member) /** * Where are list_empty_rcu() and list_first_entry_rcu()? @@ -288,7 +285,7 @@ static inline void list_splice_init_rcu(struct list_head *list, #define list_first_or_null_rcu(ptr, type, member) \ ({ \ struct list_head *__ptr = (ptr); \ - struct list_head *__next = ACCESS_ONCE(__ptr->next); \ + struct list_head *__next = READ_ONCE(__ptr->next); \ likely(__ptr != __next) ? list_entry_rcu(__next, type, member) : NULL; \ }) @@ -549,8 +546,8 @@ static inline void hlist_add_behind_rcu(struct hlist_node *n, */ #define hlist_for_each_entry_from_rcu(pos, member) \ for (; pos; \ - pos = hlist_entry_safe(rcu_dereference((pos)->member.next),\ - typeof(*(pos)), member)) + pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu( \ + &(pos)->member)), typeof(*(pos)), member)) #endif /* __KERNEL__ */ #endif diff --git a/kernel/include/linux/rcupdate.h b/kernel/include/linux/rcupdate.h index 5d090cdaa..c2f5f9551 100644 --- a/kernel/include/linux/rcupdate.h +++ b/kernel/include/linux/rcupdate.h @@ -44,6 +44,8 @@ #include <linux/debugobjects.h> #include <linux/bug.h> #include <linux/compiler.h> +#include <linux/ktime.h> + #include <asm/barrier.h> extern int rcu_expedited; /* for sysctl */ @@ -158,7 +160,7 @@ void do_trace_rcu_torture_read(const char *rcutorturename, * more than one CPU). */ void call_rcu(struct rcu_head *head, - void (*func)(struct rcu_head *head)); + rcu_callback_t func); #else /* #ifdef CONFIG_PREEMPT_RCU */ @@ -192,7 +194,7 @@ void call_rcu(struct rcu_head *head, * memory ordering guarantees. */ void call_rcu_bh(struct rcu_head *head, - void (*func)(struct rcu_head *head)); + rcu_callback_t func); #endif /** @@ -215,7 +217,7 @@ void call_rcu_bh(struct rcu_head *head, * memory ordering guarantees. */ void call_rcu_sched(struct rcu_head *head, - void (*func)(struct rcu_head *rcu)); + rcu_callback_t func); void synchronize_sched(void); @@ -228,6 +230,36 @@ struct rcu_synchronize { }; void wakeme_after_rcu(struct rcu_head *head); +void __wait_rcu_gp(bool checktiny, int n, call_rcu_func_t *crcu_array, + struct rcu_synchronize *rs_array); + +#define _wait_rcu_gp(checktiny, ...) \ +do { \ + call_rcu_func_t __crcu_array[] = { __VA_ARGS__ }; \ + struct rcu_synchronize __rs_array[ARRAY_SIZE(__crcu_array)]; \ + __wait_rcu_gp(checktiny, ARRAY_SIZE(__crcu_array), \ + __crcu_array, __rs_array); \ +} while (0) + +#define wait_rcu_gp(...) _wait_rcu_gp(false, __VA_ARGS__) + +/** + * synchronize_rcu_mult - Wait concurrently for multiple grace periods + * @...: List of call_rcu() functions for the flavors to wait on. + * + * This macro waits concurrently for multiple flavors of RCU grace periods. + * For example, synchronize_rcu_mult(call_rcu, call_rcu_bh) would wait + * on concurrent RCU and RCU-bh grace periods. Waiting on a give SRCU + * domain requires you to write a wrapper function for that SRCU domain's + * call_srcu() function, supplying the corresponding srcu_struct. + * + * If Tiny RCU, tell _wait_rcu_gp() not to bother waiting for RCU + * or RCU-bh, given that anywhere synchronize_rcu_mult() can be called + * is automatically a grace period. + */ +#define synchronize_rcu_mult(...) \ + _wait_rcu_gp(IS_ENABLED(CONFIG_TINY_RCU), __VA_ARGS__) + /** * call_rcu_tasks() - Queue an RCU for invocation task-based grace period * @head: structure to be used for queueing the RCU updates. @@ -246,7 +278,7 @@ void wakeme_after_rcu(struct rcu_head *head); * See the description of call_rcu() for more detailed information on * memory ordering guarantees. */ -void call_rcu_tasks(struct rcu_head *head, void (*func)(struct rcu_head *head)); +void call_rcu_tasks(struct rcu_head *head, rcu_callback_t func); void synchronize_rcu_tasks(void); void rcu_barrier_tasks(void); @@ -274,12 +306,14 @@ static inline int sched_rcu_preempt_depth(void) { return 0; } static inline void __rcu_read_lock(void) { - preempt_disable(); + if (IS_ENABLED(CONFIG_PREEMPT_COUNT)) + preempt_disable(); } static inline void __rcu_read_unlock(void) { - preempt_enable(); + if (IS_ENABLED(CONFIG_PREEMPT_COUNT)) + preempt_enable(); } static inline void synchronize_rcu(void) @@ -303,10 +337,6 @@ void rcu_sched_qs(void); void rcu_bh_qs(void); void rcu_check_callbacks(int user); struct notifier_block; -void rcu_idle_enter(void); -void rcu_idle_exit(void); -void rcu_irq_enter(void); -void rcu_irq_exit(void); int rcu_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu); @@ -322,7 +352,7 @@ static inline void rcu_sysrq_end(void) } #endif /* #else #ifdef CONFIG_RCU_STALL_COMMON */ -#ifdef CONFIG_RCU_USER_QS +#ifdef CONFIG_NO_HZ_FULL void rcu_user_enter(void); void rcu_user_exit(void); #else @@ -330,7 +360,7 @@ static inline void rcu_user_enter(void) { } static inline void rcu_user_exit(void) { } static inline void rcu_user_hooks_switch(struct task_struct *prev, struct task_struct *next) { } -#endif /* CONFIG_RCU_USER_QS */ +#endif /* CONFIG_NO_HZ_FULL */ #ifdef CONFIG_RCU_NOCB_CPU void rcu_init_nohz(void); @@ -375,8 +405,8 @@ extern struct srcu_struct tasks_rcu_exit_srcu; #define rcu_note_voluntary_context_switch(t) \ do { \ rcu_all_qs(); \ - if (ACCESS_ONCE((t)->rcu_tasks_holdout)) \ - ACCESS_ONCE((t)->rcu_tasks_holdout) = false; \ + if (READ_ONCE((t)->rcu_tasks_holdout)) \ + WRITE_ONCE((t)->rcu_tasks_holdout, false); \ } while (0) #else /* #ifdef CONFIG_TASKS_RCU */ #define TASKS_RCU(x) do { } while (0) @@ -405,10 +435,6 @@ bool __rcu_is_watching(void); * TREE_RCU and rcu_barrier_() primitives in TINY_RCU. */ -typedef void call_rcu_func_t(struct rcu_head *head, - void (*func)(struct rcu_head *head)); -void wait_rcu_gp(call_rcu_func_t crf); - #if defined(CONFIG_TREE_RCU) || defined(CONFIG_PREEMPT_RCU) #include <linux/rcutree.h> #elif defined(CONFIG_TINY_RCU) @@ -489,46 +515,10 @@ int rcu_read_lock_bh_held(void); * If CONFIG_DEBUG_LOCK_ALLOC is selected, returns nonzero iff in an * RCU-sched read-side critical section. In absence of * CONFIG_DEBUG_LOCK_ALLOC, this assumes we are in an RCU-sched read-side - * critical section unless it can prove otherwise. Note that disabling - * of preemption (including disabling irqs) counts as an RCU-sched - * read-side critical section. This is useful for debug checks in functions - * that required that they be called within an RCU-sched read-side - * critical section. - * - * Check debug_lockdep_rcu_enabled() to prevent false positives during boot - * and while lockdep is disabled. - * - * Note that if the CPU is in the idle loop from an RCU point of - * view (ie: that we are in the section between rcu_idle_enter() and - * rcu_idle_exit()) then rcu_read_lock_held() returns false even if the CPU - * did an rcu_read_lock(). The reason for this is that RCU ignores CPUs - * that are in such a section, considering these as in extended quiescent - * state, so such a CPU is effectively never in an RCU read-side critical - * section regardless of what RCU primitives it invokes. This state of - * affairs is required --- we need to keep an RCU-free window in idle - * where the CPU may possibly enter into low power mode. This way we can - * notice an extended quiescent state to other CPUs that started a grace - * period. Otherwise we would delay any grace period as long as we run in - * the idle task. - * - * Similarly, we avoid claiming an SRCU read lock held if the current - * CPU is offline. + * critical section unless it can prove otherwise. */ #ifdef CONFIG_PREEMPT_COUNT -static inline int rcu_read_lock_sched_held(void) -{ - int lockdep_opinion = 0; - - if (!debug_lockdep_rcu_enabled()) - return 1; - if (!rcu_is_watching()) - return 0; - if (!rcu_lockdep_current_cpu_online()) - return 0; - if (debug_locks) - lockdep_opinion = lock_is_held(&rcu_sched_lock_map); - return lockdep_opinion || preempt_count() != 0 || irqs_disabled(); -} +int rcu_read_lock_sched_held(void); #else /* #ifdef CONFIG_PREEMPT_COUNT */ static inline int rcu_read_lock_sched_held(void) { @@ -568,14 +558,14 @@ static inline int rcu_read_lock_sched_held(void) #ifdef CONFIG_PROVE_RCU /** - * rcu_lockdep_assert - emit lockdep splat if specified condition not met + * RCU_LOCKDEP_WARN - emit lockdep splat if specified condition is met * @c: condition to check * @s: informative message */ -#define rcu_lockdep_assert(c, s) \ +#define RCU_LOCKDEP_WARN(c, s) \ do { \ static bool __section(.data.unlikely) __warned; \ - if (debug_lockdep_rcu_enabled() && !__warned && !(c)) { \ + if (debug_lockdep_rcu_enabled() && !__warned && (c)) { \ __warned = true; \ lockdep_rcu_suspicious(__FILE__, __LINE__, s); \ } \ @@ -584,8 +574,8 @@ static inline int rcu_read_lock_sched_held(void) #if defined(CONFIG_PROVE_RCU) && !defined(CONFIG_PREEMPT_RCU) static inline void rcu_preempt_sleep_check(void) { - rcu_lockdep_assert(!lock_is_held(&rcu_lock_map), - "Illegal context switch in RCU read-side critical section"); + RCU_LOCKDEP_WARN(lock_is_held(&rcu_lock_map), + "Illegal context switch in RCU read-side critical section"); } #else /* #ifdef CONFIG_PROVE_RCU */ static inline void rcu_preempt_sleep_check(void) @@ -596,15 +586,15 @@ static inline void rcu_preempt_sleep_check(void) #define rcu_sleep_check() \ do { \ rcu_preempt_sleep_check(); \ - rcu_lockdep_assert(!lock_is_held(&rcu_bh_lock_map), \ - "Illegal context switch in RCU-bh read-side critical section"); \ - rcu_lockdep_assert(!lock_is_held(&rcu_sched_lock_map), \ - "Illegal context switch in RCU-sched read-side critical section"); \ + RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map), \ + "Illegal context switch in RCU-bh read-side critical section"); \ + RCU_LOCKDEP_WARN(lock_is_held(&rcu_sched_lock_map), \ + "Illegal context switch in RCU-sched read-side critical section"); \ } while (0) #else /* #ifdef CONFIG_PROVE_RCU */ -#define rcu_lockdep_assert(c, s) do { } while (0) +#define RCU_LOCKDEP_WARN(c, s) do { } while (0) #define rcu_sleep_check() do { } while (0) #endif /* #else #ifdef CONFIG_PROVE_RCU */ @@ -627,7 +617,7 @@ static inline void rcu_preempt_sleep_check(void) #define __rcu_access_pointer(p, space) \ ({ \ - typeof(*p) *_________p1 = (typeof(*p) *__force)ACCESS_ONCE(p); \ + typeof(*p) *_________p1 = (typeof(*p) *__force)READ_ONCE(p); \ rcu_dereference_sparse(p, space); \ ((typeof(*p) __force __kernel *)(_________p1)); \ }) @@ -635,32 +625,17 @@ static inline void rcu_preempt_sleep_check(void) ({ \ /* Dependency order vs. p above. */ \ typeof(*p) *________p1 = (typeof(*p) *__force)lockless_dereference(p); \ - rcu_lockdep_assert(c, "suspicious rcu_dereference_check() usage"); \ + RCU_LOCKDEP_WARN(!(c), "suspicious rcu_dereference_check() usage"); \ rcu_dereference_sparse(p, space); \ ((typeof(*p) __force __kernel *)(________p1)); \ }) #define __rcu_dereference_protected(p, c, space) \ ({ \ - rcu_lockdep_assert(c, "suspicious rcu_dereference_protected() usage"); \ + RCU_LOCKDEP_WARN(!(c), "suspicious rcu_dereference_protected() usage"); \ rcu_dereference_sparse(p, space); \ ((typeof(*p) __force __kernel *)(p)); \ }) -#define __rcu_access_index(p, space) \ -({ \ - typeof(p) _________p1 = ACCESS_ONCE(p); \ - rcu_dereference_sparse(p, space); \ - (_________p1); \ -}) -#define __rcu_dereference_index_check(p, c) \ -({ \ - /* Dependency order vs. p above. */ \ - typeof(p) _________p1 = lockless_dereference(p); \ - rcu_lockdep_assert(c, \ - "suspicious rcu_dereference_index_check() usage"); \ - (_________p1); \ -}) - /** * RCU_INITIALIZER() - statically initialize an RCU-protected global variable * @v: The value to statically initialize with. @@ -668,21 +643,6 @@ static inline void rcu_preempt_sleep_check(void) #define RCU_INITIALIZER(v) (typeof(*(v)) __force __rcu *)(v) /** - * lockless_dereference() - safely load a pointer for later dereference - * @p: The pointer to load - * - * Similar to rcu_dereference(), but for situations where the pointed-to - * object's lifetime is managed by something other than RCU. That - * "something other" might be reference counting or simple immortality. - */ -#define lockless_dereference(p) \ -({ \ - typeof(p) _________p1 = ACCESS_ONCE(p); \ - smp_read_barrier_depends(); /* Dependency order vs. p above. */ \ - (_________p1); \ -}) - -/** * rcu_assign_pointer() - assign to RCU-protected pointer * @p: pointer to assign to * @v: value to assign (publish) @@ -720,7 +680,7 @@ static inline void rcu_preempt_sleep_check(void) * @p: The pointer to read * * Return the value of the specified RCU-protected pointer, but omit the - * smp_read_barrier_depends() and keep the ACCESS_ONCE(). This is useful + * smp_read_barrier_depends() and keep the READ_ONCE(). This is useful * when the value of this pointer is accessed, but the pointer is not * dereferenced, for example, when testing an RCU-protected pointer against * NULL. Although rcu_access_pointer() may also be used in cases where @@ -805,47 +765,12 @@ static inline void rcu_preempt_sleep_check(void) #define rcu_dereference_raw_notrace(p) __rcu_dereference_check((p), 1, __rcu) /** - * rcu_access_index() - fetch RCU index with no dereferencing - * @p: The index to read - * - * Return the value of the specified RCU-protected index, but omit the - * smp_read_barrier_depends() and keep the ACCESS_ONCE(). This is useful - * when the value of this index is accessed, but the index is not - * dereferenced, for example, when testing an RCU-protected index against - * -1. Although rcu_access_index() may also be used in cases where - * update-side locks prevent the value of the index from changing, you - * should instead use rcu_dereference_index_protected() for this use case. - */ -#define rcu_access_index(p) __rcu_access_index((p), __rcu) - -/** - * rcu_dereference_index_check() - rcu_dereference for indices with debug checking - * @p: The pointer to read, prior to dereferencing - * @c: The conditions under which the dereference will take place - * - * Similar to rcu_dereference_check(), but omits the sparse checking. - * This allows rcu_dereference_index_check() to be used on integers, - * which can then be used as array indices. Attempting to use - * rcu_dereference_check() on an integer will give compiler warnings - * because the sparse address-space mechanism relies on dereferencing - * the RCU-protected pointer. Dereferencing integers is not something - * that even gcc will put up with. - * - * Note that this function does not implicitly check for RCU read-side - * critical sections. If this function gains lots of uses, it might - * make sense to provide versions for each flavor of RCU, but it does - * not make sense as of early 2010. - */ -#define rcu_dereference_index_check(p, c) \ - __rcu_dereference_index_check((p), (c)) - -/** * rcu_dereference_protected() - fetch RCU pointer when updates prevented * @p: The pointer to read, prior to dereferencing * @c: The conditions under which the dereference will take place * * Return the value of the specified RCU-protected pointer, but omit - * both the smp_read_barrier_depends() and the ACCESS_ONCE(). This + * both the smp_read_barrier_depends() and the READ_ONCE(). This * is useful in cases where update-side locks prevent the value of the * pointer from changing. Please note that this primitive does -not- * prevent the compiler from repeating this reference or combining it @@ -885,6 +810,28 @@ static inline void rcu_preempt_sleep_check(void) #define rcu_dereference_sched(p) rcu_dereference_sched_check(p, 0) /** + * rcu_pointer_handoff() - Hand off a pointer from RCU to other mechanism + * @p: The pointer to hand off + * + * This is simply an identity function, but it documents where a pointer + * is handed off from RCU to some other synchronization mechanism, for + * example, reference counting or locking. In C11, it would map to + * kill_dependency(). It could be used as follows: + * + * rcu_read_lock(); + * p = rcu_dereference(gp); + * long_lived = is_long_lived(p); + * if (long_lived) { + * if (!atomic_inc_not_zero(p->refcnt)) + * long_lived = false; + * else + * p = rcu_pointer_handoff(p); + * } + * rcu_read_unlock(); + */ +#define rcu_pointer_handoff(p) (p) + +/** * rcu_read_lock() - mark the beginning of an RCU read-side critical section * * When synchronize_rcu() is invoked on one CPU while other CPUs @@ -930,8 +877,8 @@ static inline void rcu_read_lock(void) __rcu_read_lock(); __acquire(RCU); rcu_lock_acquire(&rcu_lock_map); - rcu_lockdep_assert(rcu_is_watching(), - "rcu_read_lock() used illegally while idle"); + RCU_LOCKDEP_WARN(!rcu_is_watching(), + "rcu_read_lock() used illegally while idle"); } /* @@ -981,8 +928,8 @@ static inline void rcu_read_lock(void) */ static inline void rcu_read_unlock(void) { - rcu_lockdep_assert(rcu_is_watching(), - "rcu_read_unlock() used illegally while idle"); + RCU_LOCKDEP_WARN(!rcu_is_watching(), + "rcu_read_unlock() used illegally while idle"); __release(RCU); __rcu_read_unlock(); rcu_lock_release(&rcu_lock_map); /* Keep acq info for rls diags. */ @@ -1013,8 +960,8 @@ static inline void rcu_read_lock_bh(void) #else __acquire(RCU_BH); rcu_lock_acquire(&rcu_bh_lock_map); - rcu_lockdep_assert(rcu_is_watching(), - "rcu_read_lock_bh() used illegally while idle"); + RCU_LOCKDEP_WARN(!rcu_is_watching(), + "rcu_read_lock_bh() used illegally while idle"); #endif } @@ -1028,8 +975,8 @@ static inline void rcu_read_unlock_bh(void) #ifdef CONFIG_PREEMPT_RT_FULL rcu_read_unlock(); #else - rcu_lockdep_assert(rcu_is_watching(), - "rcu_read_unlock_bh() used illegally while idle"); + RCU_LOCKDEP_WARN(!rcu_is_watching(), + "rcu_read_unlock_bh() used illegally while idle"); rcu_lock_release(&rcu_bh_lock_map); __release(RCU_BH); #endif @@ -1054,8 +1001,8 @@ static inline void rcu_read_lock_sched(void) preempt_disable(); __acquire(RCU_SCHED); rcu_lock_acquire(&rcu_sched_lock_map); - rcu_lockdep_assert(rcu_is_watching(), - "rcu_read_lock_sched() used illegally while idle"); + RCU_LOCKDEP_WARN(!rcu_is_watching(), + "rcu_read_lock_sched() used illegally while idle"); } /* Used by lockdep and tracing: cannot be traced, cannot call lockdep. */ @@ -1072,8 +1019,8 @@ static inline notrace void rcu_read_lock_sched_notrace(void) */ static inline void rcu_read_unlock_sched(void) { - rcu_lockdep_assert(rcu_is_watching(), - "rcu_read_unlock_sched() used illegally while idle"); + RCU_LOCKDEP_WARN(!rcu_is_watching(), + "rcu_read_unlock_sched() used illegally while idle"); rcu_lock_release(&rcu_sched_lock_map); __release(RCU_SCHED); preempt_enable(); @@ -1124,7 +1071,7 @@ static inline notrace void rcu_read_unlock_sched_notrace(void) #define RCU_INIT_POINTER(p, v) \ do { \ rcu_dereference_sparse(p, __rcu); \ - p = RCU_INITIALIZER(v); \ + WRITE_ONCE(p, RCU_INITIALIZER(v)); \ } while (0) /** @@ -1147,7 +1094,7 @@ static inline notrace void rcu_read_unlock_sched_notrace(void) #define __kfree_rcu(head, offset) \ do { \ BUILD_BUG_ON(!__is_kfree_rcu_offset(offset)); \ - kfree_call_rcu(head, (void (*)(struct rcu_head *))(unsigned long)(offset)); \ + kfree_call_rcu(head, (rcu_callback_t)(unsigned long)(offset)); \ } while (0) /** @@ -1179,13 +1126,13 @@ static inline notrace void rcu_read_unlock_sched_notrace(void) #define kfree_rcu(ptr, rcu_head) \ __kfree_rcu(&((ptr)->rcu_head), offsetof(typeof(*(ptr)), rcu_head)) -#if defined(CONFIG_TINY_RCU) || defined(CONFIG_RCU_NOCB_CPU_ALL) -static inline int rcu_needs_cpu(unsigned long *delta_jiffies) +#ifdef CONFIG_TINY_RCU +static inline int rcu_needs_cpu(u64 basemono, u64 *nextevt) { - *delta_jiffies = ULONG_MAX; + *nextevt = KTIME_MAX; return 0; } -#endif /* #if defined(CONFIG_TINY_RCU) || defined(CONFIG_RCU_NOCB_CPU_ALL) */ +#endif /* #ifdef CONFIG_TINY_RCU */ #if defined(CONFIG_RCU_NOCB_CPU_ALL) static inline bool rcu_is_nocb_cpu(int cpu) { return true; } diff --git a/kernel/include/linux/rcutiny.h b/kernel/include/linux/rcutiny.h index 937edaeb1..4c1aaf9cc 100644 --- a/kernel/include/linux/rcutiny.h +++ b/kernel/include/linux/rcutiny.h @@ -37,6 +37,16 @@ static inline void cond_synchronize_rcu(unsigned long oldstate) might_sleep(); } +static inline unsigned long get_state_synchronize_sched(void) +{ + return 0; +} + +static inline void cond_synchronize_sched(unsigned long oldstate) +{ + might_sleep(); +} + static inline void rcu_barrier_bh(void) { wait_rcu_gp(call_rcu_bh); @@ -73,7 +83,7 @@ static inline void synchronize_sched_expedited(void) } static inline void kfree_call_rcu(struct rcu_head *head, - void (*func)(struct rcu_head *rcu)) + rcu_callback_t func) { call_rcu(head, func); } @@ -159,6 +169,22 @@ static inline void rcu_cpu_stall_reset(void) { } +static inline void rcu_idle_enter(void) +{ +} + +static inline void rcu_idle_exit(void) +{ +} + +static inline void rcu_irq_enter(void) +{ +} + +static inline void rcu_irq_exit(void) +{ +} + static inline void exit_rcu(void) { } @@ -190,6 +216,7 @@ static inline bool rcu_is_watching(void) static inline void rcu_all_qs(void) { + barrier(); /* Avoid RCU read-side critical sections leaking across. */ } #endif /* __LINUX_RCUTINY_H */ diff --git a/kernel/include/linux/rcutree.h b/kernel/include/linux/rcutree.h index 0b350893b..436c9e62b 100644 --- a/kernel/include/linux/rcutree.h +++ b/kernel/include/linux/rcutree.h @@ -31,9 +31,7 @@ #define __LINUX_RCUTREE_H void rcu_note_context_switch(void); -#ifndef CONFIG_RCU_NOCB_CPU_ALL -int rcu_needs_cpu(unsigned long *delta_jiffies); -#endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */ +int rcu_needs_cpu(u64 basem, u64 *nextevt); void rcu_cpu_stall_reset(void); /* @@ -54,7 +52,7 @@ void synchronize_rcu_bh(void); void synchronize_sched_expedited(void); void synchronize_rcu_expedited(void); -void kfree_call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu)); +void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func); /** * synchronize_rcu_bh_expedited - Brute-force RCU-bh grace period @@ -86,6 +84,8 @@ void rcu_barrier_bh(void); void rcu_barrier_sched(void); unsigned long get_state_synchronize_rcu(void); void cond_synchronize_rcu(unsigned long oldstate); +unsigned long get_state_synchronize_sched(void); +void cond_synchronize_sched(unsigned long oldstate); extern unsigned long rcutorture_testseq; extern unsigned long rcutorture_vernum; @@ -99,6 +99,11 @@ void show_rcu_gp_kthreads(void); void rcu_force_quiescent_state(void); void rcu_sched_force_quiescent_state(void); +void rcu_idle_enter(void); +void rcu_idle_exit(void); +void rcu_irq_enter(void); +void rcu_irq_exit(void); + void exit_rcu(void); void rcu_scheduler_starting(void); diff --git a/kernel/include/linux/regmap.h b/kernel/include/linux/regmap.h index 116655d92..d68bb4021 100644 --- a/kernel/include/linux/regmap.h +++ b/kernel/include/linux/regmap.h @@ -17,6 +17,7 @@ #include <linux/rbtree.h> #include <linux/err.h> #include <linux/bug.h> +#include <linux/lockdep.h> struct module; struct device; @@ -50,6 +51,20 @@ struct reg_default { unsigned int def; }; +/** + * Register/value pairs for sequences of writes with an optional delay in + * microseconds to be applied after each write. + * + * @reg: Register address. + * @def: Register value. + * @delay_us: Delay to be applied after the register write in microseconds + */ +struct reg_sequence { + unsigned int reg; + unsigned int def; + unsigned int delay_us; +}; + #ifdef CONFIG_REGMAP enum regmap_endian { @@ -281,6 +296,8 @@ typedef int (*regmap_hw_reg_read)(void *context, unsigned int reg, unsigned int *val); typedef int (*regmap_hw_reg_write)(void *context, unsigned int reg, unsigned int val); +typedef int (*regmap_hw_reg_update_bits)(void *context, unsigned int reg, + unsigned int mask, unsigned int val); typedef struct regmap_async *(*regmap_hw_async_alloc)(void); typedef void (*regmap_hw_free_context)(void *context); @@ -296,8 +313,12 @@ typedef void (*regmap_hw_free_context)(void *context); * if not implemented on a given device. * @async_write: Write operation which completes asynchronously, optional and * must serialise with respect to non-async I/O. + * @reg_write: Write a single register value to the given register address. This + * write operation has to complete when returning from the function. * @read: Read operation. Data is returned in the buffer used to transmit * data. + * @reg_read: Read a single register value from a given register address. + * @free_context: Free context. * @async_alloc: Allocate a regmap_async() structure. * @read_flag_mask: Mask to be set in the top byte of the register when doing * a read. @@ -307,7 +328,8 @@ typedef void (*regmap_hw_free_context)(void *context); * @val_format_endian_default: Default endianness for formatted register * values. Used when the regmap_config specifies DEFAULT. If this is * DEFAULT, BIG is assumed. - * @async_size: Size of struct used for async work. + * @max_raw_read: Max raw read size that can be used on the bus. + * @max_raw_write: Max raw write size that can be used on the bus. */ struct regmap_bus { bool fast_io; @@ -315,6 +337,7 @@ struct regmap_bus { regmap_hw_gather_write gather_write; regmap_hw_async_write async_write; regmap_hw_reg_write reg_write; + regmap_hw_reg_update_bits reg_update_bits; regmap_hw_read read; regmap_hw_reg_read reg_read; regmap_hw_free_context free_context; @@ -322,47 +345,186 @@ struct regmap_bus { u8 read_flag_mask; enum regmap_endian reg_format_endian_default; enum regmap_endian val_format_endian_default; + size_t max_raw_read; + size_t max_raw_write; }; -struct regmap *regmap_init(struct device *dev, - const struct regmap_bus *bus, - void *bus_context, - const struct regmap_config *config); +/* + * __regmap_init functions. + * + * These functions take a lock key and name parameter, and should not be called + * directly. Instead, use the regmap_init macros that generate a key and name + * for each call. + */ +struct regmap *__regmap_init(struct device *dev, + const struct regmap_bus *bus, + void *bus_context, + const struct regmap_config *config, + struct lock_class_key *lock_key, + const char *lock_name); +struct regmap *__regmap_init_i2c(struct i2c_client *i2c, + const struct regmap_config *config, + struct lock_class_key *lock_key, + const char *lock_name); +struct regmap *__regmap_init_spi(struct spi_device *dev, + const struct regmap_config *config, + struct lock_class_key *lock_key, + const char *lock_name); +struct regmap *__regmap_init_spmi_base(struct spmi_device *dev, + const struct regmap_config *config, + struct lock_class_key *lock_key, + const char *lock_name); +struct regmap *__regmap_init_spmi_ext(struct spmi_device *dev, + const struct regmap_config *config, + struct lock_class_key *lock_key, + const char *lock_name); +struct regmap *__regmap_init_mmio_clk(struct device *dev, const char *clk_id, + void __iomem *regs, + const struct regmap_config *config, + struct lock_class_key *lock_key, + const char *lock_name); +struct regmap *__regmap_init_ac97(struct snd_ac97 *ac97, + const struct regmap_config *config, + struct lock_class_key *lock_key, + const char *lock_name); + +struct regmap *__devm_regmap_init(struct device *dev, + const struct regmap_bus *bus, + void *bus_context, + const struct regmap_config *config, + struct lock_class_key *lock_key, + const char *lock_name); +struct regmap *__devm_regmap_init_i2c(struct i2c_client *i2c, + const struct regmap_config *config, + struct lock_class_key *lock_key, + const char *lock_name); +struct regmap *__devm_regmap_init_spi(struct spi_device *dev, + const struct regmap_config *config, + struct lock_class_key *lock_key, + const char *lock_name); +struct regmap *__devm_regmap_init_spmi_base(struct spmi_device *dev, + const struct regmap_config *config, + struct lock_class_key *lock_key, + const char *lock_name); +struct regmap *__devm_regmap_init_spmi_ext(struct spmi_device *dev, + const struct regmap_config *config, + struct lock_class_key *lock_key, + const char *lock_name); +struct regmap *__devm_regmap_init_mmio_clk(struct device *dev, + const char *clk_id, + void __iomem *regs, + const struct regmap_config *config, + struct lock_class_key *lock_key, + const char *lock_name); +struct regmap *__devm_regmap_init_ac97(struct snd_ac97 *ac97, + const struct regmap_config *config, + struct lock_class_key *lock_key, + const char *lock_name); + +/* + * Wrapper for regmap_init macros to include a unique lockdep key and name + * for each call. No-op if CONFIG_LOCKDEP is not set. + * + * @fn: Real function to call (in the form __[*_]regmap_init[_*]) + * @name: Config variable name (#config in the calling macro) + **/ +#ifdef CONFIG_LOCKDEP +#define __regmap_lockdep_wrapper(fn, name, ...) \ +( \ + ({ \ + static struct lock_class_key _key; \ + fn(__VA_ARGS__, &_key, \ + KBUILD_BASENAME ":" \ + __stringify(__LINE__) ":" \ + "(" name ")->lock"); \ + }) \ +) +#else +#define __regmap_lockdep_wrapper(fn, name, ...) fn(__VA_ARGS__, NULL, NULL) +#endif + +/** + * regmap_init(): Initialise register map + * + * @dev: Device that will be interacted with + * @bus: Bus-specific callbacks to use with device + * @bus_context: Data passed to bus-specific callbacks + * @config: Configuration for register map + * + * The return value will be an ERR_PTR() on error or a valid pointer to + * a struct regmap. This function should generally not be called + * directly, it should be called by bus-specific init functions. + */ +#define regmap_init(dev, bus, bus_context, config) \ + __regmap_lockdep_wrapper(__regmap_init, #config, \ + dev, bus, bus_context, config) int regmap_attach_dev(struct device *dev, struct regmap *map, - const struct regmap_config *config); -struct regmap *regmap_init_i2c(struct i2c_client *i2c, - const struct regmap_config *config); -struct regmap *regmap_init_spi(struct spi_device *dev, - const struct regmap_config *config); -struct regmap *regmap_init_spmi_base(struct spmi_device *dev, - const struct regmap_config *config); -struct regmap *regmap_init_spmi_ext(struct spmi_device *dev, - const struct regmap_config *config); -struct regmap *regmap_init_mmio_clk(struct device *dev, const char *clk_id, - void __iomem *regs, - const struct regmap_config *config); -struct regmap *regmap_init_ac97(struct snd_ac97 *ac97, - const struct regmap_config *config); - -struct regmap *devm_regmap_init(struct device *dev, - const struct regmap_bus *bus, - void *bus_context, - const struct regmap_config *config); -struct regmap *devm_regmap_init_i2c(struct i2c_client *i2c, - const struct regmap_config *config); -struct regmap *devm_regmap_init_spi(struct spi_device *dev, - const struct regmap_config *config); -struct regmap *devm_regmap_init_spmi_base(struct spmi_device *dev, - const struct regmap_config *config); -struct regmap *devm_regmap_init_spmi_ext(struct spmi_device *dev, - const struct regmap_config *config); -struct regmap *devm_regmap_init_mmio_clk(struct device *dev, const char *clk_id, - void __iomem *regs, - const struct regmap_config *config); -struct regmap *devm_regmap_init_ac97(struct snd_ac97 *ac97, - const struct regmap_config *config); + const struct regmap_config *config); -bool regmap_ac97_default_volatile(struct device *dev, unsigned int reg); +/** + * regmap_init_i2c(): Initialise register map + * + * @i2c: Device that will be interacted with + * @config: Configuration for register map + * + * The return value will be an ERR_PTR() on error or a valid pointer to + * a struct regmap. + */ +#define regmap_init_i2c(i2c, config) \ + __regmap_lockdep_wrapper(__regmap_init_i2c, #config, \ + i2c, config) + +/** + * regmap_init_spi(): Initialise register map + * + * @spi: Device that will be interacted with + * @config: Configuration for register map + * + * The return value will be an ERR_PTR() on error or a valid pointer to + * a struct regmap. + */ +#define regmap_init_spi(dev, config) \ + __regmap_lockdep_wrapper(__regmap_init_spi, #config, \ + dev, config) + +/** + * regmap_init_spmi_base(): Create regmap for the Base register space + * @sdev: SPMI device that will be interacted with + * @config: Configuration for register map + * + * The return value will be an ERR_PTR() on error or a valid pointer to + * a struct regmap. + */ +#define regmap_init_spmi_base(dev, config) \ + __regmap_lockdep_wrapper(__regmap_init_spmi_base, #config, \ + dev, config) + +/** + * regmap_init_spmi_ext(): Create regmap for Ext register space + * @sdev: Device that will be interacted with + * @config: Configuration for register map + * + * The return value will be an ERR_PTR() on error or a valid pointer to + * a struct regmap. + */ +#define regmap_init_spmi_ext(dev, config) \ + __regmap_lockdep_wrapper(__regmap_init_spmi_ext, #config, \ + dev, config) + +/** + * regmap_init_mmio_clk(): Initialise register map with register clock + * + * @dev: Device that will be interacted with + * @clk_id: register clock consumer ID + * @regs: Pointer to memory-mapped IO region + * @config: Configuration for register map + * + * The return value will be an ERR_PTR() on error or a valid pointer to + * a struct regmap. + */ +#define regmap_init_mmio_clk(dev, clk_id, regs, config) \ + __regmap_lockdep_wrapper(__regmap_init_mmio_clk, #config, \ + dev, clk_id, regs, config) /** * regmap_init_mmio(): Initialise register map @@ -374,12 +536,109 @@ bool regmap_ac97_default_volatile(struct device *dev, unsigned int reg); * The return value will be an ERR_PTR() on error or a valid pointer to * a struct regmap. */ -static inline struct regmap *regmap_init_mmio(struct device *dev, - void __iomem *regs, - const struct regmap_config *config) -{ - return regmap_init_mmio_clk(dev, NULL, regs, config); -} +#define regmap_init_mmio(dev, regs, config) \ + regmap_init_mmio_clk(dev, NULL, regs, config) + +/** + * regmap_init_ac97(): Initialise AC'97 register map + * + * @ac97: Device that will be interacted with + * @config: Configuration for register map + * + * The return value will be an ERR_PTR() on error or a valid pointer to + * a struct regmap. + */ +#define regmap_init_ac97(ac97, config) \ + __regmap_lockdep_wrapper(__regmap_init_ac97, #config, \ + ac97, config) +bool regmap_ac97_default_volatile(struct device *dev, unsigned int reg); + +/** + * devm_regmap_init(): Initialise managed register map + * + * @dev: Device that will be interacted with + * @bus: Bus-specific callbacks to use with device + * @bus_context: Data passed to bus-specific callbacks + * @config: Configuration for register map + * + * The return value will be an ERR_PTR() on error or a valid pointer + * to a struct regmap. This function should generally not be called + * directly, it should be called by bus-specific init functions. The + * map will be automatically freed by the device management code. + */ +#define devm_regmap_init(dev, bus, bus_context, config) \ + __regmap_lockdep_wrapper(__devm_regmap_init, #config, \ + dev, bus, bus_context, config) + +/** + * devm_regmap_init_i2c(): Initialise managed register map + * + * @i2c: Device that will be interacted with + * @config: Configuration for register map + * + * The return value will be an ERR_PTR() on error or a valid pointer + * to a struct regmap. The regmap will be automatically freed by the + * device management code. + */ +#define devm_regmap_init_i2c(i2c, config) \ + __regmap_lockdep_wrapper(__devm_regmap_init_i2c, #config, \ + i2c, config) + +/** + * devm_regmap_init_spi(): Initialise register map + * + * @spi: Device that will be interacted with + * @config: Configuration for register map + * + * The return value will be an ERR_PTR() on error or a valid pointer + * to a struct regmap. The map will be automatically freed by the + * device management code. + */ +#define devm_regmap_init_spi(dev, config) \ + __regmap_lockdep_wrapper(__devm_regmap_init_spi, #config, \ + dev, config) + +/** + * devm_regmap_init_spmi_base(): Create managed regmap for Base register space + * @sdev: SPMI device that will be interacted with + * @config: Configuration for register map + * + * The return value will be an ERR_PTR() on error or a valid pointer + * to a struct regmap. The regmap will be automatically freed by the + * device management code. + */ +#define devm_regmap_init_spmi_base(dev, config) \ + __regmap_lockdep_wrapper(__devm_regmap_init_spmi_base, #config, \ + dev, config) + +/** + * devm_regmap_init_spmi_ext(): Create managed regmap for Ext register space + * @sdev: SPMI device that will be interacted with + * @config: Configuration for register map + * + * The return value will be an ERR_PTR() on error or a valid pointer + * to a struct regmap. The regmap will be automatically freed by the + * device management code. + */ +#define devm_regmap_init_spmi_ext(dev, config) \ + __regmap_lockdep_wrapper(__devm_regmap_init_spmi_ext, #config, \ + dev, config) + +/** + * devm_regmap_init_mmio_clk(): Initialise managed register map with clock + * + * @dev: Device that will be interacted with + * @clk_id: register clock consumer ID + * @regs: Pointer to memory-mapped IO region + * @config: Configuration for register map + * + * The return value will be an ERR_PTR() on error or a valid pointer + * to a struct regmap. The regmap will be automatically freed by the + * device management code. + */ +#define devm_regmap_init_mmio_clk(dev, clk_id, regs, config) \ + __regmap_lockdep_wrapper(__devm_regmap_init_mmio_clk, #config, \ + dev, clk_id, regs, config) /** * devm_regmap_init_mmio(): Initialise managed register map @@ -392,12 +651,22 @@ static inline struct regmap *regmap_init_mmio(struct device *dev, * to a struct regmap. The regmap will be automatically freed by the * device management code. */ -static inline struct regmap *devm_regmap_init_mmio(struct device *dev, - void __iomem *regs, - const struct regmap_config *config) -{ - return devm_regmap_init_mmio_clk(dev, NULL, regs, config); -} +#define devm_regmap_init_mmio(dev, regs, config) \ + devm_regmap_init_mmio_clk(dev, NULL, regs, config) + +/** + * devm_regmap_init_ac97(): Initialise AC'97 register map + * + * @ac97: Device that will be interacted with + * @config: Configuration for register map + * + * The return value will be an ERR_PTR() on error or a valid pointer + * to a struct regmap. The regmap will be automatically freed by the + * device management code. + */ +#define devm_regmap_init_ac97(ac97, config) \ + __regmap_lockdep_wrapper(__devm_regmap_init_ac97, #config, \ + ac97, config) void regmap_exit(struct regmap *map); int regmap_reinit_cache(struct regmap *map, @@ -410,10 +679,10 @@ int regmap_raw_write(struct regmap *map, unsigned int reg, const void *val, size_t val_len); int regmap_bulk_write(struct regmap *map, unsigned int reg, const void *val, size_t val_count); -int regmap_multi_reg_write(struct regmap *map, const struct reg_default *regs, +int regmap_multi_reg_write(struct regmap *map, const struct reg_sequence *regs, int num_regs); int regmap_multi_reg_write_bypassed(struct regmap *map, - const struct reg_default *regs, + const struct reg_sequence *regs, int num_regs); int regmap_raw_write_async(struct regmap *map, unsigned int reg, const void *val, size_t val_len); @@ -424,6 +693,8 @@ int regmap_bulk_read(struct regmap *map, unsigned int reg, void *val, size_t val_count); int regmap_update_bits(struct regmap *map, unsigned int reg, unsigned int mask, unsigned int val); +int regmap_write_bits(struct regmap *map, unsigned int reg, + unsigned int mask, unsigned int val); int regmap_update_bits_async(struct regmap *map, unsigned int reg, unsigned int mask, unsigned int val); int regmap_update_bits_check(struct regmap *map, unsigned int reg, @@ -433,8 +704,12 @@ int regmap_update_bits_check_async(struct regmap *map, unsigned int reg, unsigned int mask, unsigned int val, bool *change); int regmap_get_val_bytes(struct regmap *map); +int regmap_get_max_register(struct regmap *map); +int regmap_get_reg_stride(struct regmap *map); int regmap_async_complete(struct regmap *map); bool regmap_can_raw_write(struct regmap *map); +size_t regmap_get_raw_read_max(struct regmap *map); +size_t regmap_get_raw_write_max(struct regmap *map); int regcache_sync(struct regmap *map); int regcache_sync_region(struct regmap *map, unsigned int min, @@ -448,7 +723,7 @@ void regcache_mark_dirty(struct regmap *map); bool regmap_check_range_table(struct regmap *map, unsigned int reg, const struct regmap_access_table *table); -int regmap_register_patch(struct regmap *map, const struct reg_default *regs, +int regmap_register_patch(struct regmap *map, const struct reg_sequence *regs, int num_regs); int regmap_parse_val(struct regmap *map, const void *buf, unsigned int *val); @@ -501,6 +776,8 @@ int regmap_field_update_bits(struct regmap_field *field, int regmap_fields_write(struct regmap_field *field, unsigned int id, unsigned int val); +int regmap_fields_force_write(struct regmap_field *field, unsigned int id, + unsigned int val); int regmap_fields_read(struct regmap_field *field, unsigned int id, unsigned int *val); int regmap_fields_update_bits(struct regmap_field *field, unsigned int id, @@ -517,6 +794,9 @@ struct regmap_irq { unsigned int mask; }; +#define REGMAP_IRQ_REG(_irq, _off, _mask) \ + [_irq] = { .reg_offset = (_off), .mask = (_mask) } + /** * Description of a generic regmap irq_chip. This is not intended to * handle every possible interrupt controller, but it should handle a @@ -526,6 +806,8 @@ struct regmap_irq { * * @status_base: Base status register address. * @mask_base: Base mask register address. + * @unmask_base: Base unmask register address. for chips who have + * separate mask and unmask registers * @ack_base: Base ack address. If zero then the chip is clear on read. * Using zero value is possible with @use_ack bit. * @wake_base: Base address for wake enables. If zero unsupported. @@ -533,6 +815,7 @@ struct regmap_irq { * @init_ack_masked: Ack all masked interrupts once during initalization. * @mask_invert: Inverted mask register: cleared bits are masked out. * @use_ack: Use @ack register even if it is zero. + * @ack_invert: Inverted ack register: cleared bits for ack. * @wake_invert: Inverted wake register: cleared bits are wake enabled. * @runtime_pm: Hold a runtime PM lock on the device when accessing it. * @@ -546,12 +829,14 @@ struct regmap_irq_chip { unsigned int status_base; unsigned int mask_base; + unsigned int unmask_base; unsigned int ack_base; unsigned int wake_base; unsigned int irq_reg_stride; bool init_ack_masked:1; bool mask_invert:1; bool use_ack:1; + bool ack_invert:1; bool wake_invert:1; bool runtime_pm:1; @@ -643,6 +928,13 @@ static inline int regmap_update_bits(struct regmap *map, unsigned int reg, return -EINVAL; } +static inline int regmap_write_bits(struct regmap *map, unsigned int reg, + unsigned int mask, unsigned int val) +{ + WARN_ONCE(1, "regmap API is disabled"); + return -EINVAL; +} + static inline int regmap_update_bits_async(struct regmap *map, unsigned int reg, unsigned int mask, unsigned int val) @@ -676,6 +968,18 @@ static inline int regmap_get_val_bytes(struct regmap *map) return -EINVAL; } +static inline int regmap_get_max_register(struct regmap *map) +{ + WARN_ONCE(1, "regmap API is disabled"); + return -EINVAL; +} + +static inline int regmap_get_reg_stride(struct regmap *map) +{ + WARN_ONCE(1, "regmap API is disabled"); + return -EINVAL; +} + static inline int regcache_sync(struct regmap *map) { WARN_ONCE(1, "regmap API is disabled"); diff --git a/kernel/include/linux/regulator/consumer.h b/kernel/include/linux/regulator/consumer.h index f8a689ed6..9e0e76992 100644 --- a/kernel/include/linux/regulator/consumer.h +++ b/kernel/include/linux/regulator/consumer.h @@ -550,8 +550,24 @@ static inline int regulator_count_voltages(struct regulator *regulator) { return 0; } + +static inline int regulator_list_voltage(struct regulator *regulator, unsigned selector) +{ + return -EINVAL; +} + #endif +static inline int regulator_set_voltage_triplet(struct regulator *regulator, + int min_uV, int target_uV, + int max_uV) +{ + if (regulator_set_voltage(regulator, target_uV, max_uV) == 0) + return 0; + + return regulator_set_voltage(regulator, min_uV, max_uV); +} + static inline int regulator_set_voltage_tol(struct regulator *regulator, int new_uV, int tol_uV) { diff --git a/kernel/include/linux/regulator/da9211.h b/kernel/include/linux/regulator/da9211.h index 5dd65acc2..a43a5ca11 100644 --- a/kernel/include/linux/regulator/da9211.h +++ b/kernel/include/linux/regulator/da9211.h @@ -1,16 +1,16 @@ /* - * da9211.h - Regulator device driver for DA9211/DA9213 - * Copyright (C) 2014 Dialog Semiconductor Ltd. + * da9211.h - Regulator device driver for DA9211/DA9213/DA9215 + * Copyright (C) 2015 Dialog Semiconductor Ltd. * - * This library is free software; you can redistribute it and/or - * modify it under the terms of the GNU Library General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version 2 + * of the License, or (at your option) any later version. * - * This library is distributed in the hope that it will be useful, + * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * Library General Public License for more details. + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. */ #ifndef __LINUX_REGULATOR_DA9211_H @@ -23,6 +23,7 @@ enum da9211_chip_id { DA9211, DA9213, + DA9215, }; struct da9211_pdata { diff --git a/kernel/include/linux/regulator/driver.h b/kernel/include/linux/regulator/driver.h index fffa688ac..9c2903e58 100644 --- a/kernel/include/linux/regulator/driver.h +++ b/kernel/include/linux/regulator/driver.h @@ -91,6 +91,7 @@ struct regulator_linear_range { * @set_current_limit: Configure a limit for a current-limited regulator. * The driver should select the current closest to max_uA. * @get_current_limit: Get the configured limit for a current-limited regulator. + * @set_input_current_limit: Configure an input limit. * * @set_mode: Set the configured operating mode for the regulator. * @get_mode: Get the configured operating mode for the regulator. @@ -111,6 +112,7 @@ struct regulator_linear_range { * to stabilise after being set to a new value, in microseconds. * The function provides the from and to voltage selector, the * function should return the worst case. + * @set_soft_start: Enable soft start for the regulator. * * @set_suspend_voltage: Set the voltage for the regulator when the system * is suspended. @@ -121,6 +123,9 @@ struct regulator_linear_range { * @set_suspend_mode: Set the operating mode for the regulator when the * system is suspended. * + * @set_pull_down: Configure the regulator to pull down when the regulator + * is disabled. + * * This struct describes regulator operations which can be implemented by * regulator chip drivers. */ @@ -142,6 +147,9 @@ struct regulator_ops { int min_uA, int max_uA); int (*get_current_limit) (struct regulator_dev *); + int (*set_input_current_limit) (struct regulator_dev *, int lim_uA); + int (*set_over_current_protection) (struct regulator_dev *); + /* enable/disable regulator */ int (*enable) (struct regulator_dev *); int (*disable) (struct regulator_dev *); @@ -158,6 +166,8 @@ struct regulator_ops { unsigned int old_selector, unsigned int new_selector); + int (*set_soft_start) (struct regulator_dev *); + /* report regulator status ... most other accessors report * control inputs, this reports results of combining inputs * from Linux (and other sources) with the actual load. @@ -187,6 +197,8 @@ struct regulator_ops { /* set regulator suspend operating mode (defined in consumer.h) */ int (*set_suspend_mode) (struct regulator_dev *, unsigned int mode); + + int (*set_pull_down) (struct regulator_dev *); }; /* @@ -233,6 +245,7 @@ enum regulator_type { * @linear_min_sel: Minimal selector for starting linear mapping * @fixed_uV: Fixed voltage of rails. * @ramp_delay: Time to settle down after voltage change (unit: uV/us) + * @min_dropout_uV: The minimum dropout voltage this regulator can handle * @linear_ranges: A constant table of possible voltage ranges. * @n_linear_ranges: Number of entries in the @linear_ranges table. * @volt_table: Voltage mapping table (if table based mapping) @@ -280,6 +293,7 @@ struct regulator_desc { unsigned int linear_min_sel; int fixed_uV; unsigned int ramp_delay; + int min_dropout_uV; const struct regulator_linear_range *linear_ranges; int n_linear_ranges; diff --git a/kernel/include/linux/regulator/machine.h b/kernel/include/linux/regulator/machine.h index b07562e08..a1067d0b3 100644 --- a/kernel/include/linux/regulator/machine.h +++ b/kernel/include/linux/regulator/machine.h @@ -75,6 +75,8 @@ struct regulator_state { * * @min_uA: Smallest current consumers may set. * @max_uA: Largest current consumers may set. + * @ilim_uA: Maximum input current. + * @system_load: Load that isn't captured by any consumer requests. * * @valid_modes_mask: Mask of modes which may be configured by consumers. * @valid_ops_mask: Operations which may be performed by consumers. @@ -86,6 +88,8 @@ struct regulator_state { * applied. * @apply_uV: Apply the voltage constraint when initialising. * @ramp_disable: Disable ramp delay when initialising or when setting voltage. + * @soft_start: Enable soft start so that voltage ramps slowly. + * @pull_down: Enable pull down when regulator is disabled. * * @input_uV: Input voltage for regulator when supplied by another regulator. * @@ -111,6 +115,9 @@ struct regulation_constraints { /* current output range (inclusive) - for current control */ int min_uA; int max_uA; + int ilim_uA; + + int system_load; /* valid regulator operating modes for this machine */ unsigned int valid_modes_mask; @@ -138,6 +145,9 @@ struct regulation_constraints { unsigned boot_on:1; /* bootloader/firmware enabled regulator */ unsigned apply_uV:1; /* apply uV constraint if min == max */ unsigned ramp_disable:1; /* disable ramp delay */ + unsigned soft_start:1; /* ramp voltage slowly */ + unsigned pull_down:1; /* pull down resistor when regulator off */ + unsigned over_current_protection:1; /* auto disable on over current */ }; /** diff --git a/kernel/include/linux/regulator/max8973-regulator.h b/kernel/include/linux/regulator/max8973-regulator.h index f8acc052e..f6a8a16a0 100644 --- a/kernel/include/linux/regulator/max8973-regulator.h +++ b/kernel/include/linux/regulator/max8973-regulator.h @@ -58,6 +58,9 @@ * control signal from EN input pin. If it is false then * voltage output will be enabled/disabled through EN bit of * device register. + * @enable_gpio: Enable GPIO. If EN pin is controlled through GPIO from host + * then GPIO number can be provided. If no GPIO controlled then + * it should be -1. * @dvs_gpio: GPIO for dvs. It should be -1 if this is tied with fixed logic. * @dvs_def_state: Default state of dvs. 1 if it is high else 0. */ @@ -65,6 +68,7 @@ struct max8973_regulator_platform_data { struct regulator_init_data *reg_init_data; unsigned long control_flags; bool enable_ext_control; + int enable_gpio; int dvs_gpio; unsigned dvs_def_state:1; }; diff --git a/kernel/include/linux/regulator/mt6311.h b/kernel/include/linux/regulator/mt6311.h new file mode 100644 index 000000000..847325939 --- /dev/null +++ b/kernel/include/linux/regulator/mt6311.h @@ -0,0 +1,29 @@ +/* + * Copyright (c) 2015 MediaTek Inc. + * Author: Henry Chen <henryc.chen@mediatek.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef __LINUX_REGULATOR_MT6311_H +#define __LINUX_REGULATOR_MT6311_H + +#define MT6311_MAX_REGULATORS 2 + +enum { + MT6311_ID_VDVFS = 0, + MT6311_ID_VBIASN, +}; + +#define MT6311_E1_CID_CODE 0x10 +#define MT6311_E2_CID_CODE 0x20 +#define MT6311_E3_CID_CODE 0x30 + +#endif /* __LINUX_REGULATOR_MT6311_H */ diff --git a/kernel/include/linux/remoteproc.h b/kernel/include/linux/remoteproc.h index 78b8a9b9d..9c4e1384f 100644 --- a/kernel/include/linux/remoteproc.h +++ b/kernel/include/linux/remoteproc.h @@ -36,11 +36,11 @@ #define REMOTEPROC_H #include <linux/types.h> -#include <linux/klist.h> #include <linux/mutex.h> #include <linux/virtio.h> #include <linux/completion.h> #include <linux/idr.h> +#include <linux/of.h> /** * struct resource_table - firmware resource table header @@ -330,11 +330,13 @@ struct rproc; * @start: power on the device and boot it * @stop: power off the device * @kick: kick a virtqueue (virtqueue id given as a parameter) + * @da_to_va: optional platform hook to perform address translations */ struct rproc_ops { int (*start)(struct rproc *rproc); int (*stop)(struct rproc *rproc); void (*kick)(struct rproc *rproc, int vqid); + void * (*da_to_va)(struct rproc *rproc, u64 da, int len); }; /** @@ -375,7 +377,7 @@ enum rproc_crash_type { /** * struct rproc - represents a physical remote processor device - * @node: klist node of this rproc object + * @node: list node of this rproc object * @domain: iommu domain * @name: human readable name of the rproc * @firmware: name of firmware file to be loaded @@ -407,7 +409,7 @@ enum rproc_crash_type { * @has_iommu: flag to indicate if remote processor is behind an MMU */ struct rproc { - struct klist_node node; + struct list_head node; struct iommu_domain *domain; const char *name; const char *firmware; @@ -481,6 +483,7 @@ struct rproc_vdev { u32 rsc_offset; }; +struct rproc *rproc_get_by_phandle(phandle phandle); struct rproc *rproc_alloc(struct device *dev, const char *name, const struct rproc_ops *ops, const char *firmware, int len); diff --git a/kernel/include/linux/reset.h b/kernel/include/linux/reset.h index da5602bd7..7f65f9cff 100644 --- a/kernel/include/linux/reset.h +++ b/kernel/include/linux/reset.h @@ -74,6 +74,20 @@ static inline int device_reset_optional(struct device *dev) return -ENOSYS; } +static inline struct reset_control *__must_check reset_control_get( + struct device *dev, const char *id) +{ + WARN_ON(1); + return ERR_PTR(-EINVAL); +} + +static inline struct reset_control *__must_check devm_reset_control_get( + struct device *dev, const char *id) +{ + WARN_ON(1); + return ERR_PTR(-EINVAL); +} + static inline struct reset_control *reset_control_get_optional( struct device *dev, const char *id) { diff --git a/kernel/include/linux/reset/bcm63xx_pmb.h b/kernel/include/linux/reset/bcm63xx_pmb.h new file mode 100644 index 000000000..bb4af7b5e --- /dev/null +++ b/kernel/include/linux/reset/bcm63xx_pmb.h @@ -0,0 +1,88 @@ +/* + * Broadcom BCM63xx Processor Monitor Bus shared routines (SMP and reset) + * + * Copyright (C) 2015, Broadcom Corporation + * Author: Florian Fainelli <f.fainelli@gmail.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation version 2. + * + * This program is distributed "as is" WITHOUT ANY WARRANTY of any + * kind, whether express or implied; without even the implied warranty + * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ +#ifndef __BCM63XX_PMB_H +#define __BCM63XX_PMB_H + +#include <linux/io.h> +#include <linux/types.h> +#include <linux/delay.h> +#include <linux/err.h> + +/* PMB Master controller register */ +#define PMB_CTRL 0x00 +#define PMC_PMBM_START (1 << 31) +#define PMC_PMBM_TIMEOUT (1 << 30) +#define PMC_PMBM_SLAVE_ERR (1 << 29) +#define PMC_PMBM_BUSY (1 << 28) +#define PMC_PMBM_READ (0 << 20) +#define PMC_PMBM_WRITE (1 << 20) +#define PMB_WR_DATA 0x04 +#define PMB_TIMEOUT 0x08 +#define PMB_RD_DATA 0x0C + +#define PMB_BUS_ID_SHIFT 8 + +/* Perform the low-level PMB master operation, shared between reads and + * writes. + */ +static inline int __bpcm_do_op(void __iomem *master, unsigned int addr, + u32 off, u32 op) +{ + unsigned int timeout = 1000; + u32 cmd; + + cmd = (PMC_PMBM_START | op | (addr & 0xff) << 12 | off); + writel(cmd, master + PMB_CTRL); + do { + cmd = readl(master + PMB_CTRL); + if (!(cmd & PMC_PMBM_START)) + return 0; + + if (cmd & PMC_PMBM_SLAVE_ERR) + return -EIO; + + if (cmd & PMC_PMBM_TIMEOUT) + return -ETIMEDOUT; + + udelay(1); + } while (timeout-- > 0); + + return -ETIMEDOUT; +} + +static inline int bpcm_rd(void __iomem *master, unsigned int addr, + u32 off, u32 *val) +{ + int ret = 0; + + ret = __bpcm_do_op(master, addr, off >> 2, PMC_PMBM_READ); + *val = readl(master + PMB_RD_DATA); + + return ret; +} + +static inline int bpcm_wr(void __iomem *master, unsigned int addr, + u32 off, u32 val) +{ + int ret = 0; + + writel(val, master + PMB_WR_DATA); + ret = __bpcm_do_op(master, addr, off >> 2, PMC_PMBM_WRITE); + + return ret; +} + +#endif /* __BCM63XX_PMB_H */ diff --git a/kernel/include/linux/rhashtable.h b/kernel/include/linux/rhashtable.h index 843ceca9a..e50b31d18 100644 --- a/kernel/include/linux/rhashtable.h +++ b/kernel/include/linux/rhashtable.h @@ -19,6 +19,7 @@ #include <linux/atomic.h> #include <linux/compiler.h> +#include <linux/err.h> #include <linux/errno.h> #include <linux/jhash.h> #include <linux/list_nulls.h> @@ -339,10 +340,11 @@ static inline int lockdep_rht_bucket_is_held(const struct bucket_table *tbl, int rhashtable_init(struct rhashtable *ht, const struct rhashtable_params *params); -int rhashtable_insert_slow(struct rhashtable *ht, const void *key, - struct rhash_head *obj, - struct bucket_table *old_tbl); -int rhashtable_insert_rehash(struct rhashtable *ht); +struct bucket_table *rhashtable_insert_slow(struct rhashtable *ht, + const void *key, + struct rhash_head *obj, + struct bucket_table *old_tbl); +int rhashtable_insert_rehash(struct rhashtable *ht, struct bucket_table *tbl); int rhashtable_walk_init(struct rhashtable *ht, struct rhashtable_iter *iter); void rhashtable_walk_exit(struct rhashtable_iter *iter); @@ -598,9 +600,11 @@ restart: new_tbl = rht_dereference_rcu(tbl->future_tbl, ht); if (unlikely(new_tbl)) { - err = rhashtable_insert_slow(ht, key, obj, new_tbl); - if (err == -EAGAIN) + tbl = rhashtable_insert_slow(ht, key, obj, new_tbl); + if (!IS_ERR_OR_NULL(tbl)) goto slow_path; + + err = PTR_ERR(tbl); goto out; } @@ -611,7 +615,7 @@ restart: if (unlikely(rht_grow_above_100(ht, tbl))) { slow_path: spin_unlock_bh(lock); - err = rhashtable_insert_rehash(ht); + err = rhashtable_insert_rehash(ht, tbl); rcu_read_unlock(); if (err) return err; diff --git a/kernel/include/linux/ring_buffer.h b/kernel/include/linux/ring_buffer.h index e2c13cd86..4acc552e9 100644 --- a/kernel/include/linux/ring_buffer.h +++ b/kernel/include/linux/ring_buffer.h @@ -154,8 +154,8 @@ ring_buffer_swap_cpu(struct ring_buffer *buffer_a, } #endif -int ring_buffer_empty(struct ring_buffer *buffer); -int ring_buffer_empty_cpu(struct ring_buffer *buffer, int cpu); +bool ring_buffer_empty(struct ring_buffer *buffer); +bool ring_buffer_empty_cpu(struct ring_buffer *buffer, int cpu); void ring_buffer_record_disable(struct ring_buffer *buffer); void ring_buffer_record_enable(struct ring_buffer *buffer); diff --git a/kernel/include/linux/rio.h b/kernel/include/linux/rio.h index 6bda06f21..cde976e86 100644 --- a/kernel/include/linux/rio.h +++ b/kernel/include/linux/rio.h @@ -298,7 +298,7 @@ struct rio_id_table { * struct rio_net - RIO network info * @node: Node in global list of RIO networks * @devices: List of devices in this network - * @switches: List of switches in this netowrk + * @switches: List of switches in this network * @mports: List of master ports accessing this network * @hport: Default port for accessing this network * @id: RIO network ID diff --git a/kernel/include/linux/rmap.h b/kernel/include/linux/rmap.h index c89c53a11..ddda2ac34 100644 --- a/kernel/include/linux/rmap.h +++ b/kernel/include/linux/rmap.h @@ -89,6 +89,9 @@ enum ttu_flags { TTU_IGNORE_MLOCK = (1 << 8), /* ignore mlock */ TTU_IGNORE_ACCESS = (1 << 9), /* don't age */ TTU_IGNORE_HWPOISON = (1 << 10),/* corrupted page is recoverable */ + TTU_BATCH_FLUSH = (1 << 11), /* Batch TLB flushes where possible + * and caller guarantees they will + * do a final flush if necessary */ }; #ifdef CONFIG_MMU @@ -105,20 +108,6 @@ static inline void put_anon_vma(struct anon_vma *anon_vma) __put_anon_vma(anon_vma); } -static inline void vma_lock_anon_vma(struct vm_area_struct *vma) -{ - struct anon_vma *anon_vma = vma->anon_vma; - if (anon_vma) - down_write(&anon_vma->root->rwsem); -} - -static inline void vma_unlock_anon_vma(struct vm_area_struct *vma) -{ - struct anon_vma *anon_vma = vma->anon_vma; - if (anon_vma) - up_write(&anon_vma->root->rwsem); -} - static inline void anon_vma_lock_write(struct anon_vma *anon_vma) { down_write(&anon_vma->root->rwsem); diff --git a/kernel/include/linux/rotary_encoder.h b/kernel/include/linux/rotary_encoder.h index 3f594dce5..fe3dc64e5 100644 --- a/kernel/include/linux/rotary_encoder.h +++ b/kernel/include/linux/rotary_encoder.h @@ -8,9 +8,10 @@ struct rotary_encoder_platform_data { unsigned int gpio_b; unsigned int inverted_a; unsigned int inverted_b; + unsigned int steps_per_period; bool relative_axis; bool rollover; - bool half_period; + bool wakeup_source; }; #endif /* __ROTARY_ENCODER_H__ */ diff --git a/kernel/include/linux/rtc.h b/kernel/include/linux/rtc.h index 8dcf6825f..3359f0422 100644 --- a/kernel/include/linux/rtc.h +++ b/kernel/include/linux/rtc.h @@ -24,6 +24,14 @@ extern void rtc_time64_to_tm(time64_t time, struct rtc_time *tm); ktime_t rtc_tm_to_ktime(struct rtc_time tm); struct rtc_time rtc_ktime_to_tm(ktime_t kt); +/* + * rtc_tm_sub - Return the difference in seconds. + */ +static inline time64_t rtc_tm_sub(struct rtc_time *lhs, struct rtc_time *rhs) +{ + return rtc_tm_to_time64(lhs) - rtc_tm_to_time64(rhs); +} + /** * Deprecated. Use rtc_time64_to_tm(). */ @@ -101,8 +109,7 @@ struct rtc_timer { /* flags */ #define RTC_DEV_BUSY 0 -struct rtc_device -{ +struct rtc_device { struct device dev; struct module *owner; @@ -161,7 +168,6 @@ extern void devm_rtc_device_unregister(struct device *dev, extern int rtc_read_time(struct rtc_device *rtc, struct rtc_time *tm); extern int rtc_set_time(struct rtc_device *rtc, struct rtc_time *tm); -extern int rtc_set_mmss(struct rtc_device *rtc, unsigned long secs); extern int rtc_set_ntp_time(struct timespec64 now); int __rtc_read_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm); extern int rtc_read_alarm(struct rtc_device *rtc, @@ -198,10 +204,10 @@ int rtc_register(rtc_task_t *task); int rtc_unregister(rtc_task_t *task); int rtc_control(rtc_task_t *t, unsigned int cmd, unsigned long arg); -void rtc_timer_init(struct rtc_timer *timer, void (*f)(void* p), void* data); -int rtc_timer_start(struct rtc_device *rtc, struct rtc_timer* timer, - ktime_t expires, ktime_t period); -int rtc_timer_cancel(struct rtc_device *rtc, struct rtc_timer* timer); +void rtc_timer_init(struct rtc_timer *timer, void (*f)(void *p), void *data); +int rtc_timer_start(struct rtc_device *rtc, struct rtc_timer *timer, + ktime_t expires, ktime_t period); +void rtc_timer_cancel(struct rtc_device *rtc, struct rtc_timer *timer); void rtc_timer_do_work(struct work_struct *work); static inline bool is_leap_year(unsigned int year) diff --git a/kernel/include/linux/rtc/sirfsoc_rtciobrg.h b/kernel/include/linux/rtc/sirfsoc_rtciobrg.h index 2c92e1c8e..aefd99726 100644 --- a/kernel/include/linux/rtc/sirfsoc_rtciobrg.h +++ b/kernel/include/linux/rtc/sirfsoc_rtciobrg.h @@ -9,10 +9,14 @@ #ifndef _SIRFSOC_RTC_IOBRG_H_ #define _SIRFSOC_RTC_IOBRG_H_ +struct regmap_config; + extern void sirfsoc_rtc_iobrg_besyncing(void); extern u32 sirfsoc_rtc_iobrg_readl(u32 addr); extern void sirfsoc_rtc_iobrg_writel(u32 val, u32 addr); +struct regmap *devm_regmap_init_iobg(struct device *dev, + const struct regmap_config *config); #endif diff --git a/kernel/include/linux/rtmutex.h b/kernel/include/linux/rtmutex.h index d5a04ea47..30211c627 100644 --- a/kernel/include/linux/rtmutex.h +++ b/kernel/include/linux/rtmutex.h @@ -13,8 +13,8 @@ #define __LINUX_RT_MUTEX_H #include <linux/linkage.h> -#include <linux/rbtree.h> #include <linux/spinlock_types_raw.h> +#include <linux/rbtree.h> extern int max_lock_depth; /* for sysctl */ diff --git a/kernel/include/linux/rtnetlink.h b/kernel/include/linux/rtnetlink.h index 7b8e260c4..4be5048b1 100644 --- a/kernel/include/linux/rtnetlink.h +++ b/kernel/include/linux/rtnetlink.h @@ -33,11 +33,11 @@ extern wait_queue_head_t netdev_unregistering_wq; extern struct mutex net_mutex; #ifdef CONFIG_PROVE_LOCKING -extern int lockdep_rtnl_is_held(void); +extern bool lockdep_rtnl_is_held(void); #else -static inline int lockdep_rtnl_is_held(void) +static inline bool lockdep_rtnl_is_held(void) { - return 1; + return true; } #endif /* #ifdef CONFIG_PROVE_LOCKING */ @@ -79,17 +79,9 @@ static inline struct netdev_queue *dev_ingress_queue(struct net_device *dev) struct netdev_queue *dev_ingress_queue_create(struct net_device *dev); -#ifdef CONFIG_NET_CLS_ACT +#ifdef CONFIG_NET_INGRESS void net_inc_ingress_queue(void); void net_dec_ingress_queue(void); -#else -static inline void net_inc_ingress_queue(void) -{ -} - -static inline void net_dec_ingress_queue(void) -{ -} #endif extern void rtnetlink_init(void); @@ -122,5 +114,9 @@ extern int ndo_dflt_fdb_del(struct ndmsg *ndm, extern int ndo_dflt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, struct net_device *dev, u16 mode, - u32 flags, u32 mask, int nlflags); + u32 flags, u32 mask, int nlflags, + u32 filter_mask, + int (*vlan_fill)(struct sk_buff *skb, + struct net_device *dev, + u32 filter_mask)); #endif /* __LINUX_RTNETLINK_H */ diff --git a/kernel/include/linux/rwsem_rt.h b/kernel/include/linux/rwsem_rt.h index 928a05cbf..f97860b2e 100644 --- a/kernel/include/linux/rwsem_rt.h +++ b/kernel/include/linux/rwsem_rt.h @@ -51,18 +51,20 @@ do { \ __rt_init_rwsem((sem), #sem, &__key); \ } while (0) -extern void rt_down_write(struct rw_semaphore *rwsem); +extern void rt_down_write(struct rw_semaphore *rwsem); extern void rt_down_read_nested(struct rw_semaphore *rwsem, int subclass); extern void rt_down_write_nested(struct rw_semaphore *rwsem, int subclass); extern void rt_down_write_nested_lock(struct rw_semaphore *rwsem, - struct lockdep_map *nest); -extern void rt_down_read(struct rw_semaphore *rwsem); + struct lockdep_map *nest); +extern void rt__down_read(struct rw_semaphore *rwsem); +extern void rt_down_read(struct rw_semaphore *rwsem); extern int rt_down_write_trylock(struct rw_semaphore *rwsem); +extern int rt__down_read_trylock(struct rw_semaphore *rwsem); extern int rt_down_read_trylock(struct rw_semaphore *rwsem); -extern void __rt_up_read(struct rw_semaphore *rwsem); -extern void rt_up_read(struct rw_semaphore *rwsem); -extern void rt_up_write(struct rw_semaphore *rwsem); -extern void rt_downgrade_write(struct rw_semaphore *rwsem); +extern void __rt_up_read(struct rw_semaphore *rwsem); +extern void rt_up_read(struct rw_semaphore *rwsem); +extern void rt_up_write(struct rw_semaphore *rwsem); +extern void rt_downgrade_write(struct rw_semaphore *rwsem); #define init_rwsem(sem) rt_init_rwsem(sem) #define rwsem_is_locked(s) rt_mutex_is_locked(&(s)->lock) @@ -73,11 +75,21 @@ static inline int rwsem_is_contended(struct rw_semaphore *sem) return !RB_EMPTY_ROOT(&sem->lock.waiters); } +static inline void __down_read(struct rw_semaphore *sem) +{ + rt__down_read(sem); +} + static inline void down_read(struct rw_semaphore *sem) { rt_down_read(sem); } +static inline int __down_read_trylock(struct rw_semaphore *sem) +{ + return rt__down_read_trylock(sem); +} + static inline int down_read_trylock(struct rw_semaphore *sem) { return rt_down_read_trylock(sem); diff --git a/kernel/include/linux/scatterlist.h b/kernel/include/linux/scatterlist.h index ed8f9e70d..556ec1ea2 100644 --- a/kernel/include/linux/scatterlist.h +++ b/kernel/include/linux/scatterlist.h @@ -2,13 +2,39 @@ #define _LINUX_SCATTERLIST_H #include <linux/string.h> +#include <linux/types.h> #include <linux/bug.h> #include <linux/mm.h> - -#include <asm/types.h> -#include <asm/scatterlist.h> #include <asm/io.h> +struct scatterlist { +#ifdef CONFIG_DEBUG_SG + unsigned long sg_magic; +#endif + unsigned long page_link; + unsigned int offset; + unsigned int length; + dma_addr_t dma_address; +#ifdef CONFIG_NEED_SG_DMA_LENGTH + unsigned int dma_length; +#endif +}; + +/* + * These macros should be used after a dma_map_sg call has been done + * to get bus addresses of each of the SG entries and their lengths. + * You should only work with the number of sg entries dma_map_sg + * returns, or alternatively stop on the first sg_dma_len(sg) which + * is 0. + */ +#define sg_dma_address(sg) ((sg)->dma_address) + +#ifdef CONFIG_NEED_SG_DMA_LENGTH +#define sg_dma_len(sg) ((sg)->dma_length) +#else +#define sg_dma_len(sg) ((sg)->length) +#endif + struct sg_table { struct scatterlist *sgl; /* the list */ unsigned int nents; /* number of mapped entries */ @@ -18,10 +44,9 @@ struct sg_table { /* * Notes on SG table design. * - * Architectures must provide an unsigned long page_link field in the - * scatterlist struct. We use that to place the page pointer AND encode - * information about the sg table as well. The two lower bits are reserved - * for this information. + * We use the unsigned long page_link field in the scatterlist struct to place + * the page pointer AND encode information about the sg table as well. The two + * lower bits are reserved for this information. * * If bit 0 is set, then the page_link contains a pointer to the next sg * table list. Otherwise the next entry is at sg + 1. @@ -136,10 +161,6 @@ static inline void sg_set_buf(struct scatterlist *sg, const void *buf, static inline void sg_chain(struct scatterlist *prv, unsigned int prv_nents, struct scatterlist *sgl) { -#ifndef CONFIG_ARCH_HAS_SG_CHAIN - BUG(); -#endif - /* * offset and length are unused for chain entry. Clear them. */ @@ -221,10 +242,16 @@ static inline void *sg_virt(struct scatterlist *sg) } int sg_nents(struct scatterlist *sg); +int sg_nents_for_len(struct scatterlist *sg, u64 len); struct scatterlist *sg_next(struct scatterlist *); struct scatterlist *sg_last(struct scatterlist *s, unsigned int); void sg_init_table(struct scatterlist *, unsigned int); void sg_init_one(struct scatterlist *, const void *, unsigned int); +int sg_split(struct scatterlist *in, const int in_mapped_nents, + const off_t skip, const int nb_splits, + const size_t *split_sizes, + struct scatterlist **out, int *out_mapped_nents, + gfp_t gfp_mask); typedef struct scatterlist *(sg_alloc_fn)(unsigned int, gfp_t); typedef void (sg_free_fn)(struct scatterlist *, unsigned int); @@ -239,13 +266,16 @@ int sg_alloc_table_from_pages(struct sg_table *sgt, unsigned long offset, unsigned long size, gfp_t gfp_mask); +size_t sg_copy_buffer(struct scatterlist *sgl, unsigned int nents, void *buf, + size_t buflen, off_t skip, bool to_buffer); + size_t sg_copy_from_buffer(struct scatterlist *sgl, unsigned int nents, - void *buf, size_t buflen); + const void *buf, size_t buflen); size_t sg_copy_to_buffer(struct scatterlist *sgl, unsigned int nents, void *buf, size_t buflen); size_t sg_pcopy_from_buffer(struct scatterlist *sgl, unsigned int nents, - void *buf, size_t buflen, off_t skip); + const void *buf, size_t buflen, off_t skip); size_t sg_pcopy_to_buffer(struct scatterlist *sgl, unsigned int nents, void *buf, size_t buflen, off_t skip); diff --git a/kernel/include/linux/sched.h b/kernel/include/linux/sched.h index 956658437..58c5ec8c3 100644 --- a/kernel/include/linux/sched.h +++ b/kernel/include/linux/sched.h @@ -25,7 +25,7 @@ struct sched_param { #include <linux/errno.h> #include <linux/nodemask.h> #include <linux/mm_types.h> -#include <linux/preempt_mask.h> +#include <linux/preempt.h> #include <asm/kmap_types.h> #include <asm/page.h> @@ -59,6 +59,7 @@ struct sched_param { #include <linux/uidgid.h> #include <linux/gfp.h> #include <linux/magic.h> +#include <linux/cgroup-defs.h> #include <asm/processor.h> @@ -133,6 +134,7 @@ struct fs_struct; struct perf_event_context; struct blk_plug; struct filename; +struct nameidata; #define VMACACHE_BITS 2 #define VMACACHE_SIZE (1U << VMACACHE_BITS) @@ -174,9 +176,12 @@ extern unsigned long nr_iowait_cpu(int cpu); extern void get_iowait_load(unsigned long *nr_waiters, unsigned long *load); extern void calc_global_load(unsigned long ticks); -extern void update_cpu_load_nohz(void); -extern unsigned long get_parent_ip(unsigned long addr); +#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) +extern void update_cpu_load_nohz(void); +#else +static inline void update_cpu_load_nohz(void) { } +#endif extern void dump_cpu_task(int cpu); @@ -186,8 +191,6 @@ struct task_group; #ifdef CONFIG_SCHED_DEBUG extern void proc_sched_show_task(struct task_struct *p, struct seq_file *m); extern void proc_sched_set_task(struct task_struct *p); -extern void -print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq); #endif /* @@ -214,9 +217,10 @@ print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq); #define TASK_WAKEKILL 128 #define TASK_WAKING 256 #define TASK_PARKED 512 -#define TASK_STATE_MAX 1024 +#define TASK_NOLOAD 1024 +#define TASK_STATE_MAX 2048 -#define TASK_STATE_TO_CHAR_STR "RSDTtXZxKWP" +#define TASK_STATE_TO_CHAR_STR "RSDTtXZxKWPN" extern char ___assert_task_state[1 - 2*!!( sizeof(TASK_STATE_TO_CHAR_STR)-1 != ilog2(TASK_STATE_MAX)+1)]; @@ -226,6 +230,8 @@ extern char ___assert_task_state[1 - 2*!!( #define TASK_STOPPED (TASK_WAKEKILL | __TASK_STOPPED) #define TASK_TRACED (TASK_WAKEKILL | __TASK_TRACED) +#define TASK_IDLE (TASK_UNINTERRUPTIBLE | TASK_NOLOAD) + /* Convenience macros for the sake of wake_up */ #define TASK_NORMAL (TASK_INTERRUPTIBLE | TASK_UNINTERRUPTIBLE) #define TASK_ALL (TASK_NORMAL | __TASK_STOPPED | __TASK_TRACED) @@ -238,7 +244,8 @@ extern char ___assert_task_state[1 - 2*!!( #define task_is_stopped(task) ((task->state & __TASK_STOPPED) != 0) #define task_contributes_to_load(task) \ ((task->state & TASK_UNINTERRUPTIBLE) != 0 && \ - (task->flags & PF_FROZEN) == 0) + (task->flags & PF_FROZEN) == 0 && \ + (task->state & TASK_NOLOAD) == 0) #ifdef CONFIG_DEBUG_ATOMIC_SLEEP @@ -250,7 +257,7 @@ extern char ___assert_task_state[1 - 2*!!( #define set_task_state(tsk, state_value) \ do { \ (tsk)->task_state_change = _THIS_IP_; \ - set_mb((tsk)->state, (state_value)); \ + smp_store_mb((tsk)->state, (state_value)); \ } while (0) /* @@ -272,7 +279,7 @@ extern char ___assert_task_state[1 - 2*!!( #define set_current_state(state_value) \ do { \ current->task_state_change = _THIS_IP_; \ - set_mb(current->state, (state_value)); \ + smp_store_mb(current->state, (state_value)); \ } while (0) #else @@ -280,7 +287,7 @@ extern char ___assert_task_state[1 - 2*!!( #define __set_task_state(tsk, state_value) \ do { (tsk)->state = (state_value); } while (0) #define set_task_state(tsk, state_value) \ - set_mb((tsk)->state, (state_value)) + smp_store_mb((tsk)->state, (state_value)) /* * set_current_state() includes a barrier so that the write of current->state @@ -296,7 +303,7 @@ extern char ___assert_task_state[1 - 2*!!( #define __set_current_state(state_value) \ do { current->state = (state_value); } while (0) #define set_current_state(state_value) \ - set_mb(current->state, (state_value)) + smp_store_mb(current->state, (state_value)) #endif @@ -338,14 +345,10 @@ extern int runqueue_is_locked(int cpu); #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) extern void nohz_balance_enter_idle(int cpu); extern void set_cpu_sd_state_idle(void); -extern int get_nohz_timer_target(int pinned); +extern int get_nohz_timer_target(void); #else static inline void nohz_balance_enter_idle(int cpu) { } static inline void set_cpu_sd_state_idle(void) { } -static inline int get_nohz_timer_target(int pinned) -{ - return smp_processor_id(); -} #endif /* @@ -382,6 +385,7 @@ extern int proc_dowatchdog_thresh(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); extern unsigned int softlockup_panic; +extern unsigned int hardlockup_panic; void lockup_detector_init(void); #else static inline void touch_softlockup_watchdog(void) @@ -481,9 +485,11 @@ static inline int get_dumpable(struct mm_struct *mm) #define MMF_DUMP_ELF_HEADERS 6 #define MMF_DUMP_HUGETLB_PRIVATE 7 #define MMF_DUMP_HUGETLB_SHARED 8 +#define MMF_DUMP_DAX_PRIVATE 9 +#define MMF_DUMP_DAX_SHARED 10 #define MMF_DUMP_FILTER_SHIFT MMF_DUMPABLE_BITS -#define MMF_DUMP_FILTER_BITS 7 +#define MMF_DUMP_FILTER_BITS 9 #define MMF_DUMP_FILTER_MASK \ (((1 << MMF_DUMP_FILTER_BITS) - 1) << MMF_DUMP_FILTER_SHIFT) #define MMF_DUMP_FILTER_DEFAULT \ @@ -528,39 +534,49 @@ struct cpu_itimer { }; /** - * struct cputime - snaphsot of system and user cputime + * struct prev_cputime - snaphsot of system and user cputime * @utime: time spent in user mode * @stime: time spent in system mode + * @lock: protects the above two fields * - * Gathers a generic snapshot of user and system time. + * Stores previous user/system time values such that we can guarantee + * monotonicity. */ -struct cputime { +struct prev_cputime { +#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE cputime_t utime; cputime_t stime; + raw_spinlock_t lock; +#endif }; +static inline void prev_cputime_init(struct prev_cputime *prev) +{ +#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE + prev->utime = prev->stime = 0; + raw_spin_lock_init(&prev->lock); +#endif +} + /** * struct task_cputime - collected CPU time counts * @utime: time spent in user mode, in &cputime_t units * @stime: time spent in kernel mode, in &cputime_t units * @sum_exec_runtime: total time spent on the CPU, in nanoseconds * - * This is an extension of struct cputime that includes the total runtime - * spent by the task from the scheduler point of view. - * - * As a result, this structure groups together three kinds of CPU time - * that are tracked for threads and thread groups. Most things considering - * CPU time want to group these counts together and treat all three - * of them in parallel. + * This structure groups together three kinds of CPU time that are tracked for + * threads and thread groups. Most things considering CPU time want to group + * these counts together and treat all three of them in parallel. */ struct task_cputime { cputime_t utime; cputime_t stime; unsigned long long sum_exec_runtime; }; + /* Alternate field names when used to cache expirations. */ -#define prof_exp stime #define virt_exp utime +#define prof_exp stime #define sched_exp sum_exec_runtime #define INIT_CPUTIME \ @@ -570,35 +586,59 @@ struct task_cputime { .sum_exec_runtime = 0, \ } -#ifdef CONFIG_PREEMPT_COUNT -#define PREEMPT_DISABLED (1 + PREEMPT_ENABLED) -#else -#define PREEMPT_DISABLED PREEMPT_ENABLED -#endif +/* + * This is the atomic variant of task_cputime, which can be used for + * storing and updating task_cputime statistics without locking. + */ +struct task_cputime_atomic { + atomic64_t utime; + atomic64_t stime; + atomic64_t sum_exec_runtime; +}; + +#define INIT_CPUTIME_ATOMIC \ + (struct task_cputime_atomic) { \ + .utime = ATOMIC64_INIT(0), \ + .stime = ATOMIC64_INIT(0), \ + .sum_exec_runtime = ATOMIC64_INIT(0), \ + } + +#define PREEMPT_DISABLED (PREEMPT_DISABLE_OFFSET + PREEMPT_ENABLED) + +/* + * Disable preemption until the scheduler is running -- use an unconditional + * value so that it also works on !PREEMPT_COUNT kernels. + * + * Reset by start_kernel()->sched_init()->init_idle()->init_idle_preempt_count(). + */ +#define INIT_PREEMPT_COUNT PREEMPT_OFFSET /* - * Disable preemption until the scheduler is running. - * Reset by start_kernel()->sched_init()->init_idle(). + * Initial preempt_count value; reflects the preempt_count schedule invariant + * which states that during context switches: + * + * preempt_count() == 2*PREEMPT_DISABLE_OFFSET * - * We include PREEMPT_ACTIVE to avoid cond_resched() from working - * before the scheduler is active -- see should_resched(). + * Note: PREEMPT_DISABLE_OFFSET is 0 for !PREEMPT_COUNT kernels. + * Note: See finish_task_switch(). */ -#define INIT_PREEMPT_COUNT (PREEMPT_DISABLED + PREEMPT_ACTIVE) +#define FORK_PREEMPT_COUNT (2*PREEMPT_DISABLE_OFFSET + PREEMPT_ENABLED) /** * struct thread_group_cputimer - thread group interval timer counts - * @cputime: thread group interval timers. - * @running: non-zero when there are timers running and - * @cputime receives updates. - * @lock: lock for fields in this struct. + * @cputime_atomic: atomic thread group interval timers. + * @running: true when there are timers running and + * @cputime_atomic receives updates. + * @checking_timer: true when a thread in the group is in the + * process of checking for thread group timers. * * This structure contains the version of task_cputime, above, that is * used for thread group CPU timer calculations. */ struct thread_group_cputimer { - struct task_cputime cputime; - int running; - raw_spinlock_t lock; + struct task_cputime_atomic cputime_atomic; + bool running; + bool checking_timer; }; #include <linux/rwsem.h> @@ -698,9 +738,7 @@ struct signal_struct { cputime_t utime, stime, cutime, cstime; cputime_t gtime; cputime_t cgtime; -#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE - struct cputime prev_cputime; -#endif + struct prev_cputime prev_cputime; unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw; unsigned long min_flt, maj_flt, cmin_flt, cmaj_flt; unsigned long inblock, oublock, cinblock, coublock; @@ -737,18 +775,6 @@ struct signal_struct { unsigned audit_tty_log_passwd; struct tty_audit_buf *tty_audit_buf; #endif -#ifdef CONFIG_CGROUPS - /* - * group_rwsem prevents new tasks from entering the threadgroup and - * member tasks from exiting,a more specifically, setting of - * PF_EXITING. fork and exit paths are protected with this rwsem - * using threadgroup_change_begin/end(). Users which require - * threadgroup to remain stable should use threadgroup_[un]lock() - * which also takes care of exec path. Currently, cgroup is the - * only user. - */ - struct rw_semaphore group_rwsem; -#endif oom_flags_t oom_flags; short oom_score_adj; /* OOM kill score adjustment */ @@ -805,6 +831,7 @@ struct user_struct { unsigned long mq_bytes; /* How many bytes can be allocated to mqueue? */ #endif unsigned long locked_shm; /* How many pages of mlocked shm ? */ + unsigned long unix_inflight; /* How many files in flight in unix sockets */ #ifdef CONFIG_KEYS struct key *uid_keyring; /* UID specific keyring */ @@ -815,7 +842,7 @@ struct user_struct { struct hlist_node uidhash_node; kuid_t uid; -#ifdef CONFIG_PERF_EVENTS +#if defined(CONFIG_PERF_EVENTS) || defined(CONFIG_BPF_SYSCALL) atomic_long_t locked_vm; #endif }; @@ -831,7 +858,7 @@ extern struct user_struct root_user; struct backing_dev_info; struct reclaim_state; -#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) +#ifdef CONFIG_SCHED_INFO struct sched_info { /* cumulative counters */ unsigned long pcount; /* # of times run on this cpu */ @@ -841,7 +868,7 @@ struct sched_info { unsigned long long last_arrival,/* when we last ran on a cpu */ last_queued; /* when we were last queued to run */ }; -#endif /* defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) */ +#endif /* CONFIG_SCHED_INFO */ #ifdef CONFIG_TASK_DELAY_ACCT struct task_delay_info { @@ -943,8 +970,18 @@ struct wake_q_head { struct wake_q_head name = { WAKE_Q_TAIL, &name.first } extern void wake_q_add(struct wake_q_head *head, - struct task_struct *task); -extern void wake_up_q(struct wake_q_head *head); + struct task_struct *task); +extern void __wake_up_q(struct wake_q_head *head, bool sleeper); + +static inline void wake_up_q(struct wake_q_head *head) +{ + __wake_up_q(head, false); +} + +static inline void wake_up_q_sleeper(struct wake_q_head *head) +{ + __wake_up_q(head, true); +} /* * sched-domains (multiprocessor balancing) declarations: @@ -1114,8 +1151,6 @@ struct sched_domain_topology_level { #endif }; -extern struct sched_domain_topology_level *sched_domain_topology; - extern void set_sched_topology(struct sched_domain_topology_level *tl); extern void wake_up_if_idle(int cpu); @@ -1162,29 +1197,24 @@ struct load_weight { u32 inv_weight; }; +/* + * The load_avg/util_avg accumulates an infinite geometric series. + * 1) load_avg factors frequency scaling into the amount of time that a + * sched_entity is runnable on a rq into its weight. For cfs_rq, it is the + * aggregated such weights of all runnable and blocked sched_entities. + * 2) util_avg factors frequency and cpu scaling into the amount of time + * that a sched_entity is running on a CPU, in the range [0..SCHED_LOAD_SCALE]. + * For cfs_rq, it is the aggregated such times of all runnable and + * blocked sched_entities. + * The 64 bit load_sum can: + * 1) for cfs_rq, afford 4353082796 (=2^64/47742/88761) entities with + * the highest weight (=88761) always runnable, we should not overflow + * 2) for entity, support any load.weight always runnable + */ struct sched_avg { - u64 last_runnable_update; - s64 decay_count; - /* - * utilization_avg_contrib describes the amount of time that a - * sched_entity is running on a CPU. It is based on running_avg_sum - * and is scaled in the range [0..SCHED_LOAD_SCALE]. - * load_avg_contrib described the amount of time that a sched_entity - * is runnable on a rq. It is based on both runnable_avg_sum and the - * weight of the task. - */ - unsigned long load_avg_contrib, utilization_avg_contrib; - /* - * These sums represent an infinite geometric series and so are bound - * above by 1024/(1-y). Thus we only need a u32 to store them for all - * choices of y < 1-2^(-32)*1024. - * running_avg_sum reflects the time that the sched_entity is - * effectively running on the CPU. - * runnable_avg_sum represents the amount of time a sched_entity is on - * a runqueue which includes the running time that is monitored by - * running_avg_sum. - */ - u32 runnable_avg_sum, avg_period, running_avg_sum; + u64 last_update_time, load_sum; + u32 util_sum, period_contrib; + unsigned long load_avg, util_avg; }; #ifdef CONFIG_SCHEDSTATS @@ -1250,7 +1280,7 @@ struct sched_entity { #endif #ifdef CONFIG_SMP - /* Per-entity load-tracking */ + /* Per entity load average tracking */ struct sched_avg avg; #endif }; @@ -1322,10 +1352,12 @@ struct sched_dl_entity { union rcu_special { struct { - bool blocked; - bool need_qs; - } b; - short s; + u8 blocked; + u8 need_qs; + u8 exp_need_qs; + u8 pad; /* Otherwise the compiler can store garbage here. */ + } b; /* Bits. */ + u32 s; /* Set of bits. */ }; struct rcu_node; @@ -1336,6 +1368,25 @@ enum perf_event_task_context { perf_nr_task_contexts, }; +/* Track pages that require TLB flushes */ +struct tlbflush_unmap_batch { + /* + * Each bit set is a CPU that potentially has a TLB entry for one of + * the PFNs being flushed. See set_tlb_ubc_flush_pending(). + */ + struct cpumask cpumask; + + /* True if any bit in cpumask is set */ + bool flush_required; + + /* + * If true then the PTE was dirty when unmapped. The entry must be + * flushed before IO is initiated or a stale TLB entry potentially + * allows an update without redirtying the page. + */ + bool writable; +}; + struct task_struct { volatile long state; /* -1 unrunnable, 0 runnable, >0 stopped */ volatile long saved_state; /* saved state for "spinlock sleepers" */ @@ -1347,9 +1398,9 @@ struct task_struct { #ifdef CONFIG_SMP struct llist_node wake_entry; int on_cpu; - struct task_struct *last_wakee; - unsigned long wakee_flips; + unsigned int wakee_flips; unsigned long wakee_flip_decay_ts; + struct task_struct *last_wakee; int wake_cpu; #endif @@ -1388,8 +1439,6 @@ struct task_struct { int rcu_read_lock_nesting; union rcu_special rcu_read_unlock_special; struct list_head rcu_node_entry; -#endif /* #ifdef CONFIG_PREEMPT_RCU */ -#ifdef CONFIG_PREEMPT_RCU struct rcu_node *rcu_blocked_node; #endif /* #ifdef CONFIG_PREEMPT_RCU */ #ifdef CONFIG_TASKS_RCU @@ -1399,7 +1448,7 @@ struct task_struct { int rcu_tasks_idle_cpu; #endif /* #ifdef CONFIG_TASKS_RCU */ -#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) +#ifdef CONFIG_SCHED_INFO struct sched_info sched_info; #endif @@ -1410,9 +1459,6 @@ struct task_struct { #endif struct mm_struct *mm, *active_mm; -#ifdef CONFIG_COMPAT_BRK - unsigned brk_randomized:1; -#endif /* per-thread vma caching */ u32 vmacache_seqnum; struct vm_area_struct *vmacache[VMACACHE_SIZE]; @@ -1423,22 +1469,29 @@ struct task_struct { int exit_state; int exit_code, exit_signal; int pdeath_signal; /* The signal sent when the parent dies */ - unsigned int jobctl; /* JOBCTL_*, siglock protected */ + unsigned long jobctl; /* JOBCTL_*, siglock protected */ /* Used for emulating ABI behavior of previous Linux versions */ unsigned int personality; - unsigned in_execve:1; /* Tell the LSMs that the process is doing an - * execve */ - unsigned in_iowait:1; - - /* Revert to default priority/policy when forking */ + /* scheduler bits, serialized by scheduler locks */ unsigned sched_reset_on_fork:1; unsigned sched_contributes_to_load:1; + unsigned sched_migrated:1; + unsigned :0; /* force alignment to the next boundary */ + /* unserialized, strictly 'current' */ + unsigned in_execve:1; /* bit to tell LSMs we're in execve */ + unsigned in_iowait:1; +#ifdef CONFIG_MEMCG + unsigned memcg_may_oom:1; +#endif #ifdef CONFIG_MEMCG_KMEM unsigned memcg_kmem_skip_account:1; #endif +#ifdef CONFIG_COMPAT_BRK + unsigned brk_randomized:1; +#endif unsigned long atomic_flags; /* Flags needing atomic access. */ @@ -1484,9 +1537,7 @@ struct task_struct { cputime_t utime, stime, utimescaled, stimescaled; cputime_t gtime; -#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE - struct cputime prev_cputime; -#endif + struct prev_cputime prev_cputime; #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN raw_spinlock_t vtime_lock; seqcount_t vtime_seq; @@ -1519,7 +1570,7 @@ struct task_struct { it with task_lock()) - initialized normally by setup_new_exec */ /* file system info */ - int link_count, total_link_count; + struct nameidata *nameidata; #ifdef CONFIG_SYSVIPC /* ipc stuff */ struct sysv_sem sysvsem; @@ -1529,8 +1580,6 @@ struct task_struct { /* hung task detection */ unsigned long last_switch_count; #endif -/* CPU-specific state of this task */ - struct thread_struct thread; /* filesystem information */ struct fs_struct *fs; /* open file information */ @@ -1552,9 +1601,7 @@ struct task_struct { unsigned long sas_ss_sp; size_t sas_ss_size; - int (*notifier)(void *priv); - void *notifier_data; - sigset_t *notifier_mask; + struct callback_head *task_works; struct audit_context *audit_context; @@ -1713,6 +1760,10 @@ struct task_struct { unsigned long numa_pages_migrated; #endif /* CONFIG_NUMA_BALANCING */ +#ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH + struct tlbflush_unmap_batch tlb_ubc; +#endif + struct rcu_head rcu; /* @@ -1778,12 +1829,12 @@ struct task_struct { #endif #endif /* CONFIG_TRACING */ #ifdef CONFIG_MEMCG - struct memcg_oom_info { - struct mem_cgroup *memcg; - gfp_t gfp_mask; - int order; - unsigned int may_oom:1; - } memcg_oom; + struct mem_cgroup *memcg_in_oom; + gfp_t memcg_oom_gfp_mask; + int memcg_oom_order; + + /* number of pages to reclaim on returning to userland */ + unsigned int memcg_nr_pages_over_high; #endif #ifdef CONFIG_UPROBES struct uprobe_task *utask; @@ -1806,9 +1857,26 @@ struct task_struct { #ifdef CONFIG_DEBUG_ATOMIC_SLEEP unsigned long task_state_change; #endif +#ifdef CONFIG_PREEMPT_RT_FULL + int xmit_recursion; +#endif int pagefault_disabled; +/* CPU-specific state of this task */ + struct thread_struct thread; +/* + * WARNING: on x86, 'thread_struct' contains a variable-sized + * structure. It *MUST* be at the end of 'task_struct'. + * + * Do not put anything below here! + */ }; +#ifdef CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT +extern int arch_task_struct_size __read_mostly; +#else +# define arch_task_struct_size (sizeof(struct task_struct)) +#endif + #define TNF_MIGRATED 0x01 #define TNF_NO_GROUP 0x02 #define TNF_SHARED 0x04 @@ -1980,7 +2048,8 @@ static inline int pid_alive(const struct task_struct *p) } /** - * is_global_init - check if a task structure is init + * is_global_init - check if a task structure is init. Since init + * is free to have sub-threads we need to check tgid. * @tsk: Task structure to be checked. * * Check if a task structure is the first user space task the kernel created. @@ -1989,7 +2058,7 @@ static inline int pid_alive(const struct task_struct *p) */ static inline int is_global_init(struct task_struct *tsk) { - return tsk->pid == 1; + return task_tgid_nr(tsk) == 1; } extern struct pid *cad_pid; @@ -2168,22 +2237,22 @@ TASK_PFA_CLEAR(SPREAD_SLAB, spread_slab) #define JOBCTL_TRAPPING_BIT 21 /* switching to TRACED */ #define JOBCTL_LISTENING_BIT 22 /* ptracer is listening for events */ -#define JOBCTL_STOP_DEQUEUED (1 << JOBCTL_STOP_DEQUEUED_BIT) -#define JOBCTL_STOP_PENDING (1 << JOBCTL_STOP_PENDING_BIT) -#define JOBCTL_STOP_CONSUME (1 << JOBCTL_STOP_CONSUME_BIT) -#define JOBCTL_TRAP_STOP (1 << JOBCTL_TRAP_STOP_BIT) -#define JOBCTL_TRAP_NOTIFY (1 << JOBCTL_TRAP_NOTIFY_BIT) -#define JOBCTL_TRAPPING (1 << JOBCTL_TRAPPING_BIT) -#define JOBCTL_LISTENING (1 << JOBCTL_LISTENING_BIT) +#define JOBCTL_STOP_DEQUEUED (1UL << JOBCTL_STOP_DEQUEUED_BIT) +#define JOBCTL_STOP_PENDING (1UL << JOBCTL_STOP_PENDING_BIT) +#define JOBCTL_STOP_CONSUME (1UL << JOBCTL_STOP_CONSUME_BIT) +#define JOBCTL_TRAP_STOP (1UL << JOBCTL_TRAP_STOP_BIT) +#define JOBCTL_TRAP_NOTIFY (1UL << JOBCTL_TRAP_NOTIFY_BIT) +#define JOBCTL_TRAPPING (1UL << JOBCTL_TRAPPING_BIT) +#define JOBCTL_LISTENING (1UL << JOBCTL_LISTENING_BIT) #define JOBCTL_TRAP_MASK (JOBCTL_TRAP_STOP | JOBCTL_TRAP_NOTIFY) #define JOBCTL_PENDING_MASK (JOBCTL_STOP_PENDING | JOBCTL_TRAP_MASK) extern bool task_set_jobctl_pending(struct task_struct *task, - unsigned int mask); + unsigned long mask); extern void task_clear_jobctl_trapping(struct task_struct *task); extern void task_clear_jobctl_pending(struct task_struct *task, - unsigned int mask); + unsigned long mask); static inline void rcu_copy_process(struct task_struct *p) { @@ -2246,13 +2315,6 @@ static inline void calc_load_enter_idle(void) { } static inline void calc_load_exit_idle(void) { } #endif /* CONFIG_NO_HZ_COMMON */ -#ifndef CONFIG_CPUMASK_OFFSTACK -static inline int set_cpus_allowed(struct task_struct *p, cpumask_t new_mask) -{ - return set_cpus_allowed_ptr(p, &new_mask); -} -#endif - /* * Do not use outside of architecture code which knows its limitations. * @@ -2464,26 +2526,33 @@ extern void sched_dead(struct task_struct *p); extern void proc_caches_init(void); extern void flush_signals(struct task_struct *); -extern void __flush_signals(struct task_struct *); extern void ignore_signals(struct task_struct *); extern void flush_signal_handlers(struct task_struct *, int force_default); extern int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info); -static inline int dequeue_signal_lock(struct task_struct *tsk, sigset_t *mask, siginfo_t *info) +static inline int kernel_dequeue_signal(siginfo_t *info) { - unsigned long flags; + struct task_struct *tsk = current; + siginfo_t __info; int ret; - spin_lock_irqsave(&tsk->sighand->siglock, flags); - ret = dequeue_signal(tsk, mask, info); - spin_unlock_irqrestore(&tsk->sighand->siglock, flags); + spin_lock_irq(&tsk->sighand->siglock); + ret = dequeue_signal(tsk, &tsk->blocked, info ?: &__info); + spin_unlock_irq(&tsk->sighand->siglock); return ret; } -extern void block_all_signals(int (*notifier)(void *priv), void *priv, - sigset_t *mask); -extern void unblock_all_signals(void); +static inline void kernel_signal_stop(void) +{ + spin_lock_irq(¤t->sighand->siglock); + if (current->jobctl & JOBCTL_STOP_DEQUEUED) + __set_current_state(TASK_STOPPED); + spin_unlock_irq(¤t->sighand->siglock); + + schedule(); +} + extern void release_task(struct task_struct * p); extern int send_sig_info(int, struct siginfo *, struct task_struct *); extern int force_sigsegv(int, struct task_struct *); @@ -2600,8 +2669,22 @@ extern struct mm_struct *mm_access(struct task_struct *task, unsigned int mode); /* Remove the current tasks stale references to the old mm_struct */ extern void mm_release(struct task_struct *, struct mm_struct *); +#ifdef CONFIG_HAVE_COPY_THREAD_TLS +extern int copy_thread_tls(unsigned long, unsigned long, unsigned long, + struct task_struct *, unsigned long); +#else extern int copy_thread(unsigned long, unsigned long, unsigned long, struct task_struct *); + +/* Architectures that haven't opted into copy_thread_tls get the tls argument + * via pt_regs, so ignore the tls argument passed via C. */ +static inline int copy_thread_tls( + unsigned long clone_flags, unsigned long sp, unsigned long arg, + struct task_struct *p, unsigned long tls) +{ + return copy_thread(clone_flags, sp, arg, p); +} +#endif extern void flush_thread(void); extern void exit_thread(void); @@ -2620,6 +2703,7 @@ extern int do_execveat(int, struct filename *, const char __user * const __user *, const char __user * const __user *, int); +extern long _do_fork(unsigned long, unsigned long, unsigned long, int __user *, int __user *, unsigned long); extern long do_fork(unsigned long, unsigned long, unsigned long, int __user *, int __user *); struct task_struct *fork_idle(int); extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags); @@ -2643,6 +2727,9 @@ static inline unsigned long wait_task_inactive(struct task_struct *p, } #endif +#define tasklist_empty() \ + list_empty(&init_task.tasks) + #define next_task(p) \ list_entry_rcu((p)->tasks.next, struct task_struct, tasks) @@ -2751,53 +2838,33 @@ static inline void unlock_task_sighand(struct task_struct *tsk, spin_unlock_irqrestore(&tsk->sighand->siglock, *flags); } -#ifdef CONFIG_CGROUPS -static inline void threadgroup_change_begin(struct task_struct *tsk) -{ - down_read(&tsk->signal->group_rwsem); -} -static inline void threadgroup_change_end(struct task_struct *tsk) -{ - up_read(&tsk->signal->group_rwsem); -} - /** - * threadgroup_lock - lock threadgroup - * @tsk: member task of the threadgroup to lock + * threadgroup_change_begin - mark the beginning of changes to a threadgroup + * @tsk: task causing the changes * - * Lock the threadgroup @tsk belongs to. No new task is allowed to enter - * and member tasks aren't allowed to exit (as indicated by PF_EXITING) or - * change ->group_leader/pid. This is useful for cases where the threadgroup - * needs to stay stable across blockable operations. - * - * fork and exit paths explicitly call threadgroup_change_{begin|end}() for - * synchronization. While held, no new task will be added to threadgroup - * and no existing live task will have its PF_EXITING set. - * - * de_thread() does threadgroup_change_{begin|end}() when a non-leader - * sub-thread becomes a new leader. + * All operations which modify a threadgroup - a new thread joining the + * group, death of a member thread (the assertion of PF_EXITING) and + * exec(2) dethreading the process and replacing the leader - are wrapped + * by threadgroup_change_{begin|end}(). This is to provide a place which + * subsystems needing threadgroup stability can hook into for + * synchronization. */ -static inline void threadgroup_lock(struct task_struct *tsk) +static inline void threadgroup_change_begin(struct task_struct *tsk) { - down_write(&tsk->signal->group_rwsem); + might_sleep(); + cgroup_threadgroup_change_begin(tsk); } /** - * threadgroup_unlock - unlock threadgroup - * @tsk: member task of the threadgroup to unlock + * threadgroup_change_end - mark the end of changes to a threadgroup + * @tsk: task causing the changes * - * Reverse threadgroup_lock(). + * See threadgroup_change_begin(). */ -static inline void threadgroup_unlock(struct task_struct *tsk) +static inline void threadgroup_change_end(struct task_struct *tsk) { - up_write(&tsk->signal->group_rwsem); + cgroup_threadgroup_change_end(tsk); } -#else -static inline void threadgroup_change_begin(struct task_struct *tsk) {} -static inline void threadgroup_change_end(struct task_struct *tsk) {} -static inline void threadgroup_lock(struct task_struct *tsk) {} -static inline void threadgroup_unlock(struct task_struct *tsk) {} -#endif #ifndef __HAVE_THREAD_FUNCTIONS @@ -3027,12 +3094,6 @@ extern int _cond_resched(void); extern int __cond_resched_lock(spinlock_t *lock); -#if defined(CONFIG_PREEMPT_COUNT) && !defined(CONFIG_PREEMPT_RT_FULL) -#define PREEMPT_LOCK_OFFSET PREEMPT_OFFSET -#else -#define PREEMPT_LOCK_OFFSET 0 -#endif - #define cond_resched_lock(lock) ({ \ ___might_sleep(__FILE__, __LINE__, PREEMPT_LOCK_OFFSET);\ __cond_resched_lock(lock); \ @@ -3159,11 +3220,6 @@ static __always_inline bool need_resched(void) void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times); void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times); -static inline void thread_group_cputime_init(struct signal_struct *sig) -{ - raw_spin_lock_init(&sig->cputimer.lock); -} - /* * Reevaluate whether the task has signals pending delivery. * Wake the task if so. @@ -3226,14 +3282,19 @@ static inline int __migrate_disabled(struct task_struct *p) /* Future-safe accessor for struct task_struct's cpus_allowed. */ static inline const struct cpumask *tsk_cpus_allowed(struct task_struct *p) { -#ifdef CONFIG_PREEMPT_RT_FULL - if (p->migrate_disable) + if (__migrate_disabled(p)) return cpumask_of(task_cpu(p)); -#endif return &p->cpus_allowed; } +static inline int tsk_nr_cpus_allowed(struct task_struct *p) +{ + if (__migrate_disabled(p)) + return 1; + return p->nr_cpus_allowed; +} + extern long sched_setaffinity(pid_t pid, const struct cpumask *new_mask); extern long sched_getaffinity(pid_t pid, struct cpumask *mask); @@ -3297,13 +3358,13 @@ static inline void mm_update_next_owner(struct mm_struct *mm) static inline unsigned long task_rlimit(const struct task_struct *tsk, unsigned int limit) { - return ACCESS_ONCE(tsk->signal->rlim[limit].rlim_cur); + return READ_ONCE(tsk->signal->rlim[limit].rlim_cur); } static inline unsigned long task_rlimit_max(const struct task_struct *tsk, unsigned int limit) { - return ACCESS_ONCE(tsk->signal->rlim[limit].rlim_max); + return READ_ONCE(tsk->signal->rlim[limit].rlim_max); } static inline unsigned long rlimit(unsigned int limit) diff --git a/kernel/include/linux/sched/deadline.h b/kernel/include/linux/sched/deadline.h index 9d303b884..9089a2ae9 100644 --- a/kernel/include/linux/sched/deadline.h +++ b/kernel/include/linux/sched/deadline.h @@ -21,4 +21,9 @@ static inline int dl_task(struct task_struct *p) return dl_prio(p->prio); } +static inline bool dl_time_before(u64 a, u64 b) +{ + return (s64)(a - b) < 0; +} + #endif /* _SCHED_DEADLINE_H */ diff --git a/kernel/include/linux/sched/sysctl.h b/kernel/include/linux/sched/sysctl.h index 596a0e007..c9e4731cf 100644 --- a/kernel/include/linux/sched/sysctl.h +++ b/kernel/include/linux/sched/sysctl.h @@ -57,24 +57,12 @@ extern unsigned int sysctl_numa_balancing_scan_size; extern unsigned int sysctl_sched_migration_cost; extern unsigned int sysctl_sched_nr_migrate; extern unsigned int sysctl_sched_time_avg; -extern unsigned int sysctl_timer_migration; extern unsigned int sysctl_sched_shares_window; int sched_proc_update_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos); #endif -#ifdef CONFIG_SCHED_DEBUG -static inline unsigned int get_sysctl_timer_migration(void) -{ - return sysctl_timer_migration; -} -#else -static inline unsigned int get_sysctl_timer_migration(void) -{ - return 1; -} -#endif /* * control realtime throttling: diff --git a/kernel/include/linux/scif.h b/kernel/include/linux/scif.h new file mode 100644 index 000000000..49a35d6ed --- /dev/null +++ b/kernel/include/linux/scif.h @@ -0,0 +1,1339 @@ +/* + * Intel MIC Platform Software Stack (MPSS) + * + * This file is provided under a dual BSD/GPLv2 license. When using or + * redistributing this file, you may do so under either license. + * + * GPL LICENSE SUMMARY + * + * Copyright(c) 2014 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public License as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * BSD LICENSE + * + * Copyright(c) 2014 Intel Corporation. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * * Neither the name of Intel Corporation nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + * + * Intel SCIF driver. + * + */ +#ifndef __SCIF_H__ +#define __SCIF_H__ + +#include <linux/types.h> +#include <linux/poll.h> +#include <linux/device.h> +#include <linux/scif_ioctl.h> + +#define SCIF_ACCEPT_SYNC 1 +#define SCIF_SEND_BLOCK 1 +#define SCIF_RECV_BLOCK 1 + +enum { + SCIF_PROT_READ = (1 << 0), + SCIF_PROT_WRITE = (1 << 1) +}; + +enum { + SCIF_MAP_FIXED = 0x10, + SCIF_MAP_KERNEL = 0x20, +}; + +enum { + SCIF_FENCE_INIT_SELF = (1 << 0), + SCIF_FENCE_INIT_PEER = (1 << 1), + SCIF_SIGNAL_LOCAL = (1 << 4), + SCIF_SIGNAL_REMOTE = (1 << 5) +}; + +enum { + SCIF_RMA_USECPU = (1 << 0), + SCIF_RMA_USECACHE = (1 << 1), + SCIF_RMA_SYNC = (1 << 2), + SCIF_RMA_ORDERED = (1 << 3) +}; + +/* End of SCIF Admin Reserved Ports */ +#define SCIF_ADMIN_PORT_END 1024 + +/* End of SCIF Reserved Ports */ +#define SCIF_PORT_RSVD 1088 + +typedef struct scif_endpt *scif_epd_t; +typedef struct scif_pinned_pages *scif_pinned_pages_t; + +/** + * struct scif_range - SCIF registered range used in kernel mode + * @cookie: cookie used internally by SCIF + * @nr_pages: number of pages of PAGE_SIZE + * @prot_flags: R/W protection + * @phys_addr: Array of bus addresses + * @va: Array of kernel virtual addresses backed by the pages in the phys_addr + * array. The va is populated only when called on the host for a remote + * SCIF connection on MIC. This is required to support the use case of DMA + * between MIC and another device which is not a SCIF node e.g., an IB or + * ethernet NIC. + */ +struct scif_range { + void *cookie; + int nr_pages; + int prot_flags; + dma_addr_t *phys_addr; + void __iomem **va; +}; + +/** + * struct scif_pollepd - SCIF endpoint to be monitored via scif_poll + * @epd: SCIF endpoint + * @events: requested events + * @revents: returned events + */ +struct scif_pollepd { + scif_epd_t epd; + short events; + short revents; +}; + +/** + * scif_peer_dev - representation of a peer SCIF device + * + * Peer devices show up as PCIe devices for the mgmt node but not the cards. + * The mgmt node discovers all the cards on the PCIe bus and informs the other + * cards about their peers. Upon notification of a peer a node adds a peer + * device to the peer bus to maintain symmetry in the way devices are + * discovered across all nodes in the SCIF network. + * + * @dev: underlying device + * @dnode - The destination node which this device will communicate with. + */ +struct scif_peer_dev { + struct device dev; + u8 dnode; +}; + +/** + * scif_client - representation of a SCIF client + * @name: client name + * @probe - client method called when a peer device is registered + * @remove - client method called when a peer device is unregistered + * @si - subsys_interface used internally for implementing SCIF clients + */ +struct scif_client { + const char *name; + void (*probe)(struct scif_peer_dev *spdev); + void (*remove)(struct scif_peer_dev *spdev); + struct subsys_interface si; +}; + +#define SCIF_OPEN_FAILED ((scif_epd_t)-1) +#define SCIF_REGISTER_FAILED ((off_t)-1) +#define SCIF_MMAP_FAILED ((void *)-1) + +/** + * scif_open() - Create an endpoint + * + * Return: + * Upon successful completion, scif_open() returns an endpoint descriptor to + * be used in subsequent SCIF functions calls to refer to that endpoint; + * otherwise in user mode SCIF_OPEN_FAILED (that is ((scif_epd_t)-1)) is + * returned and errno is set to indicate the error; in kernel mode a NULL + * scif_epd_t is returned. + * + * Errors: + * ENOMEM - Insufficient kernel memory was available + */ +scif_epd_t scif_open(void); + +/** + * scif_bind() - Bind an endpoint to a port + * @epd: endpoint descriptor + * @pn: port number + * + * scif_bind() binds endpoint epd to port pn, where pn is a port number on the + * local node. If pn is zero, a port number greater than or equal to + * SCIF_PORT_RSVD is assigned and returned. Each endpoint may be bound to + * exactly one local port. Ports less than 1024 when requested can only be bound + * by system (or root) processes or by processes executed by privileged users. + * + * Return: + * Upon successful completion, scif_bind() returns the port number to which epd + * is bound; otherwise in user mode -1 is returned and errno is set to + * indicate the error; in kernel mode the negative of one of the following + * errors is returned. + * + * Errors: + * EBADF, ENOTTY - epd is not a valid endpoint descriptor + * EINVAL - the endpoint or the port is already bound + * EISCONN - The endpoint is already connected + * ENOSPC - No port number available for assignment + * EACCES - The port requested is protected and the user is not the superuser + */ +int scif_bind(scif_epd_t epd, u16 pn); + +/** + * scif_listen() - Listen for connections on an endpoint + * @epd: endpoint descriptor + * @backlog: maximum pending connection requests + * + * scif_listen() marks the endpoint epd as a listening endpoint - that is, as + * an endpoint that will be used to accept incoming connection requests. Once + * so marked, the endpoint is said to be in the listening state and may not be + * used as the endpoint of a connection. + * + * The endpoint, epd, must have been bound to a port. + * + * The backlog argument defines the maximum length to which the queue of + * pending connections for epd may grow. If a connection request arrives when + * the queue is full, the client may receive an error with an indication that + * the connection was refused. + * + * Return: + * Upon successful completion, scif_listen() returns 0; otherwise in user mode + * -1 is returned and errno is set to indicate the error; in kernel mode the + * negative of one of the following errors is returned. + * + * Errors: + * EBADF, ENOTTY - epd is not a valid endpoint descriptor + * EINVAL - the endpoint is not bound to a port + * EISCONN - The endpoint is already connected or listening + */ +int scif_listen(scif_epd_t epd, int backlog); + +/** + * scif_connect() - Initiate a connection on a port + * @epd: endpoint descriptor + * @dst: global id of port to which to connect + * + * The scif_connect() function requests the connection of endpoint epd to remote + * port dst. If the connection is successful, a peer endpoint, bound to dst, is + * created on node dst.node. On successful return, the connection is complete. + * + * If the endpoint epd has not already been bound to a port, scif_connect() + * will bind it to an unused local port. + * + * A connection is terminated when an endpoint of the connection is closed, + * either explicitly by scif_close(), or when a process that owns one of the + * endpoints of the connection is terminated. + * + * In user space, scif_connect() supports an asynchronous connection mode + * if the application has set the O_NONBLOCK flag on the endpoint via the + * fcntl() system call. Setting this flag will result in the calling process + * not to wait during scif_connect(). + * + * Return: + * Upon successful completion, scif_connect() returns the port ID to which the + * endpoint, epd, is bound; otherwise in user mode -1 is returned and errno is + * set to indicate the error; in kernel mode the negative of one of the + * following errors is returned. + * + * Errors: + * EBADF, ENOTTY - epd is not a valid endpoint descriptor + * ECONNREFUSED - The destination was not listening for connections or refused + * the connection request + * EINVAL - dst.port is not a valid port ID + * EISCONN - The endpoint is already connected + * ENOMEM - No buffer space is available + * ENODEV - The destination node does not exist, or the node is lost or existed, + * but is not currently in the network since it may have crashed + * ENOSPC - No port number available for assignment + * EOPNOTSUPP - The endpoint is listening and cannot be connected + */ +int scif_connect(scif_epd_t epd, struct scif_port_id *dst); + +/** + * scif_accept() - Accept a connection on an endpoint + * @epd: endpoint descriptor + * @peer: global id of port to which connected + * @newepd: new connected endpoint descriptor + * @flags: flags + * + * The scif_accept() call extracts the first connection request from the queue + * of pending connections for the port on which epd is listening. scif_accept() + * creates a new endpoint, bound to the same port as epd, and allocates a new + * SCIF endpoint descriptor, returned in newepd, for the endpoint. The new + * endpoint is connected to the endpoint through which the connection was + * requested. epd is unaffected by this call, and remains in the listening + * state. + * + * On successful return, peer holds the global port identifier (node id and + * local port number) of the port which requested the connection. + * + * A connection is terminated when an endpoint of the connection is closed, + * either explicitly by scif_close(), or when a process that owns one of the + * endpoints of the connection is terminated. + * + * The number of connections that can (subsequently) be accepted on epd is only + * limited by system resources (memory). + * + * The flags argument is formed by OR'ing together zero or more of the + * following values. + * SCIF_ACCEPT_SYNC - block until a connection request is presented. If + * SCIF_ACCEPT_SYNC is not in flags, and no pending + * connections are present on the queue, scif_accept() + * fails with an EAGAIN error + * + * In user mode, the select() and poll() functions can be used to determine + * when there is a connection request. In kernel mode, the scif_poll() + * function may be used for this purpose. A readable event will be delivered + * when a connection is requested. + * + * Return: + * Upon successful completion, scif_accept() returns 0; otherwise in user mode + * -1 is returned and errno is set to indicate the error; in kernel mode the + * negative of one of the following errors is returned. + * + * Errors: + * EAGAIN - SCIF_ACCEPT_SYNC is not set and no connections are present to be + * accepted or SCIF_ACCEPT_SYNC is not set and remote node failed to complete + * its connection request + * EBADF, ENOTTY - epd is not a valid endpoint descriptor + * EINTR - Interrupted function + * EINVAL - epd is not a listening endpoint, or flags is invalid, or peer is + * NULL, or newepd is NULL + * ENODEV - The requesting node is lost or existed, but is not currently in the + * network since it may have crashed + * ENOMEM - Not enough space + * ENOENT - Secondary part of epd registration failed + */ +int scif_accept(scif_epd_t epd, struct scif_port_id *peer, scif_epd_t + *newepd, int flags); + +/** + * scif_close() - Close an endpoint + * @epd: endpoint descriptor + * + * scif_close() closes an endpoint and performs necessary teardown of + * facilities associated with that endpoint. + * + * If epd is a listening endpoint then it will no longer accept connection + * requests on the port to which it is bound. Any pending connection requests + * are rejected. + * + * If epd is a connected endpoint, then its peer endpoint is also closed. RMAs + * which are in-process through epd or its peer endpoint will complete before + * scif_close() returns. Registered windows of the local and peer endpoints are + * released as if scif_unregister() was called against each window. + * + * Closing a SCIF endpoint does not affect local registered memory mapped by + * a SCIF endpoint on a remote node. The local memory remains mapped by the peer + * SCIF endpoint explicitly removed by calling munmap(..) by the peer. + * + * If the peer endpoint's receive queue is not empty at the time that epd is + * closed, then the peer endpoint can be passed as the endpoint parameter to + * scif_recv() until the receive queue is empty. + * + * epd is freed and may no longer be accessed. + * + * Return: + * Upon successful completion, scif_close() returns 0; otherwise in user mode + * -1 is returned and errno is set to indicate the error; in kernel mode the + * negative of one of the following errors is returned. + * + * Errors: + * EBADF, ENOTTY - epd is not a valid endpoint descriptor + */ +int scif_close(scif_epd_t epd); + +/** + * scif_send() - Send a message + * @epd: endpoint descriptor + * @msg: message buffer address + * @len: message length + * @flags: blocking mode flags + * + * scif_send() sends data to the peer of endpoint epd. Up to len bytes of data + * are copied from memory starting at address msg. On successful execution the + * return value of scif_send() is the number of bytes that were sent, and is + * zero if no bytes were sent because len was zero. scif_send() may be called + * only when the endpoint is in a connected state. + * + * If a scif_send() call is non-blocking, then it sends only those bytes which + * can be sent without waiting, up to a maximum of len bytes. + * + * If a scif_send() call is blocking, then it normally returns after sending + * all len bytes. If a blocking call is interrupted or the connection is + * reset, the call is considered successful if some bytes were sent or len is + * zero, otherwise the call is considered unsuccessful. + * + * In user mode, the select() and poll() functions can be used to determine + * when the send queue is not full. In kernel mode, the scif_poll() function + * may be used for this purpose. + * + * It is recommended that scif_send()/scif_recv() only be used for short + * control-type message communication between SCIF endpoints. The SCIF RMA + * APIs are expected to provide better performance for transfer sizes of + * 1024 bytes or longer for the current MIC hardware and software + * implementation. + * + * scif_send() will block until the entire message is sent if SCIF_SEND_BLOCK + * is passed as the flags argument. + * + * Return: + * Upon successful completion, scif_send() returns the number of bytes sent; + * otherwise in user mode -1 is returned and errno is set to indicate the + * error; in kernel mode the negative of one of the following errors is + * returned. + * + * Errors: + * EBADF, ENOTTY - epd is not a valid endpoint descriptor + * ECONNRESET - Connection reset by peer + * EINVAL - flags is invalid, or len is negative + * ENODEV - The remote node is lost or existed, but is not currently in the + * network since it may have crashed + * ENOMEM - Not enough space + * ENOTCONN - The endpoint is not connected + */ +int scif_send(scif_epd_t epd, void *msg, int len, int flags); + +/** + * scif_recv() - Receive a message + * @epd: endpoint descriptor + * @msg: message buffer address + * @len: message buffer length + * @flags: blocking mode flags + * + * scif_recv() receives data from the peer of endpoint epd. Up to len bytes of + * data are copied to memory starting at address msg. On successful execution + * the return value of scif_recv() is the number of bytes that were received, + * and is zero if no bytes were received because len was zero. scif_recv() may + * be called only when the endpoint is in a connected state. + * + * If a scif_recv() call is non-blocking, then it receives only those bytes + * which can be received without waiting, up to a maximum of len bytes. + * + * If a scif_recv() call is blocking, then it normally returns after receiving + * all len bytes. If the blocking call was interrupted due to a disconnection, + * subsequent calls to scif_recv() will copy all bytes received upto the point + * of disconnection. + * + * In user mode, the select() and poll() functions can be used to determine + * when data is available to be received. In kernel mode, the scif_poll() + * function may be used for this purpose. + * + * It is recommended that scif_send()/scif_recv() only be used for short + * control-type message communication between SCIF endpoints. The SCIF RMA + * APIs are expected to provide better performance for transfer sizes of + * 1024 bytes or longer for the current MIC hardware and software + * implementation. + * + * scif_recv() will block until the entire message is received if + * SCIF_RECV_BLOCK is passed as the flags argument. + * + * Return: + * Upon successful completion, scif_recv() returns the number of bytes + * received; otherwise in user mode -1 is returned and errno is set to + * indicate the error; in kernel mode the negative of one of the following + * errors is returned. + * + * Errors: + * EAGAIN - The destination node is returning from a low power state + * EBADF, ENOTTY - epd is not a valid endpoint descriptor + * ECONNRESET - Connection reset by peer + * EINVAL - flags is invalid, or len is negative + * ENODEV - The remote node is lost or existed, but is not currently in the + * network since it may have crashed + * ENOMEM - Not enough space + * ENOTCONN - The endpoint is not connected + */ +int scif_recv(scif_epd_t epd, void *msg, int len, int flags); + +/** + * scif_register() - Mark a memory region for remote access. + * @epd: endpoint descriptor + * @addr: starting virtual address + * @len: length of range + * @offset: offset of window + * @prot_flags: read/write protection flags + * @map_flags: mapping flags + * + * The scif_register() function opens a window, a range of whole pages of the + * registered address space of the endpoint epd, starting at offset po and + * continuing for len bytes. The value of po, further described below, is a + * function of the parameters offset and len, and the value of map_flags. Each + * page of the window represents the physical memory page which backs the + * corresponding page of the range of virtual address pages starting at addr + * and continuing for len bytes. addr and len are constrained to be multiples + * of the page size. A successful scif_register() call returns po. + * + * When SCIF_MAP_FIXED is set in the map_flags argument, po will be offset + * exactly, and offset is constrained to be a multiple of the page size. The + * mapping established by scif_register() will not replace any existing + * registration; an error is returned if any page within the range [offset, + * offset + len - 1] intersects an existing window. + * + * When SCIF_MAP_FIXED is not set, the implementation uses offset in an + * implementation-defined manner to arrive at po. The po value so chosen will + * be an area of the registered address space that the implementation deems + * suitable for a mapping of len bytes. An offset value of 0 is interpreted as + * granting the implementation complete freedom in selecting po, subject to + * constraints described below. A non-zero value of offset is taken to be a + * suggestion of an offset near which the mapping should be placed. When the + * implementation selects a value for po, it does not replace any extant + * window. In all cases, po will be a multiple of the page size. + * + * The physical pages which are so represented by a window are available for + * access in calls to mmap(), scif_readfrom(), scif_writeto(), + * scif_vreadfrom(), and scif_vwriteto(). While a window is registered, the + * physical pages represented by the window will not be reused by the memory + * subsystem for any other purpose. Note that the same physical page may be + * represented by multiple windows. + * + * Subsequent operations which change the memory pages to which virtual + * addresses are mapped (such as mmap(), munmap()) have no effect on + * existing window. + * + * If the process will fork(), it is recommended that the registered + * virtual address range be marked with MADV_DONTFORK. Doing so will prevent + * problems due to copy-on-write semantics. + * + * The prot_flags argument is formed by OR'ing together one or more of the + * following values. + * SCIF_PROT_READ - allow read operations from the window + * SCIF_PROT_WRITE - allow write operations to the window + * + * Return: + * Upon successful completion, scif_register() returns the offset at which the + * mapping was placed (po); otherwise in user mode SCIF_REGISTER_FAILED (that + * is (off_t *)-1) is returned and errno is set to indicate the error; in + * kernel mode the negative of one of the following errors is returned. + * + * Errors: + * EADDRINUSE - SCIF_MAP_FIXED is set in map_flags, and pages in the range + * [offset, offset + len -1] are already registered + * EAGAIN - The mapping could not be performed due to lack of resources + * EBADF, ENOTTY - epd is not a valid endpoint descriptor + * ECONNRESET - Connection reset by peer + * EINVAL - map_flags is invalid, or prot_flags is invalid, or SCIF_MAP_FIXED is + * set in flags, and offset is not a multiple of the page size, or addr is not a + * multiple of the page size, or len is not a multiple of the page size, or is + * 0, or offset is negative + * ENODEV - The remote node is lost or existed, but is not currently in the + * network since it may have crashed + * ENOMEM - Not enough space + * ENOTCONN -The endpoint is not connected + */ +off_t scif_register(scif_epd_t epd, void *addr, size_t len, off_t offset, + int prot_flags, int map_flags); + +/** + * scif_unregister() - Mark a memory region for remote access. + * @epd: endpoint descriptor + * @offset: start of range to unregister + * @len: length of range to unregister + * + * The scif_unregister() function closes those previously registered windows + * which are entirely within the range [offset, offset + len - 1]. It is an + * error to specify a range which intersects only a subrange of a window. + * + * On a successful return, pages within the window may no longer be specified + * in calls to mmap(), scif_readfrom(), scif_writeto(), scif_vreadfrom(), + * scif_vwriteto(), scif_get_pages, and scif_fence_signal(). The window, + * however, continues to exist until all previous references against it are + * removed. A window is referenced if there is a mapping to it created by + * mmap(), or if scif_get_pages() was called against the window + * (and the pages have not been returned via scif_put_pages()). A window is + * also referenced while an RMA, in which some range of the window is a source + * or destination, is in progress. Finally a window is referenced while some + * offset in that window was specified to scif_fence_signal(), and the RMAs + * marked by that call to scif_fence_signal() have not completed. While a + * window is in this state, its registered address space pages are not + * available for use in a new registered window. + * + * When all such references to the window have been removed, its references to + * all the physical pages which it represents are removed. Similarly, the + * registered address space pages of the window become available for + * registration in a new window. + * + * Return: + * Upon successful completion, scif_unregister() returns 0; otherwise in user + * mode -1 is returned and errno is set to indicate the error; in kernel mode + * the negative of one of the following errors is returned. In the event of an + * error, no windows are unregistered. + * + * Errors: + * EBADF, ENOTTY - epd is not a valid endpoint descriptor + * ECONNRESET - Connection reset by peer + * EINVAL - the range [offset, offset + len - 1] intersects a subrange of a + * window, or offset is negative + * ENODEV - The remote node is lost or existed, but is not currently in the + * network since it may have crashed + * ENOTCONN - The endpoint is not connected + * ENXIO - Offsets in the range [offset, offset + len - 1] are invalid for the + * registered address space of epd + */ +int scif_unregister(scif_epd_t epd, off_t offset, size_t len); + +/** + * scif_readfrom() - Copy from a remote address space + * @epd: endpoint descriptor + * @loffset: offset in local registered address space to + * which to copy + * @len: length of range to copy + * @roffset: offset in remote registered address space + * from which to copy + * @rma_flags: transfer mode flags + * + * scif_readfrom() copies len bytes from the remote registered address space of + * the peer of endpoint epd, starting at the offset roffset to the local + * registered address space of epd, starting at the offset loffset. + * + * Each of the specified ranges [loffset, loffset + len - 1] and [roffset, + * roffset + len - 1] must be within some registered window or windows of the + * local and remote nodes. A range may intersect multiple registered windows, + * but only if those windows are contiguous in the registered address space. + * + * If rma_flags includes SCIF_RMA_USECPU, then the data is copied using + * programmed read/writes. Otherwise the data is copied using DMA. If rma_- + * flags includes SCIF_RMA_SYNC, then scif_readfrom() will return after the + * transfer is complete. Otherwise, the transfer may be performed asynchron- + * ously. The order in which any two asynchronous RMA operations complete + * is non-deterministic. The synchronization functions, scif_fence_mark()/ + * scif_fence_wait() and scif_fence_signal(), can be used to synchronize to + * the completion of asynchronous RMA operations on the same endpoint. + * + * The DMA transfer of individual bytes is not guaranteed to complete in + * address order. If rma_flags includes SCIF_RMA_ORDERED, then the last + * cacheline or partial cacheline of the source range will become visible on + * the destination node after all other transferred data in the source + * range has become visible on the destination node. + * + * The optimal DMA performance will likely be realized if both + * loffset and roffset are cacheline aligned (are a multiple of 64). Lower + * performance will likely be realized if loffset and roffset are not + * cacheline aligned but are separated by some multiple of 64. The lowest level + * of performance is likely if loffset and roffset are not separated by a + * multiple of 64. + * + * The rma_flags argument is formed by ORing together zero or more of the + * following values. + * SCIF_RMA_USECPU - perform the transfer using the CPU, otherwise use the DMA + * engine. + * SCIF_RMA_SYNC - perform the transfer synchronously, returning after the + * transfer has completed. Passing this flag results in the + * current implementation busy waiting and consuming CPU cycles + * while the DMA transfer is in progress for best performance by + * avoiding the interrupt latency. + * SCIF_RMA_ORDERED - ensure that the last cacheline or partial cacheline of + * the source range becomes visible on the destination node + * after all other transferred data in the source range has + * become visible on the destination + * + * Return: + * Upon successful completion, scif_readfrom() returns 0; otherwise in user + * mode -1 is returned and errno is set to indicate the error; in kernel mode + * the negative of one of the following errors is returned. + * + * Errors: + * EACCESS - Attempt to write to a read-only range + * EBADF, ENOTTY - epd is not a valid endpoint descriptor + * ECONNRESET - Connection reset by peer + * EINVAL - rma_flags is invalid + * ENODEV - The remote node is lost or existed, but is not currently in the + * network since it may have crashed + * ENOTCONN - The endpoint is not connected + * ENXIO - The range [loffset, loffset + len - 1] is invalid for the registered + * address space of epd, or, The range [roffset, roffset + len - 1] is invalid + * for the registered address space of the peer of epd, or loffset or roffset + * is negative + */ +int scif_readfrom(scif_epd_t epd, off_t loffset, size_t len, off_t + roffset, int rma_flags); + +/** + * scif_writeto() - Copy to a remote address space + * @epd: endpoint descriptor + * @loffset: offset in local registered address space + * from which to copy + * @len: length of range to copy + * @roffset: offset in remote registered address space to + * which to copy + * @rma_flags: transfer mode flags + * + * scif_writeto() copies len bytes from the local registered address space of + * epd, starting at the offset loffset to the remote registered address space + * of the peer of endpoint epd, starting at the offset roffset. + * + * Each of the specified ranges [loffset, loffset + len - 1] and [roffset, + * roffset + len - 1] must be within some registered window or windows of the + * local and remote nodes. A range may intersect multiple registered windows, + * but only if those windows are contiguous in the registered address space. + * + * If rma_flags includes SCIF_RMA_USECPU, then the data is copied using + * programmed read/writes. Otherwise the data is copied using DMA. If rma_- + * flags includes SCIF_RMA_SYNC, then scif_writeto() will return after the + * transfer is complete. Otherwise, the transfer may be performed asynchron- + * ously. The order in which any two asynchronous RMA operations complete + * is non-deterministic. The synchronization functions, scif_fence_mark()/ + * scif_fence_wait() and scif_fence_signal(), can be used to synchronize to + * the completion of asynchronous RMA operations on the same endpoint. + * + * The DMA transfer of individual bytes is not guaranteed to complete in + * address order. If rma_flags includes SCIF_RMA_ORDERED, then the last + * cacheline or partial cacheline of the source range will become visible on + * the destination node after all other transferred data in the source + * range has become visible on the destination node. + * + * The optimal DMA performance will likely be realized if both + * loffset and roffset are cacheline aligned (are a multiple of 64). Lower + * performance will likely be realized if loffset and roffset are not cacheline + * aligned but are separated by some multiple of 64. The lowest level of + * performance is likely if loffset and roffset are not separated by a multiple + * of 64. + * + * The rma_flags argument is formed by ORing together zero or more of the + * following values. + * SCIF_RMA_USECPU - perform the transfer using the CPU, otherwise use the DMA + * engine. + * SCIF_RMA_SYNC - perform the transfer synchronously, returning after the + * transfer has completed. Passing this flag results in the + * current implementation busy waiting and consuming CPU cycles + * while the DMA transfer is in progress for best performance by + * avoiding the interrupt latency. + * SCIF_RMA_ORDERED - ensure that the last cacheline or partial cacheline of + * the source range becomes visible on the destination node + * after all other transferred data in the source range has + * become visible on the destination + * + * Return: + * Upon successful completion, scif_readfrom() returns 0; otherwise in user + * mode -1 is returned and errno is set to indicate the error; in kernel mode + * the negative of one of the following errors is returned. + * + * Errors: + * EACCESS - Attempt to write to a read-only range + * EBADF, ENOTTY - epd is not a valid endpoint descriptor + * ECONNRESET - Connection reset by peer + * EINVAL - rma_flags is invalid + * ENODEV - The remote node is lost or existed, but is not currently in the + * network since it may have crashed + * ENOTCONN - The endpoint is not connected + * ENXIO - The range [loffset, loffset + len - 1] is invalid for the registered + * address space of epd, or, The range [roffset , roffset + len -1] is invalid + * for the registered address space of the peer of epd, or loffset or roffset + * is negative + */ +int scif_writeto(scif_epd_t epd, off_t loffset, size_t len, off_t + roffset, int rma_flags); + +/** + * scif_vreadfrom() - Copy from a remote address space + * @epd: endpoint descriptor + * @addr: address to which to copy + * @len: length of range to copy + * @roffset: offset in remote registered address space + * from which to copy + * @rma_flags: transfer mode flags + * + * scif_vreadfrom() copies len bytes from the remote registered address + * space of the peer of endpoint epd, starting at the offset roffset, to local + * memory, starting at addr. + * + * The specified range [roffset, roffset + len - 1] must be within some + * registered window or windows of the remote nodes. The range may + * intersect multiple registered windows, but only if those windows are + * contiguous in the registered address space. + * + * If rma_flags includes SCIF_RMA_USECPU, then the data is copied using + * programmed read/writes. Otherwise the data is copied using DMA. If rma_- + * flags includes SCIF_RMA_SYNC, then scif_vreadfrom() will return after the + * transfer is complete. Otherwise, the transfer may be performed asynchron- + * ously. The order in which any two asynchronous RMA operations complete + * is non-deterministic. The synchronization functions, scif_fence_mark()/ + * scif_fence_wait() and scif_fence_signal(), can be used to synchronize to + * the completion of asynchronous RMA operations on the same endpoint. + * + * The DMA transfer of individual bytes is not guaranteed to complete in + * address order. If rma_flags includes SCIF_RMA_ORDERED, then the last + * cacheline or partial cacheline of the source range will become visible on + * the destination node after all other transferred data in the source + * range has become visible on the destination node. + * + * If rma_flags includes SCIF_RMA_USECACHE, then the physical pages which back + * the specified local memory range may be remain in a pinned state even after + * the specified transfer completes. This may reduce overhead if some or all of + * the same virtual address range is referenced in a subsequent call of + * scif_vreadfrom() or scif_vwriteto(). + * + * The optimal DMA performance will likely be realized if both + * addr and roffset are cacheline aligned (are a multiple of 64). Lower + * performance will likely be realized if addr and roffset are not + * cacheline aligned but are separated by some multiple of 64. The lowest level + * of performance is likely if addr and roffset are not separated by a + * multiple of 64. + * + * The rma_flags argument is formed by ORing together zero or more of the + * following values. + * SCIF_RMA_USECPU - perform the transfer using the CPU, otherwise use the DMA + * engine. + * SCIF_RMA_USECACHE - enable registration caching + * SCIF_RMA_SYNC - perform the transfer synchronously, returning after the + * transfer has completed. Passing this flag results in the + * current implementation busy waiting and consuming CPU cycles + * while the DMA transfer is in progress for best performance by + * avoiding the interrupt latency. + * SCIF_RMA_ORDERED - ensure that the last cacheline or partial cacheline of + * the source range becomes visible on the destination node + * after all other transferred data in the source range has + * become visible on the destination + * + * Return: + * Upon successful completion, scif_vreadfrom() returns 0; otherwise in user + * mode -1 is returned and errno is set to indicate the error; in kernel mode + * the negative of one of the following errors is returned. + * + * Errors: + * EACCESS - Attempt to write to a read-only range + * EBADF, ENOTTY - epd is not a valid endpoint descriptor + * ECONNRESET - Connection reset by peer + * EINVAL - rma_flags is invalid + * ENODEV - The remote node is lost or existed, but is not currently in the + * network since it may have crashed + * ENOTCONN - The endpoint is not connected + * ENXIO - Offsets in the range [roffset, roffset + len - 1] are invalid for the + * registered address space of epd + */ +int scif_vreadfrom(scif_epd_t epd, void *addr, size_t len, off_t roffset, + int rma_flags); + +/** + * scif_vwriteto() - Copy to a remote address space + * @epd: endpoint descriptor + * @addr: address from which to copy + * @len: length of range to copy + * @roffset: offset in remote registered address space to + * which to copy + * @rma_flags: transfer mode flags + * + * scif_vwriteto() copies len bytes from the local memory, starting at addr, to + * the remote registered address space of the peer of endpoint epd, starting at + * the offset roffset. + * + * The specified range [roffset, roffset + len - 1] must be within some + * registered window or windows of the remote nodes. The range may intersect + * multiple registered windows, but only if those windows are contiguous in the + * registered address space. + * + * If rma_flags includes SCIF_RMA_USECPU, then the data is copied using + * programmed read/writes. Otherwise the data is copied using DMA. If rma_- + * flags includes SCIF_RMA_SYNC, then scif_vwriteto() will return after the + * transfer is complete. Otherwise, the transfer may be performed asynchron- + * ously. The order in which any two asynchronous RMA operations complete + * is non-deterministic. The synchronization functions, scif_fence_mark()/ + * scif_fence_wait() and scif_fence_signal(), can be used to synchronize to + * the completion of asynchronous RMA operations on the same endpoint. + * + * The DMA transfer of individual bytes is not guaranteed to complete in + * address order. If rma_flags includes SCIF_RMA_ORDERED, then the last + * cacheline or partial cacheline of the source range will become visible on + * the destination node after all other transferred data in the source + * range has become visible on the destination node. + * + * If rma_flags includes SCIF_RMA_USECACHE, then the physical pages which back + * the specified local memory range may be remain in a pinned state even after + * the specified transfer completes. This may reduce overhead if some or all of + * the same virtual address range is referenced in a subsequent call of + * scif_vreadfrom() or scif_vwriteto(). + * + * The optimal DMA performance will likely be realized if both + * addr and offset are cacheline aligned (are a multiple of 64). Lower + * performance will likely be realized if addr and offset are not cacheline + * aligned but are separated by some multiple of 64. The lowest level of + * performance is likely if addr and offset are not separated by a multiple of + * 64. + * + * The rma_flags argument is formed by ORing together zero or more of the + * following values. + * SCIF_RMA_USECPU - perform the transfer using the CPU, otherwise use the DMA + * engine. + * SCIF_RMA_USECACHE - allow registration caching + * SCIF_RMA_SYNC - perform the transfer synchronously, returning after the + * transfer has completed. Passing this flag results in the + * current implementation busy waiting and consuming CPU cycles + * while the DMA transfer is in progress for best performance by + * avoiding the interrupt latency. + * SCIF_RMA_ORDERED - ensure that the last cacheline or partial cacheline of + * the source range becomes visible on the destination node + * after all other transferred data in the source range has + * become visible on the destination + * + * Return: + * Upon successful completion, scif_vwriteto() returns 0; otherwise in user + * mode -1 is returned and errno is set to indicate the error; in kernel mode + * the negative of one of the following errors is returned. + * + * Errors: + * EACCESS - Attempt to write to a read-only range + * EBADF, ENOTTY - epd is not a valid endpoint descriptor + * ECONNRESET - Connection reset by peer + * EINVAL - rma_flags is invalid + * ENODEV - The remote node is lost or existed, but is not currently in the + * network since it may have crashed + * ENOTCONN - The endpoint is not connected + * ENXIO - Offsets in the range [roffset, roffset + len - 1] are invalid for the + * registered address space of epd + */ +int scif_vwriteto(scif_epd_t epd, void *addr, size_t len, off_t roffset, + int rma_flags); + +/** + * scif_fence_mark() - Mark previously issued RMAs + * @epd: endpoint descriptor + * @flags: control flags + * @mark: marked value returned as output. + * + * scif_fence_mark() returns after marking the current set of all uncompleted + * RMAs initiated through the endpoint epd or the current set of all + * uncompleted RMAs initiated through the peer of endpoint epd. The RMAs are + * marked with a value returned at mark. The application may subsequently call + * scif_fence_wait(), passing the value returned at mark, to await completion + * of all RMAs so marked. + * + * The flags argument has exactly one of the following values. + * SCIF_FENCE_INIT_SELF - RMA operations initiated through endpoint + * epd are marked + * SCIF_FENCE_INIT_PEER - RMA operations initiated through the peer + * of endpoint epd are marked + * + * Return: + * Upon successful completion, scif_fence_mark() returns 0; otherwise in user + * mode -1 is returned and errno is set to indicate the error; in kernel mode + * the negative of one of the following errors is returned. + * + * Errors: + * EBADF, ENOTTY - epd is not a valid endpoint descriptor + * ECONNRESET - Connection reset by peer + * EINVAL - flags is invalid + * ENODEV - The remote node is lost or existed, but is not currently in the + * network since it may have crashed + * ENOTCONN - The endpoint is not connected + * ENOMEM - Insufficient kernel memory was available + */ +int scif_fence_mark(scif_epd_t epd, int flags, int *mark); + +/** + * scif_fence_wait() - Wait for completion of marked RMAs + * @epd: endpoint descriptor + * @mark: mark request + * + * scif_fence_wait() returns after all RMAs marked with mark have completed. + * The value passed in mark must have been obtained in a previous call to + * scif_fence_mark(). + * + * Return: + * Upon successful completion, scif_fence_wait() returns 0; otherwise in user + * mode -1 is returned and errno is set to indicate the error; in kernel mode + * the negative of one of the following errors is returned. + * + * Errors: + * EBADF, ENOTTY - epd is not a valid endpoint descriptor + * ECONNRESET - Connection reset by peer + * ENODEV - The remote node is lost or existed, but is not currently in the + * network since it may have crashed + * ENOTCONN - The endpoint is not connected + * ENOMEM - Insufficient kernel memory was available + */ +int scif_fence_wait(scif_epd_t epd, int mark); + +/** + * scif_fence_signal() - Request a memory update on completion of RMAs + * @epd: endpoint descriptor + * @loff: local offset + * @lval: local value to write to loffset + * @roff: remote offset + * @rval: remote value to write to roffset + * @flags: flags + * + * scif_fence_signal() returns after marking the current set of all uncompleted + * RMAs initiated through the endpoint epd or marking the current set of all + * uncompleted RMAs initiated through the peer of endpoint epd. + * + * If flags includes SCIF_SIGNAL_LOCAL, then on completion of the RMAs in the + * marked set, lval is written to memory at the address corresponding to offset + * loff in the local registered address space of epd. loff must be within a + * registered window. If flags includes SCIF_SIGNAL_REMOTE, then on completion + * of the RMAs in the marked set, rval is written to memory at the address + * corresponding to offset roff in the remote registered address space of epd. + * roff must be within a remote registered window of the peer of epd. Note + * that any specified offset must be DWORD (4 byte / 32 bit) aligned. + * + * The flags argument is formed by OR'ing together the following. + * Exactly one of the following values. + * SCIF_FENCE_INIT_SELF - RMA operations initiated through endpoint + * epd are marked + * SCIF_FENCE_INIT_PEER - RMA operations initiated through the peer + * of endpoint epd are marked + * One or more of the following values. + * SCIF_SIGNAL_LOCAL - On completion of the marked set of RMAs, write lval to + * memory at the address corresponding to offset loff in the local + * registered address space of epd. + * SCIF_SIGNAL_REMOTE - On completion of the marked set of RMAs, write rval to + * memory at the address corresponding to offset roff in the remote + * registered address space of epd. + * + * Return: + * Upon successful completion, scif_fence_signal() returns 0; otherwise in + * user mode -1 is returned and errno is set to indicate the error; in kernel + * mode the negative of one of the following errors is returned. + * + * Errors: + * EBADF, ENOTTY - epd is not a valid endpoint descriptor + * ECONNRESET - Connection reset by peer + * EINVAL - flags is invalid, or loff or roff are not DWORD aligned + * ENODEV - The remote node is lost or existed, but is not currently in the + * network since it may have crashed + * ENOTCONN - The endpoint is not connected + * ENXIO - loff is invalid for the registered address of epd, or roff is invalid + * for the registered address space, of the peer of epd + */ +int scif_fence_signal(scif_epd_t epd, off_t loff, u64 lval, off_t roff, + u64 rval, int flags); + +/** + * scif_get_node_ids() - Return information about online nodes + * @nodes: array in which to return online node IDs + * @len: number of entries in the nodes array + * @self: address to place the node ID of the local node + * + * scif_get_node_ids() fills in the nodes array with up to len node IDs of the + * nodes in the SCIF network. If there is not enough space in nodes, as + * indicated by the len parameter, only len node IDs are returned in nodes. The + * return value of scif_get_node_ids() is the total number of nodes currently in + * the SCIF network. By checking the return value against the len parameter, + * the user may determine if enough space for nodes was allocated. + * + * The node ID of the local node is returned at self. + * + * Return: + * Upon successful completion, scif_get_node_ids() returns the actual number of + * online nodes in the SCIF network including 'self'; otherwise in user mode + * -1 is returned and errno is set to indicate the error; in kernel mode no + * errors are returned. + */ +int scif_get_node_ids(u16 *nodes, int len, u16 *self); + +/** + * scif_pin_pages() - Pin a set of pages + * @addr: Virtual address of range to pin + * @len: Length of range to pin + * @prot_flags: Page protection flags + * @map_flags: Page classification flags + * @pinned_pages: Handle to pinned pages + * + * scif_pin_pages() pins (locks in physical memory) the physical pages which + * back the range of virtual address pages starting at addr and continuing for + * len bytes. addr and len are constrained to be multiples of the page size. A + * successful scif_pin_pages() call returns a handle to pinned_pages which may + * be used in subsequent calls to scif_register_pinned_pages(). + * + * The pages will remain pinned as long as there is a reference against the + * scif_pinned_pages_t value returned by scif_pin_pages() and until + * scif_unpin_pages() is called, passing the scif_pinned_pages_t value. A + * reference is added to a scif_pinned_pages_t value each time a window is + * created by calling scif_register_pinned_pages() and passing the + * scif_pinned_pages_t value. A reference is removed from a + * scif_pinned_pages_t value each time such a window is deleted. + * + * Subsequent operations which change the memory pages to which virtual + * addresses are mapped (such as mmap(), munmap()) have no effect on the + * scif_pinned_pages_t value or windows created against it. + * + * If the process will fork(), it is recommended that the registered + * virtual address range be marked with MADV_DONTFORK. Doing so will prevent + * problems due to copy-on-write semantics. + * + * The prot_flags argument is formed by OR'ing together one or more of the + * following values. + * SCIF_PROT_READ - allow read operations against the pages + * SCIF_PROT_WRITE - allow write operations against the pages + * The map_flags argument can be set as SCIF_MAP_KERNEL to interpret addr as a + * kernel space address. By default, addr is interpreted as a user space + * address. + * + * Return: + * Upon successful completion, scif_pin_pages() returns 0; otherwise the + * negative of one of the following errors is returned. + * + * Errors: + * EINVAL - prot_flags is invalid, map_flags is invalid, or offset is negative + * ENOMEM - Not enough space + */ +int scif_pin_pages(void *addr, size_t len, int prot_flags, int map_flags, + scif_pinned_pages_t *pinned_pages); + +/** + * scif_unpin_pages() - Unpin a set of pages + * @pinned_pages: Handle to pinned pages to be unpinned + * + * scif_unpin_pages() prevents scif_register_pinned_pages() from registering new + * windows against pinned_pages. The physical pages represented by pinned_pages + * will remain pinned until all windows previously registered against + * pinned_pages are deleted (the window is scif_unregister()'d and all + * references to the window are removed (see scif_unregister()). + * + * pinned_pages must have been obtain from a previous call to scif_pin_pages(). + * After calling scif_unpin_pages(), it is an error to pass pinned_pages to + * scif_register_pinned_pages(). + * + * Return: + * Upon successful completion, scif_unpin_pages() returns 0; otherwise the + * negative of one of the following errors is returned. + * + * Errors: + * EINVAL - pinned_pages is not valid + */ +int scif_unpin_pages(scif_pinned_pages_t pinned_pages); + +/** + * scif_register_pinned_pages() - Mark a memory region for remote access. + * @epd: endpoint descriptor + * @pinned_pages: Handle to pinned pages + * @offset: Registered address space offset + * @map_flags: Flags which control where pages are mapped + * + * The scif_register_pinned_pages() function opens a window, a range of whole + * pages of the registered address space of the endpoint epd, starting at + * offset po. The value of po, further described below, is a function of the + * parameters offset and pinned_pages, and the value of map_flags. Each page of + * the window represents a corresponding physical memory page of the range + * represented by pinned_pages; the length of the window is the same as the + * length of range represented by pinned_pages. A successful + * scif_register_pinned_pages() call returns po as the return value. + * + * When SCIF_MAP_FIXED is set in the map_flags argument, po will be offset + * exactly, and offset is constrained to be a multiple of the page size. The + * mapping established by scif_register_pinned_pages() will not replace any + * existing registration; an error is returned if any page of the new window + * would intersect an existing window. + * + * When SCIF_MAP_FIXED is not set, the implementation uses offset in an + * implementation-defined manner to arrive at po. The po so chosen will be an + * area of the registered address space that the implementation deems suitable + * for a mapping of the required size. An offset value of 0 is interpreted as + * granting the implementation complete freedom in selecting po, subject to + * constraints described below. A non-zero value of offset is taken to be a + * suggestion of an offset near which the mapping should be placed. When the + * implementation selects a value for po, it does not replace any extant + * window. In all cases, po will be a multiple of the page size. + * + * The physical pages which are so represented by a window are available for + * access in calls to scif_get_pages(), scif_readfrom(), scif_writeto(), + * scif_vreadfrom(), and scif_vwriteto(). While a window is registered, the + * physical pages represented by the window will not be reused by the memory + * subsystem for any other purpose. Note that the same physical page may be + * represented by multiple windows. + * + * Windows created by scif_register_pinned_pages() are unregistered by + * scif_unregister(). + * + * The map_flags argument can be set to SCIF_MAP_FIXED which interprets a + * fixed offset. + * + * Return: + * Upon successful completion, scif_register_pinned_pages() returns the offset + * at which the mapping was placed (po); otherwise the negative of one of the + * following errors is returned. + * + * Errors: + * EADDRINUSE - SCIF_MAP_FIXED is set in map_flags and pages in the new window + * would intersect an existing window + * EAGAIN - The mapping could not be performed due to lack of resources + * ECONNRESET - Connection reset by peer + * EINVAL - map_flags is invalid, or SCIF_MAP_FIXED is set in map_flags, and + * offset is not a multiple of the page size, or offset is negative + * ENODEV - The remote node is lost or existed, but is not currently in the + * network since it may have crashed + * ENOMEM - Not enough space + * ENOTCONN - The endpoint is not connected + */ +off_t scif_register_pinned_pages(scif_epd_t epd, + scif_pinned_pages_t pinned_pages, + off_t offset, int map_flags); + +/** + * scif_get_pages() - Add references to remote registered pages + * @epd: endpoint descriptor + * @offset: remote registered offset + * @len: length of range of pages + * @pages: returned scif_range structure + * + * scif_get_pages() returns the addresses of the physical pages represented by + * those pages of the registered address space of the peer of epd, starting at + * offset and continuing for len bytes. offset and len are constrained to be + * multiples of the page size. + * + * All of the pages in the specified range [offset, offset + len - 1] must be + * within a single window of the registered address space of the peer of epd. + * + * The addresses are returned as a virtually contiguous array pointed to by the + * phys_addr component of the scif_range structure whose address is returned in + * pages. The nr_pages component of scif_range is the length of the array. The + * prot_flags component of scif_range holds the protection flag value passed + * when the pages were registered. + * + * Each physical page whose address is returned by scif_get_pages() remains + * available and will not be released for reuse until the scif_range structure + * is returned in a call to scif_put_pages(). The scif_range structure returned + * by scif_get_pages() must be unmodified. + * + * It is an error to call scif_close() on an endpoint on which a scif_range + * structure of that endpoint has not been returned to scif_put_pages(). + * + * Return: + * Upon successful completion, scif_get_pages() returns 0; otherwise the + * negative of one of the following errors is returned. + * Errors: + * ECONNRESET - Connection reset by peer. + * EINVAL - offset is not a multiple of the page size, or offset is negative, or + * len is not a multiple of the page size + * ENODEV - The remote node is lost or existed, but is not currently in the + * network since it may have crashed + * ENOTCONN - The endpoint is not connected + * ENXIO - Offsets in the range [offset, offset + len - 1] are invalid + * for the registered address space of the peer epd + */ +int scif_get_pages(scif_epd_t epd, off_t offset, size_t len, + struct scif_range **pages); + +/** + * scif_put_pages() - Remove references from remote registered pages + * @pages: pages to be returned + * + * scif_put_pages() releases a scif_range structure previously obtained by + * calling scif_get_pages(). The physical pages represented by pages may + * be reused when the window which represented those pages is unregistered. + * Therefore, those pages must not be accessed after calling scif_put_pages(). + * + * Return: + * Upon successful completion, scif_put_pages() returns 0; otherwise the + * negative of one of the following errors is returned. + * Errors: + * EINVAL - pages does not point to a valid scif_range structure, or + * the scif_range structure pointed to by pages was already returned + * ENODEV - The remote node is lost or existed, but is not currently in the + * network since it may have crashed + * ENOTCONN - The endpoint is not connected + */ +int scif_put_pages(struct scif_range *pages); + +/** + * scif_poll() - Wait for some event on an endpoint + * @epds: Array of endpoint descriptors + * @nepds: Length of epds + * @timeout: Upper limit on time for which scif_poll() will block + * + * scif_poll() waits for one of a set of endpoints to become ready to perform + * an I/O operation. + * + * The epds argument specifies the endpoint descriptors to be examined and the + * events of interest for each endpoint descriptor. epds is a pointer to an + * array with one member for each open endpoint descriptor of interest. + * + * The number of items in the epds array is specified in nepds. The epd field + * of scif_pollepd is an endpoint descriptor of an open endpoint. The field + * events is a bitmask specifying the events which the application is + * interested in. The field revents is an output parameter, filled by the + * kernel with the events that actually occurred. The bits returned in revents + * can include any of those specified in events, or one of the values POLLERR, + * POLLHUP, or POLLNVAL. (These three bits are meaningless in the events + * field, and will be set in the revents field whenever the corresponding + * condition is true.) + * + * If none of the events requested (and no error) has occurred for any of the + * endpoint descriptors, then scif_poll() blocks until one of the events occurs. + * + * The timeout argument specifies an upper limit on the time for which + * scif_poll() will block, in milliseconds. Specifying a negative value in + * timeout means an infinite timeout. + * + * The following bits may be set in events and returned in revents. + * POLLIN - Data may be received without blocking. For a connected + * endpoint, this means that scif_recv() may be called without blocking. For a + * listening endpoint, this means that scif_accept() may be called without + * blocking. + * POLLOUT - Data may be sent without blocking. For a connected endpoint, this + * means that scif_send() may be called without blocking. POLLOUT may also be + * used to block waiting for a non-blocking connect to complete. This bit value + * has no meaning for a listening endpoint and is ignored if specified. + * + * The following bits are only returned in revents, and are ignored if set in + * events. + * POLLERR - An error occurred on the endpoint + * POLLHUP - The connection to the peer endpoint was disconnected + * POLLNVAL - The specified endpoint descriptor is invalid. + * + * Return: + * Upon successful completion, scif_poll() returns a non-negative value. A + * positive value indicates the total number of endpoint descriptors that have + * been selected (that is, endpoint descriptors for which the revents member is + * non-zero). A value of 0 indicates that the call timed out and no endpoint + * descriptors have been selected. Otherwise in user mode -1 is returned and + * errno is set to indicate the error; in kernel mode the negative of one of + * the following errors is returned. + * + * Errors: + * EINTR - A signal occurred before any requested event + * EINVAL - The nepds argument is greater than {OPEN_MAX} + * ENOMEM - There was no space to allocate file descriptor tables + */ +int scif_poll(struct scif_pollepd *epds, unsigned int nepds, long timeout); + +/** + * scif_client_register() - Register a SCIF client + * @client: client to be registered + * + * scif_client_register() registers a SCIF client. The probe() method + * of the client is called when SCIF peer devices come online and the + * remove() method is called when the peer devices disappear. + * + * Return: + * Upon successful completion, scif_client_register() returns a non-negative + * value. Otherwise the return value is the same as subsys_interface_register() + * in the kernel. + */ +int scif_client_register(struct scif_client *client); + +/** + * scif_client_unregister() - Unregister a SCIF client + * @client: client to be unregistered + * + * scif_client_unregister() unregisters a SCIF client. + * + * Return: + * None + */ +void scif_client_unregister(struct scif_client *client); + +#endif /* __SCIF_H__ */ diff --git a/kernel/include/linux/scpi_protocol.h b/kernel/include/linux/scpi_protocol.h new file mode 100644 index 000000000..72ce932c6 --- /dev/null +++ b/kernel/include/linux/scpi_protocol.h @@ -0,0 +1,78 @@ +/* + * SCPI Message Protocol driver header + * + * Copyright (C) 2014 ARM Ltd. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program. If not, see <http://www.gnu.org/licenses/>. + */ +#include <linux/types.h> + +struct scpi_opp { + u32 freq; + u32 m_volt; +} __packed; + +struct scpi_dvfs_info { + unsigned int count; + unsigned int latency; /* in nanoseconds */ + struct scpi_opp *opps; +}; + +enum scpi_sensor_class { + TEMPERATURE, + VOLTAGE, + CURRENT, + POWER, +}; + +struct scpi_sensor_info { + u16 sensor_id; + u8 class; + u8 trigger_type; + char name[20]; +} __packed; + +/** + * struct scpi_ops - represents the various operations provided + * by SCP through SCPI message protocol + * @get_version: returns the major and minor revision on the SCPI + * message protocol + * @clk_get_range: gets clock range limit(min - max in Hz) + * @clk_get_val: gets clock value(in Hz) + * @clk_set_val: sets the clock value, setting to 0 will disable the + * clock (if supported) + * @dvfs_get_idx: gets the Operating Point of the given power domain. + * OPP is an index to the list return by @dvfs_get_info + * @dvfs_set_idx: sets the Operating Point of the given power domain. + * OPP is an index to the list return by @dvfs_get_info + * @dvfs_get_info: returns the DVFS capabilities of the given power + * domain. It includes the OPP list and the latency information + */ +struct scpi_ops { + u32 (*get_version)(void); + int (*clk_get_range)(u16, unsigned long *, unsigned long *); + unsigned long (*clk_get_val)(u16); + int (*clk_set_val)(u16, unsigned long); + int (*dvfs_get_idx)(u8); + int (*dvfs_set_idx)(u8, u8); + struct scpi_dvfs_info *(*dvfs_get_info)(u8); + int (*sensor_get_capability)(u16 *sensors); + int (*sensor_get_info)(u16 sensor_id, struct scpi_sensor_info *); + int (*sensor_get_value)(u16, u32 *); +}; + +#if IS_REACHABLE(CONFIG_ARM_SCPI_PROTOCOL) +struct scpi_ops *get_scpi_ops(void); +#else +static inline struct scpi_ops *get_scpi_ops(void) { return NULL; } +#endif diff --git a/kernel/include/linux/seccomp.h b/kernel/include/linux/seccomp.h index a19ddacda..2296e6b2f 100644 --- a/kernel/include/linux/seccomp.h +++ b/kernel/include/linux/seccomp.h @@ -78,7 +78,7 @@ static inline long prctl_set_seccomp(unsigned long arg2, char __user *arg3) static inline int seccomp_mode(struct seccomp *s) { - return 0; + return SECCOMP_MODE_DISABLED; } #endif /* CONFIG_SECCOMP */ @@ -95,4 +95,15 @@ static inline void get_seccomp_filter(struct task_struct *tsk) return; } #endif /* CONFIG_SECCOMP_FILTER */ + +#if defined(CONFIG_SECCOMP_FILTER) && defined(CONFIG_CHECKPOINT_RESTORE) +extern long seccomp_get_filter(struct task_struct *task, + unsigned long filter_off, void __user *data); +#else +static inline long seccomp_get_filter(struct task_struct *task, + unsigned long n, void __user *data) +{ + return -EINVAL; +} +#endif /* CONFIG_SECCOMP_FILTER && CONFIG_CHECKPOINT_RESTORE */ #endif /* _LINUX_SECCOMP_H */ diff --git a/kernel/include/linux/security.h b/kernel/include/linux/security.h index 18264ea9e..2f4c1f7aa 100644 --- a/kernel/include/linux/security.h +++ b/kernel/include/linux/security.h @@ -27,6 +27,7 @@ #include <linux/slab.h> #include <linux/err.h> #include <linux/string.h> +#include <linux/mm.h> struct linux_binprm; struct cred; @@ -43,7 +44,6 @@ struct file; struct vfsmount; struct path; struct qstr; -struct nameidata; struct iattr; struct fown_struct; struct file_operations; @@ -54,9 +54,6 @@ struct xattr; struct xfrm_sec_ctx; struct mm_struct; -/* Maximum number of letters for an LSM name string */ -#define SECURITY_NAME_MAX 10 - /* If capable should audit the security request */ #define SECURITY_CAP_NOAUDIT 0 #define SECURITY_CAP_AUDIT 1 @@ -69,10 +66,7 @@ struct audit_krule; struct user_namespace; struct timezone; -/* - * These functions are in security/capability.c and are used - * as the default capabilities functions - */ +/* These functions are in security/commoncap.c */ extern int cap_capable(const struct cred *cred, struct user_namespace *ns, int cap, int audit); extern int cap_settime(const struct timespec *ts, const struct timezone *tz); @@ -114,10 +108,6 @@ struct xfrm_state; struct xfrm_user_sec_ctx; struct seq_file; -extern int cap_netlink_send(struct sock *sk, struct sk_buff *skb); - -void reset_security_ops(void); - #ifdef CONFIG_MMU extern unsigned long mmap_min_addr; extern unsigned long dac_mmap_min_addr; @@ -188,1581 +178,8 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts) opts->num_mnt_opts = 0; } -/** - * struct security_operations - main security structure - * - * Security module identifier. - * - * @name: - * A string that acts as a unique identifier for the LSM with max number - * of characters = SECURITY_NAME_MAX. - * - * Security hooks for program execution operations. - * - * @bprm_set_creds: - * Save security information in the bprm->security field, typically based - * on information about the bprm->file, for later use by the apply_creds - * hook. This hook may also optionally check permissions (e.g. for - * transitions between security domains). - * This hook may be called multiple times during a single execve, e.g. for - * interpreters. The hook can tell whether it has already been called by - * checking to see if @bprm->security is non-NULL. If so, then the hook - * may decide either to retain the security information saved earlier or - * to replace it. - * @bprm contains the linux_binprm structure. - * Return 0 if the hook is successful and permission is granted. - * @bprm_check_security: - * This hook mediates the point when a search for a binary handler will - * begin. It allows a check the @bprm->security value which is set in the - * preceding set_creds call. The primary difference from set_creds is - * that the argv list and envp list are reliably available in @bprm. This - * hook may be called multiple times during a single execve; and in each - * pass set_creds is called first. - * @bprm contains the linux_binprm structure. - * Return 0 if the hook is successful and permission is granted. - * @bprm_committing_creds: - * Prepare to install the new security attributes of a process being - * transformed by an execve operation, based on the old credentials - * pointed to by @current->cred and the information set in @bprm->cred by - * the bprm_set_creds hook. @bprm points to the linux_binprm structure. - * This hook is a good place to perform state changes on the process such - * as closing open file descriptors to which access will no longer be - * granted when the attributes are changed. This is called immediately - * before commit_creds(). - * @bprm_committed_creds: - * Tidy up after the installation of the new security attributes of a - * process being transformed by an execve operation. The new credentials - * have, by this point, been set to @current->cred. @bprm points to the - * linux_binprm structure. This hook is a good place to perform state - * changes on the process such as clearing out non-inheritable signal - * state. This is called immediately after commit_creds(). - * @bprm_secureexec: - * Return a boolean value (0 or 1) indicating whether a "secure exec" - * is required. The flag is passed in the auxiliary table - * on the initial stack to the ELF interpreter to indicate whether libc - * should enable secure mode. - * @bprm contains the linux_binprm structure. - * - * Security hooks for filesystem operations. - * - * @sb_alloc_security: - * Allocate and attach a security structure to the sb->s_security field. - * The s_security field is initialized to NULL when the structure is - * allocated. - * @sb contains the super_block structure to be modified. - * Return 0 if operation was successful. - * @sb_free_security: - * Deallocate and clear the sb->s_security field. - * @sb contains the super_block structure to be modified. - * @sb_statfs: - * Check permission before obtaining filesystem statistics for the @mnt - * mountpoint. - * @dentry is a handle on the superblock for the filesystem. - * Return 0 if permission is granted. - * @sb_mount: - * Check permission before an object specified by @dev_name is mounted on - * the mount point named by @nd. For an ordinary mount, @dev_name - * identifies a device if the file system type requires a device. For a - * remount (@flags & MS_REMOUNT), @dev_name is irrelevant. For a - * loopback/bind mount (@flags & MS_BIND), @dev_name identifies the - * pathname of the object being mounted. - * @dev_name contains the name for object being mounted. - * @path contains the path for mount point object. - * @type contains the filesystem type. - * @flags contains the mount flags. - * @data contains the filesystem-specific data. - * Return 0 if permission is granted. - * @sb_copy_data: - * Allow mount option data to be copied prior to parsing by the filesystem, - * so that the security module can extract security-specific mount - * options cleanly (a filesystem may modify the data e.g. with strsep()). - * This also allows the original mount data to be stripped of security- - * specific options to avoid having to make filesystems aware of them. - * @type the type of filesystem being mounted. - * @orig the original mount data copied from userspace. - * @copy copied data which will be passed to the security module. - * Returns 0 if the copy was successful. - * @sb_remount: - * Extracts security system specific mount options and verifies no changes - * are being made to those options. - * @sb superblock being remounted - * @data contains the filesystem-specific data. - * Return 0 if permission is granted. - * @sb_umount: - * Check permission before the @mnt file system is unmounted. - * @mnt contains the mounted file system. - * @flags contains the unmount flags, e.g. MNT_FORCE. - * Return 0 if permission is granted. - * @sb_pivotroot: - * Check permission before pivoting the root filesystem. - * @old_path contains the path for the new location of the current root (put_old). - * @new_path contains the path for the new root (new_root). - * Return 0 if permission is granted. - * @sb_set_mnt_opts: - * Set the security relevant mount options used for a superblock - * @sb the superblock to set security mount options for - * @opts binary data structure containing all lsm mount data - * @sb_clone_mnt_opts: - * Copy all security options from a given superblock to another - * @oldsb old superblock which contain information to clone - * @newsb new superblock which needs filled in - * @sb_parse_opts_str: - * Parse a string of security data filling in the opts structure - * @options string containing all mount options known by the LSM - * @opts binary data structure usable by the LSM - * @dentry_init_security: - * Compute a context for a dentry as the inode is not yet available - * since NFSv4 has no label backed by an EA anyway. - * @dentry dentry to use in calculating the context. - * @mode mode used to determine resource type. - * @name name of the last path component used to create file - * @ctx pointer to place the pointer to the resulting context in. - * @ctxlen point to place the length of the resulting context. - * - * - * Security hooks for inode operations. - * - * @inode_alloc_security: - * Allocate and attach a security structure to @inode->i_security. The - * i_security field is initialized to NULL when the inode structure is - * allocated. - * @inode contains the inode structure. - * Return 0 if operation was successful. - * @inode_free_security: - * @inode contains the inode structure. - * Deallocate the inode security structure and set @inode->i_security to - * NULL. - * @inode_init_security: - * Obtain the security attribute name suffix and value to set on a newly - * created inode and set up the incore security field for the new inode. - * This hook is called by the fs code as part of the inode creation - * transaction and provides for atomic labeling of the inode, unlike - * the post_create/mkdir/... hooks called by the VFS. The hook function - * is expected to allocate the name and value via kmalloc, with the caller - * being responsible for calling kfree after using them. - * If the security module does not use security attributes or does - * not wish to put a security attribute on this particular inode, - * then it should return -EOPNOTSUPP to skip this processing. - * @inode contains the inode structure of the newly created inode. - * @dir contains the inode structure of the parent directory. - * @qstr contains the last path component of the new object - * @name will be set to the allocated name suffix (e.g. selinux). - * @value will be set to the allocated attribute value. - * @len will be set to the length of the value. - * Returns 0 if @name and @value have been successfully set, - * -EOPNOTSUPP if no security attribute is needed, or - * -ENOMEM on memory allocation failure. - * @inode_create: - * Check permission to create a regular file. - * @dir contains inode structure of the parent of the new file. - * @dentry contains the dentry structure for the file to be created. - * @mode contains the file mode of the file to be created. - * Return 0 if permission is granted. - * @inode_link: - * Check permission before creating a new hard link to a file. - * @old_dentry contains the dentry structure for an existing link to the file. - * @dir contains the inode structure of the parent directory of the new link. - * @new_dentry contains the dentry structure for the new link. - * Return 0 if permission is granted. - * @path_link: - * Check permission before creating a new hard link to a file. - * @old_dentry contains the dentry structure for an existing link - * to the file. - * @new_dir contains the path structure of the parent directory of - * the new link. - * @new_dentry contains the dentry structure for the new link. - * Return 0 if permission is granted. - * @inode_unlink: - * Check the permission to remove a hard link to a file. - * @dir contains the inode structure of parent directory of the file. - * @dentry contains the dentry structure for file to be unlinked. - * Return 0 if permission is granted. - * @path_unlink: - * Check the permission to remove a hard link to a file. - * @dir contains the path structure of parent directory of the file. - * @dentry contains the dentry structure for file to be unlinked. - * Return 0 if permission is granted. - * @inode_symlink: - * Check the permission to create a symbolic link to a file. - * @dir contains the inode structure of parent directory of the symbolic link. - * @dentry contains the dentry structure of the symbolic link. - * @old_name contains the pathname of file. - * Return 0 if permission is granted. - * @path_symlink: - * Check the permission to create a symbolic link to a file. - * @dir contains the path structure of parent directory of - * the symbolic link. - * @dentry contains the dentry structure of the symbolic link. - * @old_name contains the pathname of file. - * Return 0 if permission is granted. - * @inode_mkdir: - * Check permissions to create a new directory in the existing directory - * associated with inode structure @dir. - * @dir contains the inode structure of parent of the directory to be created. - * @dentry contains the dentry structure of new directory. - * @mode contains the mode of new directory. - * Return 0 if permission is granted. - * @path_mkdir: - * Check permissions to create a new directory in the existing directory - * associated with path structure @path. - * @dir contains the path structure of parent of the directory - * to be created. - * @dentry contains the dentry structure of new directory. - * @mode contains the mode of new directory. - * Return 0 if permission is granted. - * @inode_rmdir: - * Check the permission to remove a directory. - * @dir contains the inode structure of parent of the directory to be removed. - * @dentry contains the dentry structure of directory to be removed. - * Return 0 if permission is granted. - * @path_rmdir: - * Check the permission to remove a directory. - * @dir contains the path structure of parent of the directory to be - * removed. - * @dentry contains the dentry structure of directory to be removed. - * Return 0 if permission is granted. - * @inode_mknod: - * Check permissions when creating a special file (or a socket or a fifo - * file created via the mknod system call). Note that if mknod operation - * is being done for a regular file, then the create hook will be called - * and not this hook. - * @dir contains the inode structure of parent of the new file. - * @dentry contains the dentry structure of the new file. - * @mode contains the mode of the new file. - * @dev contains the device number. - * Return 0 if permission is granted. - * @path_mknod: - * Check permissions when creating a file. Note that this hook is called - * even if mknod operation is being done for a regular file. - * @dir contains the path structure of parent of the new file. - * @dentry contains the dentry structure of the new file. - * @mode contains the mode of the new file. - * @dev contains the undecoded device number. Use new_decode_dev() to get - * the decoded device number. - * Return 0 if permission is granted. - * @inode_rename: - * Check for permission to rename a file or directory. - * @old_dir contains the inode structure for parent of the old link. - * @old_dentry contains the dentry structure of the old link. - * @new_dir contains the inode structure for parent of the new link. - * @new_dentry contains the dentry structure of the new link. - * Return 0 if permission is granted. - * @path_rename: - * Check for permission to rename a file or directory. - * @old_dir contains the path structure for parent of the old link. - * @old_dentry contains the dentry structure of the old link. - * @new_dir contains the path structure for parent of the new link. - * @new_dentry contains the dentry structure of the new link. - * Return 0 if permission is granted. - * @path_chmod: - * Check for permission to change DAC's permission of a file or directory. - * @dentry contains the dentry structure. - * @mnt contains the vfsmnt structure. - * @mode contains DAC's mode. - * Return 0 if permission is granted. - * @path_chown: - * Check for permission to change owner/group of a file or directory. - * @path contains the path structure. - * @uid contains new owner's ID. - * @gid contains new group's ID. - * Return 0 if permission is granted. - * @path_chroot: - * Check for permission to change root directory. - * @path contains the path structure. - * Return 0 if permission is granted. - * @inode_readlink: - * Check the permission to read the symbolic link. - * @dentry contains the dentry structure for the file link. - * Return 0 if permission is granted. - * @inode_follow_link: - * Check permission to follow a symbolic link when looking up a pathname. - * @dentry contains the dentry structure for the link. - * @nd contains the nameidata structure for the parent directory. - * Return 0 if permission is granted. - * @inode_permission: - * Check permission before accessing an inode. This hook is called by the - * existing Linux permission function, so a security module can use it to - * provide additional checking for existing Linux permission checks. - * Notice that this hook is called when a file is opened (as well as many - * other operations), whereas the file_security_ops permission hook is - * called when the actual read/write operations are performed. - * @inode contains the inode structure to check. - * @mask contains the permission mask. - * Return 0 if permission is granted. - * @inode_setattr: - * Check permission before setting file attributes. Note that the kernel - * call to notify_change is performed from several locations, whenever - * file attributes change (such as when a file is truncated, chown/chmod - * operations, transferring disk quotas, etc). - * @dentry contains the dentry structure for the file. - * @attr is the iattr structure containing the new file attributes. - * Return 0 if permission is granted. - * @path_truncate: - * Check permission before truncating a file. - * @path contains the path structure for the file. - * Return 0 if permission is granted. - * @inode_getattr: - * Check permission before obtaining file attributes. - * @mnt is the vfsmount where the dentry was looked up - * @dentry contains the dentry structure for the file. - * Return 0 if permission is granted. - * @inode_setxattr: - * Check permission before setting the extended attributes - * @value identified by @name for @dentry. - * Return 0 if permission is granted. - * @inode_post_setxattr: - * Update inode security field after successful setxattr operation. - * @value identified by @name for @dentry. - * @inode_getxattr: - * Check permission before obtaining the extended attributes - * identified by @name for @dentry. - * Return 0 if permission is granted. - * @inode_listxattr: - * Check permission before obtaining the list of extended attribute - * names for @dentry. - * Return 0 if permission is granted. - * @inode_removexattr: - * Check permission before removing the extended attribute - * identified by @name for @dentry. - * Return 0 if permission is granted. - * @inode_getsecurity: - * Retrieve a copy of the extended attribute representation of the - * security label associated with @name for @inode via @buffer. Note that - * @name is the remainder of the attribute name after the security prefix - * has been removed. @alloc is used to specify of the call should return a - * value via the buffer or just the value length Return size of buffer on - * success. - * @inode_setsecurity: - * Set the security label associated with @name for @inode from the - * extended attribute value @value. @size indicates the size of the - * @value in bytes. @flags may be XATTR_CREATE, XATTR_REPLACE, or 0. - * Note that @name is the remainder of the attribute name after the - * security. prefix has been removed. - * Return 0 on success. - * @inode_listsecurity: - * Copy the extended attribute names for the security labels - * associated with @inode into @buffer. The maximum size of @buffer - * is specified by @buffer_size. @buffer may be NULL to request - * the size of the buffer required. - * Returns number of bytes used/required on success. - * @inode_need_killpriv: - * Called when an inode has been changed. - * @dentry is the dentry being changed. - * Return <0 on error to abort the inode change operation. - * Return 0 if inode_killpriv does not need to be called. - * Return >0 if inode_killpriv does need to be called. - * @inode_killpriv: - * The setuid bit is being removed. Remove similar security labels. - * Called with the dentry->d_inode->i_mutex held. - * @dentry is the dentry being changed. - * Return 0 on success. If error is returned, then the operation - * causing setuid bit removal is failed. - * @inode_getsecid: - * Get the secid associated with the node. - * @inode contains a pointer to the inode. - * @secid contains a pointer to the location where result will be saved. - * In case of failure, @secid will be set to zero. - * - * Security hooks for file operations - * - * @file_permission: - * Check file permissions before accessing an open file. This hook is - * called by various operations that read or write files. A security - * module can use this hook to perform additional checking on these - * operations, e.g. to revalidate permissions on use to support privilege - * bracketing or policy changes. Notice that this hook is used when the - * actual read/write operations are performed, whereas the - * inode_security_ops hook is called when a file is opened (as well as - * many other operations). - * Caveat: Although this hook can be used to revalidate permissions for - * various system call operations that read or write files, it does not - * address the revalidation of permissions for memory-mapped files. - * Security modules must handle this separately if they need such - * revalidation. - * @file contains the file structure being accessed. - * @mask contains the requested permissions. - * Return 0 if permission is granted. - * @file_alloc_security: - * Allocate and attach a security structure to the file->f_security field. - * The security field is initialized to NULL when the structure is first - * created. - * @file contains the file structure to secure. - * Return 0 if the hook is successful and permission is granted. - * @file_free_security: - * Deallocate and free any security structures stored in file->f_security. - * @file contains the file structure being modified. - * @file_ioctl: - * @file contains the file structure. - * @cmd contains the operation to perform. - * @arg contains the operational arguments. - * Check permission for an ioctl operation on @file. Note that @arg - * sometimes represents a user space pointer; in other cases, it may be a - * simple integer value. When @arg represents a user space pointer, it - * should never be used by the security module. - * Return 0 if permission is granted. - * @mmap_addr : - * Check permissions for a mmap operation at @addr. - * @addr contains virtual address that will be used for the operation. - * Return 0 if permission is granted. - * @mmap_file : - * Check permissions for a mmap operation. The @file may be NULL, e.g. - * if mapping anonymous memory. - * @file contains the file structure for file to map (may be NULL). - * @reqprot contains the protection requested by the application. - * @prot contains the protection that will be applied by the kernel. - * @flags contains the operational flags. - * Return 0 if permission is granted. - * @file_mprotect: - * Check permissions before changing memory access permissions. - * @vma contains the memory region to modify. - * @reqprot contains the protection requested by the application. - * @prot contains the protection that will be applied by the kernel. - * Return 0 if permission is granted. - * @file_lock: - * Check permission before performing file locking operations. - * Note: this hook mediates both flock and fcntl style locks. - * @file contains the file structure. - * @cmd contains the posix-translated lock operation to perform - * (e.g. F_RDLCK, F_WRLCK). - * Return 0 if permission is granted. - * @file_fcntl: - * Check permission before allowing the file operation specified by @cmd - * from being performed on the file @file. Note that @arg sometimes - * represents a user space pointer; in other cases, it may be a simple - * integer value. When @arg represents a user space pointer, it should - * never be used by the security module. - * @file contains the file structure. - * @cmd contains the operation to be performed. - * @arg contains the operational arguments. - * Return 0 if permission is granted. - * @file_set_fowner: - * Save owner security information (typically from current->security) in - * file->f_security for later use by the send_sigiotask hook. - * @file contains the file structure to update. - * Return 0 on success. - * @file_send_sigiotask: - * Check permission for the file owner @fown to send SIGIO or SIGURG to the - * process @tsk. Note that this hook is sometimes called from interrupt. - * Note that the fown_struct, @fown, is never outside the context of a - * struct file, so the file structure (and associated security information) - * can always be obtained: - * container_of(fown, struct file, f_owner) - * @tsk contains the structure of task receiving signal. - * @fown contains the file owner information. - * @sig is the signal that will be sent. When 0, kernel sends SIGIO. - * Return 0 if permission is granted. - * @file_receive: - * This hook allows security modules to control the ability of a process - * to receive an open file descriptor via socket IPC. - * @file contains the file structure being received. - * Return 0 if permission is granted. - * @file_open - * Save open-time permission checking state for later use upon - * file_permission, and recheck access if anything has changed - * since inode_permission. - * - * Security hooks for task operations. - * - * @task_create: - * Check permission before creating a child process. See the clone(2) - * manual page for definitions of the @clone_flags. - * @clone_flags contains the flags indicating what should be shared. - * Return 0 if permission is granted. - * @task_free: - * @task task being freed - * Handle release of task-related resources. (Note that this can be called - * from interrupt context.) - * @cred_alloc_blank: - * @cred points to the credentials. - * @gfp indicates the atomicity of any memory allocations. - * Only allocate sufficient memory and attach to @cred such that - * cred_transfer() will not get ENOMEM. - * @cred_free: - * @cred points to the credentials. - * Deallocate and clear the cred->security field in a set of credentials. - * @cred_prepare: - * @new points to the new credentials. - * @old points to the original credentials. - * @gfp indicates the atomicity of any memory allocations. - * Prepare a new set of credentials by copying the data from the old set. - * @cred_transfer: - * @new points to the new credentials. - * @old points to the original credentials. - * Transfer data from original creds to new creds - * @kernel_act_as: - * Set the credentials for a kernel service to act as (subjective context). - * @new points to the credentials to be modified. - * @secid specifies the security ID to be set - * The current task must be the one that nominated @secid. - * Return 0 if successful. - * @kernel_create_files_as: - * Set the file creation context in a set of credentials to be the same as - * the objective context of the specified inode. - * @new points to the credentials to be modified. - * @inode points to the inode to use as a reference. - * The current task must be the one that nominated @inode. - * Return 0 if successful. - * @kernel_fw_from_file: - * Load firmware from userspace (not called for built-in firmware). - * @file contains the file structure pointing to the file containing - * the firmware to load. This argument will be NULL if the firmware - * was loaded via the uevent-triggered blob-based interface exposed - * by CONFIG_FW_LOADER_USER_HELPER. - * @buf pointer to buffer containing firmware contents. - * @size length of the firmware contents. - * Return 0 if permission is granted. - * @kernel_module_request: - * Ability to trigger the kernel to automatically upcall to userspace for - * userspace to load a kernel module with the given name. - * @kmod_name name of the module requested by the kernel - * Return 0 if successful. - * @kernel_module_from_file: - * Load a kernel module from userspace. - * @file contains the file structure pointing to the file containing - * the kernel module to load. If the module is being loaded from a blob, - * this argument will be NULL. - * Return 0 if permission is granted. - * @task_fix_setuid: - * Update the module's state after setting one or more of the user - * identity attributes of the current process. The @flags parameter - * indicates which of the set*uid system calls invoked this hook. If - * @new is the set of credentials that will be installed. Modifications - * should be made to this rather than to @current->cred. - * @old is the set of credentials that are being replaces - * @flags contains one of the LSM_SETID_* values. - * Return 0 on success. - * @task_setpgid: - * Check permission before setting the process group identifier of the - * process @p to @pgid. - * @p contains the task_struct for process being modified. - * @pgid contains the new pgid. - * Return 0 if permission is granted. - * @task_getpgid: - * Check permission before getting the process group identifier of the - * process @p. - * @p contains the task_struct for the process. - * Return 0 if permission is granted. - * @task_getsid: - * Check permission before getting the session identifier of the process - * @p. - * @p contains the task_struct for the process. - * Return 0 if permission is granted. - * @task_getsecid: - * Retrieve the security identifier of the process @p. - * @p contains the task_struct for the process and place is into @secid. - * In case of failure, @secid will be set to zero. - * - * @task_setnice: - * Check permission before setting the nice value of @p to @nice. - * @p contains the task_struct of process. - * @nice contains the new nice value. - * Return 0 if permission is granted. - * @task_setioprio - * Check permission before setting the ioprio value of @p to @ioprio. - * @p contains the task_struct of process. - * @ioprio contains the new ioprio value - * Return 0 if permission is granted. - * @task_getioprio - * Check permission before getting the ioprio value of @p. - * @p contains the task_struct of process. - * Return 0 if permission is granted. - * @task_setrlimit: - * Check permission before setting the resource limits of the current - * process for @resource to @new_rlim. The old resource limit values can - * be examined by dereferencing (current->signal->rlim + resource). - * @resource contains the resource whose limit is being set. - * @new_rlim contains the new limits for @resource. - * Return 0 if permission is granted. - * @task_setscheduler: - * Check permission before setting scheduling policy and/or parameters of - * process @p based on @policy and @lp. - * @p contains the task_struct for process. - * @policy contains the scheduling policy. - * @lp contains the scheduling parameters. - * Return 0 if permission is granted. - * @task_getscheduler: - * Check permission before obtaining scheduling information for process - * @p. - * @p contains the task_struct for process. - * Return 0 if permission is granted. - * @task_movememory - * Check permission before moving memory owned by process @p. - * @p contains the task_struct for process. - * Return 0 if permission is granted. - * @task_kill: - * Check permission before sending signal @sig to @p. @info can be NULL, - * the constant 1, or a pointer to a siginfo structure. If @info is 1 or - * SI_FROMKERNEL(info) is true, then the signal should be viewed as coming - * from the kernel and should typically be permitted. - * SIGIO signals are handled separately by the send_sigiotask hook in - * file_security_ops. - * @p contains the task_struct for process. - * @info contains the signal information. - * @sig contains the signal value. - * @secid contains the sid of the process where the signal originated - * Return 0 if permission is granted. - * @task_wait: - * Check permission before allowing a process to reap a child process @p - * and collect its status information. - * @p contains the task_struct for process. - * Return 0 if permission is granted. - * @task_prctl: - * Check permission before performing a process control operation on the - * current process. - * @option contains the operation. - * @arg2 contains a argument. - * @arg3 contains a argument. - * @arg4 contains a argument. - * @arg5 contains a argument. - * Return -ENOSYS if no-one wanted to handle this op, any other value to - * cause prctl() to return immediately with that value. - * @task_to_inode: - * Set the security attributes for an inode based on an associated task's - * security attributes, e.g. for /proc/pid inodes. - * @p contains the task_struct for the task. - * @inode contains the inode structure for the inode. - * - * Security hooks for Netlink messaging. - * - * @netlink_send: - * Save security information for a netlink message so that permission - * checking can be performed when the message is processed. The security - * information can be saved using the eff_cap field of the - * netlink_skb_parms structure. Also may be used to provide fine - * grained control over message transmission. - * @sk associated sock of task sending the message. - * @skb contains the sk_buff structure for the netlink message. - * Return 0 if the information was successfully saved and message - * is allowed to be transmitted. - * - * Security hooks for Unix domain networking. - * - * @unix_stream_connect: - * Check permissions before establishing a Unix domain stream connection - * between @sock and @other. - * @sock contains the sock structure. - * @other contains the peer sock structure. - * @newsk contains the new sock structure. - * Return 0 if permission is granted. - * @unix_may_send: - * Check permissions before connecting or sending datagrams from @sock to - * @other. - * @sock contains the socket structure. - * @other contains the peer socket structure. - * Return 0 if permission is granted. - * - * The @unix_stream_connect and @unix_may_send hooks were necessary because - * Linux provides an alternative to the conventional file name space for Unix - * domain sockets. Whereas binding and connecting to sockets in the file name - * space is mediated by the typical file permissions (and caught by the mknod - * and permission hooks in inode_security_ops), binding and connecting to - * sockets in the abstract name space is completely unmediated. Sufficient - * control of Unix domain sockets in the abstract name space isn't possible - * using only the socket layer hooks, since we need to know the actual target - * socket, which is not looked up until we are inside the af_unix code. - * - * Security hooks for socket operations. - * - * @socket_create: - * Check permissions prior to creating a new socket. - * @family contains the requested protocol family. - * @type contains the requested communications type. - * @protocol contains the requested protocol. - * @kern set to 1 if a kernel socket. - * Return 0 if permission is granted. - * @socket_post_create: - * This hook allows a module to update or allocate a per-socket security - * structure. Note that the security field was not added directly to the - * socket structure, but rather, the socket security information is stored - * in the associated inode. Typically, the inode alloc_security hook will - * allocate and and attach security information to - * sock->inode->i_security. This hook may be used to update the - * sock->inode->i_security field with additional information that wasn't - * available when the inode was allocated. - * @sock contains the newly created socket structure. - * @family contains the requested protocol family. - * @type contains the requested communications type. - * @protocol contains the requested protocol. - * @kern set to 1 if a kernel socket. - * @socket_bind: - * Check permission before socket protocol layer bind operation is - * performed and the socket @sock is bound to the address specified in the - * @address parameter. - * @sock contains the socket structure. - * @address contains the address to bind to. - * @addrlen contains the length of address. - * Return 0 if permission is granted. - * @socket_connect: - * Check permission before socket protocol layer connect operation - * attempts to connect socket @sock to a remote address, @address. - * @sock contains the socket structure. - * @address contains the address of remote endpoint. - * @addrlen contains the length of address. - * Return 0 if permission is granted. - * @socket_listen: - * Check permission before socket protocol layer listen operation. - * @sock contains the socket structure. - * @backlog contains the maximum length for the pending connection queue. - * Return 0 if permission is granted. - * @socket_accept: - * Check permission before accepting a new connection. Note that the new - * socket, @newsock, has been created and some information copied to it, - * but the accept operation has not actually been performed. - * @sock contains the listening socket structure. - * @newsock contains the newly created server socket for connection. - * Return 0 if permission is granted. - * @socket_sendmsg: - * Check permission before transmitting a message to another socket. - * @sock contains the socket structure. - * @msg contains the message to be transmitted. - * @size contains the size of message. - * Return 0 if permission is granted. - * @socket_recvmsg: - * Check permission before receiving a message from a socket. - * @sock contains the socket structure. - * @msg contains the message structure. - * @size contains the size of message structure. - * @flags contains the operational flags. - * Return 0 if permission is granted. - * @socket_getsockname: - * Check permission before the local address (name) of the socket object - * @sock is retrieved. - * @sock contains the socket structure. - * Return 0 if permission is granted. - * @socket_getpeername: - * Check permission before the remote address (name) of a socket object - * @sock is retrieved. - * @sock contains the socket structure. - * Return 0 if permission is granted. - * @socket_getsockopt: - * Check permissions before retrieving the options associated with socket - * @sock. - * @sock contains the socket structure. - * @level contains the protocol level to retrieve option from. - * @optname contains the name of option to retrieve. - * Return 0 if permission is granted. - * @socket_setsockopt: - * Check permissions before setting the options associated with socket - * @sock. - * @sock contains the socket structure. - * @level contains the protocol level to set options for. - * @optname contains the name of the option to set. - * Return 0 if permission is granted. - * @socket_shutdown: - * Checks permission before all or part of a connection on the socket - * @sock is shut down. - * @sock contains the socket structure. - * @how contains the flag indicating how future sends and receives are handled. - * Return 0 if permission is granted. - * @socket_sock_rcv_skb: - * Check permissions on incoming network packets. This hook is distinct - * from Netfilter's IP input hooks since it is the first time that the - * incoming sk_buff @skb has been associated with a particular socket, @sk. - * Must not sleep inside this hook because some callers hold spinlocks. - * @sk contains the sock (not socket) associated with the incoming sk_buff. - * @skb contains the incoming network data. - * @socket_getpeersec_stream: - * This hook allows the security module to provide peer socket security - * state for unix or connected tcp sockets to userspace via getsockopt - * SO_GETPEERSEC. For tcp sockets this can be meaningful if the - * socket is associated with an ipsec SA. - * @sock is the local socket. - * @optval userspace memory where the security state is to be copied. - * @optlen userspace int where the module should copy the actual length - * of the security state. - * @len as input is the maximum length to copy to userspace provided - * by the caller. - * Return 0 if all is well, otherwise, typical getsockopt return - * values. - * @socket_getpeersec_dgram: - * This hook allows the security module to provide peer socket security - * state for udp sockets on a per-packet basis to userspace via - * getsockopt SO_GETPEERSEC. The application must first have indicated - * the IP_PASSSEC option via getsockopt. It can then retrieve the - * security state returned by this hook for a packet via the SCM_SECURITY - * ancillary message type. - * @skb is the skbuff for the packet being queried - * @secdata is a pointer to a buffer in which to copy the security data - * @seclen is the maximum length for @secdata - * Return 0 on success, error on failure. - * @sk_alloc_security: - * Allocate and attach a security structure to the sk->sk_security field, - * which is used to copy security attributes between local stream sockets. - * @sk_free_security: - * Deallocate security structure. - * @sk_clone_security: - * Clone/copy security structure. - * @sk_getsecid: - * Retrieve the LSM-specific secid for the sock to enable caching of network - * authorizations. - * @sock_graft: - * Sets the socket's isec sid to the sock's sid. - * @inet_conn_request: - * Sets the openreq's sid to socket's sid with MLS portion taken from peer sid. - * @inet_csk_clone: - * Sets the new child socket's sid to the openreq sid. - * @inet_conn_established: - * Sets the connection's peersid to the secmark on skb. - * @secmark_relabel_packet: - * check if the process should be allowed to relabel packets to the given secid - * @security_secmark_refcount_inc - * tells the LSM to increment the number of secmark labeling rules loaded - * @security_secmark_refcount_dec - * tells the LSM to decrement the number of secmark labeling rules loaded - * @req_classify_flow: - * Sets the flow's sid to the openreq sid. - * @tun_dev_alloc_security: - * This hook allows a module to allocate a security structure for a TUN - * device. - * @security pointer to a security structure pointer. - * Returns a zero on success, negative values on failure. - * @tun_dev_free_security: - * This hook allows a module to free the security structure for a TUN - * device. - * @security pointer to the TUN device's security structure - * @tun_dev_create: - * Check permissions prior to creating a new TUN device. - * @tun_dev_attach_queue: - * Check permissions prior to attaching to a TUN device queue. - * @security pointer to the TUN device's security structure. - * @tun_dev_attach: - * This hook can be used by the module to update any security state - * associated with the TUN device's sock structure. - * @sk contains the existing sock structure. - * @security pointer to the TUN device's security structure. - * @tun_dev_open: - * This hook can be used by the module to update any security state - * associated with the TUN device's security structure. - * @security pointer to the TUN devices's security structure. - * @skb_owned_by: - * This hook sets the packet's owning sock. - * @skb is the packet. - * @sk the sock which owns the packet. - * - * Security hooks for XFRM operations. - * - * @xfrm_policy_alloc_security: - * @ctxp is a pointer to the xfrm_sec_ctx being added to Security Policy - * Database used by the XFRM system. - * @sec_ctx contains the security context information being provided by - * the user-level policy update program (e.g., setkey). - * Allocate a security structure to the xp->security field; the security - * field is initialized to NULL when the xfrm_policy is allocated. - * Return 0 if operation was successful (memory to allocate, legal context) - * @gfp is to specify the context for the allocation - * @xfrm_policy_clone_security: - * @old_ctx contains an existing xfrm_sec_ctx. - * @new_ctxp contains a new xfrm_sec_ctx being cloned from old. - * Allocate a security structure in new_ctxp that contains the - * information from the old_ctx structure. - * Return 0 if operation was successful (memory to allocate). - * @xfrm_policy_free_security: - * @ctx contains the xfrm_sec_ctx - * Deallocate xp->security. - * @xfrm_policy_delete_security: - * @ctx contains the xfrm_sec_ctx. - * Authorize deletion of xp->security. - * @xfrm_state_alloc: - * @x contains the xfrm_state being added to the Security Association - * Database by the XFRM system. - * @sec_ctx contains the security context information being provided by - * the user-level SA generation program (e.g., setkey or racoon). - * Allocate a security structure to the x->security field; the security - * field is initialized to NULL when the xfrm_state is allocated. Set the - * context to correspond to sec_ctx. Return 0 if operation was successful - * (memory to allocate, legal context). - * @xfrm_state_alloc_acquire: - * @x contains the xfrm_state being added to the Security Association - * Database by the XFRM system. - * @polsec contains the policy's security context. - * @secid contains the secid from which to take the mls portion of the - * context. - * Allocate a security structure to the x->security field; the security - * field is initialized to NULL when the xfrm_state is allocated. Set the - * context to correspond to secid. Return 0 if operation was successful - * (memory to allocate, legal context). - * @xfrm_state_free_security: - * @x contains the xfrm_state. - * Deallocate x->security. - * @xfrm_state_delete_security: - * @x contains the xfrm_state. - * Authorize deletion of x->security. - * @xfrm_policy_lookup: - * @ctx contains the xfrm_sec_ctx for which the access control is being - * checked. - * @fl_secid contains the flow security label that is used to authorize - * access to the policy xp. - * @dir contains the direction of the flow (input or output). - * Check permission when a flow selects a xfrm_policy for processing - * XFRMs on a packet. The hook is called when selecting either a - * per-socket policy or a generic xfrm policy. - * Return 0 if permission is granted, -ESRCH otherwise, or -errno - * on other errors. - * @xfrm_state_pol_flow_match: - * @x contains the state to match. - * @xp contains the policy to check for a match. - * @fl contains the flow to check for a match. - * Return 1 if there is a match. - * @xfrm_decode_session: - * @skb points to skb to decode. - * @secid points to the flow key secid to set. - * @ckall says if all xfrms used should be checked for same secid. - * Return 0 if ckall is zero or all xfrms used have the same secid. - * - * Security hooks affecting all Key Management operations - * - * @key_alloc: - * Permit allocation of a key and assign security data. Note that key does - * not have a serial number assigned at this point. - * @key points to the key. - * @flags is the allocation flags - * Return 0 if permission is granted, -ve error otherwise. - * @key_free: - * Notification of destruction; free security data. - * @key points to the key. - * No return value. - * @key_permission: - * See whether a specific operational right is granted to a process on a - * key. - * @key_ref refers to the key (key pointer + possession attribute bit). - * @cred points to the credentials to provide the context against which to - * evaluate the security data on the key. - * @perm describes the combination of permissions required of this key. - * Return 0 if permission is granted, -ve error otherwise. - * @key_getsecurity: - * Get a textual representation of the security context attached to a key - * for the purposes of honouring KEYCTL_GETSECURITY. This function - * allocates the storage for the NUL-terminated string and the caller - * should free it. - * @key points to the key to be queried. - * @_buffer points to a pointer that should be set to point to the - * resulting string (if no label or an error occurs). - * Return the length of the string (including terminating NUL) or -ve if - * an error. - * May also return 0 (and a NULL buffer pointer) if there is no label. - * - * Security hooks affecting all System V IPC operations. - * - * @ipc_permission: - * Check permissions for access to IPC - * @ipcp contains the kernel IPC permission structure - * @flag contains the desired (requested) permission set - * Return 0 if permission is granted. - * @ipc_getsecid: - * Get the secid associated with the ipc object. - * @ipcp contains the kernel IPC permission structure. - * @secid contains a pointer to the location where result will be saved. - * In case of failure, @secid will be set to zero. - * - * Security hooks for individual messages held in System V IPC message queues - * @msg_msg_alloc_security: - * Allocate and attach a security structure to the msg->security field. - * The security field is initialized to NULL when the structure is first - * created. - * @msg contains the message structure to be modified. - * Return 0 if operation was successful and permission is granted. - * @msg_msg_free_security: - * Deallocate the security structure for this message. - * @msg contains the message structure to be modified. - * - * Security hooks for System V IPC Message Queues - * - * @msg_queue_alloc_security: - * Allocate and attach a security structure to the - * msq->q_perm.security field. The security field is initialized to - * NULL when the structure is first created. - * @msq contains the message queue structure to be modified. - * Return 0 if operation was successful and permission is granted. - * @msg_queue_free_security: - * Deallocate security structure for this message queue. - * @msq contains the message queue structure to be modified. - * @msg_queue_associate: - * Check permission when a message queue is requested through the - * msgget system call. This hook is only called when returning the - * message queue identifier for an existing message queue, not when a - * new message queue is created. - * @msq contains the message queue to act upon. - * @msqflg contains the operation control flags. - * Return 0 if permission is granted. - * @msg_queue_msgctl: - * Check permission when a message control operation specified by @cmd - * is to be performed on the message queue @msq. - * The @msq may be NULL, e.g. for IPC_INFO or MSG_INFO. - * @msq contains the message queue to act upon. May be NULL. - * @cmd contains the operation to be performed. - * Return 0 if permission is granted. - * @msg_queue_msgsnd: - * Check permission before a message, @msg, is enqueued on the message - * queue, @msq. - * @msq contains the message queue to send message to. - * @msg contains the message to be enqueued. - * @msqflg contains operational flags. - * Return 0 if permission is granted. - * @msg_queue_msgrcv: - * Check permission before a message, @msg, is removed from the message - * queue, @msq. The @target task structure contains a pointer to the - * process that will be receiving the message (not equal to the current - * process when inline receives are being performed). - * @msq contains the message queue to retrieve message from. - * @msg contains the message destination. - * @target contains the task structure for recipient process. - * @type contains the type of message requested. - * @mode contains the operational flags. - * Return 0 if permission is granted. - * - * Security hooks for System V Shared Memory Segments - * - * @shm_alloc_security: - * Allocate and attach a security structure to the shp->shm_perm.security - * field. The security field is initialized to NULL when the structure is - * first created. - * @shp contains the shared memory structure to be modified. - * Return 0 if operation was successful and permission is granted. - * @shm_free_security: - * Deallocate the security struct for this memory segment. - * @shp contains the shared memory structure to be modified. - * @shm_associate: - * Check permission when a shared memory region is requested through the - * shmget system call. This hook is only called when returning the shared - * memory region identifier for an existing region, not when a new shared - * memory region is created. - * @shp contains the shared memory structure to be modified. - * @shmflg contains the operation control flags. - * Return 0 if permission is granted. - * @shm_shmctl: - * Check permission when a shared memory control operation specified by - * @cmd is to be performed on the shared memory region @shp. - * The @shp may be NULL, e.g. for IPC_INFO or SHM_INFO. - * @shp contains shared memory structure to be modified. - * @cmd contains the operation to be performed. - * Return 0 if permission is granted. - * @shm_shmat: - * Check permissions prior to allowing the shmat system call to attach the - * shared memory segment @shp to the data segment of the calling process. - * The attaching address is specified by @shmaddr. - * @shp contains the shared memory structure to be modified. - * @shmaddr contains the address to attach memory region to. - * @shmflg contains the operational flags. - * Return 0 if permission is granted. - * - * Security hooks for System V Semaphores - * - * @sem_alloc_security: - * Allocate and attach a security structure to the sma->sem_perm.security - * field. The security field is initialized to NULL when the structure is - * first created. - * @sma contains the semaphore structure - * Return 0 if operation was successful and permission is granted. - * @sem_free_security: - * deallocate security struct for this semaphore - * @sma contains the semaphore structure. - * @sem_associate: - * Check permission when a semaphore is requested through the semget - * system call. This hook is only called when returning the semaphore - * identifier for an existing semaphore, not when a new one must be - * created. - * @sma contains the semaphore structure. - * @semflg contains the operation control flags. - * Return 0 if permission is granted. - * @sem_semctl: - * Check permission when a semaphore operation specified by @cmd is to be - * performed on the semaphore @sma. The @sma may be NULL, e.g. for - * IPC_INFO or SEM_INFO. - * @sma contains the semaphore structure. May be NULL. - * @cmd contains the operation to be performed. - * Return 0 if permission is granted. - * @sem_semop - * Check permissions before performing operations on members of the - * semaphore set @sma. If the @alter flag is nonzero, the semaphore set - * may be modified. - * @sma contains the semaphore structure. - * @sops contains the operations to perform. - * @nsops contains the number of operations to perform. - * @alter contains the flag indicating whether changes are to be made. - * Return 0 if permission is granted. - * - * @binder_set_context_mgr - * Check whether @mgr is allowed to be the binder context manager. - * @mgr contains the task_struct for the task being registered. - * Return 0 if permission is granted. - * @binder_transaction - * Check whether @from is allowed to invoke a binder transaction call - * to @to. - * @from contains the task_struct for the sending task. - * @to contains the task_struct for the receiving task. - * @binder_transfer_binder - * Check whether @from is allowed to transfer a binder reference to @to. - * @from contains the task_struct for the sending task. - * @to contains the task_struct for the receiving task. - * @binder_transfer_file - * Check whether @from is allowed to transfer @file to @to. - * @from contains the task_struct for the sending task. - * @file contains the struct file being transferred. - * @to contains the task_struct for the receiving task. - * - * @ptrace_access_check: - * Check permission before allowing the current process to trace the - * @child process. - * Security modules may also want to perform a process tracing check - * during an execve in the set_security or apply_creds hooks of - * tracing check during an execve in the bprm_set_creds hook of - * binprm_security_ops if the process is being traced and its security - * attributes would be changed by the execve. - * @child contains the task_struct structure for the target process. - * @mode contains the PTRACE_MODE flags indicating the form of access. - * Return 0 if permission is granted. - * @ptrace_traceme: - * Check that the @parent process has sufficient permission to trace the - * current process before allowing the current process to present itself - * to the @parent process for tracing. - * @parent contains the task_struct structure for debugger process. - * Return 0 if permission is granted. - * @capget: - * Get the @effective, @inheritable, and @permitted capability sets for - * the @target process. The hook may also perform permission checking to - * determine if the current process is allowed to see the capability sets - * of the @target process. - * @target contains the task_struct structure for target process. - * @effective contains the effective capability set. - * @inheritable contains the inheritable capability set. - * @permitted contains the permitted capability set. - * Return 0 if the capability sets were successfully obtained. - * @capset: - * Set the @effective, @inheritable, and @permitted capability sets for - * the current process. - * @new contains the new credentials structure for target process. - * @old contains the current credentials structure for target process. - * @effective contains the effective capability set. - * @inheritable contains the inheritable capability set. - * @permitted contains the permitted capability set. - * Return 0 and update @new if permission is granted. - * @capable: - * Check whether the @tsk process has the @cap capability in the indicated - * credentials. - * @cred contains the credentials to use. - * @ns contains the user namespace we want the capability in - * @cap contains the capability <include/linux/capability.h>. - * @audit: Whether to write an audit message or not - * Return 0 if the capability is granted for @tsk. - * @syslog: - * Check permission before accessing the kernel message ring or changing - * logging to the console. - * See the syslog(2) manual page for an explanation of the @type values. - * @type contains the type of action. - * @from_file indicates the context of action (if it came from /proc). - * Return 0 if permission is granted. - * @settime: - * Check permission to change the system time. - * struct timespec and timezone are defined in include/linux/time.h - * @ts contains new time - * @tz contains new timezone - * Return 0 if permission is granted. - * @vm_enough_memory: - * Check permissions for allocating a new virtual mapping. - * @mm contains the mm struct it is being added to. - * @pages contains the number of pages. - * Return 0 if permission is granted. - * - * @ismaclabel: - * Check if the extended attribute specified by @name - * represents a MAC label. Returns 1 if name is a MAC - * attribute otherwise returns 0. - * @name full extended attribute name to check against - * LSM as a MAC label. - * - * @secid_to_secctx: - * Convert secid to security context. If secdata is NULL the length of - * the result will be returned in seclen, but no secdata will be returned. - * This does mean that the length could change between calls to check the - * length and the next call which actually allocates and returns the secdata. - * @secid contains the security ID. - * @secdata contains the pointer that stores the converted security context. - * @seclen pointer which contains the length of the data - * @secctx_to_secid: - * Convert security context to secid. - * @secid contains the pointer to the generated security ID. - * @secdata contains the security context. - * - * @release_secctx: - * Release the security context. - * @secdata contains the security context. - * @seclen contains the length of the security context. - * - * Security hooks for Audit - * - * @audit_rule_init: - * Allocate and initialize an LSM audit rule structure. - * @field contains the required Audit action. Fields flags are defined in include/linux/audit.h - * @op contains the operator the rule uses. - * @rulestr contains the context where the rule will be applied to. - * @lsmrule contains a pointer to receive the result. - * Return 0 if @lsmrule has been successfully set, - * -EINVAL in case of an invalid rule. - * - * @audit_rule_known: - * Specifies whether given @rule contains any fields related to current LSM. - * @rule contains the audit rule of interest. - * Return 1 in case of relation found, 0 otherwise. - * - * @audit_rule_match: - * Determine if given @secid matches a rule previously approved - * by @audit_rule_known. - * @secid contains the security id in question. - * @field contains the field which relates to current LSM. - * @op contains the operator that will be used for matching. - * @rule points to the audit rule that will be checked against. - * @actx points to the audit context associated with the check. - * Return 1 if secid matches the rule, 0 if it does not, -ERRNO on failure. - * - * @audit_rule_free: - * Deallocate the LSM audit rule structure previously allocated by - * audit_rule_init. - * @rule contains the allocated rule - * - * @inode_notifysecctx: - * Notify the security module of what the security context of an inode - * should be. Initializes the incore security context managed by the - * security module for this inode. Example usage: NFS client invokes - * this hook to initialize the security context in its incore inode to the - * value provided by the server for the file when the server returned the - * file's attributes to the client. - * - * Must be called with inode->i_mutex locked. - * - * @inode we wish to set the security context of. - * @ctx contains the string which we wish to set in the inode. - * @ctxlen contains the length of @ctx. - * - * @inode_setsecctx: - * Change the security context of an inode. Updates the - * incore security context managed by the security module and invokes the - * fs code as needed (via __vfs_setxattr_noperm) to update any backing - * xattrs that represent the context. Example usage: NFS server invokes - * this hook to change the security context in its incore inode and on the - * backing filesystem to a value provided by the client on a SETATTR - * operation. - * - * Must be called with inode->i_mutex locked. - * - * @dentry contains the inode we wish to set the security context of. - * @ctx contains the string which we wish to set in the inode. - * @ctxlen contains the length of @ctx. - * - * @inode_getsecctx: - * On success, returns 0 and fills out @ctx and @ctxlen with the security - * context for the given @inode. - * - * @inode we wish to get the security context of. - * @ctx is a pointer in which to place the allocated security context. - * @ctxlen points to the place to put the length of @ctx. - * This is the main security structure. - */ -struct security_operations { - char name[SECURITY_NAME_MAX + 1]; - - int (*binder_set_context_mgr) (struct task_struct *mgr); - int (*binder_transaction) (struct task_struct *from, - struct task_struct *to); - int (*binder_transfer_binder) (struct task_struct *from, - struct task_struct *to); - int (*binder_transfer_file) (struct task_struct *from, - struct task_struct *to, struct file *file); - - int (*ptrace_access_check) (struct task_struct *child, unsigned int mode); - int (*ptrace_traceme) (struct task_struct *parent); - int (*capget) (struct task_struct *target, - kernel_cap_t *effective, - kernel_cap_t *inheritable, kernel_cap_t *permitted); - int (*capset) (struct cred *new, - const struct cred *old, - const kernel_cap_t *effective, - const kernel_cap_t *inheritable, - const kernel_cap_t *permitted); - int (*capable) (const struct cred *cred, struct user_namespace *ns, - int cap, int audit); - int (*quotactl) (int cmds, int type, int id, struct super_block *sb); - int (*quota_on) (struct dentry *dentry); - int (*syslog) (int type); - int (*settime) (const struct timespec *ts, const struct timezone *tz); - int (*vm_enough_memory) (struct mm_struct *mm, long pages); - - int (*bprm_set_creds) (struct linux_binprm *bprm); - int (*bprm_check_security) (struct linux_binprm *bprm); - int (*bprm_secureexec) (struct linux_binprm *bprm); - void (*bprm_committing_creds) (struct linux_binprm *bprm); - void (*bprm_committed_creds) (struct linux_binprm *bprm); - - int (*sb_alloc_security) (struct super_block *sb); - void (*sb_free_security) (struct super_block *sb); - int (*sb_copy_data) (char *orig, char *copy); - int (*sb_remount) (struct super_block *sb, void *data); - int (*sb_kern_mount) (struct super_block *sb, int flags, void *data); - int (*sb_show_options) (struct seq_file *m, struct super_block *sb); - int (*sb_statfs) (struct dentry *dentry); - int (*sb_mount) (const char *dev_name, struct path *path, - const char *type, unsigned long flags, void *data); - int (*sb_umount) (struct vfsmount *mnt, int flags); - int (*sb_pivotroot) (struct path *old_path, - struct path *new_path); - int (*sb_set_mnt_opts) (struct super_block *sb, - struct security_mnt_opts *opts, - unsigned long kern_flags, - unsigned long *set_kern_flags); - int (*sb_clone_mnt_opts) (const struct super_block *oldsb, - struct super_block *newsb); - int (*sb_parse_opts_str) (char *options, struct security_mnt_opts *opts); - int (*dentry_init_security) (struct dentry *dentry, int mode, - struct qstr *name, void **ctx, - u32 *ctxlen); - - -#ifdef CONFIG_SECURITY_PATH - int (*path_unlink) (struct path *dir, struct dentry *dentry); - int (*path_mkdir) (struct path *dir, struct dentry *dentry, umode_t mode); - int (*path_rmdir) (struct path *dir, struct dentry *dentry); - int (*path_mknod) (struct path *dir, struct dentry *dentry, umode_t mode, - unsigned int dev); - int (*path_truncate) (struct path *path); - int (*path_symlink) (struct path *dir, struct dentry *dentry, - const char *old_name); - int (*path_link) (struct dentry *old_dentry, struct path *new_dir, - struct dentry *new_dentry); - int (*path_rename) (struct path *old_dir, struct dentry *old_dentry, - struct path *new_dir, struct dentry *new_dentry); - int (*path_chmod) (struct path *path, umode_t mode); - int (*path_chown) (struct path *path, kuid_t uid, kgid_t gid); - int (*path_chroot) (struct path *path); -#endif - - int (*inode_alloc_security) (struct inode *inode); - void (*inode_free_security) (struct inode *inode); - int (*inode_init_security) (struct inode *inode, struct inode *dir, - const struct qstr *qstr, const char **name, - void **value, size_t *len); - int (*inode_create) (struct inode *dir, - struct dentry *dentry, umode_t mode); - int (*inode_link) (struct dentry *old_dentry, - struct inode *dir, struct dentry *new_dentry); - int (*inode_unlink) (struct inode *dir, struct dentry *dentry); - int (*inode_symlink) (struct inode *dir, - struct dentry *dentry, const char *old_name); - int (*inode_mkdir) (struct inode *dir, struct dentry *dentry, umode_t mode); - int (*inode_rmdir) (struct inode *dir, struct dentry *dentry); - int (*inode_mknod) (struct inode *dir, struct dentry *dentry, - umode_t mode, dev_t dev); - int (*inode_rename) (struct inode *old_dir, struct dentry *old_dentry, - struct inode *new_dir, struct dentry *new_dentry); - int (*inode_readlink) (struct dentry *dentry); - int (*inode_follow_link) (struct dentry *dentry, struct nameidata *nd); - int (*inode_permission) (struct inode *inode, int mask); - int (*inode_setattr) (struct dentry *dentry, struct iattr *attr); - int (*inode_getattr) (const struct path *path); - int (*inode_setxattr) (struct dentry *dentry, const char *name, - const void *value, size_t size, int flags); - void (*inode_post_setxattr) (struct dentry *dentry, const char *name, - const void *value, size_t size, int flags); - int (*inode_getxattr) (struct dentry *dentry, const char *name); - int (*inode_listxattr) (struct dentry *dentry); - int (*inode_removexattr) (struct dentry *dentry, const char *name); - int (*inode_need_killpriv) (struct dentry *dentry); - int (*inode_killpriv) (struct dentry *dentry); - int (*inode_getsecurity) (const struct inode *inode, const char *name, void **buffer, bool alloc); - int (*inode_setsecurity) (struct inode *inode, const char *name, const void *value, size_t size, int flags); - int (*inode_listsecurity) (struct inode *inode, char *buffer, size_t buffer_size); - void (*inode_getsecid) (const struct inode *inode, u32 *secid); - - int (*file_permission) (struct file *file, int mask); - int (*file_alloc_security) (struct file *file); - void (*file_free_security) (struct file *file); - int (*file_ioctl) (struct file *file, unsigned int cmd, - unsigned long arg); - int (*mmap_addr) (unsigned long addr); - int (*mmap_file) (struct file *file, - unsigned long reqprot, unsigned long prot, - unsigned long flags); - int (*file_mprotect) (struct vm_area_struct *vma, - unsigned long reqprot, - unsigned long prot); - int (*file_lock) (struct file *file, unsigned int cmd); - int (*file_fcntl) (struct file *file, unsigned int cmd, - unsigned long arg); - void (*file_set_fowner) (struct file *file); - int (*file_send_sigiotask) (struct task_struct *tsk, - struct fown_struct *fown, int sig); - int (*file_receive) (struct file *file); - int (*file_open) (struct file *file, const struct cred *cred); - - int (*task_create) (unsigned long clone_flags); - void (*task_free) (struct task_struct *task); - int (*cred_alloc_blank) (struct cred *cred, gfp_t gfp); - void (*cred_free) (struct cred *cred); - int (*cred_prepare)(struct cred *new, const struct cred *old, - gfp_t gfp); - void (*cred_transfer)(struct cred *new, const struct cred *old); - int (*kernel_act_as)(struct cred *new, u32 secid); - int (*kernel_create_files_as)(struct cred *new, struct inode *inode); - int (*kernel_fw_from_file)(struct file *file, char *buf, size_t size); - int (*kernel_module_request)(char *kmod_name); - int (*kernel_module_from_file)(struct file *file); - int (*task_fix_setuid) (struct cred *new, const struct cred *old, - int flags); - int (*task_setpgid) (struct task_struct *p, pid_t pgid); - int (*task_getpgid) (struct task_struct *p); - int (*task_getsid) (struct task_struct *p); - void (*task_getsecid) (struct task_struct *p, u32 *secid); - int (*task_setnice) (struct task_struct *p, int nice); - int (*task_setioprio) (struct task_struct *p, int ioprio); - int (*task_getioprio) (struct task_struct *p); - int (*task_setrlimit) (struct task_struct *p, unsigned int resource, - struct rlimit *new_rlim); - int (*task_setscheduler) (struct task_struct *p); - int (*task_getscheduler) (struct task_struct *p); - int (*task_movememory) (struct task_struct *p); - int (*task_kill) (struct task_struct *p, - struct siginfo *info, int sig, u32 secid); - int (*task_wait) (struct task_struct *p); - int (*task_prctl) (int option, unsigned long arg2, - unsigned long arg3, unsigned long arg4, - unsigned long arg5); - void (*task_to_inode) (struct task_struct *p, struct inode *inode); - - int (*ipc_permission) (struct kern_ipc_perm *ipcp, short flag); - void (*ipc_getsecid) (struct kern_ipc_perm *ipcp, u32 *secid); - - int (*msg_msg_alloc_security) (struct msg_msg *msg); - void (*msg_msg_free_security) (struct msg_msg *msg); - - int (*msg_queue_alloc_security) (struct msg_queue *msq); - void (*msg_queue_free_security) (struct msg_queue *msq); - int (*msg_queue_associate) (struct msg_queue *msq, int msqflg); - int (*msg_queue_msgctl) (struct msg_queue *msq, int cmd); - int (*msg_queue_msgsnd) (struct msg_queue *msq, - struct msg_msg *msg, int msqflg); - int (*msg_queue_msgrcv) (struct msg_queue *msq, - struct msg_msg *msg, - struct task_struct *target, - long type, int mode); - - int (*shm_alloc_security) (struct shmid_kernel *shp); - void (*shm_free_security) (struct shmid_kernel *shp); - int (*shm_associate) (struct shmid_kernel *shp, int shmflg); - int (*shm_shmctl) (struct shmid_kernel *shp, int cmd); - int (*shm_shmat) (struct shmid_kernel *shp, - char __user *shmaddr, int shmflg); - - int (*sem_alloc_security) (struct sem_array *sma); - void (*sem_free_security) (struct sem_array *sma); - int (*sem_associate) (struct sem_array *sma, int semflg); - int (*sem_semctl) (struct sem_array *sma, int cmd); - int (*sem_semop) (struct sem_array *sma, - struct sembuf *sops, unsigned nsops, int alter); - - int (*netlink_send) (struct sock *sk, struct sk_buff *skb); - - void (*d_instantiate) (struct dentry *dentry, struct inode *inode); - - int (*getprocattr) (struct task_struct *p, char *name, char **value); - int (*setprocattr) (struct task_struct *p, char *name, void *value, size_t size); - int (*ismaclabel) (const char *name); - int (*secid_to_secctx) (u32 secid, char **secdata, u32 *seclen); - int (*secctx_to_secid) (const char *secdata, u32 seclen, u32 *secid); - void (*release_secctx) (char *secdata, u32 seclen); - - int (*inode_notifysecctx)(struct inode *inode, void *ctx, u32 ctxlen); - int (*inode_setsecctx)(struct dentry *dentry, void *ctx, u32 ctxlen); - int (*inode_getsecctx)(struct inode *inode, void **ctx, u32 *ctxlen); - -#ifdef CONFIG_SECURITY_NETWORK - int (*unix_stream_connect) (struct sock *sock, struct sock *other, struct sock *newsk); - int (*unix_may_send) (struct socket *sock, struct socket *other); - - int (*socket_create) (int family, int type, int protocol, int kern); - int (*socket_post_create) (struct socket *sock, int family, - int type, int protocol, int kern); - int (*socket_bind) (struct socket *sock, - struct sockaddr *address, int addrlen); - int (*socket_connect) (struct socket *sock, - struct sockaddr *address, int addrlen); - int (*socket_listen) (struct socket *sock, int backlog); - int (*socket_accept) (struct socket *sock, struct socket *newsock); - int (*socket_sendmsg) (struct socket *sock, - struct msghdr *msg, int size); - int (*socket_recvmsg) (struct socket *sock, - struct msghdr *msg, int size, int flags); - int (*socket_getsockname) (struct socket *sock); - int (*socket_getpeername) (struct socket *sock); - int (*socket_getsockopt) (struct socket *sock, int level, int optname); - int (*socket_setsockopt) (struct socket *sock, int level, int optname); - int (*socket_shutdown) (struct socket *sock, int how); - int (*socket_sock_rcv_skb) (struct sock *sk, struct sk_buff *skb); - int (*socket_getpeersec_stream) (struct socket *sock, char __user *optval, int __user *optlen, unsigned len); - int (*socket_getpeersec_dgram) (struct socket *sock, struct sk_buff *skb, u32 *secid); - int (*sk_alloc_security) (struct sock *sk, int family, gfp_t priority); - void (*sk_free_security) (struct sock *sk); - void (*sk_clone_security) (const struct sock *sk, struct sock *newsk); - void (*sk_getsecid) (struct sock *sk, u32 *secid); - void (*sock_graft) (struct sock *sk, struct socket *parent); - int (*inet_conn_request) (struct sock *sk, struct sk_buff *skb, - struct request_sock *req); - void (*inet_csk_clone) (struct sock *newsk, const struct request_sock *req); - void (*inet_conn_established) (struct sock *sk, struct sk_buff *skb); - int (*secmark_relabel_packet) (u32 secid); - void (*secmark_refcount_inc) (void); - void (*secmark_refcount_dec) (void); - void (*req_classify_flow) (const struct request_sock *req, struct flowi *fl); - int (*tun_dev_alloc_security) (void **security); - void (*tun_dev_free_security) (void *security); - int (*tun_dev_create) (void); - int (*tun_dev_attach_queue) (void *security); - int (*tun_dev_attach) (struct sock *sk, void *security); - int (*tun_dev_open) (void *security); -#endif /* CONFIG_SECURITY_NETWORK */ - -#ifdef CONFIG_SECURITY_NETWORK_XFRM - int (*xfrm_policy_alloc_security) (struct xfrm_sec_ctx **ctxp, - struct xfrm_user_sec_ctx *sec_ctx, gfp_t gfp); - int (*xfrm_policy_clone_security) (struct xfrm_sec_ctx *old_ctx, struct xfrm_sec_ctx **new_ctx); - void (*xfrm_policy_free_security) (struct xfrm_sec_ctx *ctx); - int (*xfrm_policy_delete_security) (struct xfrm_sec_ctx *ctx); - int (*xfrm_state_alloc) (struct xfrm_state *x, - struct xfrm_user_sec_ctx *sec_ctx); - int (*xfrm_state_alloc_acquire) (struct xfrm_state *x, - struct xfrm_sec_ctx *polsec, - u32 secid); - void (*xfrm_state_free_security) (struct xfrm_state *x); - int (*xfrm_state_delete_security) (struct xfrm_state *x); - int (*xfrm_policy_lookup) (struct xfrm_sec_ctx *ctx, u32 fl_secid, u8 dir); - int (*xfrm_state_pol_flow_match) (struct xfrm_state *x, - struct xfrm_policy *xp, - const struct flowi *fl); - int (*xfrm_decode_session) (struct sk_buff *skb, u32 *secid, int ckall); -#endif /* CONFIG_SECURITY_NETWORK_XFRM */ - - /* key management security hooks */ -#ifdef CONFIG_KEYS - int (*key_alloc) (struct key *key, const struct cred *cred, unsigned long flags); - void (*key_free) (struct key *key); - int (*key_permission) (key_ref_t key_ref, - const struct cred *cred, - unsigned perm); - int (*key_getsecurity)(struct key *key, char **_buffer); -#endif /* CONFIG_KEYS */ - -#ifdef CONFIG_AUDIT - int (*audit_rule_init) (u32 field, u32 op, char *rulestr, void **lsmrule); - int (*audit_rule_known) (struct audit_krule *krule); - int (*audit_rule_match) (u32 secid, u32 field, u32 op, void *lsmrule, - struct audit_context *actx); - void (*audit_rule_free) (void *lsmrule); -#endif /* CONFIG_AUDIT */ -}; - /* prototypes */ extern int security_init(void); -extern int security_module_enable(struct security_operations *ops); -extern int register_security(struct security_operations *ops); -extern void __init security_fixup_ops(struct security_operations *ops); - /* Security operations */ int security_binder_set_context_mgr(struct task_struct *mgr); @@ -1839,7 +256,8 @@ int security_inode_rename(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags); int security_inode_readlink(struct dentry *dentry); -int security_inode_follow_link(struct dentry *dentry, struct nameidata *nd); +int security_inode_follow_link(struct dentry *dentry, struct inode *inode, + bool rcu); int security_inode_permission(struct inode *inode, int mask); int security_inode_setattr(struct dentry *dentry, struct iattr *attr); int security_inode_getattr(const struct path *path); @@ -2047,7 +465,7 @@ static inline int security_settime(const struct timespec *ts, static inline int security_vm_enough_memory_mm(struct mm_struct *mm, long pages) { - return cap_vm_enough_memory(mm, pages); + return __vm_enough_memory(mm, pages, cap_vm_enough_memory(mm, pages)); } static inline int security_bprm_set_creds(struct linux_binprm *bprm) @@ -2242,7 +660,8 @@ static inline int security_inode_readlink(struct dentry *dentry) } static inline int security_inode_follow_link(struct dentry *dentry, - struct nameidata *nd) + struct inode *inode, + bool rcu) { return 0; } @@ -2527,7 +946,7 @@ static inline int security_task_prctl(int option, unsigned long arg2, unsigned long arg4, unsigned long arg5) { - return cap_task_prctl(option, arg2, arg3, arg3, arg5); + return cap_task_prctl(option, arg2, arg3, arg4, arg5); } static inline void security_task_to_inode(struct task_struct *p, struct inode *inode) @@ -2650,7 +1069,7 @@ static inline int security_setprocattr(struct task_struct *p, char *name, void * static inline int security_netlink_send(struct sock *sk, struct sk_buff *skb) { - return cap_netlink_send(sk, skb); + return 0; } static inline int security_ismaclabel(const char *name) @@ -3218,36 +1637,5 @@ static inline void free_secdata(void *secdata) { } #endif /* CONFIG_SECURITY */ -#ifdef CONFIG_SECURITY_YAMA -extern int yama_ptrace_access_check(struct task_struct *child, - unsigned int mode); -extern int yama_ptrace_traceme(struct task_struct *parent); -extern void yama_task_free(struct task_struct *task); -extern int yama_task_prctl(int option, unsigned long arg2, unsigned long arg3, - unsigned long arg4, unsigned long arg5); -#else -static inline int yama_ptrace_access_check(struct task_struct *child, - unsigned int mode) -{ - return 0; -} - -static inline int yama_ptrace_traceme(struct task_struct *parent) -{ - return 0; -} - -static inline void yama_task_free(struct task_struct *task) -{ -} - -static inline int yama_task_prctl(int option, unsigned long arg2, - unsigned long arg3, unsigned long arg4, - unsigned long arg5) -{ - return -ENOSYS; -} -#endif /* CONFIG_SECURITY_YAMA */ - #endif /* ! __LINUX_SECURITY_H */ diff --git a/kernel/include/linux/seq_file.h b/kernel/include/linux/seq_file.h index 7848473a5..dde00defb 100644 --- a/kernel/include/linux/seq_file.h +++ b/kernel/include/linux/seq_file.h @@ -114,15 +114,25 @@ int seq_open(struct file *, const struct seq_operations *); ssize_t seq_read(struct file *, char __user *, size_t, loff_t *); loff_t seq_lseek(struct file *, loff_t, int); int seq_release(struct inode *, struct file *); -int seq_escape(struct seq_file *, const char *, const char *); -int seq_putc(struct seq_file *m, char c); -int seq_puts(struct seq_file *m, const char *s); int seq_write(struct seq_file *seq, const void *data, size_t len); -__printf(2, 3) int seq_printf(struct seq_file *, const char *, ...); -__printf(2, 0) int seq_vprintf(struct seq_file *, const char *, va_list args); +__printf(2, 0) +void seq_vprintf(struct seq_file *m, const char *fmt, va_list args); +__printf(2, 3) +void seq_printf(struct seq_file *m, const char *fmt, ...); +void seq_putc(struct seq_file *m, char c); +void seq_puts(struct seq_file *m, const char *s); +void seq_put_decimal_ull(struct seq_file *m, char delimiter, + unsigned long long num); +void seq_put_decimal_ll(struct seq_file *m, char delimiter, long long num); +void seq_escape(struct seq_file *m, const char *s, const char *esc); + +void seq_hex_dump(struct seq_file *m, const char *prefix_str, int prefix_type, + int rowsize, int groupsize, const void *buf, size_t len, + bool ascii); int seq_path(struct seq_file *, const struct path *, const char *); +int seq_file_path(struct seq_file *, struct file *, const char *); int seq_dentry(struct seq_file *, struct dentry *, const char *); int seq_path_root(struct seq_file *m, const struct path *path, const struct path *root, const char *esc); @@ -133,10 +143,6 @@ int single_release(struct inode *, struct file *); void *__seq_open_private(struct file *, const struct seq_operations *, int); int seq_open_private(struct file *, const struct seq_operations *, int); int seq_release_private(struct inode *, struct file *); -int seq_put_decimal_ull(struct seq_file *m, char delimiter, - unsigned long long num); -int seq_put_decimal_ll(struct seq_file *m, char delimiter, - long long num); static inline struct user_namespace *seq_user_ns(struct seq_file *seq) { diff --git a/kernel/include/linux/seqlock.h b/kernel/include/linux/seqlock.h index eaade3619..b14f4d236 100644 --- a/kernel/include/linux/seqlock.h +++ b/kernel/include/linux/seqlock.h @@ -35,6 +35,7 @@ #include <linux/spinlock.h> #include <linux/preempt.h> #include <linux/lockdep.h> +#include <linux/compiler.h> #include <asm/processor.h> /* @@ -243,9 +244,128 @@ static inline void raw_write_seqcount_end(seqcount_t *s) preempt_enable_rt(); } -/* +/** + * raw_write_seqcount_barrier - do a seq write barrier + * @s: pointer to seqcount_t + * + * This can be used to provide an ordering guarantee instead of the + * usual consistency guarantee. It is one wmb cheaper, because we can + * collapse the two back-to-back wmb()s. + * + * seqcount_t seq; + * bool X = true, Y = false; + * + * void read(void) + * { + * bool x, y; + * + * do { + * int s = read_seqcount_begin(&seq); + * + * x = X; y = Y; + * + * } while (read_seqcount_retry(&seq, s)); + * + * BUG_ON(!x && !y); + * } + * + * void write(void) + * { + * Y = true; + * + * raw_write_seqcount_barrier(seq); + * + * X = false; + * } + */ +static inline void raw_write_seqcount_barrier(seqcount_t *s) +{ + s->sequence++; + smp_wmb(); + s->sequence++; +} + +static inline int raw_read_seqcount_latch(seqcount_t *s) +{ + return lockless_dereference(s->sequence); +} + +/** * raw_write_seqcount_latch - redirect readers to even/odd copy * @s: pointer to seqcount_t + * + * The latch technique is a multiversion concurrency control method that allows + * queries during non-atomic modifications. If you can guarantee queries never + * interrupt the modification -- e.g. the concurrency is strictly between CPUs + * -- you most likely do not need this. + * + * Where the traditional RCU/lockless data structures rely on atomic + * modifications to ensure queries observe either the old or the new state the + * latch allows the same for non-atomic updates. The trade-off is doubling the + * cost of storage; we have to maintain two copies of the entire data + * structure. + * + * Very simply put: we first modify one copy and then the other. This ensures + * there is always one copy in a stable state, ready to give us an answer. + * + * The basic form is a data structure like: + * + * struct latch_struct { + * seqcount_t seq; + * struct data_struct data[2]; + * }; + * + * Where a modification, which is assumed to be externally serialized, does the + * following: + * + * void latch_modify(struct latch_struct *latch, ...) + * { + * smp_wmb(); <- Ensure that the last data[1] update is visible + * latch->seq++; + * smp_wmb(); <- Ensure that the seqcount update is visible + * + * modify(latch->data[0], ...); + * + * smp_wmb(); <- Ensure that the data[0] update is visible + * latch->seq++; + * smp_wmb(); <- Ensure that the seqcount update is visible + * + * modify(latch->data[1], ...); + * } + * + * The query will have a form like: + * + * struct entry *latch_query(struct latch_struct *latch, ...) + * { + * struct entry *entry; + * unsigned seq, idx; + * + * do { + * seq = lockless_dereference(latch->seq); + * + * idx = seq & 0x01; + * entry = data_query(latch->data[idx], ...); + * + * smp_rmb(); + * } while (seq != latch->seq); + * + * return entry; + * } + * + * So during the modification, queries are first redirected to data[1]. Then we + * modify data[0]. When that is complete, we redirect queries back to data[0] + * and we can modify data[1]. + * + * NOTE: The non-requirement for atomic modifications does _NOT_ include + * the publishing of new entries in the case where data is a dynamic + * data structure. + * + * An iteration might start in data[0] and get suspended long enough + * to miss an entire modification sequence, once it resumes it might + * observe the new entry. + * + * NOTE: When data is a dynamic data structure; one should use regular RCU + * patterns to manage the lifetimes of the objects within. */ static inline void raw_write_seqcount_latch(seqcount_t *s) { @@ -276,13 +396,13 @@ static inline void write_seqcount_end(seqcount_t *s) } /** - * write_seqcount_barrier - invalidate in-progress read-side seq operations + * write_seqcount_invalidate - invalidate in-progress read-side seq operations * @s: pointer to seqcount_t * - * After write_seqcount_barrier, no read-side seq operations will complete + * After write_seqcount_invalidate, no read-side seq operations will complete * successfully and see data older than this. */ -static inline void write_seqcount_barrier(seqcount_t *s) +static inline void write_seqcount_invalidate(seqcount_t *s) { smp_wmb(); s->sequence+=2; diff --git a/kernel/include/linux/serial_8250.h b/kernel/include/linux/serial_8250.h index 78097e7a3..faa0e0370 100644 --- a/kernel/include/linux/serial_8250.h +++ b/kernel/include/linux/serial_8250.h @@ -12,6 +12,7 @@ #define _LINUX_SERIAL_8250_H #include <linux/serial_core.h> +#include <linux/serial_reg.h> #include <linux/platform_device.h> /* @@ -135,8 +136,8 @@ void serial8250_resume_port(int line); extern int early_serial_setup(struct uart_port *port); -extern unsigned int serial8250_early_in(struct uart_port *port, int offset); -extern void serial8250_early_out(struct uart_port *port, int offset, int value); +extern int early_serial8250_setup(struct earlycon_device *device, + const char *options); extern void serial8250_do_set_termios(struct uart_port *port, struct ktermios *termios, struct ktermios *old); extern int serial8250_do_startup(struct uart_port *port); @@ -149,6 +150,11 @@ int serial8250_handle_irq(struct uart_port *port, unsigned int iir); unsigned char serial8250_rx_chars(struct uart_8250_port *up, unsigned char lsr); void serial8250_tx_chars(struct uart_8250_port *up); unsigned int serial8250_modem_status(struct uart_8250_port *up); +void serial8250_init_port(struct uart_8250_port *up); +void serial8250_set_defaults(struct uart_8250_port *up); +void serial8250_console_write(struct uart_8250_port *up, const char *s, + unsigned int count); +int serial8250_console_setup(struct uart_port *port, char *options, bool probe); extern void serial8250_set_isa_configurator(void (*v) (int port, struct uart_port *up, diff --git a/kernel/include/linux/serial_core.h b/kernel/include/linux/serial_core.h index 025dad9dc..297d4fa1c 100644 --- a/kernel/include/linux/serial_core.h +++ b/kernel/include/linux/serial_core.h @@ -35,7 +35,7 @@ #define uart_console(port) \ ((port)->cons && (port)->cons->index == (port)->line) #else -#define uart_console(port) (0) +#define uart_console(port) ({ (void)port; 0; }) #endif struct uart_port; diff --git a/kernel/include/linux/serial_sci.h b/kernel/include/linux/serial_sci.h index 6c5e3bb28..7c536ac5b 100644 --- a/kernel/include/linux/serial_sci.h +++ b/kernel/include/linux/serial_sci.h @@ -1,6 +1,7 @@ #ifndef __LINUX_SERIAL_SCI_H #define __LINUX_SERIAL_SCI_H +#include <linux/bitops.h> #include <linux/serial_core.h> #include <linux/sh_dma.h> @@ -10,59 +11,16 @@ #define SCIx_NOT_SUPPORTED (-1) -/* SCSMR (Serial Mode Register) */ -#define SCSMR_CHR (1 << 6) /* 7-bit Character Length */ -#define SCSMR_PE (1 << 5) /* Parity Enable */ -#define SCSMR_ODD (1 << 4) /* Odd Parity */ -#define SCSMR_STOP (1 << 3) /* Stop Bit Length */ -#define SCSMR_CKS 0x0003 /* Clock Select */ - /* Serial Control Register (@ = not supported by all parts) */ -#define SCSCR_TIE (1 << 7) /* Transmit Interrupt Enable */ -#define SCSCR_RIE (1 << 6) /* Receive Interrupt Enable */ -#define SCSCR_TE (1 << 5) /* Transmit Enable */ -#define SCSCR_RE (1 << 4) /* Receive Enable */ -#define SCSCR_REIE (1 << 3) /* Receive Error Interrupt Enable @ */ -#define SCSCR_TOIE (1 << 2) /* Timeout Interrupt Enable @ */ -#define SCSCR_CKE1 (1 << 1) /* Clock Enable 1 */ -#define SCSCR_CKE0 (1 << 0) /* Clock Enable 0 */ -/* SCIFA/SCIFB only */ -#define SCSCR_TDRQE (1 << 15) /* Tx Data Transfer Request Enable */ -#define SCSCR_RDRQE (1 << 14) /* Rx Data Transfer Request Enable */ - -/* SCxSR (Serial Status Register) on SCI */ -#define SCI_TDRE 0x80 /* Transmit Data Register Empty */ -#define SCI_RDRF 0x40 /* Receive Data Register Full */ -#define SCI_ORER 0x20 /* Overrun Error */ -#define SCI_FER 0x10 /* Framing Error */ -#define SCI_PER 0x08 /* Parity Error */ -#define SCI_TEND 0x04 /* Transmit End */ - -#define SCI_DEFAULT_ERROR_MASK (SCI_PER | SCI_FER) - -/* SCxSR (Serial Status Register) on SCIF, HSCIF */ -#define SCIF_ER 0x0080 /* Receive Error */ -#define SCIF_TEND 0x0040 /* Transmission End */ -#define SCIF_TDFE 0x0020 /* Transmit FIFO Data Empty */ -#define SCIF_BRK 0x0010 /* Break Detect */ -#define SCIF_FER 0x0008 /* Framing Error */ -#define SCIF_PER 0x0004 /* Parity Error */ -#define SCIF_RDF 0x0002 /* Receive FIFO Data Full */ -#define SCIF_DR 0x0001 /* Receive Data Ready */ - -#define SCIF_DEFAULT_ERROR_MASK (SCIF_PER | SCIF_FER | SCIF_ER | SCIF_BRK) - -/* SCFCR (FIFO Control Register) */ -#define SCFCR_LOOP (1 << 0) /* Loopback Test */ - -/* SCSPTR (Serial Port Register), optional */ -#define SCSPTR_RTSIO (1 << 7) /* Serial Port RTS Pin Input/Output */ -#define SCSPTR_CTSIO (1 << 5) /* Serial Port CTS Pin Input/Output */ -#define SCSPTR_SPB2IO (1 << 1) /* Serial Port Break Input/Output */ -#define SCSPTR_SPB2DT (1 << 0) /* Serial Port Break Data */ - -/* HSSRR HSCIF */ -#define HSCIF_SRE 0x8000 /* Sampling Rate Register Enable */ +#define SCSCR_TIE BIT(7) /* Transmit Interrupt Enable */ +#define SCSCR_RIE BIT(6) /* Receive Interrupt Enable */ +#define SCSCR_TE BIT(5) /* Transmit Enable */ +#define SCSCR_RE BIT(4) /* Receive Enable */ +#define SCSCR_REIE BIT(3) /* Receive Error Interrupt Enable @ */ +#define SCSCR_TOIE BIT(2) /* Timeout Interrupt Enable @ */ +#define SCSCR_CKE1 BIT(1) /* Clock Enable 1 */ +#define SCSCR_CKE0 BIT(0) /* Clock Enable 0 */ + enum { SCIx_PROBE_REGTYPE, @@ -82,28 +40,6 @@ enum { SCIx_NR_REGTYPES, }; -/* - * SCI register subset common for all port types. - * Not all registers will exist on all parts. - */ -enum { - SCSMR, /* Serial Mode Register */ - SCBRR, /* Bit Rate Register */ - SCSCR, /* Serial Control Register */ - SCxSR, /* Serial Status Register */ - SCFCR, /* FIFO Control Register */ - SCFDR, /* FIFO Data Count Register */ - SCxTDR, /* Transmit (FIFO) Data Register */ - SCxRDR, /* Receive (FIFO) Data Register */ - SCLSR, /* Line Status Register */ - SCTFDR, /* Transmit FIFO Data Count Register */ - SCRFDR, /* Receive FIFO Data Count Register */ - SCSPTR, /* Serial Port Register */ - HSSRR, /* Sampling Rate Register */ - - SCIx_NR_REGS, -}; - struct device; struct plat_sci_port_ops { @@ -113,7 +49,7 @@ struct plat_sci_port_ops { /* * Port-specific capabilities */ -#define SCIx_HAVE_RTSCTS (1 << 0) +#define SCIx_HAVE_RTSCTS BIT(0) /* * Platform device specific platform_data struct diff --git a/kernel/include/linux/serio.h b/kernel/include/linux/serio.h index 9f779c7a2..df4ab5de1 100644 --- a/kernel/include/linux/serio.h +++ b/kernel/include/linux/serio.h @@ -18,6 +18,8 @@ #include <linux/mod_devicetable.h> #include <uapi/linux/serio.h> +extern struct bus_type serio_bus; + struct serio { void *port_data; diff --git a/kernel/include/linux/shdma-base.h b/kernel/include/linux/shdma-base.h index dd0ba502c..d927647e6 100644 --- a/kernel/include/linux/shdma-base.h +++ b/kernel/include/linux/shdma-base.h @@ -128,7 +128,10 @@ void shdma_cleanup(struct shdma_dev *sdev); #if IS_ENABLED(CONFIG_SH_DMAE_BASE) bool shdma_chan_filter(struct dma_chan *chan, void *arg); #else -#define shdma_chan_filter NULL +static inline bool shdma_chan_filter(struct dma_chan *chan, void *arg) +{ + return false; +} #endif #endif diff --git a/kernel/include/linux/shmem_fs.h b/kernel/include/linux/shmem_fs.h index 50777b5b1..92d112aee 100644 --- a/kernel/include/linux/shmem_fs.h +++ b/kernel/include/linux/shmem_fs.h @@ -15,10 +15,7 @@ struct shmem_inode_info { unsigned int seals; /* shmem seals */ unsigned long flags; unsigned long alloced; /* data pages alloced to file */ - union { - unsigned long swapped; /* subtotal assigned to swap */ - char *symlink; /* unswappable short symlink */ - }; + unsigned long swapped; /* subtotal assigned to swap */ struct shared_policy policy; /* NUMA memory alloc policy */ struct list_head swaplist; /* chain of maybes on swap */ struct simple_xattrs xattrs; /* list of xattrs */ diff --git a/kernel/include/linux/signal.h b/kernel/include/linux/signal.h index 66215b20a..561a1283e 100644 --- a/kernel/include/linux/signal.h +++ b/kernel/include/linux/signal.h @@ -240,7 +240,6 @@ extern int sigprocmask(int, sigset_t *, sigset_t *); extern void set_current_blocked(sigset_t *); extern void __set_current_blocked(const sigset_t *); extern int show_unhandled_signals; -extern int sigsuspend(sigset_t *); struct sigaction { #ifndef __ARCH_HAS_IRIX_SIGACTION diff --git a/kernel/include/linux/skbuff.h b/kernel/include/linux/skbuff.h index b42539122..71a6f5b04 100644 --- a/kernel/include/linux/skbuff.h +++ b/kernel/include/linux/skbuff.h @@ -34,7 +34,10 @@ #include <linux/dma-mapping.h> #include <linux/netdev_features.h> #include <linux/sched.h> -#include <net/flow_keys.h> +#include <net/flow_dissector.h> +#include <linux/splice.h> +#include <linux/in6.h> +#include <net/flow.h> /* A. Checksumming of received packets by device. * @@ -170,13 +173,26 @@ struct nf_bridge_info { BRNF_PROTO_UNCHANGED, BRNF_PROTO_8021Q, BRNF_PROTO_PPPOE - } orig_proto; - bool pkt_otherhost; - unsigned int mask; + } orig_proto:8; + u8 pkt_otherhost:1; + u8 in_prerouting:1; + u8 bridged_dnat:1; + __u16 frag_max_size; struct net_device *physindev; + + /* always valid & non-NULL from FORWARD on, for physdev match */ struct net_device *physoutdev; - char neigh_header[8]; - __be32 ipv4_daddr; + union { + /* prerouting: detect dnat in orig/reply direction */ + __be32 ipv4_daddr; + struct in6_addr ipv6_daddr; + + /* after prerouting + nat detected: store original source + * mac since neigh resolution overwrites it, only used while + * skb is out in neigh layer. + */ + char neigh_header[8]; + }; }; #endif @@ -204,6 +220,7 @@ struct sk_buff; #else #define MAX_SKB_FRAGS (65536/PAGE_SIZE + 1) #endif +extern int sysctl_max_skb_frags; typedef struct skb_frag_struct skb_frag_t; @@ -448,6 +465,15 @@ static inline u32 skb_mstamp_us_delta(const struct skb_mstamp *t1, return delta_us; } +static inline bool skb_mstamp_after(const struct skb_mstamp *t1, + const struct skb_mstamp *t0) +{ + s32 diff = t1->stamp_jiffies - t0->stamp_jiffies; + + if (!diff) + diff = t1->stamp_us - t0->stamp_us; + return diff > 0; +} /** * struct sk_buff - socket buffer @@ -499,6 +525,7 @@ static inline u32 skb_mstamp_us_delta(const struct skb_mstamp *t1, * @no_fcs: Request NIC to treat last 4 bytes as Ethernet FCS * @napi_id: id of the NAPI struct this skb came from * @secmark: security marking + * @offload_fwd_mark: fwding offload mark * @mark: Generic packet mark * @vlan_proto: vlan encapsulation protocol * @vlan_tci: vlan tag control information @@ -643,9 +670,15 @@ struct sk_buff { unsigned int sender_cpu; }; #endif + union { #ifdef CONFIG_NETWORK_SECMARK - __u32 secmark; + __u32 secmark; +#endif +#ifdef CONFIG_NET_SWITCHDEV + __u32 offload_fwd_mark; #endif + }; + union { __u32 mark; __u32 reserved_tailroom; @@ -860,6 +893,9 @@ int skb_append_datato_frags(struct sock *sk, struct sk_buff *skb, int len, int odd, struct sk_buff *skb), void *from, int length); +int skb_append_pagefrags(struct sk_buff *skb, struct page *page, + int offset, size_t size); + struct skb_seq_state { __u32 lower_offset; __u32 upper_offset; @@ -912,15 +948,90 @@ enum pkt_hash_types { PKT_HASH_TYPE_L4, /* Input: src_IP, dst_IP, src_port, dst_port */ }; -static inline void -skb_set_hash(struct sk_buff *skb, __u32 hash, enum pkt_hash_types type) +static inline void skb_clear_hash(struct sk_buff *skb) { - skb->l4_hash = (type == PKT_HASH_TYPE_L4); + skb->hash = 0; skb->sw_hash = 0; + skb->l4_hash = 0; +} + +static inline void skb_clear_hash_if_not_l4(struct sk_buff *skb) +{ + if (!skb->l4_hash) + skb_clear_hash(skb); +} + +static inline void +__skb_set_hash(struct sk_buff *skb, __u32 hash, bool is_sw, bool is_l4) +{ + skb->l4_hash = is_l4; + skb->sw_hash = is_sw; skb->hash = hash; } +static inline void +skb_set_hash(struct sk_buff *skb, __u32 hash, enum pkt_hash_types type) +{ + /* Used by drivers to set hash from HW */ + __skb_set_hash(skb, hash, false, type == PKT_HASH_TYPE_L4); +} + +static inline void +__skb_set_sw_hash(struct sk_buff *skb, __u32 hash, bool is_l4) +{ + __skb_set_hash(skb, hash, true, is_l4); +} + void __skb_get_hash(struct sk_buff *skb); +u32 skb_get_poff(const struct sk_buff *skb); +u32 __skb_get_poff(const struct sk_buff *skb, void *data, + const struct flow_keys *keys, int hlen); +__be32 __skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto, + void *data, int hlen_proto); + +static inline __be32 skb_flow_get_ports(const struct sk_buff *skb, + int thoff, u8 ip_proto) +{ + return __skb_flow_get_ports(skb, thoff, ip_proto, NULL, 0); +} + +void skb_flow_dissector_init(struct flow_dissector *flow_dissector, + const struct flow_dissector_key *key, + unsigned int key_count); + +bool __skb_flow_dissect(const struct sk_buff *skb, + struct flow_dissector *flow_dissector, + void *target_container, + void *data, __be16 proto, int nhoff, int hlen, + unsigned int flags); + +static inline bool skb_flow_dissect(const struct sk_buff *skb, + struct flow_dissector *flow_dissector, + void *target_container, unsigned int flags) +{ + return __skb_flow_dissect(skb, flow_dissector, target_container, + NULL, 0, 0, 0, flags); +} + +static inline bool skb_flow_dissect_flow_keys(const struct sk_buff *skb, + struct flow_keys *flow, + unsigned int flags) +{ + memset(flow, 0, sizeof(*flow)); + return __skb_flow_dissect(skb, &flow_keys_dissector, flow, + NULL, 0, 0, 0, flags); +} + +static inline bool skb_flow_dissect_flow_keys_buf(struct flow_keys *flow, + void *data, __be16 proto, + int nhoff, int hlen, + unsigned int flags) +{ + memset(flow, 0, sizeof(*flow)); + return __skb_flow_dissect(NULL, &flow_keys_buf_dissector, flow, + data, proto, nhoff, hlen, flags); +} + static inline __u32 skb_get_hash(struct sk_buff *skb) { if (!skb->l4_hash && !skb->sw_hash) @@ -929,22 +1040,39 @@ static inline __u32 skb_get_hash(struct sk_buff *skb) return skb->hash; } -static inline __u32 skb_get_hash_raw(const struct sk_buff *skb) +__u32 __skb_get_hash_flowi6(struct sk_buff *skb, const struct flowi6 *fl6); + +static inline __u32 skb_get_hash_flowi6(struct sk_buff *skb, const struct flowi6 *fl6) { + if (!skb->l4_hash && !skb->sw_hash) { + struct flow_keys keys; + __u32 hash = __get_hash_from_flowi6(fl6, &keys); + + __skb_set_sw_hash(skb, hash, flow_keys_have_l4(&keys)); + } + return skb->hash; } -static inline void skb_clear_hash(struct sk_buff *skb) +__u32 __skb_get_hash_flowi4(struct sk_buff *skb, const struct flowi4 *fl); + +static inline __u32 skb_get_hash_flowi4(struct sk_buff *skb, const struct flowi4 *fl4) { - skb->hash = 0; - skb->sw_hash = 0; - skb->l4_hash = 0; + if (!skb->l4_hash && !skb->sw_hash) { + struct flow_keys keys; + __u32 hash = __get_hash_from_flowi4(fl4, &keys); + + __skb_set_sw_hash(skb, hash, flow_keys_have_l4(&keys)); + } + + return skb->hash; } -static inline void skb_clear_hash_if_not_l4(struct sk_buff *skb) +__u32 skb_get_hash_perturb(const struct sk_buff *skb, u32 perturb); + +static inline __u32 skb_get_hash_raw(const struct sk_buff *skb) { - if (!skb->l4_hash) - skb_clear_hash(skb); + return skb->hash; } static inline void skb_copy_hash(struct sk_buff *to, const struct sk_buff *from) @@ -1098,7 +1226,7 @@ static inline int skb_cloned(const struct sk_buff *skb) static inline int skb_unclone(struct sk_buff *skb, gfp_t pri) { - might_sleep_if(pri & __GFP_WAIT); + might_sleep_if(gfpflags_allow_blocking(pri)); if (skb_cloned(skb)) return pskb_expand_head(skb, 0, 0, pri); @@ -1182,7 +1310,7 @@ static inline int skb_shared(const struct sk_buff *skb) */ static inline struct sk_buff *skb_share_check(struct sk_buff *skb, gfp_t pri) { - might_sleep_if(pri & __GFP_WAIT); + might_sleep_if(gfpflags_allow_blocking(pri)); if (skb_shared(skb)) { struct sk_buff *nskb = skb_clone(skb, pri); @@ -1218,7 +1346,7 @@ static inline struct sk_buff *skb_share_check(struct sk_buff *skb, gfp_t pri) static inline struct sk_buff *skb_unshare(struct sk_buff *skb, gfp_t pri) { - might_sleep_if(pri & __GFP_WAIT); + might_sleep_if(gfpflags_allow_blocking(pri)); if (skb_cloned(skb)) { struct sk_buff *nskb = skb_copy(skb, pri); @@ -1938,8 +2066,8 @@ static inline void skb_probe_transport_header(struct sk_buff *skb, if (skb_transport_header_was_set(skb)) return; - else if (skb_flow_dissect(skb, &keys)) - skb_set_transport_header(skb, keys.thoff); + else if (skb_flow_dissect_flow_keys(skb, &keys, 0)) + skb_set_transport_header(skb, keys.control.thoff); else skb_set_transport_header(skb, offset_hint); } @@ -2130,10 +2258,6 @@ static inline void __skb_queue_purge(struct sk_buff_head *list) kfree_skb(skb); } -#define NETDEV_FRAG_PAGE_MAX_ORDER get_order(32768) -#define NETDEV_FRAG_PAGE_MAX_SIZE (PAGE_SIZE << NETDEV_FRAG_PAGE_MAX_ORDER) -#define NETDEV_PAGECNT_MAX_BIAS NETDEV_FRAG_PAGE_MAX_SIZE - void *netdev_alloc_frag(unsigned int fragsz); struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int length, @@ -2188,6 +2312,11 @@ static inline struct sk_buff *netdev_alloc_skb_ip_align(struct net_device *dev, return __netdev_alloc_skb_ip_align(dev, length, GFP_ATOMIC); } +static inline void skb_free_frag(void *addr) +{ + __free_page_frag(addr); +} + void *napi_alloc_frag(unsigned int fragsz); struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, unsigned int length, gfp_t gfp_mask); @@ -2595,6 +2724,9 @@ static inline void skb_postpull_rcsum(struct sk_buff *skb, { if (skb->ip_summed == CHECKSUM_COMPLETE) skb->csum = csum_sub(skb->csum, csum_partial(start, len, 0)); + else if (skb->ip_summed == CHECKSUM_PARTIAL && + skb_checksum_start_offset(skb) < 0) + skb->ip_summed = CHECKSUM_NONE; } unsigned char *skb_pull_rcsum(struct sk_buff *skb, unsigned int len); @@ -2661,12 +2793,6 @@ static inline void skb_frag_list_init(struct sk_buff *skb) skb_shinfo(skb)->frag_list = NULL; } -static inline void skb_frag_add_head(struct sk_buff *skb, struct sk_buff *frag) -{ - frag->next = skb_shinfo(skb)->frag_list; - skb_shinfo(skb)->frag_list = frag; -} - #define skb_walk_frags(skb, iter) \ for (iter = skb_shinfo(skb)->frag_list; iter; iter = iter->next) @@ -2695,9 +2821,15 @@ int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len); int skb_store_bits(struct sk_buff *skb, int offset, const void *from, int len); __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, u8 *to, int len, __wsum csum); -int skb_splice_bits(struct sk_buff *skb, unsigned int offset, +ssize_t skb_socket_splice(struct sock *sk, + struct pipe_inode_info *pipe, + struct splice_pipe_desc *spd); +int skb_splice_bits(struct sk_buff *skb, struct sock *sk, unsigned int offset, struct pipe_inode_info *pipe, unsigned int len, - unsigned int flags); + unsigned int flags, + ssize_t (*splice_cb)(struct sock *, + struct pipe_inode_info *, + struct splice_pipe_desc *)); void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to); unsigned int skb_zerocopy_headlen(const struct sk_buff *from); int skb_zerocopy(struct sk_buff *to, struct sk_buff *from, @@ -2732,8 +2864,9 @@ __wsum __skb_checksum(const struct sk_buff *skb, int offset, int len, __wsum skb_checksum(const struct sk_buff *skb, int offset, int len, __wsum csum); -static inline void *__skb_header_pointer(const struct sk_buff *skb, int offset, - int len, void *data, int hlen, void *buffer) +static inline void * __must_check +__skb_header_pointer(const struct sk_buff *skb, int offset, + int len, void *data, int hlen, void *buffer) { if (hlen - offset >= len) return data + offset; @@ -2745,8 +2878,8 @@ static inline void *__skb_header_pointer(const struct sk_buff *skb, int offset, return buffer; } -static inline void *skb_header_pointer(const struct sk_buff *skb, int offset, - int len, void *buffer) +static inline void * __must_check +skb_header_pointer(const struct sk_buff *skb, int offset, int len, void *buffer) { return __skb_header_pointer(skb, offset, len, skb->data, skb_headlen(skb), buffer); @@ -2867,11 +3000,11 @@ static inline bool skb_defer_rx_timestamp(struct sk_buff *skb) * * PHY drivers may accept clones of transmitted packets for * timestamping via their phy_driver.txtstamp method. These drivers - * must call this function to return the skb back to the stack, with - * or without a timestamp. + * must call this function to return the skb back to the stack with a + * timestamp. * * @skb: clone of the the original outgoing packet - * @hwtstamps: hardware time stamps, may be NULL if not available + * @hwtstamps: hardware time stamps * */ void skb_complete_tx_timestamp(struct sk_buff *skb, @@ -3053,7 +3186,7 @@ static inline __sum16 __skb_checksum_validate_complete(struct sk_buff *skb, } } else if (skb->csum_bad) { /* ip_summed == CHECKSUM_NONE in this case */ - return 1; + return (__force __sum16)1; } skb->csum = psum; @@ -3301,9 +3434,6 @@ static inline bool skb_rx_queue_recorded(const struct sk_buff *skb) return skb->queue_mapping != 0; } -u16 __skb_tx_hash(const struct net_device *dev, struct sk_buff *skb, - unsigned int num_tx_queues); - static inline struct sec_path *skb_sec_path(struct sk_buff *skb) { #ifdef CONFIG_XFRM @@ -3324,7 +3454,8 @@ struct skb_gso_cb { int encap_level; __u16 csum_start; }; -#define SKB_GSO_CB(skb) ((struct skb_gso_cb *)(skb)->cb) +#define SKB_SGO_CB_OFFSET 32 +#define SKB_GSO_CB(skb) ((struct skb_gso_cb *)((skb)->cb + SKB_SGO_CB_OFFSET)) static inline int skb_tnl_header_len(const struct sk_buff *inner_skb) { @@ -3358,15 +3489,14 @@ static inline int gso_pskb_expand_head(struct sk_buff *skb, int extra) static inline __sum16 gso_make_checksum(struct sk_buff *skb, __wsum res) { int plen = SKB_GSO_CB(skb)->csum_start - skb_headroom(skb) - - skb_transport_offset(skb); - __u16 csum; + skb_transport_offset(skb); + __wsum partial; - csum = csum_fold(csum_partial(skb_transport_header(skb), - plen, skb->csum)); + partial = csum_partial(skb_transport_header(skb), plen, skb->csum); skb->csum = res; SKB_GSO_CB(skb)->csum_start -= plen; - return csum; + return csum_fold(partial); } static inline bool skb_is_gso(const struct sk_buff *skb) @@ -3421,10 +3551,9 @@ static inline void skb_checksum_none_assert(const struct sk_buff *skb) bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off); int skb_checksum_setup(struct sk_buff *skb, bool recalculate); - -u32 skb_get_poff(const struct sk_buff *skb); -u32 __skb_get_poff(const struct sk_buff *skb, void *data, - const struct flow_keys *keys, int hlen); +struct sk_buff *skb_checksum_trimmed(struct sk_buff *skb, + unsigned int transport_len, + __sum16(*skb_chkf)(struct sk_buff *skb)); /** * skb_head_is_locked - Determine if the skb->head is locked down @@ -3456,5 +3585,6 @@ static inline unsigned int skb_gso_network_seglen(const struct sk_buff *skb) skb_network_header(skb); return hdr_len + skb_gso_transport_seglen(skb); } + #endif /* __KERNEL__ */ #endif /* _LINUX_SKBUFF_H */ diff --git a/kernel/include/linux/slab.h b/kernel/include/linux/slab.h index ffd24c830..2037a861e 100644 --- a/kernel/include/linux/slab.h +++ b/kernel/include/linux/slab.h @@ -111,7 +111,7 @@ struct mem_cgroup; * struct kmem_cache related prototypes */ void __init kmem_cache_init(void); -int slab_is_available(void); +bool slab_is_available(void); struct kmem_cache *kmem_cache_create(const char *, size_t, size_t, unsigned long, @@ -158,6 +158,24 @@ size_t ksize(const void *); #endif /* + * Setting ARCH_SLAB_MINALIGN in arch headers allows a different alignment. + * Intended for arches that get misalignment faults even for 64 bit integer + * aligned buffers. + */ +#ifndef ARCH_SLAB_MINALIGN +#define ARCH_SLAB_MINALIGN __alignof__(unsigned long long) +#endif + +/* + * kmalloc and friends return ARCH_KMALLOC_MINALIGN aligned + * pointers. kmem_cache_alloc and friends return ARCH_SLAB_MINALIGN + * aligned pointers. + */ +#define __assume_kmalloc_alignment __assume_aligned(ARCH_KMALLOC_MINALIGN) +#define __assume_slab_alignment __assume_aligned(ARCH_SLAB_MINALIGN) +#define __assume_page_alignment __assume_aligned(PAGE_SIZE) + +/* * Kmalloc array related definitions */ @@ -240,8 +258,8 @@ extern struct kmem_cache *kmalloc_dma_caches[KMALLOC_SHIFT_HIGH + 1]; * belongs to. * 0 = zero alloc * 1 = 65 .. 96 bytes - * 2 = 120 .. 192 bytes - * n = 2^(n-1) .. 2^n -1 + * 2 = 129 .. 192 bytes + * n = 2^(n-1)+1 .. 2^n */ static __always_inline int kmalloc_index(size_t size) { @@ -286,13 +304,23 @@ static __always_inline int kmalloc_index(size_t size) } #endif /* !CONFIG_SLOB */ -void *__kmalloc(size_t size, gfp_t flags); -void *kmem_cache_alloc(struct kmem_cache *, gfp_t flags); +void *__kmalloc(size_t size, gfp_t flags) __assume_kmalloc_alignment; +void *kmem_cache_alloc(struct kmem_cache *, gfp_t flags) __assume_slab_alignment; void kmem_cache_free(struct kmem_cache *, void *); +/* + * Bulk allocation and freeing operations. These are accellerated in an + * allocator specific way to avoid taking locks repeatedly or building + * metadata structures unnecessarily. + * + * Note that interrupts must be enabled when calling these functions. + */ +void kmem_cache_free_bulk(struct kmem_cache *, size_t, void **); +int kmem_cache_alloc_bulk(struct kmem_cache *, gfp_t, size_t, void **); + #ifdef CONFIG_NUMA -void *__kmalloc_node(size_t size, gfp_t flags, int node); -void *kmem_cache_alloc_node(struct kmem_cache *, gfp_t flags, int node); +void *__kmalloc_node(size_t size, gfp_t flags, int node) __assume_kmalloc_alignment; +void *kmem_cache_alloc_node(struct kmem_cache *, gfp_t flags, int node) __assume_slab_alignment; #else static __always_inline void *__kmalloc_node(size_t size, gfp_t flags, int node) { @@ -306,12 +334,12 @@ static __always_inline void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t f #endif #ifdef CONFIG_TRACING -extern void *kmem_cache_alloc_trace(struct kmem_cache *, gfp_t, size_t); +extern void *kmem_cache_alloc_trace(struct kmem_cache *, gfp_t, size_t) __assume_slab_alignment; #ifdef CONFIG_NUMA extern void *kmem_cache_alloc_node_trace(struct kmem_cache *s, gfp_t gfpflags, - int node, size_t size); + int node, size_t size) __assume_slab_alignment; #else static __always_inline void * kmem_cache_alloc_node_trace(struct kmem_cache *s, @@ -344,10 +372,10 @@ kmem_cache_alloc_node_trace(struct kmem_cache *s, } #endif /* CONFIG_TRACING */ -extern void *kmalloc_order(size_t size, gfp_t flags, unsigned int order); +extern void *kmalloc_order(size_t size, gfp_t flags, unsigned int order) __assume_page_alignment; #ifdef CONFIG_TRACING -extern void *kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order); +extern void *kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order) __assume_page_alignment; #else static __always_inline void * kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order) @@ -472,15 +500,6 @@ static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node) return __kmalloc_node(size, flags, node); } -/* - * Setting ARCH_SLAB_MINALIGN in arch headers allows a different alignment. - * Intended for arches that get misalignment faults even for 64 bit integer - * aligned buffers. - */ -#ifndef ARCH_SLAB_MINALIGN -#define ARCH_SLAB_MINALIGN __alignof__(unsigned long long) -#endif - struct memcg_cache_array { struct rcu_head rcu; struct kmem_cache *entries[0]; diff --git a/kernel/include/linux/smpboot.h b/kernel/include/linux/smpboot.h index d600afb21..12910cf19 100644 --- a/kernel/include/linux/smpboot.h +++ b/kernel/include/linux/smpboot.h @@ -24,9 +24,8 @@ struct smpboot_thread_data; * parked (cpu offline) * @unpark: Optional unpark function, called when the thread is * unparked (cpu online) - * @pre_unpark: Optional unpark function, called before the thread is - * unparked (cpu online). This is not guaranteed to be - * called on the target cpu of the thread. Careful! + * @cpumask: Internal state. To update which threads are unparked, + * call smpboot_update_cpumask_percpu_thread(). * @selfparking: Thread is not parked by the park function. * @thread_comm: The base name of the thread */ @@ -40,12 +39,23 @@ struct smp_hotplug_thread { void (*cleanup)(unsigned int cpu, bool online); void (*park)(unsigned int cpu); void (*unpark)(unsigned int cpu); - void (*pre_unpark)(unsigned int cpu); + cpumask_var_t cpumask; bool selfparking; const char *thread_comm; }; -int smpboot_register_percpu_thread(struct smp_hotplug_thread *plug_thread); +int smpboot_register_percpu_thread_cpumask(struct smp_hotplug_thread *plug_thread, + const struct cpumask *cpumask); + +static inline int +smpboot_register_percpu_thread(struct smp_hotplug_thread *plug_thread) +{ + return smpboot_register_percpu_thread_cpumask(plug_thread, + cpu_possible_mask); +} + void smpboot_unregister_percpu_thread(struct smp_hotplug_thread *plug_thread); +int smpboot_update_cpumask_percpu_thread(struct smp_hotplug_thread *plug_thread, + const struct cpumask *); #endif diff --git a/kernel/include/linux/soc/brcmstb/brcmstb.h b/kernel/include/linux/soc/brcmstb/brcmstb.h new file mode 100644 index 000000000..337ce414e --- /dev/null +++ b/kernel/include/linux/soc/brcmstb/brcmstb.h @@ -0,0 +1,10 @@ +#ifndef __BRCMSTB_SOC_H +#define __BRCMSTB_SOC_H + +/* + * Bus Interface Unit control register setup, must happen early during boot, + * before SMP is brought up, called by machine entry point. + */ +void brcmstb_biuctrl_init(void); + +#endif /* __BRCMSTB_SOC_H */ diff --git a/kernel/include/linux/soc/dove/pmu.h b/kernel/include/linux/soc/dove/pmu.h new file mode 100644 index 000000000..9c99f84bc --- /dev/null +++ b/kernel/include/linux/soc/dove/pmu.h @@ -0,0 +1,6 @@ +#ifndef LINUX_SOC_DOVE_PMU_H +#define LINUX_SOC_DOVE_PMU_H + +int dove_init_pmu(void); + +#endif diff --git a/kernel/include/linux/soc/mediatek/infracfg.h b/kernel/include/linux/soc/mediatek/infracfg.h new file mode 100644 index 000000000..a5714e93f --- /dev/null +++ b/kernel/include/linux/soc/mediatek/infracfg.h @@ -0,0 +1,26 @@ +#ifndef __SOC_MEDIATEK_INFRACFG_H +#define __SOC_MEDIATEK_INFRACFG_H + +#define MT8173_TOP_AXI_PROT_EN_MCI_M2 BIT(0) +#define MT8173_TOP_AXI_PROT_EN_MM_M0 BIT(1) +#define MT8173_TOP_AXI_PROT_EN_MM_M1 BIT(2) +#define MT8173_TOP_AXI_PROT_EN_MMAPB_S BIT(6) +#define MT8173_TOP_AXI_PROT_EN_L2C_M2 BIT(9) +#define MT8173_TOP_AXI_PROT_EN_L2SS_SMI BIT(11) +#define MT8173_TOP_AXI_PROT_EN_L2SS_ADD BIT(12) +#define MT8173_TOP_AXI_PROT_EN_CCI_M2 BIT(13) +#define MT8173_TOP_AXI_PROT_EN_MFG_S BIT(14) +#define MT8173_TOP_AXI_PROT_EN_PERI_M0 BIT(15) +#define MT8173_TOP_AXI_PROT_EN_PERI_M1 BIT(16) +#define MT8173_TOP_AXI_PROT_EN_DEBUGSYS BIT(17) +#define MT8173_TOP_AXI_PROT_EN_CQ_DMA BIT(18) +#define MT8173_TOP_AXI_PROT_EN_GCPU BIT(19) +#define MT8173_TOP_AXI_PROT_EN_IOMMU BIT(20) +#define MT8173_TOP_AXI_PROT_EN_MFG_M0 BIT(21) +#define MT8173_TOP_AXI_PROT_EN_MFG_M1 BIT(22) +#define MT8173_TOP_AXI_PROT_EN_MFG_SNOOP_OUT BIT(23) + +int mtk_infracfg_set_bus_protection(struct regmap *infracfg, u32 mask); +int mtk_infracfg_clear_bus_protection(struct regmap *infracfg, u32 mask); + +#endif /* __SOC_MEDIATEK_INFRACFG_H */ diff --git a/kernel/include/linux/soc/qcom/smd-rpm.h b/kernel/include/linux/soc/qcom/smd-rpm.h new file mode 100644 index 000000000..2a53dcaee --- /dev/null +++ b/kernel/include/linux/soc/qcom/smd-rpm.h @@ -0,0 +1,35 @@ +#ifndef __QCOM_SMD_RPM_H__ +#define __QCOM_SMD_RPM_H__ + +struct qcom_smd_rpm; + +#define QCOM_SMD_RPM_ACTIVE_STATE 0 +#define QCOM_SMD_RPM_SLEEP_STATE 1 + +/* + * Constants used for addressing resources in the RPM. + */ +#define QCOM_SMD_RPM_BOOST 0x61747362 +#define QCOM_SMD_RPM_BUS_CLK 0x316b6c63 +#define QCOM_SMD_RPM_BUS_MASTER 0x73616d62 +#define QCOM_SMD_RPM_BUS_SLAVE 0x766c7362 +#define QCOM_SMD_RPM_CLK_BUF_A 0x616B6C63 +#define QCOM_SMD_RPM_LDOA 0x616f646c +#define QCOM_SMD_RPM_LDOB 0x626F646C +#define QCOM_SMD_RPM_MEM_CLK 0x326b6c63 +#define QCOM_SMD_RPM_MISC_CLK 0x306b6c63 +#define QCOM_SMD_RPM_NCPA 0x6170636E +#define QCOM_SMD_RPM_NCPB 0x6270636E +#define QCOM_SMD_RPM_OCMEM_PWR 0x706d636f +#define QCOM_SMD_RPM_QPIC_CLK 0x63697071 +#define QCOM_SMD_RPM_SMPA 0x61706d73 +#define QCOM_SMD_RPM_SMPB 0x62706d73 +#define QCOM_SMD_RPM_SPDM 0x63707362 +#define QCOM_SMD_RPM_VSA 0x00617376 + +int qcom_rpm_smd_write(struct qcom_smd_rpm *rpm, + int state, + u32 resource_type, u32 resource_id, + void *buf, size_t count); + +#endif diff --git a/kernel/include/linux/soc/qcom/smd.h b/kernel/include/linux/soc/qcom/smd.h new file mode 100644 index 000000000..d0cb6d189 --- /dev/null +++ b/kernel/include/linux/soc/qcom/smd.h @@ -0,0 +1,57 @@ +#ifndef __QCOM_SMD_H__ +#define __QCOM_SMD_H__ + +#include <linux/device.h> +#include <linux/mod_devicetable.h> + +struct qcom_smd; +struct qcom_smd_channel; +struct qcom_smd_lookup; + +/** + * struct qcom_smd_id - struct used for matching a smd device + * @name: name of the channel + */ +struct qcom_smd_id { + char name[20]; +}; + +/** + * struct qcom_smd_device - smd device struct + * @dev: the device struct + * @channel: handle to the smd channel for this device + */ +struct qcom_smd_device { + struct device dev; + struct qcom_smd_channel *channel; +}; + +/** + * struct qcom_smd_driver - smd driver struct + * @driver: underlying device driver + * @smd_match_table: static channel match table + * @probe: invoked when the smd channel is found + * @remove: invoked when the smd channel is closed + * @callback: invoked when an inbound message is received on the channel, + * should return 0 on success or -EBUSY if the data cannot be + * consumed at this time + */ +struct qcom_smd_driver { + struct device_driver driver; + const struct qcom_smd_id *smd_match_table; + + int (*probe)(struct qcom_smd_device *dev); + void (*remove)(struct qcom_smd_device *dev); + int (*callback)(struct qcom_smd_device *, const void *, size_t); +}; + +int qcom_smd_driver_register(struct qcom_smd_driver *drv); +void qcom_smd_driver_unregister(struct qcom_smd_driver *drv); + +#define module_qcom_smd_driver(__smd_driver) \ + module_driver(__smd_driver, qcom_smd_driver_register, \ + qcom_smd_driver_unregister) + +int qcom_smd_send(struct qcom_smd_channel *channel, const void *data, int len); + +#endif diff --git a/kernel/include/linux/soc/qcom/smem.h b/kernel/include/linux/soc/qcom/smem.h new file mode 100644 index 000000000..785e196ee --- /dev/null +++ b/kernel/include/linux/soc/qcom/smem.h @@ -0,0 +1,11 @@ +#ifndef __QCOM_SMEM_H__ +#define __QCOM_SMEM_H__ + +#define QCOM_SMEM_HOST_ANY -1 + +int qcom_smem_alloc(unsigned host, unsigned item, size_t size); +void *qcom_smem_get(unsigned host, unsigned item, size_t *size); + +int qcom_smem_get_free_space(unsigned host); + +#endif diff --git a/kernel/include/linux/soc/sunxi/sunxi_sram.h b/kernel/include/linux/soc/sunxi/sunxi_sram.h new file mode 100644 index 000000000..c5f663bba --- /dev/null +++ b/kernel/include/linux/soc/sunxi/sunxi_sram.h @@ -0,0 +1,19 @@ +/* + * Allwinner SoCs SRAM Controller Driver + * + * Copyright (C) 2015 Maxime Ripard + * + * Author: Maxime Ripard <maxime.ripard@free-electrons.com> + * + * This file is licensed under the terms of the GNU General Public + * License version 2. This program is licensed "as is" without any + * warranty of any kind, whether express or implied. + */ + +#ifndef _SUNXI_SRAM_H_ +#define _SUNXI_SRAM_H_ + +int sunxi_sram_claim(struct device *dev); +int sunxi_sram_release(struct device *dev); + +#endif /* _SUNXI_SRAM_H_ */ diff --git a/kernel/include/linux/sock_diag.h b/kernel/include/linux/sock_diag.h index 083ac3880..fddebc617 100644 --- a/kernel/include/linux/sock_diag.h +++ b/kernel/include/linux/sock_diag.h @@ -1,7 +1,10 @@ #ifndef __SOCK_DIAG_H__ #define __SOCK_DIAG_H__ +#include <linux/netlink.h> #include <linux/user_namespace.h> +#include <net/net_namespace.h> +#include <net/sock.h> #include <uapi/linux/sock_diag.h> struct sk_buff; @@ -11,6 +14,7 @@ struct sock; struct sock_diag_handler { __u8 family; int (*dump)(struct sk_buff *skb, struct nlmsghdr *nlh); + int (*get_info)(struct sk_buff *skb, struct sock *sk); }; int sock_diag_register(const struct sock_diag_handler *h); @@ -26,4 +30,42 @@ int sock_diag_put_meminfo(struct sock *sk, struct sk_buff *skb, int attr); int sock_diag_put_filterinfo(bool may_report_filterinfo, struct sock *sk, struct sk_buff *skb, int attrtype); +static inline +enum sknetlink_groups sock_diag_destroy_group(const struct sock *sk) +{ + switch (sk->sk_family) { + case AF_INET: + switch (sk->sk_protocol) { + case IPPROTO_TCP: + return SKNLGRP_INET_TCP_DESTROY; + case IPPROTO_UDP: + return SKNLGRP_INET_UDP_DESTROY; + default: + return SKNLGRP_NONE; + } + case AF_INET6: + switch (sk->sk_protocol) { + case IPPROTO_TCP: + return SKNLGRP_INET6_TCP_DESTROY; + case IPPROTO_UDP: + return SKNLGRP_INET6_UDP_DESTROY; + default: + return SKNLGRP_NONE; + } + default: + return SKNLGRP_NONE; + } +} + +static inline +bool sock_diag_has_destroy_listeners(const struct sock *sk) +{ + const struct net *n = sock_net(sk); + const enum sknetlink_groups group = sock_diag_destroy_group(sk); + + return group != SKNLGRP_NONE && n->diag_nlsk && + netlink_has_listeners(n->diag_nlsk, group); +} +void sock_diag_broadcast_destroy(struct sock *sk); + #endif diff --git a/kernel/include/linux/spi/cc2520.h b/kernel/include/linux/spi/cc2520.h index e741e8baa..85b8ee67e 100644 --- a/kernel/include/linux/spi/cc2520.h +++ b/kernel/include/linux/spi/cc2520.h @@ -21,7 +21,6 @@ struct cc2520_platform_data { int sfd; int reset; int vreg; - bool amplified; }; #endif diff --git a/kernel/include/linux/spi/pxa2xx_spi.h b/kernel/include/linux/spi/pxa2xx_spi.h index 6d36dacec..9ec4c147a 100644 --- a/kernel/include/linux/spi/pxa2xx_spi.h +++ b/kernel/include/linux/spi/pxa2xx_spi.h @@ -23,7 +23,6 @@ struct dma_chan; /* device.platform_data for SSP controller devices */ struct pxa2xx_spi_master { - u32 clock_enable; u16 num_chipselect; u8 enable_dma; diff --git a/kernel/include/linux/spi/spi.h b/kernel/include/linux/spi/spi.h index d67307234..cce80e6dc 100644 --- a/kernel/include/linux/spi/spi.h +++ b/kernel/include/linux/spi/spi.h @@ -23,6 +23,8 @@ #include <linux/scatterlist.h> struct dma_chan; +struct spi_master; +struct spi_transfer; /* * INTERFACES between SPI master-side drivers and SPI infrastructure. @@ -31,6 +33,63 @@ struct dma_chan; extern struct bus_type spi_bus_type; /** + * struct spi_statistics - statistics for spi transfers + * @lock: lock protecting this structure + * + * @messages: number of spi-messages handled + * @transfers: number of spi_transfers handled + * @errors: number of errors during spi_transfer + * @timedout: number of timeouts during spi_transfer + * + * @spi_sync: number of times spi_sync is used + * @spi_sync_immediate: + * number of times spi_sync is executed immediately + * in calling context without queuing and scheduling + * @spi_async: number of times spi_async is used + * + * @bytes: number of bytes transferred to/from device + * @bytes_tx: number of bytes sent to device + * @bytes_rx: number of bytes received from device + * + * @transfer_bytes_histo: + * transfer bytes histogramm + */ +struct spi_statistics { + spinlock_t lock; /* lock for the whole structure */ + + unsigned long messages; + unsigned long transfers; + unsigned long errors; + unsigned long timedout; + + unsigned long spi_sync; + unsigned long spi_sync_immediate; + unsigned long spi_async; + + unsigned long long bytes; + unsigned long long bytes_rx; + unsigned long long bytes_tx; + +#define SPI_STATISTICS_HISTO_SIZE 17 + unsigned long transfer_bytes_histo[SPI_STATISTICS_HISTO_SIZE]; +}; + +void spi_statistics_add_transfer_stats(struct spi_statistics *stats, + struct spi_transfer *xfer, + struct spi_master *master); + +#define SPI_STATISTICS_ADD_TO_FIELD(stats, field, count) \ + do { \ + unsigned long flags; \ + spin_lock_irqsave(&(stats)->lock, flags); \ + (stats)->field += count; \ + spin_unlock_irqrestore(&(stats)->lock, flags); \ + } while (0) + +#define SPI_STATISTICS_INCREMENT_FIELD(stats, field) \ + SPI_STATISTICS_ADD_TO_FIELD(stats, field, 1) + +/** * struct spi_device - Master side proxy for an SPI slave device * @dev: Driver model representation of the device. * @master: SPI controller used with the device. @@ -60,6 +119,8 @@ extern struct bus_type spi_bus_type; * @cs_gpio: gpio number of the chipselect line (optional, -ENOENT when * when not using a GPIO line) * + * @statistics: statistics for the spi_device + * * A @spi_device is used to interchange data between an SPI slave * (usually a discrete chip) and CPU memory. * @@ -98,6 +159,9 @@ struct spi_device { char modalias[SPI_NAME_SIZE]; int cs_gpio; /* chip select gpio */ + /* the statistics */ + struct spi_statistics statistics; + /* * likely need more hooks for more protocol options affecting how * the controller talks to each chip, like: @@ -190,7 +254,7 @@ static inline struct spi_driver *to_spi_driver(struct device_driver *drv) return drv ? container_of(drv, struct spi_driver, driver) : NULL; } -extern int spi_register_driver(struct spi_driver *sdrv); +extern int __spi_register_driver(struct module *owner, struct spi_driver *sdrv); /** * spi_unregister_driver - reverse effect of spi_register_driver @@ -203,6 +267,10 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv) driver_unregister(&sdrv->driver); } +/* use a define to avoid include chaining to get THIS_MODULE */ +#define spi_register_driver(driver) \ + __spi_register_driver(THIS_MODULE, driver) + /** * module_spi_driver() - Helper macro for registering a SPI driver * @__spi_driver: spi_driver struct @@ -296,6 +364,7 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv) * @cs_gpios: Array of GPIOs to use as chip select lines; one per CS * number. Any individual value may be -ENOENT for CS lines that * are not GPIOs (driven by the SPI controller itself). + * @statistics: statistics for the spi_master * @dma_tx: DMA transmit channel * @dma_rx: DMA receive channel * @dummy_rx: dummy receive buffer for full-duplex devices @@ -452,6 +521,9 @@ struct spi_master { /* gpio chip select */ int *cs_gpios; + /* statistics */ + struct spi_statistics statistics; + /* DMA channels for use with core dmaengine helpers */ struct dma_chan *dma_tx; struct dma_chan *dma_rx; @@ -779,8 +851,10 @@ extern int spi_bus_unlock(struct spi_master *master); * @len: data buffer size * Context: can sleep * - * This writes the buffer and returns zero or a negative error code. + * This function writes the buffer @buf. * Callable only from contexts that can sleep. + * + * Return: zero on success, else a negative error code. */ static inline int spi_write(struct spi_device *spi, const void *buf, size_t len) @@ -803,8 +877,10 @@ spi_write(struct spi_device *spi, const void *buf, size_t len) * @len: data buffer size * Context: can sleep * - * This reads the buffer and returns zero or a negative error code. + * This function reads the buffer @buf. * Callable only from contexts that can sleep. + * + * Return: zero on success, else a negative error code. */ static inline int spi_read(struct spi_device *spi, void *buf, size_t len) @@ -831,7 +907,7 @@ spi_read(struct spi_device *spi, void *buf, size_t len) * * For more specific semantics see spi_sync(). * - * It returns zero on success, else a negative error code. + * Return: Return: zero on success, else a negative error code. */ static inline int spi_sync_transfer(struct spi_device *spi, struct spi_transfer *xfers, @@ -855,9 +931,10 @@ extern int spi_write_then_read(struct spi_device *spi, * @cmd: command to be written before data is read back * Context: can sleep * - * This returns the (unsigned) eight bit number returned by the - * device, or else a negative error code. Callable only from - * contexts that can sleep. + * Callable only from contexts that can sleep. + * + * Return: the (unsigned) eight bit number returned by the + * device, or else a negative error code. */ static inline ssize_t spi_w8r8(struct spi_device *spi, u8 cmd) { @@ -876,12 +953,13 @@ static inline ssize_t spi_w8r8(struct spi_device *spi, u8 cmd) * @cmd: command to be written before data is read back * Context: can sleep * - * This returns the (unsigned) sixteen bit number returned by the - * device, or else a negative error code. Callable only from - * contexts that can sleep. - * * The number is returned in wire-order, which is at least sometimes * big-endian. + * + * Callable only from contexts that can sleep. + * + * Return: the (unsigned) sixteen bit number returned by the + * device, or else a negative error code. */ static inline ssize_t spi_w8r16(struct spi_device *spi, u8 cmd) { @@ -900,13 +978,13 @@ static inline ssize_t spi_w8r16(struct spi_device *spi, u8 cmd) * @cmd: command to be written before data is read back * Context: can sleep * - * This returns the (unsigned) sixteen bit number returned by the device in cpu - * endianness, or else a negative error code. Callable only from contexts that - * can sleep. - * * This function is similar to spi_w8r16, with the exception that it will * convert the read 16 bit data word from big-endian to native endianness. * + * Callable only from contexts that can sleep. + * + * Return: the (unsigned) sixteen bit number returned by the device in cpu + * endianness, or else a negative error code. */ static inline ssize_t spi_w8r16be(struct spi_device *spi, u8 cmd) diff --git a/kernel/include/linux/spi/spi_bitbang.h b/kernel/include/linux/spi/spi_bitbang.h index 85578d4be..154788ed2 100644 --- a/kernel/include/linux/spi/spi_bitbang.h +++ b/kernel/include/linux/spi/spi_bitbang.h @@ -4,7 +4,7 @@ #include <linux/workqueue.h> struct spi_bitbang { - spinlock_t lock; + struct mutex lock; u8 busy; u8 use_dma; u8 flags; /* extra spi->mode support */ diff --git a/kernel/include/linux/spinlock.h b/kernel/include/linux/spinlock.h index 28f4366fd..b241cc044 100644 --- a/kernel/include/linux/spinlock.h +++ b/kernel/include/linux/spinlock.h @@ -120,7 +120,7 @@ do { \ /* * Despite its name it doesn't necessarily has to be a full barrier. * It should only guarantee that a STORE before the critical section - * can not be reordered with a LOAD inside this section. + * can not be reordered with LOADs and STOREs inside this section. * spin_lock() is the one-way barrier, this LOAD can not escape out * of the region. So the default implementation simply ensures that * a STORE can not move into the critical section, smp_wmb() should @@ -130,16 +130,6 @@ do { \ #define smp_mb__before_spinlock() smp_wmb() #endif -/* - * Place this after a lock-acquisition primitive to guarantee that - * an UNLOCK+LOCK pair act as a full barrier. This guarantee applies - * if the UNLOCK and LOCK are executed by the same CPU or if the - * UNLOCK and LOCK operate on the same lock variable. - */ -#ifndef smp_mb__after_unlock_lock -#define smp_mb__after_unlock_lock() do { } while (0) -#endif - /** * raw_spin_unlock_wait - wait until the spinlock gets unlocked * @lock: the spinlock in question. @@ -304,7 +294,7 @@ static inline void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock) * Map the spin_lock functions to the raw variants for PREEMPT_RT=n */ -static inline raw_spinlock_t *spinlock_check(spinlock_t *lock) +static __always_inline raw_spinlock_t *spinlock_check(spinlock_t *lock) { return &lock->rlock; } @@ -315,17 +305,17 @@ do { \ raw_spin_lock_init(&(_lock)->rlock); \ } while (0) -static inline void spin_lock(spinlock_t *lock) +static __always_inline void spin_lock(spinlock_t *lock) { raw_spin_lock(&lock->rlock); } -static inline void spin_lock_bh(spinlock_t *lock) +static __always_inline void spin_lock_bh(spinlock_t *lock) { raw_spin_lock_bh(&lock->rlock); } -static inline int spin_trylock(spinlock_t *lock) +static __always_inline int spin_trylock(spinlock_t *lock) { return raw_spin_trylock(&lock->rlock); } @@ -345,7 +335,7 @@ do { \ raw_spin_lock_nest_lock(spinlock_check(lock), nest_lock); \ } while (0) -static inline void spin_lock_irq(spinlock_t *lock) +static __always_inline void spin_lock_irq(spinlock_t *lock) { raw_spin_lock_irq(&lock->rlock); } @@ -360,32 +350,32 @@ do { \ raw_spin_lock_irqsave_nested(spinlock_check(lock), flags, subclass); \ } while (0) -static inline void spin_unlock(spinlock_t *lock) +static __always_inline void spin_unlock(spinlock_t *lock) { raw_spin_unlock(&lock->rlock); } -static inline void spin_unlock_bh(spinlock_t *lock) +static __always_inline void spin_unlock_bh(spinlock_t *lock) { raw_spin_unlock_bh(&lock->rlock); } -static inline void spin_unlock_irq(spinlock_t *lock) +static __always_inline void spin_unlock_irq(spinlock_t *lock) { raw_spin_unlock_irq(&lock->rlock); } -static inline void spin_unlock_irqrestore(spinlock_t *lock, unsigned long flags) +static __always_inline void spin_unlock_irqrestore(spinlock_t *lock, unsigned long flags) { raw_spin_unlock_irqrestore(&lock->rlock, flags); } -static inline int spin_trylock_bh(spinlock_t *lock) +static __always_inline int spin_trylock_bh(spinlock_t *lock) { return raw_spin_trylock_bh(&lock->rlock); } -static inline int spin_trylock_irq(spinlock_t *lock) +static __always_inline int spin_trylock_irq(spinlock_t *lock) { return raw_spin_trylock_irq(&lock->rlock); } @@ -395,22 +385,22 @@ static inline int spin_trylock_irq(spinlock_t *lock) raw_spin_trylock_irqsave(spinlock_check(lock), flags); \ }) -static inline void spin_unlock_wait(spinlock_t *lock) +static __always_inline void spin_unlock_wait(spinlock_t *lock) { raw_spin_unlock_wait(&lock->rlock); } -static inline int spin_is_locked(spinlock_t *lock) +static __always_inline int spin_is_locked(spinlock_t *lock) { return raw_spin_is_locked(&lock->rlock); } -static inline int spin_is_contended(spinlock_t *lock) +static __always_inline int spin_is_contended(spinlock_t *lock) { return raw_spin_is_contended(&lock->rlock); } -static inline int spin_can_lock(spinlock_t *lock) +static __always_inline int spin_can_lock(spinlock_t *lock) { return raw_spin_can_lock(&lock->rlock); } diff --git a/kernel/include/linux/spinlock_rt.h b/kernel/include/linux/spinlock_rt.h index f757096b2..3b2825537 100644 --- a/kernel/include/linux/spinlock_rt.h +++ b/kernel/include/linux/spinlock_rt.h @@ -18,6 +18,10 @@ do { \ __rt_spin_lock_init(slock, #slock, &__key); \ } while (0) +void __lockfunc rt_spin_lock__no_mg(spinlock_t *lock); +void __lockfunc rt_spin_unlock__no_mg(spinlock_t *lock); +int __lockfunc rt_spin_trylock__no_mg(spinlock_t *lock); + extern void __lockfunc rt_spin_lock(spinlock_t *lock); extern unsigned long __lockfunc rt_spin_lock_trace_flags(spinlock_t *lock); extern void __lockfunc rt_spin_lock_nested(spinlock_t *lock, int subclass); @@ -32,20 +36,16 @@ extern int atomic_dec_and_spin_lock(atomic_t *atomic, spinlock_t *lock); * lockdep-less calls, for derived types like rwlock: * (for trylock they can use rt_mutex_trylock() directly. */ +extern void __lockfunc __rt_spin_lock__no_mg(struct rt_mutex *lock); extern void __lockfunc __rt_spin_lock(struct rt_mutex *lock); extern void __lockfunc __rt_spin_unlock(struct rt_mutex *lock); extern int __lockfunc __rt_spin_trylock(struct rt_mutex *lock); -#define spin_lock(lock) \ - do { \ - migrate_disable(); \ - rt_spin_lock(lock); \ - } while (0) +#define spin_lock(lock) rt_spin_lock(lock) #define spin_lock_bh(lock) \ do { \ local_bh_disable(); \ - migrate_disable(); \ rt_spin_lock(lock); \ } while (0) @@ -56,24 +56,19 @@ extern int __lockfunc __rt_spin_trylock(struct rt_mutex *lock); #define spin_trylock(lock) \ ({ \ int __locked; \ - migrate_disable(); \ __locked = spin_do_trylock(lock); \ - if (!__locked) \ - migrate_enable(); \ __locked; \ }) #ifdef CONFIG_LOCKDEP # define spin_lock_nested(lock, subclass) \ do { \ - migrate_disable(); \ rt_spin_lock_nested(lock, subclass); \ } while (0) #define spin_lock_bh_nested(lock, subclass) \ do { \ local_bh_disable(); \ - migrate_disable(); \ rt_spin_lock_nested(lock, subclass); \ } while (0) @@ -81,7 +76,6 @@ extern int __lockfunc __rt_spin_trylock(struct rt_mutex *lock); do { \ typecheck(unsigned long, flags); \ flags = 0; \ - migrate_disable(); \ rt_spin_lock_nested(lock, subclass); \ } while (0) #else @@ -117,16 +111,11 @@ static inline unsigned long spin_lock_trace_flags(spinlock_t *lock) /* FIXME: we need rt_spin_lock_nest_lock */ #define spin_lock_nest_lock(lock, nest_lock) spin_lock_nested(lock, 0) -#define spin_unlock(lock) \ - do { \ - rt_spin_unlock(lock); \ - migrate_enable(); \ - } while (0) +#define spin_unlock(lock) rt_spin_unlock(lock) #define spin_unlock_bh(lock) \ do { \ rt_spin_unlock(lock); \ - migrate_enable(); \ local_bh_enable(); \ } while (0) diff --git a/kernel/include/linux/spmi.h b/kernel/include/linux/spmi.h index f84212cd3..1396a255d 100644 --- a/kernel/include/linux/spmi.h +++ b/kernel/include/linux/spmi.h @@ -153,7 +153,9 @@ static inline struct spmi_driver *to_spmi_driver(struct device_driver *d) return container_of(d, struct spmi_driver, driver); } -int spmi_driver_register(struct spmi_driver *sdrv); +#define spmi_driver_register(sdrv) \ + __spmi_driver_register(sdrv, THIS_MODULE) +int __spmi_driver_register(struct spmi_driver *sdrv, struct module *owner); /** * spmi_driver_unregister() - unregister an SPMI client driver diff --git a/kernel/include/linux/srcu.h b/kernel/include/linux/srcu.h index a9c3c49cd..ec1a8f015 100644 --- a/kernel/include/linux/srcu.h +++ b/kernel/include/linux/srcu.h @@ -215,8 +215,11 @@ static inline int srcu_read_lock_held(struct srcu_struct *sp) */ static inline int srcu_read_lock(struct srcu_struct *sp) __acquires(sp) { - int retval = __srcu_read_lock(sp); + int retval; + preempt_disable(); + retval = __srcu_read_lock(sp); + preempt_enable(); rcu_lock_acquire(&(sp)->dep_map); return retval; } diff --git a/kernel/include/linux/ssb/ssb.h b/kernel/include/linux/ssb/ssb.h index 4568a5cc9..c3d1a525b 100644 --- a/kernel/include/linux/ssb/ssb.h +++ b/kernel/include/linux/ssb/ssb.h @@ -29,10 +29,13 @@ struct ssb_sprom { u8 il0mac[6] __aligned(sizeof(u16)); /* MAC address for 802.11b/g */ u8 et0mac[6] __aligned(sizeof(u16)); /* MAC address for Ethernet */ u8 et1mac[6] __aligned(sizeof(u16)); /* MAC address for 802.11a */ + u8 et2mac[6] __aligned(sizeof(u16)); /* MAC address for extra Ethernet */ u8 et0phyaddr; /* MII address for enet0 */ u8 et1phyaddr; /* MII address for enet1 */ + u8 et2phyaddr; /* MII address for enet2 */ u8 et0mdcport; /* MDIO for enet0 */ u8 et1mdcport; /* MDIO for enet1 */ + u8 et2mdcport; /* MDIO for enet2 */ u16 dev_id; /* Device ID overriding e.g. PCI ID */ u16 board_rev; /* Board revision number from SPROM. */ u16 board_num; /* Board number from SPROM. */ @@ -88,11 +91,14 @@ struct ssb_sprom { u32 ofdm5glpo; /* 5.2GHz OFDM power offset */ u32 ofdm5gpo; /* 5.3GHz OFDM power offset */ u32 ofdm5ghpo; /* 5.8GHz OFDM power offset */ + u32 boardflags; + u32 boardflags2; + u32 boardflags3; + /* TODO: Switch all drivers to new u32 fields and drop below ones */ u16 boardflags_lo; /* Board flags (bits 0-15) */ u16 boardflags_hi; /* Board flags (bits 16-31) */ u16 boardflags2_lo; /* Board flags (bits 32-47) */ u16 boardflags2_hi; /* Board flags (bits 48-63) */ - /* TODO store board flags in a single u64 */ struct ssb_sprom_core_pwr_info core_pwr_info[4]; diff --git a/kernel/include/linux/stddef.h b/kernel/include/linux/stddef.h index 076af4372..9c61c7cda 100644 --- a/kernel/include/linux/stddef.h +++ b/kernel/include/linux/stddef.h @@ -3,7 +3,6 @@ #include <uapi/linux/stddef.h> - #undef NULL #define NULL ((void *)0) @@ -14,10 +13,9 @@ enum { #undef offsetof #ifdef __compiler_offsetof -#define offsetof(TYPE,MEMBER) __compiler_offsetof(TYPE,MEMBER) +#define offsetof(TYPE, MEMBER) __compiler_offsetof(TYPE, MEMBER) #else -#define offsetof(TYPE, MEMBER) ((size_t) &((TYPE *)0)->MEMBER) -#endif +#define offsetof(TYPE, MEMBER) ((size_t)&((TYPE *)0)->MEMBER) #endif /** @@ -28,3 +26,5 @@ enum { */ #define offsetofend(TYPE, MEMBER) \ (offsetof(TYPE, MEMBER) + sizeof(((TYPE *)0)->MEMBER)) + +#endif diff --git a/kernel/include/linux/stm.h b/kernel/include/linux/stm.h new file mode 100644 index 000000000..9d0083d36 --- /dev/null +++ b/kernel/include/linux/stm.h @@ -0,0 +1,126 @@ +/* + * System Trace Module (STM) infrastructure apis + * Copyright (C) 2014 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ + +#ifndef _STM_H_ +#define _STM_H_ + +#include <linux/device.h> + +/** + * enum stp_packet_type - STP packets that an STM driver sends + */ +enum stp_packet_type { + STP_PACKET_DATA = 0, + STP_PACKET_FLAG, + STP_PACKET_USER, + STP_PACKET_MERR, + STP_PACKET_GERR, + STP_PACKET_TRIG, + STP_PACKET_XSYNC, +}; + +/** + * enum stp_packet_flags - STP packet modifiers + */ +enum stp_packet_flags { + STP_PACKET_MARKED = 0x1, + STP_PACKET_TIMESTAMPED = 0x2, +}; + +struct stp_policy; + +struct stm_device; + +/** + * struct stm_data - STM device description and callbacks + * @name: device name + * @stm: internal structure, only used by stm class code + * @sw_start: first STP master available to software + * @sw_end: last STP master available to software + * @sw_nchannels: number of STP channels per master + * @sw_mmiosz: size of one channel's IO space, for mmap, optional + * @packet: callback that sends an STP packet + * @mmio_addr: mmap callback, optional + * @link: called when a new stm_source gets linked to us, optional + * @unlink: likewise for unlinking, again optional + * @set_options: set device-specific options on a channel + * + * Fill out this structure before calling stm_register_device() to create + * an STM device and stm_unregister_device() to destroy it. It will also be + * passed back to @packet(), @mmio_addr(), @link(), @unlink() and @set_options() + * callbacks. + * + * Normally, an STM device will have a range of masters available to software + * and the rest being statically assigned to various hardware trace sources. + * The former is defined by the the range [@sw_start..@sw_end] of the device + * description. That is, the lowest master that can be allocated to software + * writers is @sw_start and data from this writer will appear is @sw_start + * master in the STP stream. + */ +struct stm_data { + const char *name; + struct stm_device *stm; + unsigned int sw_start; + unsigned int sw_end; + unsigned int sw_nchannels; + unsigned int sw_mmiosz; + ssize_t (*packet)(struct stm_data *, unsigned int, + unsigned int, unsigned int, + unsigned int, unsigned int, + const unsigned char *); + phys_addr_t (*mmio_addr)(struct stm_data *, unsigned int, + unsigned int, unsigned int); + int (*link)(struct stm_data *, unsigned int, + unsigned int); + void (*unlink)(struct stm_data *, unsigned int, + unsigned int); + long (*set_options)(struct stm_data *, unsigned int, + unsigned int, unsigned int, + unsigned long); +}; + +int stm_register_device(struct device *parent, struct stm_data *stm_data, + struct module *owner); +void stm_unregister_device(struct stm_data *stm_data); + +struct stm_source_device; + +/** + * struct stm_source_data - STM source device description and callbacks + * @name: device name, will be used for policy lookup + * @src: internal structure, only used by stm class code + * @nr_chans: number of channels to allocate + * @link: called when this source gets linked to an STM device + * @unlink: called when this source is about to get unlinked from its STM + * + * Fill in this structure before calling stm_source_register_device() to + * register a source device. Also pass it to unregister and write calls. + */ +struct stm_source_data { + const char *name; + struct stm_source_device *src; + unsigned int percpu; + unsigned int nr_chans; + int (*link)(struct stm_source_data *data); + void (*unlink)(struct stm_source_data *data); +}; + +int stm_source_register_device(struct device *parent, + struct stm_source_data *data); +void stm_source_unregister_device(struct stm_source_data *data); + +int stm_source_write(struct stm_source_data *data, unsigned int chan, + const char *buf, size_t count); + +#endif /* _STM_H_ */ diff --git a/kernel/include/linux/stmmac.h b/kernel/include/linux/stmmac.h index 7f484a239..eead8ab93 100644 --- a/kernel/include/linux/stmmac.h +++ b/kernel/include/linux/stmmac.h @@ -99,6 +99,7 @@ struct plat_stmmacenet_data { int phy_addr; int interface; struct stmmac_mdio_bus_data *mdio_bus_data; + struct device_node *phy_node; struct stmmac_dma_cfg *dma_cfg; int clk_csr; int has_gmac; @@ -118,30 +119,8 @@ struct plat_stmmacenet_data { int rx_fifo_size; void (*fix_mac_speed)(void *priv, unsigned int speed); void (*bus_setup)(void __iomem *ioaddr); - void *(*setup)(struct platform_device *pdev); - void (*free)(struct platform_device *pdev, void *priv); int (*init)(struct platform_device *pdev, void *priv); void (*exit)(struct platform_device *pdev, void *priv); - void *custom_cfg; - void *custom_data; void *bsp_priv; }; - -/* of_data for SoC glue layer device tree bindings */ - -struct stmmac_of_data { - int has_gmac; - int enh_desc; - int tx_coe; - int rx_coe; - int bugged_jumbo; - int pmt; - int riwt_off; - void (*fix_mac_speed)(void *priv, unsigned int speed); - void (*bus_setup)(void __iomem *ioaddr); - void *(*setup)(struct platform_device *pdev); - void (*free)(struct platform_device *pdev, void *priv); - int (*init)(struct platform_device *pdev, void *priv); - void (*exit)(struct platform_device *pdev, void *priv); -}; #endif diff --git a/kernel/include/linux/stop_machine.h b/kernel/include/linux/stop_machine.h index d2abbdb8c..0e1b15405 100644 --- a/kernel/include/linux/stop_machine.h +++ b/kernel/include/linux/stop_machine.h @@ -33,6 +33,8 @@ void stop_one_cpu_nowait(unsigned int cpu, cpu_stop_fn_t fn, void *arg, struct cpu_stop_work *work_buf); int stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg); int try_stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg); +void stop_machine_park(int cpu); +void stop_machine_unpark(int cpu); #else /* CONFIG_SMP */ @@ -97,7 +99,7 @@ static inline int try_stop_cpus(const struct cpumask *cpumask, * grabbing every spinlock (and more). So the "read" side to such a * lock is anything which disables preemption. */ -#if defined(CONFIG_STOP_MACHINE) && defined(CONFIG_SMP) +#if defined(CONFIG_SMP) || defined(CONFIG_HOTPLUG_CPU) /** * stop_machine: freeze the machine on all CPUs and run this function @@ -112,25 +114,13 @@ static inline int try_stop_cpus(const struct cpumask *cpumask, * * This can be thought of as a very heavy write lock, equivalent to * grabbing every spinlock in the kernel. */ -int stop_machine(int (*fn)(void *), void *data, const struct cpumask *cpus); +int stop_machine(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus); -/** - * __stop_machine: freeze the machine on all CPUs and run this function - * @fn: the function to run - * @data: the data ptr for the @fn - * @cpus: the cpus to run the @fn() on (NULL = any online cpu) - * - * Description: This is a special version of the above, which assumes cpus - * won't come or go while it's being called. Used by hotplug cpu. - */ -int __stop_machine(int (*fn)(void *), void *data, const struct cpumask *cpus); - -int stop_machine_from_inactive_cpu(int (*fn)(void *), void *data, +int stop_machine_from_inactive_cpu(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus); +#else /* CONFIG_SMP || CONFIG_HOTPLUG_CPU */ -#else /* CONFIG_STOP_MACHINE && CONFIG_SMP */ - -static inline int __stop_machine(int (*fn)(void *), void *data, +static inline int stop_machine(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus) { unsigned long flags; @@ -141,17 +131,11 @@ static inline int __stop_machine(int (*fn)(void *), void *data, return ret; } -static inline int stop_machine(int (*fn)(void *), void *data, - const struct cpumask *cpus) -{ - return __stop_machine(fn, data, cpus); -} - -static inline int stop_machine_from_inactive_cpu(int (*fn)(void *), void *data, +static inline int stop_machine_from_inactive_cpu(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus) { - return __stop_machine(fn, data, cpus); + return stop_machine(fn, data, cpus); } -#endif /* CONFIG_STOP_MACHINE && CONFIG_SMP */ +#endif /* CONFIG_SMP || CONFIG_HOTPLUG_CPU */ #endif /* _LINUX_STOP_MACHINE */ diff --git a/kernel/include/linux/string.h b/kernel/include/linux/string.h index e40099e58..9ef7795e6 100644 --- a/kernel/include/linux/string.h +++ b/kernel/include/linux/string.h @@ -25,6 +25,9 @@ extern char * strncpy(char *,const char *, __kernel_size_t); #ifndef __HAVE_ARCH_STRLCPY size_t strlcpy(char *, const char *, size_t); #endif +#ifndef __HAVE_ARCH_STRSCPY +ssize_t __must_check strscpy(char *, const char *, size_t); +#endif #ifndef __HAVE_ARCH_STRCAT extern char * strcat(char *, const char *); #endif @@ -111,6 +114,7 @@ extern int memcmp(const void *,const void *,__kernel_size_t); extern void * memchr(const void *,int,__kernel_size_t); #endif void *memchr_inv(const void *s, int c, size_t n); +char *strreplace(char *s, char old, char new); extern void kfree_const(const void *x); diff --git a/kernel/include/linux/string_helpers.h b/kernel/include/linux/string_helpers.h index 71f711db4..dabe643eb 100644 --- a/kernel/include/linux/string_helpers.h +++ b/kernel/include/linux/string_helpers.h @@ -48,24 +48,24 @@ static inline int string_unescape_any_inplace(char *buf) #define ESCAPE_HEX 0x20 int string_escape_mem(const char *src, size_t isz, char *dst, size_t osz, - unsigned int flags, const char *esc); + unsigned int flags, const char *only); static inline int string_escape_mem_any_np(const char *src, size_t isz, - char *dst, size_t osz, const char *esc) + char *dst, size_t osz, const char *only) { - return string_escape_mem(src, isz, dst, osz, ESCAPE_ANY_NP, esc); + return string_escape_mem(src, isz, dst, osz, ESCAPE_ANY_NP, only); } static inline int string_escape_str(const char *src, char *dst, size_t sz, - unsigned int flags, const char *esc) + unsigned int flags, const char *only) { - return string_escape_mem(src, strlen(src), dst, sz, flags, esc); + return string_escape_mem(src, strlen(src), dst, sz, flags, only); } static inline int string_escape_str_any_np(const char *src, char *dst, - size_t sz, const char *esc) + size_t sz, const char *only) { - return string_escape_str(src, dst, sz, ESCAPE_ANY_NP, esc); + return string_escape_str(src, dst, sz, ESCAPE_ANY_NP, only); } #endif diff --git a/kernel/include/linux/sunrpc/addr.h b/kernel/include/linux/sunrpc/addr.h index 07d8e53be..5c9c6cd08 100644 --- a/kernel/include/linux/sunrpc/addr.h +++ b/kernel/include/linux/sunrpc/addr.h @@ -46,8 +46,8 @@ static inline void rpc_set_port(struct sockaddr *sap, #define IPV6_SCOPE_DELIMITER '%' #define IPV6_SCOPE_ID_LEN sizeof("%nnnnnnnnnn") -static inline bool __rpc_cmp_addr4(const struct sockaddr *sap1, - const struct sockaddr *sap2) +static inline bool rpc_cmp_addr4(const struct sockaddr *sap1, + const struct sockaddr *sap2) { const struct sockaddr_in *sin1 = (const struct sockaddr_in *)sap1; const struct sockaddr_in *sin2 = (const struct sockaddr_in *)sap2; @@ -67,8 +67,8 @@ static inline bool __rpc_copy_addr4(struct sockaddr *dst, } #if IS_ENABLED(CONFIG_IPV6) -static inline bool __rpc_cmp_addr6(const struct sockaddr *sap1, - const struct sockaddr *sap2) +static inline bool rpc_cmp_addr6(const struct sockaddr *sap1, + const struct sockaddr *sap2) { const struct sockaddr_in6 *sin1 = (const struct sockaddr_in6 *)sap1; const struct sockaddr_in6 *sin2 = (const struct sockaddr_in6 *)sap2; @@ -93,7 +93,7 @@ static inline bool __rpc_copy_addr6(struct sockaddr *dst, return true; } #else /* !(IS_ENABLED(CONFIG_IPV6) */ -static inline bool __rpc_cmp_addr6(const struct sockaddr *sap1, +static inline bool rpc_cmp_addr6(const struct sockaddr *sap1, const struct sockaddr *sap2) { return false; @@ -122,15 +122,28 @@ static inline bool rpc_cmp_addr(const struct sockaddr *sap1, if (sap1->sa_family == sap2->sa_family) { switch (sap1->sa_family) { case AF_INET: - return __rpc_cmp_addr4(sap1, sap2); + return rpc_cmp_addr4(sap1, sap2); case AF_INET6: - return __rpc_cmp_addr6(sap1, sap2); + return rpc_cmp_addr6(sap1, sap2); } } return false; } /** + * rpc_cmp_addr_port - compare the address and port number of two sockaddrs. + * @sap1: first sockaddr + * @sap2: second sockaddr + */ +static inline bool rpc_cmp_addr_port(const struct sockaddr *sap1, + const struct sockaddr *sap2) +{ + if (!rpc_cmp_addr(sap1, sap2)) + return false; + return rpc_get_port(sap1) == rpc_get_port(sap2); +} + +/** * rpc_copy_addr - copy the address portion of one sockaddr to another * @dst: destination sockaddr * @src: source sockaddr diff --git a/kernel/include/linux/sunrpc/auth.h b/kernel/include/linux/sunrpc/auth.h index a7cbb570c..1ecf13e14 100644 --- a/kernel/include/linux/sunrpc/auth.h +++ b/kernel/include/linux/sunrpc/auth.h @@ -18,9 +18,13 @@ #include <linux/atomic.h> #include <linux/rcupdate.h> #include <linux/uidgid.h> +#include <linux/utsname.h> -/* size of the nodename buffer */ -#define UNX_MAXNODENAME 32 +/* + * Size of the nodename buffer. RFC1831 specifies a hard limit of 255 bytes, + * but Linux hostnames are actually limited to __NEW_UTS_LEN bytes. + */ +#define UNX_MAXNODENAME __NEW_UTS_LEN struct rpcsec_gss_info; diff --git a/kernel/include/linux/sunrpc/bc_xprt.h b/kernel/include/linux/sunrpc/bc_xprt.h index 2ca67b55e..4397a4824 100644 --- a/kernel/include/linux/sunrpc/bc_xprt.h +++ b/kernel/include/linux/sunrpc/bc_xprt.h @@ -37,7 +37,11 @@ void xprt_complete_bc_request(struct rpc_rqst *req, uint32_t copied); void xprt_free_bc_request(struct rpc_rqst *req); int xprt_setup_backchannel(struct rpc_xprt *, unsigned int min_reqs); void xprt_destroy_backchannel(struct rpc_xprt *, unsigned int max_reqs); -int bc_send(struct rpc_rqst *req); + +/* Socket backchannel transport methods */ +int xprt_setup_bc(struct rpc_xprt *xprt, unsigned int min_reqs); +void xprt_destroy_bc(struct rpc_xprt *xprt, unsigned int max_reqs); +void xprt_free_bc_rqst(struct rpc_rqst *req); /* * Determine if a shared backchannel is in use diff --git a/kernel/include/linux/sunrpc/cache.h b/kernel/include/linux/sunrpc/cache.h index 437ddb6c4..ed03c9f7f 100644 --- a/kernel/include/linux/sunrpc/cache.h +++ b/kernel/include/linux/sunrpc/cache.h @@ -46,10 +46,12 @@ * */ struct cache_head { - struct cache_head * next; + struct hlist_node cache_list; time_t expiry_time; /* After time time, don't use the data */ - time_t last_refresh; /* If CACHE_PENDING, this is when upcall - * was sent, else this is when update was received + time_t last_refresh; /* If CACHE_PENDING, this is when upcall was + * sent, else this is when update was + * received, though it is alway set to + * be *after* ->flush_time. */ struct kref ref; unsigned long flags; @@ -73,7 +75,7 @@ struct cache_detail_pipefs { struct cache_detail { struct module * owner; int hash_size; - struct cache_head ** hash_table; + struct hlist_head * hash_table; rwlock_t hash_lock; atomic_t inuse; /* active user-space update or lookup */ @@ -105,8 +107,12 @@ struct cache_detail { /* fields below this comment are for internal use * and should not be touched by cache owners */ - time_t flush_time; /* flush all cache items with last_refresh - * earlier than this */ + time_t flush_time; /* flush all cache items with + * last_refresh at or earlier + * than this. last_refresh + * is never set at or earlier + * than this. + */ struct list_head others; time_t nextcheck; int entries; @@ -203,7 +209,7 @@ static inline void cache_put(struct cache_head *h, struct cache_detail *cd) static inline int cache_is_expired(struct cache_detail *detail, struct cache_head *h) { return (h->expiry_time < seconds_since_boot()) || - (detail->flush_time > h->last_refresh); + (detail->flush_time >= h->last_refresh); } extern int cache_check(struct cache_detail *detail, @@ -224,6 +230,11 @@ extern int sunrpc_cache_register_pipefs(struct dentry *parent, const char *, umode_t, struct cache_detail *); extern void sunrpc_cache_unregister_pipefs(struct cache_detail *); +/* Must store cache_detail in seq_file->private if using next three functions */ +extern void *cache_seq_start(struct seq_file *file, loff_t *pos); +extern void *cache_seq_next(struct seq_file *file, void *p, loff_t *pos); +extern void cache_seq_stop(struct seq_file *file, void *p); + extern void qword_add(char **bpp, int *lp, char *str); extern void qword_addhex(char **bpp, int *lp, char *buf, int blen); extern int qword_get(char **bpp, char *dest, int bufsize); diff --git a/kernel/include/linux/sunrpc/clnt.h b/kernel/include/linux/sunrpc/clnt.h index 598ba80ec..131032f15 100644 --- a/kernel/include/linux/sunrpc/clnt.h +++ b/kernel/include/linux/sunrpc/clnt.h @@ -56,6 +56,7 @@ struct rpc_clnt { struct rpc_rtt * cl_rtt; /* RTO estimator data */ const struct rpc_timeout *cl_timeout; /* Timeout strategy */ + atomic_t cl_swapper; /* swapfile count */ int cl_nodelen; /* nodename length */ char cl_nodename[UNX_MAXNODENAME+1]; struct rpc_pipe_dir_head cl_pipedir_objects; diff --git a/kernel/include/linux/sunrpc/sched.h b/kernel/include/linux/sunrpc/sched.h index 5f1e6bd4c..d703f0ef3 100644 --- a/kernel/include/linux/sunrpc/sched.h +++ b/kernel/include/linux/sunrpc/sched.h @@ -205,8 +205,7 @@ struct rpc_wait_queue { */ struct rpc_task *rpc_new_task(const struct rpc_task_setup *); struct rpc_task *rpc_run_task(const struct rpc_task_setup *); -struct rpc_task *rpc_run_bc_task(struct rpc_rqst *req, - const struct rpc_call_ops *ops); +struct rpc_task *rpc_run_bc_task(struct rpc_rqst *req); void rpc_put_task(struct rpc_task *); void rpc_put_task_async(struct rpc_task *); void rpc_exit_task(struct rpc_task *); @@ -269,4 +268,20 @@ static inline void rpc_assign_waitqueue_name(struct rpc_wait_queue *q, } #endif +#if IS_ENABLED(CONFIG_SUNRPC_SWAP) +int rpc_clnt_swap_activate(struct rpc_clnt *clnt); +void rpc_clnt_swap_deactivate(struct rpc_clnt *clnt); +#else +static inline int +rpc_clnt_swap_activate(struct rpc_clnt *clnt) +{ + return -EINVAL; +} + +static inline void +rpc_clnt_swap_deactivate(struct rpc_clnt *clnt) +{ +} +#endif /* CONFIG_SUNRPC_SWAP */ + #endif /* _LINUX_SUNRPC_SCHED_H_ */ diff --git a/kernel/include/linux/sunrpc/svc.h b/kernel/include/linux/sunrpc/svc.h index fae6fb947..cc0fc712b 100644 --- a/kernel/include/linux/sunrpc/svc.h +++ b/kernel/include/linux/sunrpc/svc.h @@ -19,11 +19,6 @@ #include <linux/wait.h> #include <linux/mm.h> -/* - * This is the RPC server thread function prototype - */ -typedef int (*svc_thread_fn)(void *); - /* statistics for svc_pool structures */ struct svc_pool_stats { atomic_long_t packets; @@ -54,6 +49,25 @@ struct svc_pool { unsigned long sp_flags; } ____cacheline_aligned_in_smp; +struct svc_serv; + +struct svc_serv_ops { + /* Callback to use when last thread exits. */ + void (*svo_shutdown)(struct svc_serv *, struct net *); + + /* function for service threads to run */ + int (*svo_function)(void *); + + /* queue up a transport for servicing */ + void (*svo_enqueue_xprt)(struct svc_xprt *); + + /* set up thread (or whatever) execution context */ + int (*svo_setup)(struct svc_serv *, struct svc_pool *, int); + + /* optional module to count when adding threads (pooled svcs only) */ + struct module *svo_module; +}; + /* * RPC service. * @@ -85,16 +99,7 @@ struct svc_serv { unsigned int sv_nrpools; /* number of thread pools */ struct svc_pool * sv_pools; /* array of thread pools */ - - void (*sv_shutdown)(struct svc_serv *serv, - struct net *net); - /* Callback to use when last thread - * exits. - */ - - struct module * sv_module; /* optional module to count when - * adding threads */ - svc_thread_fn sv_function; /* main function for threads */ + struct svc_serv_ops *sv_ops; /* server operations */ #if defined(CONFIG_SUNRPC_BACKCHANNEL) struct list_head sv_cb_list; /* queue for callback requests * that arrive over the same @@ -423,19 +428,46 @@ struct svc_procedure { }; /* + * Mode for mapping cpus to pools. + */ +enum { + SVC_POOL_AUTO = -1, /* choose one of the others */ + SVC_POOL_GLOBAL, /* no mapping, just a single global pool + * (legacy & UP mode) */ + SVC_POOL_PERCPU, /* one pool per cpu */ + SVC_POOL_PERNODE /* one pool per numa node */ +}; + +struct svc_pool_map { + int count; /* How many svc_servs use us */ + int mode; /* Note: int not enum to avoid + * warnings about "enumeration value + * not handled in switch" */ + unsigned int npools; + unsigned int *pool_to; /* maps pool id to cpu or node */ + unsigned int *to_pool; /* maps cpu or node to pool id */ +}; + +extern struct svc_pool_map svc_pool_map; + +/* * Function prototypes. */ int svc_rpcb_setup(struct svc_serv *serv, struct net *net); void svc_rpcb_cleanup(struct svc_serv *serv, struct net *net); int svc_bind(struct svc_serv *serv, struct net *net); struct svc_serv *svc_create(struct svc_program *, unsigned int, - void (*shutdown)(struct svc_serv *, struct net *net)); + struct svc_serv_ops *); +struct svc_rqst *svc_rqst_alloc(struct svc_serv *serv, + struct svc_pool *pool, int node); struct svc_rqst *svc_prepare_thread(struct svc_serv *serv, struct svc_pool *pool, int node); +void svc_rqst_free(struct svc_rqst *); void svc_exit_thread(struct svc_rqst *); +unsigned int svc_pool_map_get(void); +void svc_pool_map_put(void); struct svc_serv * svc_create_pooled(struct svc_program *, unsigned int, - void (*shutdown)(struct svc_serv *, struct net *net), - svc_thread_fn, struct module *); + struct svc_serv_ops *); int svc_set_num_threads(struct svc_serv *, struct svc_pool *, int); int svc_pool_stats_open(struct svc_serv *serv, struct file *file); void svc_destroy(struct svc_serv *); diff --git a/kernel/include/linux/sunrpc/svc_rdma.h b/kernel/include/linux/sunrpc/svc_rdma.h index df8edf8ec..f869807a0 100644 --- a/kernel/include/linux/sunrpc/svc_rdma.h +++ b/kernel/include/linux/sunrpc/svc_rdma.h @@ -105,11 +105,9 @@ struct svc_rdma_chunk_sge { }; struct svc_rdma_fastreg_mr { struct ib_mr *mr; - void *kva; - struct ib_fast_reg_page_list *page_list; - int page_list_len; + struct scatterlist *sg; + int sg_nents; unsigned long access_flags; - unsigned long map_len; enum dma_data_direction direction; struct list_head frmr_list; }; @@ -132,6 +130,7 @@ struct svcxprt_rdma { struct list_head sc_accept_q; /* Conn. waiting accept */ int sc_ord; /* RDMA read limit */ int sc_max_sge; + int sc_max_sge_rd; /* max sge for read target */ int sc_sq_depth; /* Depth of SQ */ atomic_t sc_sq_count; /* Number of SQ WR on queue */ @@ -180,12 +179,13 @@ struct svcxprt_rdma { #define RPCRDMA_MAX_REQUESTS 32 #define RPCRDMA_MAX_REQ_SIZE 4096 +#define RPCSVC_MAXPAYLOAD_RDMA RPCSVC_MAXPAYLOAD + /* svc_rdma_marshal.c */ extern int svc_rdma_xdr_decode_req(struct rpcrdma_msg **, struct svc_rqst *); -extern int svc_rdma_xdr_decode_deferred_req(struct svc_rqst *); extern int svc_rdma_xdr_encode_error(struct svcxprt_rdma *, struct rpcrdma_msg *, - enum rpcrdma_errcode, u32 *); + enum rpcrdma_errcode, __be32 *); extern void svc_rdma_xdr_encode_write_list(struct rpcrdma_msg *, int); extern void svc_rdma_xdr_encode_reply_array(struct rpcrdma_write_array *, int); extern void svc_rdma_xdr_encode_array_chunk(struct rpcrdma_write_array *, int, @@ -207,12 +207,13 @@ extern int rdma_read_chunk_frmr(struct svcxprt_rdma *, struct svc_rqst *, /* svc_rdma_sendto.c */ extern int svc_rdma_sendto(struct svc_rqst *); +extern struct rpcrdma_read_chunk * + svc_rdma_get_read_chunk(struct rpcrdma_msg *); /* svc_rdma_transport.c */ extern int svc_rdma_send(struct svcxprt_rdma *, struct ib_send_wr *); extern void svc_rdma_send_error(struct svcxprt_rdma *, struct rpcrdma_msg *, enum rpcrdma_errcode); -struct page *svc_rdma_get_page(void); extern int svc_rdma_post_recv(struct svcxprt_rdma *); extern int svc_rdma_create_listen(struct svc_serv *, int, struct sockaddr *); extern struct svc_rdma_op_ctxt *svc_rdma_get_context(struct svcxprt_rdma *); @@ -220,96 +221,20 @@ extern void svc_rdma_put_context(struct svc_rdma_op_ctxt *, int); extern void svc_rdma_unmap_dma(struct svc_rdma_op_ctxt *ctxt); extern struct svc_rdma_req_map *svc_rdma_get_req_map(void); extern void svc_rdma_put_req_map(struct svc_rdma_req_map *); -extern int svc_rdma_fastreg(struct svcxprt_rdma *, struct svc_rdma_fastreg_mr *); extern struct svc_rdma_fastreg_mr *svc_rdma_get_frmr(struct svcxprt_rdma *); extern void svc_rdma_put_frmr(struct svcxprt_rdma *, struct svc_rdma_fastreg_mr *); extern void svc_sq_reap(struct svcxprt_rdma *); extern void svc_rq_reap(struct svcxprt_rdma *); -extern struct svc_xprt_class svc_rdma_class; extern void svc_rdma_prep_reply_hdr(struct svc_rqst *); +extern struct svc_xprt_class svc_rdma_class; +#ifdef CONFIG_SUNRPC_BACKCHANNEL +extern struct svc_xprt_class svc_rdma_bc_class; +#endif + /* svc_rdma.c */ extern int svc_rdma_init(void); extern void svc_rdma_cleanup(void); -/* - * Returns the address of the first read chunk or <nul> if no read chunk is - * present - */ -static inline struct rpcrdma_read_chunk * -svc_rdma_get_read_chunk(struct rpcrdma_msg *rmsgp) -{ - struct rpcrdma_read_chunk *ch = - (struct rpcrdma_read_chunk *)&rmsgp->rm_body.rm_chunks[0]; - - if (ch->rc_discrim == 0) - return NULL; - - return ch; -} - -/* - * Returns the address of the first read write array element or <nul> if no - * write array list is present - */ -static inline struct rpcrdma_write_array * -svc_rdma_get_write_array(struct rpcrdma_msg *rmsgp) -{ - if (rmsgp->rm_body.rm_chunks[0] != 0 - || rmsgp->rm_body.rm_chunks[1] == 0) - return NULL; - - return (struct rpcrdma_write_array *)&rmsgp->rm_body.rm_chunks[1]; -} - -/* - * Returns the address of the first reply array element or <nul> if no - * reply array is present - */ -static inline struct rpcrdma_write_array * -svc_rdma_get_reply_array(struct rpcrdma_msg *rmsgp) -{ - struct rpcrdma_read_chunk *rch; - struct rpcrdma_write_array *wr_ary; - struct rpcrdma_write_array *rp_ary; - - /* XXX: Need to fix when reply list may occur with read-list and/or - * write list */ - if (rmsgp->rm_body.rm_chunks[0] != 0 || - rmsgp->rm_body.rm_chunks[1] != 0) - return NULL; - - rch = svc_rdma_get_read_chunk(rmsgp); - if (rch) { - while (rch->rc_discrim) - rch++; - - /* The reply list follows an empty write array located - * at 'rc_position' here. The reply array is at rc_target. - */ - rp_ary = (struct rpcrdma_write_array *)&rch->rc_target; - - goto found_it; - } - - wr_ary = svc_rdma_get_write_array(rmsgp); - if (wr_ary) { - rp_ary = (struct rpcrdma_write_array *) - &wr_ary-> - wc_array[ntohl(wr_ary->wc_nchunks)].wc_target.rs_length; - - goto found_it; - } - - /* No read list, no write list */ - rp_ary = (struct rpcrdma_write_array *) - &rmsgp->rm_body.rm_chunks[2]; - - found_it: - if (rp_ary->wc_discrim == 0) - return NULL; - - return rp_ary; -} #endif diff --git a/kernel/include/linux/sunrpc/svc_xprt.h b/kernel/include/linux/sunrpc/svc_xprt.h index 79f6f8f3d..78512cfe1 100644 --- a/kernel/include/linux/sunrpc/svc_xprt.h +++ b/kernel/include/linux/sunrpc/svc_xprt.h @@ -116,6 +116,7 @@ void svc_xprt_init(struct net *, struct svc_xprt_class *, struct svc_xprt *, struct svc_serv *); int svc_create_xprt(struct svc_serv *, const char *, struct net *, const int, const unsigned short, int); +void svc_xprt_do_enqueue(struct svc_xprt *xprt); void svc_xprt_enqueue(struct svc_xprt *xprt); void svc_xprt_put(struct svc_xprt *xprt); void svc_xprt_copy_addrs(struct svc_rqst *rqstp, struct svc_xprt *xprt); diff --git a/kernel/include/linux/sunrpc/xprt.h b/kernel/include/linux/sunrpc/xprt.h index 8b93ef53d..69ef5b3ab 100644 --- a/kernel/include/linux/sunrpc/xprt.h +++ b/kernel/include/linux/sunrpc/xprt.h @@ -54,6 +54,8 @@ enum rpc_display_format_t { struct rpc_task; struct rpc_xprt; struct seq_file; +struct svc_serv; +struct net; /* * This describes a complete RPC request @@ -133,6 +135,15 @@ struct rpc_xprt_ops { void (*close)(struct rpc_xprt *xprt); void (*destroy)(struct rpc_xprt *xprt); void (*print_stats)(struct rpc_xprt *xprt, struct seq_file *seq); + int (*enable_swap)(struct rpc_xprt *xprt); + void (*disable_swap)(struct rpc_xprt *xprt); + void (*inject_disconnect)(struct rpc_xprt *xprt); + int (*bc_setup)(struct rpc_xprt *xprt, + unsigned int min_reqs); + int (*bc_up)(struct svc_serv *serv, struct net *net); + void (*bc_free_rqst)(struct rpc_rqst *rqst); + void (*bc_destroy)(struct rpc_xprt *xprt, + unsigned int max_reqs); }; /* @@ -150,6 +161,7 @@ enum xprt_transports { XPRT_TRANSPORT_TCP = IPPROTO_TCP, XPRT_TRANSPORT_BC_TCP = IPPROTO_TCP | XPRT_TRANSPORT_BC, XPRT_TRANSPORT_RDMA = 256, + XPRT_TRANSPORT_BC_RDMA = XPRT_TRANSPORT_RDMA | XPRT_TRANSPORT_BC, XPRT_TRANSPORT_LOCAL = 257, }; @@ -180,7 +192,7 @@ struct rpc_xprt { atomic_t num_reqs; /* total slots */ unsigned long state; /* transport state */ unsigned char resvport : 1; /* use a reserved port */ - unsigned int swapper; /* we're swapping over this + atomic_t swapper; /* we're swapping over this transport */ unsigned int bind_index; /* bind function index */ @@ -212,7 +224,8 @@ struct rpc_xprt { #if defined(CONFIG_SUNRPC_BACKCHANNEL) struct svc_serv *bc_serv; /* The RPC service which will */ /* process the callback */ - unsigned int bc_alloc_count; /* Total number of preallocs */ + int bc_alloc_count; /* Total number of preallocs */ + atomic_t bc_free_slots; spinlock_t bc_pa_lock; /* Protects the preallocated * items */ struct list_head bc_pa_list; /* List of preallocated @@ -241,6 +254,7 @@ struct rpc_xprt { const char *address_strings[RPC_DISPLAY_MAX]; #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) struct dentry *debugfs; /* debugfs directory */ + atomic_t inject_disconnect; #endif }; @@ -327,6 +341,18 @@ static inline __be32 *xprt_skip_transport_header(struct rpc_xprt *xprt, __be32 * return p + xprt->tsh_size; } +static inline int +xprt_enable_swap(struct rpc_xprt *xprt) +{ + return xprt->ops->enable_swap(xprt); +} + +static inline void +xprt_disable_swap(struct rpc_xprt *xprt) +{ + xprt->ops->disable_swap(xprt); +} + /* * Transport switch helper functions */ @@ -345,7 +371,6 @@ void xprt_release_rqst_cong(struct rpc_task *task); void xprt_disconnect_done(struct rpc_xprt *xprt); void xprt_force_disconnect(struct rpc_xprt *xprt); void xprt_conditional_disconnect(struct rpc_xprt *xprt, unsigned int cookie); -int xs_swapper(struct rpc_xprt *xprt, int enable); bool xprt_lock_connect(struct rpc_xprt *, struct rpc_task *, void *); void xprt_unlock_connect(struct rpc_xprt *, void *); @@ -431,6 +456,23 @@ static inline int xprt_test_and_set_binding(struct rpc_xprt *xprt) return test_and_set_bit(XPRT_BINDING, &xprt->state); } +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) +extern unsigned int rpc_inject_disconnect; +static inline void xprt_inject_disconnect(struct rpc_xprt *xprt) +{ + if (!rpc_inject_disconnect) + return; + if (atomic_dec_return(&xprt->inject_disconnect)) + return; + atomic_set(&xprt->inject_disconnect, rpc_inject_disconnect); + xprt->ops->inject_disconnect(xprt); +} +#else +static inline void xprt_inject_disconnect(struct rpc_xprt *xprt) +{ +} +#endif + #endif /* __KERNEL__*/ #endif /* _LINUX_SUNRPC_XPRT_H */ diff --git a/kernel/include/linux/sunrpc/xprtrdma.h b/kernel/include/linux/sunrpc/xprtrdma.h index c984c8598..b7b279b54 100644 --- a/kernel/include/linux/sunrpc/xprtrdma.h +++ b/kernel/include/linux/sunrpc/xprtrdma.h @@ -49,14 +49,15 @@ * a single chunk type per message is supported currently. */ #define RPCRDMA_MIN_SLOT_TABLE (2U) -#define RPCRDMA_DEF_SLOT_TABLE (32U) +#define RPCRDMA_DEF_SLOT_TABLE (128U) #define RPCRDMA_MAX_SLOT_TABLE (256U) #define RPCRDMA_DEF_INLINE (1024) /* default inline max */ #define RPCRDMA_INLINE_PAD_THRESH (512)/* payload threshold to pad (bytes) */ -/* memory registration strategies */ +/* Memory registration strategies, by number. + * This is part of a kernel / user space API. Do not remove. */ enum rpcrdma_memreg { RPCRDMA_BOUNCEBUFFERS = 0, RPCRDMA_REGISTER, diff --git a/kernel/include/linux/sunrpc/xprtsock.h b/kernel/include/linux/sunrpc/xprtsock.h index 357e44c1a..0ece4ba06 100644 --- a/kernel/include/linux/sunrpc/xprtsock.h +++ b/kernel/include/linux/sunrpc/xprtsock.h @@ -44,6 +44,8 @@ struct sock_xprt { */ unsigned long sock_state; struct delayed_work connect_worker; + struct work_struct recv_worker; + struct mutex recv_mutex; struct sockaddr_storage srcaddr; unsigned short srcport; diff --git a/kernel/include/linux/sunxi-rsb.h b/kernel/include/linux/sunxi-rsb.h new file mode 100644 index 000000000..7e75bb034 --- /dev/null +++ b/kernel/include/linux/sunxi-rsb.h @@ -0,0 +1,105 @@ +/* + * Allwinner Reduced Serial Bus Driver + * + * Copyright (c) 2015 Chen-Yu Tsai + * + * Author: Chen-Yu Tsai <wens@csie.org> + * + * This file is licensed under the terms of the GNU General Public + * License version 2. This program is licensed "as is" without any + * warranty of any kind, whether express or implied. + */ +#ifndef _SUNXI_RSB_H +#define _SUNXI_RSB_H + +#include <linux/device.h> +#include <linux/regmap.h> +#include <linux/types.h> + +struct sunxi_rsb; + +/** + * struct sunxi_rsb_device - Basic representation of an RSB device + * @dev: Driver model representation of the device. + * @ctrl: RSB controller managing the bus hosting this device. + * @rtaddr: This device's runtime address + * @hwaddr: This device's hardware address + */ +struct sunxi_rsb_device { + struct device dev; + struct sunxi_rsb *rsb; + int irq; + u8 rtaddr; + u16 hwaddr; +}; + +static inline struct sunxi_rsb_device *to_sunxi_rsb_device(struct device *d) +{ + return container_of(d, struct sunxi_rsb_device, dev); +} + +static inline void *sunxi_rsb_device_get_drvdata(const struct sunxi_rsb_device *rdev) +{ + return dev_get_drvdata(&rdev->dev); +} + +static inline void sunxi_rsb_device_set_drvdata(struct sunxi_rsb_device *rdev, + void *data) +{ + dev_set_drvdata(&rdev->dev, data); +} + +/** + * struct sunxi_rsb_driver - RSB slave device driver + * @driver: RSB device drivers should initialize name and owner field of + * this structure. + * @probe: binds this driver to a RSB device. + * @remove: unbinds this driver from the RSB device. + */ +struct sunxi_rsb_driver { + struct device_driver driver; + int (*probe)(struct sunxi_rsb_device *rdev); + int (*remove)(struct sunxi_rsb_device *rdev); +}; + +static inline struct sunxi_rsb_driver *to_sunxi_rsb_driver(struct device_driver *d) +{ + return container_of(d, struct sunxi_rsb_driver, driver); +} + +int sunxi_rsb_driver_register(struct sunxi_rsb_driver *rdrv); + +/** + * sunxi_rsb_driver_unregister() - unregister an RSB client driver + * @rdrv: the driver to unregister + */ +static inline void sunxi_rsb_driver_unregister(struct sunxi_rsb_driver *rdrv) +{ + if (rdrv) + driver_unregister(&rdrv->driver); +} + +#define module_sunxi_rsb_driver(__sunxi_rsb_driver) \ + module_driver(__sunxi_rsb_driver, sunxi_rsb_driver_register, \ + sunxi_rsb_driver_unregister) + +struct regmap *__devm_regmap_init_sunxi_rsb(struct sunxi_rsb_device *rdev, + const struct regmap_config *config, + struct lock_class_key *lock_key, + const char *lock_name); + +/** + * devm_regmap_init_sunxi_rsb(): Initialise managed register map + * + * @rdev: Device that will be interacted with + * @config: Configuration for register map + * + * The return value will be an ERR_PTR() on error or a valid pointer + * to a struct regmap. The regmap will be automatically freed by the + * device management code. + */ +#define devm_regmap_init_sunxi_rsb(rdev, config) \ + __regmap_lockdep_wrapper(__devm_regmap_init_sunxi_rsb, #config, \ + rdev, config) + +#endif /* _SUNXI_RSB_H */ diff --git a/kernel/include/linux/suspend.h b/kernel/include/linux/suspend.h index 5efe743ce..9b77d4cc9 100644 --- a/kernel/include/linux/suspend.h +++ b/kernel/include/linux/suspend.h @@ -194,6 +194,12 @@ struct platform_freeze_ops { void (*end)(void); }; +#if defined(CONFIG_SUSPEND) || defined(CONFIG_HIBERNATION) +extern bool pm_in_action; +#else +# define pm_in_action false +#endif + #ifdef CONFIG_SUSPEND /** * suspend_set_ops - set platform dependent suspend operations @@ -202,6 +208,36 @@ struct platform_freeze_ops { extern void suspend_set_ops(const struct platform_suspend_ops *ops); extern int suspend_valid_only_mem(suspend_state_t state); +extern unsigned int pm_suspend_global_flags; + +#define PM_SUSPEND_FLAG_FW_SUSPEND (1 << 0) +#define PM_SUSPEND_FLAG_FW_RESUME (1 << 1) + +static inline void pm_suspend_clear_flags(void) +{ + pm_suspend_global_flags = 0; +} + +static inline void pm_set_suspend_via_firmware(void) +{ + pm_suspend_global_flags |= PM_SUSPEND_FLAG_FW_SUSPEND; +} + +static inline void pm_set_resume_via_firmware(void) +{ + pm_suspend_global_flags |= PM_SUSPEND_FLAG_FW_RESUME; +} + +static inline bool pm_suspend_via_firmware(void) +{ + return !!(pm_suspend_global_flags & PM_SUSPEND_FLAG_FW_SUSPEND); +} + +static inline bool pm_resume_via_firmware(void) +{ + return !!(pm_suspend_global_flags & PM_SUSPEND_FLAG_FW_RESUME); +} + /* Suspend-to-idle state machnine. */ enum freeze_state { FREEZE_STATE_NONE, /* Not suspended/suspending. */ @@ -241,6 +277,12 @@ extern int pm_suspend(suspend_state_t state); #else /* !CONFIG_SUSPEND */ #define suspend_valid_only_mem NULL +static inline void pm_suspend_clear_flags(void) {} +static inline void pm_set_suspend_via_firmware(void) {} +static inline void pm_set_resume_via_firmware(void) {} +static inline bool pm_suspend_via_firmware(void) { return false; } +static inline bool pm_resume_via_firmware(void) { return false; } + static inline void suspend_set_ops(const struct platform_suspend_ops *ops) {} static inline int pm_suspend(suspend_state_t state) { return -ENOSYS; } static inline bool idle_should_freeze(void) { return false; } @@ -387,10 +429,12 @@ extern int unregister_pm_notifier(struct notifier_block *nb); /* drivers/base/power/wakeup.c */ extern bool events_check_enabled; +extern unsigned int pm_wakeup_irq; extern bool pm_wakeup_pending(void); extern void pm_system_wakeup(void); extern void pm_wakeup_clear(void); +extern void pm_system_irq_wakeup(unsigned int irq_number); extern bool pm_get_wakeup_count(unsigned int *count, bool block); extern bool pm_save_wakeup_count(unsigned int count); extern void pm_wakep_autosleep_enabled(bool set); @@ -440,6 +484,7 @@ static inline int unregister_pm_notifier(struct notifier_block *nb) static inline bool pm_wakeup_pending(void) { return false; } static inline void pm_system_wakeup(void) {} static inline void pm_wakeup_clear(void) {} +static inline void pm_system_irq_wakeup(unsigned int irq_number) {} static inline void lock_system_sleep(void) {} static inline void unlock_system_sleep(void) {} diff --git a/kernel/include/linux/sw842.h b/kernel/include/linux/sw842.h new file mode 100644 index 000000000..109ba041c --- /dev/null +++ b/kernel/include/linux/sw842.h @@ -0,0 +1,12 @@ +#ifndef __SW842_H__ +#define __SW842_H__ + +#define SW842_MEM_COMPRESS (0xf000) + +int sw842_compress(const u8 *src, unsigned int srclen, + u8 *dst, unsigned int *destlen, void *wmem); + +int sw842_decompress(const u8 *src, unsigned int srclen, + u8 *dst, unsigned int *destlen); + +#endif diff --git a/kernel/include/linux/swait.h b/kernel/include/linux/swait.h new file mode 100644 index 000000000..83f004a72 --- /dev/null +++ b/kernel/include/linux/swait.h @@ -0,0 +1,173 @@ +#ifndef _LINUX_SWAIT_H +#define _LINUX_SWAIT_H + +#include <linux/list.h> +#include <linux/stddef.h> +#include <linux/spinlock.h> +#include <asm/current.h> + +/* + * Simple wait queues + * + * While these are very similar to the other/complex wait queues (wait.h) the + * most important difference is that the simple waitqueue allows for + * deterministic behaviour -- IOW it has strictly bounded IRQ and lock hold + * times. + * + * In order to make this so, we had to drop a fair number of features of the + * other waitqueue code; notably: + * + * - mixing INTERRUPTIBLE and UNINTERRUPTIBLE sleeps on the same waitqueue; + * all wakeups are TASK_NORMAL in order to avoid O(n) lookups for the right + * sleeper state. + * + * - the exclusive mode; because this requires preserving the list order + * and this is hard. + * + * - custom wake functions; because you cannot give any guarantees about + * random code. + * + * As a side effect of this; the data structures are slimmer. + * + * One would recommend using this wait queue where possible. + */ + +struct task_struct; + +struct swait_queue_head { + raw_spinlock_t lock; + struct list_head task_list; +}; + +struct swait_queue { + struct task_struct *task; + struct list_head task_list; +}; + +#define __SWAITQUEUE_INITIALIZER(name) { \ + .task = current, \ + .task_list = LIST_HEAD_INIT((name).task_list), \ +} + +#define DECLARE_SWAITQUEUE(name) \ + struct swait_queue name = __SWAITQUEUE_INITIALIZER(name) + +#define __SWAIT_QUEUE_HEAD_INITIALIZER(name) { \ + .lock = __RAW_SPIN_LOCK_UNLOCKED(name.lock), \ + .task_list = LIST_HEAD_INIT((name).task_list), \ +} + +#define DECLARE_SWAIT_QUEUE_HEAD(name) \ + struct swait_queue_head name = __SWAIT_QUEUE_HEAD_INITIALIZER(name) + +extern void __init_swait_queue_head(struct swait_queue_head *q, const char *name, + struct lock_class_key *key); + +#define init_swait_queue_head(q) \ + do { \ + static struct lock_class_key __key; \ + __init_swait_queue_head((q), #q, &__key); \ + } while (0) + +#ifdef CONFIG_LOCKDEP +# define __SWAIT_QUEUE_HEAD_INIT_ONSTACK(name) \ + ({ init_swait_queue_head(&name); name; }) +# define DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(name) \ + struct swait_queue_head name = __SWAIT_QUEUE_HEAD_INIT_ONSTACK(name) +#else +# define DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(name) \ + DECLARE_SWAIT_QUEUE_HEAD(name) +#endif + +static inline int swait_active(struct swait_queue_head *q) +{ + return !list_empty(&q->task_list); +} + +extern void swake_up(struct swait_queue_head *q); +extern void swake_up_all(struct swait_queue_head *q); +extern void swake_up_locked(struct swait_queue_head *q); +extern void swake_up_all_locked(struct swait_queue_head *q); + +extern void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait); +extern void prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait, int state); +extern long prepare_to_swait_event(struct swait_queue_head *q, struct swait_queue *wait, int state); + +extern void __finish_swait(struct swait_queue_head *q, struct swait_queue *wait); +extern void finish_swait(struct swait_queue_head *q, struct swait_queue *wait); + +/* as per ___wait_event() but for swait, therefore "exclusive == 0" */ +#define ___swait_event(wq, condition, state, ret, cmd) \ +({ \ + struct swait_queue __wait; \ + long __ret = ret; \ + \ + INIT_LIST_HEAD(&__wait.task_list); \ + for (;;) { \ + long __int = prepare_to_swait_event(&wq, &__wait, state);\ + \ + if (condition) \ + break; \ + \ + if (___wait_is_interruptible(state) && __int) { \ + __ret = __int; \ + break; \ + } \ + \ + cmd; \ + } \ + finish_swait(&wq, &__wait); \ + __ret; \ +}) + +#define __swait_event(wq, condition) \ + (void)___swait_event(wq, condition, TASK_UNINTERRUPTIBLE, 0, \ + schedule()) + +#define swait_event(wq, condition) \ +do { \ + if (condition) \ + break; \ + __swait_event(wq, condition); \ +} while (0) + +#define __swait_event_timeout(wq, condition, timeout) \ + ___swait_event(wq, ___wait_cond_timeout(condition), \ + TASK_UNINTERRUPTIBLE, timeout, \ + __ret = schedule_timeout(__ret)) + +#define swait_event_timeout(wq, condition, timeout) \ +({ \ + long __ret = timeout; \ + if (!___wait_cond_timeout(condition)) \ + __ret = __swait_event_timeout(wq, condition, timeout); \ + __ret; \ +}) + +#define __swait_event_interruptible(wq, condition) \ + ___swait_event(wq, condition, TASK_INTERRUPTIBLE, 0, \ + schedule()) + +#define swait_event_interruptible(wq, condition) \ +({ \ + int __ret = 0; \ + if (!(condition)) \ + __ret = __swait_event_interruptible(wq, condition); \ + __ret; \ +}) + +#define __swait_event_interruptible_timeout(wq, condition, timeout) \ + ___swait_event(wq, ___wait_cond_timeout(condition), \ + TASK_INTERRUPTIBLE, timeout, \ + __ret = schedule_timeout(__ret)) + +#define swait_event_interruptible_timeout(wq, condition, timeout) \ +({ \ + long __ret = timeout; \ + if (!___wait_cond_timeout(condition)) \ + __ret = __swait_event_interruptible_timeout(wq, \ + condition, timeout); \ + __ret; \ +}) + +#endif /* _LINUX_SWAIT_H */ diff --git a/kernel/include/linux/swap.h b/kernel/include/linux/swap.h index 4c07c12d2..da646f2eb 100644 --- a/kernel/include/linux/swap.h +++ b/kernel/include/linux/swap.h @@ -354,7 +354,15 @@ extern void check_move_unevictable_pages(struct page **, int nr_pages); extern int kswapd_run(int nid); extern void kswapd_stop(int nid); #ifdef CONFIG_MEMCG -extern int mem_cgroup_swappiness(struct mem_cgroup *mem); +static inline int mem_cgroup_swappiness(struct mem_cgroup *memcg) +{ + /* root ? */ + if (mem_cgroup_disabled() || !memcg->css.parent) + return vm_swappiness; + + return memcg->swappiness; +} + #else static inline int mem_cgroup_swappiness(struct mem_cgroup *mem) { @@ -376,11 +384,10 @@ static inline void mem_cgroup_uncharge_swap(swp_entry_t entry) /* linux/mm/page_io.c */ extern int swap_readpage(struct page *); extern int swap_writepage(struct page *page, struct writeback_control *wbc); -extern void end_swap_bio_write(struct bio *bio, int err); +extern void end_swap_bio_write(struct bio *bio); extern int __swap_writepage(struct page *page, struct writeback_control *wbc, - void (*end_write_func)(struct bio *, int)); + bio_end_io_t end_write_func); extern int swap_set_page_dirty(struct page *page); -extern void end_swap_bio_read(struct bio *bio, int err); int add_swap_extent(struct swap_info_struct *sis, unsigned long start_page, unsigned long nr_pages, sector_t start_block); @@ -402,6 +409,9 @@ extern void free_pages_and_swap_cache(struct page **, int); extern struct page *lookup_swap_cache(swp_entry_t); extern struct page *read_swap_cache_async(swp_entry_t, gfp_t, struct vm_area_struct *vma, unsigned long addr); +extern struct page *__read_swap_cache_async(swp_entry_t, gfp_t, + struct vm_area_struct *vma, unsigned long addr, + bool *new_page_allocated); extern struct page *swapin_readahead(swp_entry_t, gfp_t, struct vm_area_struct *vma, unsigned long addr); @@ -435,6 +445,7 @@ extern unsigned int count_swap_pages(int, int); extern sector_t map_swap_page(struct page *, struct block_device **); extern sector_t swapdev_block(int, pgoff_t); extern int page_swapcount(struct page *); +extern int swp_swapcount(swp_entry_t entry); extern struct swap_info_struct *page_swap_info(struct page *); extern int reuse_swap_page(struct page *); extern int try_to_free_swap(struct page *); @@ -526,6 +537,11 @@ static inline int page_swapcount(struct page *page) return 0; } +static inline int swp_swapcount(swp_entry_t entry) +{ + return 0; +} + #define reuse_swap_page(page) (page_mapcount(page) == 1) static inline int try_to_free_swap(struct page *page) diff --git a/kernel/include/linux/swapops.h b/kernel/include/linux/swapops.h index cedf3d3c3..5c3a5f3e7 100644 --- a/kernel/include/linux/swapops.h +++ b/kernel/include/linux/swapops.h @@ -164,6 +164,9 @@ static inline int is_write_migration_entry(swp_entry_t entry) #endif #ifdef CONFIG_MEMORY_FAILURE + +extern atomic_long_t num_poisoned_pages __read_mostly; + /* * Support for hardware poisoned pages */ @@ -177,6 +180,31 @@ static inline int is_hwpoison_entry(swp_entry_t entry) { return swp_type(entry) == SWP_HWPOISON; } + +static inline bool test_set_page_hwpoison(struct page *page) +{ + return TestSetPageHWPoison(page); +} + +static inline void num_poisoned_pages_inc(void) +{ + atomic_long_inc(&num_poisoned_pages); +} + +static inline void num_poisoned_pages_dec(void) +{ + atomic_long_dec(&num_poisoned_pages); +} + +static inline void num_poisoned_pages_add(long num) +{ + atomic_long_add(num, &num_poisoned_pages); +} + +static inline void num_poisoned_pages_sub(long num) +{ + atomic_long_sub(num, &num_poisoned_pages); +} #else static inline swp_entry_t make_hwpoison_entry(struct page *page) @@ -188,6 +216,15 @@ static inline int is_hwpoison_entry(swp_entry_t swp) { return 0; } + +static inline bool test_set_page_hwpoison(struct page *page) +{ + return false; +} + +static inline void num_poisoned_pages_inc(void) +{ +} #endif #if defined(CONFIG_MEMORY_FAILURE) || defined(CONFIG_MIGRATION) diff --git a/kernel/include/linux/syscalls.h b/kernel/include/linux/syscalls.h index 76d1e38aa..c2b66a277 100644 --- a/kernel/include/linux/syscalls.h +++ b/kernel/include/linux/syscalls.h @@ -111,14 +111,14 @@ union bpf_attr; #define __SC_STR_ADECL(t, a) #a #define __SC_STR_TDECL(t, a) #t -extern struct ftrace_event_class event_class_syscall_enter; -extern struct ftrace_event_class event_class_syscall_exit; +extern struct trace_event_class event_class_syscall_enter; +extern struct trace_event_class event_class_syscall_exit; extern struct trace_event_functions enter_syscall_print_funcs; extern struct trace_event_functions exit_syscall_print_funcs; #define SYSCALL_TRACE_ENTER_EVENT(sname) \ static struct syscall_metadata __syscall_meta_##sname; \ - static struct ftrace_event_call __used \ + static struct trace_event_call __used \ event_enter_##sname = { \ .class = &event_class_syscall_enter, \ { \ @@ -128,13 +128,13 @@ extern struct trace_event_functions exit_syscall_print_funcs; .data = (void *)&__syscall_meta_##sname,\ .flags = TRACE_EVENT_FL_CAP_ANY, \ }; \ - static struct ftrace_event_call __used \ + static struct trace_event_call __used \ __attribute__((section("_ftrace_events"))) \ *__event_enter_##sname = &event_enter_##sname; #define SYSCALL_TRACE_EXIT_EVENT(sname) \ static struct syscall_metadata __syscall_meta_##sname; \ - static struct ftrace_event_call __used \ + static struct trace_event_call __used \ event_exit_##sname = { \ .class = &event_class_syscall_exit, \ { \ @@ -144,7 +144,7 @@ extern struct trace_event_functions exit_syscall_print_funcs; .data = (void *)&__syscall_meta_##sname,\ .flags = TRACE_EVENT_FL_CAP_ANY, \ }; \ - static struct ftrace_event_call __used \ + static struct trace_event_call __used \ __attribute__((section("_ftrace_events"))) \ *__event_exit_##sname = &event_exit_##sname; @@ -524,7 +524,7 @@ asmlinkage long sys_chown(const char __user *filename, asmlinkage long sys_lchown(const char __user *filename, uid_t user, gid_t group); asmlinkage long sys_fchown(unsigned int fd, uid_t user, gid_t group); -#ifdef CONFIG_UID16 +#ifdef CONFIG_HAVE_UID16 asmlinkage long sys_chown16(const char __user *filename, old_uid_t user, old_gid_t group); asmlinkage long sys_lchown16(const char __user *filename, @@ -810,6 +810,7 @@ asmlinkage long sys_timerfd_gettime(int ufd, struct itimerspec __user *otmr); asmlinkage long sys_eventfd(unsigned int count); asmlinkage long sys_eventfd2(unsigned int count, int flags); asmlinkage long sys_memfd_create(const char __user *uname_ptr, unsigned int flags); +asmlinkage long sys_userfaultfd(int flags); asmlinkage long sys_fallocate(int fd, int mode, loff_t offset, loff_t len); asmlinkage long sys_old_readdir(unsigned int, struct old_linux_dirent __user *, unsigned int); asmlinkage long sys_pselect6(int, fd_set __user *, fd_set __user *, @@ -827,15 +828,15 @@ asmlinkage long sys_syncfs(int fd); asmlinkage long sys_fork(void); asmlinkage long sys_vfork(void); #ifdef CONFIG_CLONE_BACKWARDS -asmlinkage long sys_clone(unsigned long, unsigned long, int __user *, int, +asmlinkage long sys_clone(unsigned long, unsigned long, int __user *, unsigned long, int __user *); #else #ifdef CONFIG_CLONE_BACKWARDS3 asmlinkage long sys_clone(unsigned long, unsigned long, int, int __user *, - int __user *, int); + int __user *, unsigned long); #else asmlinkage long sys_clone(unsigned long, unsigned long, int __user *, - int __user *, int); + int __user *, unsigned long); #endif #endif @@ -884,4 +885,8 @@ asmlinkage long sys_execveat(int dfd, const char __user *filename, const char __user *const __user *argv, const char __user *const __user *envp, int flags); +asmlinkage long sys_membarrier(int cmd, int flags); + +asmlinkage long sys_mlock2(unsigned long start, size_t len, int flags); + #endif diff --git a/kernel/include/linux/sysfs.h b/kernel/include/linux/sysfs.h index 9f6575831..c6f0f0d0e 100644 --- a/kernel/include/linux/sysfs.h +++ b/kernel/include/linux/sysfs.h @@ -64,10 +64,18 @@ do { \ * a new subdirectory with this name. * @is_visible: Optional: Function to return permissions associated with an * attribute of the group. Will be called repeatedly for each - * attribute in the group. Only read/write permissions as well as - * SYSFS_PREALLOC are accepted. Must return 0 if an attribute is - * not visible. The returned value will replace static permissions - * defined in struct attribute or struct bin_attribute. + * non-binary attribute in the group. Only read/write + * permissions as well as SYSFS_PREALLOC are accepted. Must + * return 0 if an attribute is not visible. The returned value + * will replace static permissions defined in struct attribute. + * @is_bin_visible: + * Optional: Function to return permissions associated with a + * binary attribute of the group. Will be called repeatedly + * for each binary attribute in the group. Only read/write + * permissions as well as SYSFS_PREALLOC are accepted. Must + * return 0 if a binary attribute is not visible. The returned + * value will replace static permissions defined in + * struct bin_attribute. * @attrs: Pointer to NULL terminated list of attributes. * @bin_attrs: Pointer to NULL terminated list of binary attributes. * Either attrs or bin_attrs or both must be provided. @@ -76,6 +84,8 @@ struct attribute_group { const char *name; umode_t (*is_visible)(struct kobject *, struct attribute *, int); + umode_t (*is_bin_visible)(struct kobject *, + struct bin_attribute *, int); struct attribute **attrs; struct bin_attribute **bin_attrs; }; @@ -268,6 +278,9 @@ int sysfs_add_link_to_group(struct kobject *kobj, const char *group_name, struct kobject *target, const char *link_name); void sysfs_remove_link_from_group(struct kobject *kobj, const char *group_name, const char *link_name); +int __compat_only_sysfs_link_entry_to_kobj(struct kobject *kobj, + struct kobject *target_kobj, + const char *target_name); void sysfs_notify(struct kobject *kobj, const char *dir, const char *attr); @@ -451,6 +464,14 @@ static inline void sysfs_remove_link_from_group(struct kobject *kobj, { } +static inline int __compat_only_sysfs_link_entry_to_kobj( + struct kobject *kobj, + struct kobject *target_kobj, + const char *target_name) +{ + return 0; +} + static inline void sysfs_notify(struct kobject *kobj, const char *dir, const char *attr) { diff --git a/kernel/include/linux/syslog.h b/kernel/include/linux/syslog.h index 4b7b875a7..c3a7f0cc3 100644 --- a/kernel/include/linux/syslog.h +++ b/kernel/include/linux/syslog.h @@ -47,12 +47,12 @@ #define SYSLOG_FROM_READER 0 #define SYSLOG_FROM_PROC 1 -int do_syslog(int type, char __user *buf, int count, bool from_file); +int do_syslog(int type, char __user *buf, int count, int source); #ifdef CONFIG_PRINTK -int check_syslog_permissions(int type, bool from_file); +int check_syslog_permissions(int type, int source); #else -static inline int check_syslog_permissions(int type, bool from_file) +static inline int check_syslog_permissions(int type, int source) { return 0; } diff --git a/kernel/include/linux/t10-pi.h b/kernel/include/linux/t10-pi.h index 6a8b99426..dd8de82cf 100644 --- a/kernel/include/linux/t10-pi.h +++ b/kernel/include/linux/t10-pi.h @@ -14,9 +14,9 @@ struct t10_pi_tuple { }; -extern struct blk_integrity t10_pi_type1_crc; -extern struct blk_integrity t10_pi_type1_ip; -extern struct blk_integrity t10_pi_type3_crc; -extern struct blk_integrity t10_pi_type3_ip; +extern struct blk_integrity_profile t10_pi_type1_crc; +extern struct blk_integrity_profile t10_pi_type1_ip; +extern struct blk_integrity_profile t10_pi_type3_crc; +extern struct blk_integrity_profile t10_pi_type3_ip; #endif diff --git a/kernel/include/linux/tcp.h b/kernel/include/linux/tcp.h index e8bbf4036..b386361ba 100644 --- a/kernel/include/linux/tcp.h +++ b/kernel/include/linux/tcp.h @@ -112,10 +112,11 @@ struct tcp_request_sock_ops; struct tcp_request_sock { struct inet_request_sock req; const struct tcp_request_sock_ops *af_specific; + struct skb_mstamp snt_synack; /* first SYNACK sent time */ bool tfo_listener; + u32 txhash; u32 rcv_isn; u32 snt_isn; - u32 snt_synack; /* synack sent time */ u32 last_oow_ack_time; /* last SYNACK */ u32 rcv_nxt; /* the ack # by SYNACK. For * FastOpen it's the seq# @@ -149,11 +150,16 @@ struct tcp_sock { * sum(delta(rcv_nxt)), or how many bytes * were acked. */ + u32 segs_in; /* RFC4898 tcpEStatsPerfSegsIn + * total number of segments in. + */ u32 rcv_nxt; /* What we want to receive next */ u32 copied_seq; /* Head of yet unread data */ u32 rcv_wup; /* rcv_nxt on last window update sent */ u32 snd_nxt; /* Next sequence we send */ - + u32 segs_out; /* RFC4898 tcpEStatsPerfSegsOut + * The total number of segments sent. + */ u64 bytes_acked; /* RFC4898 tcpEStatsAppHCThruOctetsAcked * sum(delta(snd_una)), or how many bytes * were acked. @@ -188,6 +194,12 @@ struct tcp_sock { u32 window_clamp; /* Maximal window to advertise */ u32 rcv_ssthresh; /* Current window clamp */ + /* Information of the most recently (s)acked skb */ + struct tcp_rack { + struct skb_mstamp mstamp; /* (Re)sent time of the skb */ + u8 advanced; /* mstamp advanced since last lost marking */ + u8 reord; /* reordering detected */ + } rack; u16 advmss; /* Advertised MSS */ u8 unused; u8 nonagle : 4,/* Disable Nagle algorithm? */ @@ -201,6 +213,7 @@ struct tcp_sock { syn_fastopen:1, /* SYN includes Fast Open option */ syn_fastopen_exp:1,/* SYN includes Fast Open exp. option */ syn_data_acked:1,/* data in SYN is acked by SYN-ACK */ + save_syn:1, /* Save headers of SYN packet */ is_cwnd_limited:1;/* forward progress limited by snd_cwnd? */ u32 tlp_high_seq; /* snd_nxt at the time of TLP retransmit. */ @@ -210,6 +223,9 @@ struct tcp_sock { u32 mdev_max_us; /* maximal mdev for the last rtt period */ u32 rttvar_us; /* smoothed mdev_max */ u32 rtt_seq; /* sequence number to update rttvar */ + struct rtt_meas { + u32 rtt, ts; /* RTT in usec and sampling time in jiffies. */ + } rtt_min[3]; u32 packets_out; /* Packets which are "in flight" */ u32 retrans_out; /* Retransmitted packets out */ @@ -273,8 +289,6 @@ struct tcp_sock { int lost_cnt_hint; u32 retransmit_high; /* L-bits may be on up to this seqno */ - u32 lost_retrans_low; /* Sent seq after any rxmit (lowest) */ - u32 prior_ssthresh; /* ssthresh saved at recovery start */ u32 high_seq; /* snd_nxt at onset of congestion */ @@ -328,6 +342,7 @@ struct tcp_sock { * socket. Used to retransmit SYNACKs etc. */ struct request_sock *fastopen_rsk; + u32 *saved_syn; }; enum tsq_flags { @@ -348,8 +363,8 @@ static inline struct tcp_sock *tcp_sk(const struct sock *sk) struct tcp_timewait_sock { struct inet_timewait_sock tw_sk; - u32 tw_rcv_nxt; - u32 tw_snd_nxt; +#define tw_rcv_nxt tw_sk.__tw_common.skc_tw_rcv_nxt +#define tw_snd_nxt tw_sk.__tw_common.skc_tw_snd_nxt u32 tw_rcv_wnd; u32 tw_ts_offset; u32 tw_ts_recent; @@ -374,25 +389,25 @@ static inline bool tcp_passive_fastopen(const struct sock *sk) tcp_sk(sk)->fastopen_rsk != NULL); } -extern void tcp_sock_destruct(struct sock *sk); +static inline void fastopen_queue_tune(struct sock *sk, int backlog) +{ + struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue; + int somaxconn = READ_ONCE(sock_net(sk)->core.sysctl_somaxconn); + + queue->fastopenq.max_qlen = min_t(unsigned int, backlog, somaxconn); +} + +static inline void tcp_move_syn(struct tcp_sock *tp, + struct request_sock *req) +{ + tp->saved_syn = req->saved_syn; + req->saved_syn = NULL; +} -static inline int fastopen_init_queue(struct sock *sk, int backlog) +static inline void tcp_saved_syn_free(struct tcp_sock *tp) { - struct request_sock_queue *queue = - &inet_csk(sk)->icsk_accept_queue; - - if (queue->fastopenq == NULL) { - queue->fastopenq = kzalloc( - sizeof(struct fastopen_queue), - sk->sk_allocation); - if (queue->fastopenq == NULL) - return -ENOMEM; - - sk->sk_destruct = tcp_sock_destruct; - spin_lock_init(&queue->fastopenq->lock); - } - queue->fastopenq->max_qlen = backlog; - return 0; + kfree(tp->saved_syn); + tp->saved_syn = NULL; } #endif /* _LINUX_TCP_H */ diff --git a/kernel/include/linux/thermal.h b/kernel/include/linux/thermal.h index 5eac31649..e13a1ace5 100644 --- a/kernel/include/linux/thermal.h +++ b/kernel/include/linux/thermal.h @@ -40,10 +40,18 @@ /* No upper/lower limit requirement */ #define THERMAL_NO_LIMIT ((u32)~0) +/* Default weight of a bound cooling device */ +#define THERMAL_WEIGHT_DEFAULT 0 + +/* use value, which < 0K, to indicate an invalid/uninitialized temperature */ +#define THERMAL_TEMP_INVALID -274000 + /* Unit conversion macros */ -#define KELVIN_TO_CELSIUS(t) (long)(((long)t-2732 >= 0) ? \ - ((long)t-2732+5)/10 : ((long)t-2732-5)/10) -#define CELSIUS_TO_KELVIN(t) ((t)*10+2732) +#define DECI_KELVIN_TO_CELSIUS(t) ({ \ + long _t = (t); \ + ((_t-2732 >= 0) ? (_t-2732+5)/10 : (_t-2732-5)/10); \ +}) +#define CELSIUS_TO_DECI_KELVIN(t) ((t)*10+2732) #define DECI_KELVIN_TO_MILLICELSIUS_WITH_OFFSET(t, off) (((t) - (off)) * 100) #define DECI_KELVIN_TO_MILLICELSIUS(t) DECI_KELVIN_TO_MILLICELSIUS_WITH_OFFSET(t, 2732) #define MILLICELSIUS_TO_DECI_KELVIN_WITH_OFFSET(t, off) (((t) / 100) + (off)) @@ -56,10 +64,13 @@ #define DEFAULT_THERMAL_GOVERNOR "fair_share" #elif defined(CONFIG_THERMAL_DEFAULT_GOV_USER_SPACE) #define DEFAULT_THERMAL_GOVERNOR "user_space" +#elif defined(CONFIG_THERMAL_DEFAULT_GOV_POWER_ALLOCATOR) +#define DEFAULT_THERMAL_GOVERNOR "power_allocator" #endif struct thermal_zone_device; struct thermal_cooling_device; +struct thermal_instance; enum thermal_device_mode { THERMAL_DEVICE_DISABLED = 0, @@ -86,23 +97,19 @@ struct thermal_zone_device_ops { struct thermal_cooling_device *); int (*unbind) (struct thermal_zone_device *, struct thermal_cooling_device *); - int (*get_temp) (struct thermal_zone_device *, unsigned long *); + int (*get_temp) (struct thermal_zone_device *, int *); int (*get_mode) (struct thermal_zone_device *, enum thermal_device_mode *); int (*set_mode) (struct thermal_zone_device *, enum thermal_device_mode); int (*get_trip_type) (struct thermal_zone_device *, int, enum thermal_trip_type *); - int (*get_trip_temp) (struct thermal_zone_device *, int, - unsigned long *); - int (*set_trip_temp) (struct thermal_zone_device *, int, - unsigned long); - int (*get_trip_hyst) (struct thermal_zone_device *, int, - unsigned long *); - int (*set_trip_hyst) (struct thermal_zone_device *, int, - unsigned long); - int (*get_crit_temp) (struct thermal_zone_device *, unsigned long *); - int (*set_emul_temp) (struct thermal_zone_device *, unsigned long); + int (*get_trip_temp) (struct thermal_zone_device *, int, int *); + int (*set_trip_temp) (struct thermal_zone_device *, int, int); + int (*get_trip_hyst) (struct thermal_zone_device *, int, int *); + int (*set_trip_hyst) (struct thermal_zone_device *, int, int); + int (*get_crit_temp) (struct thermal_zone_device *, int *); + int (*set_emul_temp) (struct thermal_zone_device *, int); int (*get_trend) (struct thermal_zone_device *, int, enum thermal_trend *); int (*notify) (struct thermal_zone_device *, int, @@ -113,6 +120,12 @@ struct thermal_cooling_device_ops { int (*get_max_state) (struct thermal_cooling_device *, unsigned long *); int (*get_cur_state) (struct thermal_cooling_device *, unsigned long *); int (*set_cur_state) (struct thermal_cooling_device *, unsigned long); + int (*get_requested_power)(struct thermal_cooling_device *, + struct thermal_zone_device *, u32 *); + int (*state2power)(struct thermal_cooling_device *, + struct thermal_zone_device *, unsigned long, u32 *); + int (*power2state)(struct thermal_cooling_device *, + struct thermal_zone_device *, u32, unsigned long *); }; struct thermal_cooling_device { @@ -144,8 +157,7 @@ struct thermal_attr { * @devdata: private pointer for device private data * @trips: number of trip points the thermal zone supports * @passive_delay: number of milliseconds to wait between polls when - * performing passive cooling. Currenty only used by the - * step-wise governor + * performing passive cooling. * @polling_delay: number of milliseconds to wait between polls when * checking whether trip points have been crossed (0 for * interrupt driven systems) @@ -155,13 +167,14 @@ struct thermal_attr { * @last_temperature: previous temperature read * @emul_temperature: emulated temperature when using CONFIG_THERMAL_EMULATION * @passive: 1 if you've crossed a passive trip point, 0 otherwise. - * Currenty only used by the step-wise governor. * @forced_passive: If > 0, temperature at which to switch on all ACPI * processor cooling devices. Currently only used by the * step-wise governor. + * @need_update: if equals 1, thermal_zone_device_update needs to be invoked. * @ops: operations this &thermal_zone_device supports * @tzp: thermal zone parameters * @governor: pointer to the governor for this thermal zone + * @governor_data: private pointer for governor data * @thermal_instances: list of &struct thermal_instance of this thermal zone * @idr: &struct idr to generate unique id for this zone's cooling * devices @@ -185,9 +198,11 @@ struct thermal_zone_device { int emul_temperature; int passive; unsigned int forced_passive; + atomic_t need_update; struct thermal_zone_device_ops *ops; - const struct thermal_zone_params *tzp; + struct thermal_zone_params *tzp; struct thermal_governor *governor; + void *governor_data; struct list_head thermal_instances; struct idr idr; struct mutex lock; @@ -198,12 +213,19 @@ struct thermal_zone_device { /** * struct thermal_governor - structure that holds thermal governor information * @name: name of the governor + * @bind_to_tz: callback called when binding to a thermal zone. If it + * returns 0, the governor is bound to the thermal zone, + * otherwise it fails. + * @unbind_from_tz: callback called when a governor is unbound from a + * thermal zone. * @throttle: callback called for every trip point even if temperature is * below the trip point temperature * @governor_list: node in thermal_governor_list (in thermal_core.c) */ struct thermal_governor { char name[THERMAL_NAME_LENGTH]; + int (*bind_to_tz)(struct thermal_zone_device *tz); + void (*unbind_from_tz)(struct thermal_zone_device *tz); int (*throttle)(struct thermal_zone_device *tz, int trip); struct list_head governor_list; }; @@ -214,9 +236,12 @@ struct thermal_bind_params { /* * This is a measure of 'how effectively these devices can - * cool 'this' thermal zone. The shall be determined by platform - * characterization. This is on a 'percentage' scale. - * See Documentation/thermal/sysfs-api.txt for more information. + * cool 'this' thermal zone. It shall be determined by + * platform characterization. This value is relative to the + * rest of the weights so a cooling device whose weight is + * double that of another cooling device is twice as + * effective. See Documentation/thermal/sysfs-api.txt for more + * information. */ int weight; @@ -253,6 +278,44 @@ struct thermal_zone_params { int num_tbps; /* Number of tbp entries */ struct thermal_bind_params *tbp; + + /* + * Sustainable power (heat) that this thermal zone can dissipate in + * mW + */ + u32 sustainable_power; + + /* + * Proportional parameter of the PID controller when + * overshooting (i.e., when temperature is below the target) + */ + s32 k_po; + + /* + * Proportional parameter of the PID controller when + * undershooting + */ + s32 k_pu; + + /* Integral parameter of the PID controller */ + s32 k_i; + + /* Derivative parameter of the PID controller */ + s32 k_d; + + /* threshold below which the error is no longer accumulated */ + s32 integral_cutoff; + + /* + * @slope: slope of a linear temperature adjustment curve. + * Used by thermal zone drivers. + */ + int slope; + /* + * @offset: offset of a linear temperature adjustment curve. + * Used by thermal zone drivers (default 0). + */ + int offset; }; struct thermal_genl_event { @@ -272,9 +335,9 @@ struct thermal_genl_event { * temperature. */ struct thermal_zone_of_device_ops { - int (*get_temp)(void *, long *); + int (*get_temp)(void *, int *); int (*get_trend)(void *, long *); - int (*set_emul_temp)(void *, unsigned long); + int (*set_emul_temp)(void *, int); }; /** @@ -304,7 +367,7 @@ static inline struct thermal_zone_device * thermal_zone_of_sensor_register(struct device *dev, int id, void *data, const struct thermal_zone_of_device_ops *ops) { - return NULL; + return ERR_PTR(-ENODEV); } static inline @@ -316,14 +379,27 @@ void thermal_zone_of_sensor_unregister(struct device *dev, #endif #if IS_ENABLED(CONFIG_THERMAL) +static inline bool cdev_is_power_actor(struct thermal_cooling_device *cdev) +{ + return cdev->ops->get_requested_power && cdev->ops->state2power && + cdev->ops->power2state; +} + +int power_actor_get_max_power(struct thermal_cooling_device *, + struct thermal_zone_device *tz, u32 *max_power); +int power_actor_get_min_power(struct thermal_cooling_device *, + struct thermal_zone_device *tz, u32 *min_power); +int power_actor_set_power(struct thermal_cooling_device *, + struct thermal_instance *, u32); struct thermal_zone_device *thermal_zone_device_register(const char *, int, int, void *, struct thermal_zone_device_ops *, - const struct thermal_zone_params *, int, int); + struct thermal_zone_params *, int, int); void thermal_zone_device_unregister(struct thermal_zone_device *); int thermal_zone_bind_cooling_device(struct thermal_zone_device *, int, struct thermal_cooling_device *, - unsigned long, unsigned long); + unsigned long, unsigned long, + unsigned int); int thermal_zone_unbind_cooling_device(struct thermal_zone_device *, int, struct thermal_cooling_device *); void thermal_zone_device_update(struct thermal_zone_device *); @@ -335,7 +411,7 @@ thermal_of_cooling_device_register(struct device_node *np, char *, void *, const struct thermal_cooling_device_ops *); void thermal_cooling_device_unregister(struct thermal_cooling_device *); struct thermal_zone_device *thermal_zone_get_zone_by_name(const char *name); -int thermal_zone_get_temp(struct thermal_zone_device *tz, unsigned long *temp); +int thermal_zone_get_temp(struct thermal_zone_device *tz, int *temp); int get_tz_trend(struct thermal_zone_device *, int); struct thermal_instance *get_thermal_instance(struct thermal_zone_device *, @@ -343,6 +419,18 @@ struct thermal_instance *get_thermal_instance(struct thermal_zone_device *, void thermal_cdev_update(struct thermal_cooling_device *); void thermal_notify_framework(struct thermal_zone_device *, int); #else +static inline bool cdev_is_power_actor(struct thermal_cooling_device *cdev) +{ return false; } +static inline int power_actor_get_max_power(struct thermal_cooling_device *cdev, + struct thermal_zone_device *tz, u32 *max_power) +{ return 0; } +static inline int power_actor_get_min_power(struct thermal_cooling_device *cdev, + struct thermal_zone_device *tz, + u32 *min_power) +{ return -ENODEV; } +static inline int power_actor_set_power(struct thermal_cooling_device *cdev, + struct thermal_instance *tz, u32 power) +{ return 0; } static inline struct thermal_zone_device *thermal_zone_device_register( const char *type, int trips, int mask, void *devdata, struct thermal_zone_device_ops *ops, @@ -355,7 +443,8 @@ static inline void thermal_zone_device_unregister( static inline int thermal_zone_bind_cooling_device( struct thermal_zone_device *tz, int trip, struct thermal_cooling_device *cdev, - unsigned long upper, unsigned long lower) + unsigned long upper, unsigned long lower, + unsigned int weight) { return -ENODEV; } static inline int thermal_zone_unbind_cooling_device( struct thermal_zone_device *tz, int trip, @@ -378,7 +467,7 @@ static inline struct thermal_zone_device *thermal_zone_get_zone_by_name( const char *name) { return ERR_PTR(-ENODEV); } static inline int thermal_zone_get_temp( - struct thermal_zone_device *tz, unsigned long *temp) + struct thermal_zone_device *tz, int *temp) { return -ENODEV; } static inline int get_tz_trend(struct thermal_zone_device *tz, int trip) { return -ENODEV; } diff --git a/kernel/include/linux/ti_wilink_st.h b/kernel/include/linux/ti_wilink_st.h index c78dcfeaf..0a0d56834 100644 --- a/kernel/include/linux/ti_wilink_st.h +++ b/kernel/include/linux/ti_wilink_st.h @@ -86,7 +86,6 @@ struct st_proto_s { extern long st_register(struct st_proto_s *); extern long st_unregister(struct st_proto_s *); -extern struct ti_st_plat_data *dt_pdata; /* * header information used by st_core.c @@ -159,6 +158,7 @@ struct st_data_s { unsigned long ll_state; void *kim_data; struct tty_struct *tty; + struct work_struct work_write_wakeup; }; /* diff --git a/kernel/include/linux/tick.h b/kernel/include/linux/tick.h index f8492da57..e312219ff 100644 --- a/kernel/include/linux/tick.h +++ b/kernel/include/linux/tick.h @@ -13,8 +13,6 @@ #ifdef CONFIG_GENERIC_CLOCKEVENTS extern void __init tick_init(void); -extern void tick_freeze(void); -extern void tick_unfreeze(void); /* Should be core only, but ARM BL switcher requires it */ extern void tick_suspend_local(void); /* Should be core only, but XEN resume magic and ARM BL switcher require it */ @@ -23,14 +21,20 @@ extern void tick_handover_do_timer(void); extern void tick_cleanup_dead_cpu(int cpu); #else /* CONFIG_GENERIC_CLOCKEVENTS */ static inline void tick_init(void) { } -static inline void tick_freeze(void) { } -static inline void tick_unfreeze(void) { } static inline void tick_suspend_local(void) { } static inline void tick_resume_local(void) { } static inline void tick_handover_do_timer(void) { } static inline void tick_cleanup_dead_cpu(int cpu) { } #endif /* !CONFIG_GENERIC_CLOCKEVENTS */ +#if defined(CONFIG_GENERIC_CLOCKEVENTS) && defined(CONFIG_SUSPEND) +extern void tick_freeze(void); +extern void tick_unfreeze(void); +#else +static inline void tick_freeze(void) { } +static inline void tick_unfreeze(void) { } +#endif + #ifdef CONFIG_TICK_ONESHOT extern void tick_irq_enter(void); # ifndef arch_needs_cpu @@ -63,10 +67,13 @@ extern void tick_broadcast_control(enum tick_broadcast_mode mode); static inline void tick_broadcast_control(enum tick_broadcast_mode mode) { } #endif /* BROADCAST */ -#if defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) && defined(CONFIG_TICK_ONESHOT) +#ifdef CONFIG_GENERIC_CLOCKEVENTS extern int tick_broadcast_oneshot_control(enum tick_broadcast_state state); #else -static inline int tick_broadcast_oneshot_control(enum tick_broadcast_state state) { return 0; } +static inline int tick_broadcast_oneshot_control(enum tick_broadcast_state state) +{ + return 0; +} #endif static inline void tick_broadcast_enable(void) @@ -134,21 +141,44 @@ static inline bool tick_nohz_full_cpu(int cpu) return cpumask_test_cpu(cpu, tick_nohz_full_mask); } -extern void __tick_nohz_full_check(void); +static inline void tick_nohz_full_add_cpus_to(struct cpumask *mask) +{ + if (tick_nohz_full_enabled()) + cpumask_or(mask, mask, tick_nohz_full_mask); +} + +static inline int housekeeping_any_cpu(void) +{ + return cpumask_any_and(housekeeping_mask, cpu_online_mask); +} + extern void tick_nohz_full_kick(void); extern void tick_nohz_full_kick_cpu(int cpu); extern void tick_nohz_full_kick_all(void); -extern void __tick_nohz_task_switch(struct task_struct *tsk); +extern void __tick_nohz_task_switch(void); #else +static inline int housekeeping_any_cpu(void) +{ + return smp_processor_id(); +} static inline bool tick_nohz_full_enabled(void) { return false; } static inline bool tick_nohz_full_cpu(int cpu) { return false; } -static inline void __tick_nohz_full_check(void) { } +static inline void tick_nohz_full_add_cpus_to(struct cpumask *mask) { } static inline void tick_nohz_full_kick_cpu(int cpu) { } static inline void tick_nohz_full_kick(void) { } static inline void tick_nohz_full_kick_all(void) { } -static inline void __tick_nohz_task_switch(struct task_struct *tsk) { } +static inline void __tick_nohz_task_switch(void) { } #endif +static inline const struct cpumask *housekeeping_cpumask(void) +{ +#ifdef CONFIG_NO_HZ_FULL + if (tick_nohz_full_enabled()) + return housekeeping_mask; +#endif + return cpu_possible_mask; +} + static inline bool is_housekeeping_cpu(int cpu) { #ifdef CONFIG_NO_HZ_FULL @@ -167,16 +197,10 @@ static inline void housekeeping_affine(struct task_struct *t) #endif } -static inline void tick_nohz_full_check(void) -{ - if (tick_nohz_full_enabled()) - __tick_nohz_full_check(); -} - -static inline void tick_nohz_task_switch(struct task_struct *tsk) +static inline void tick_nohz_task_switch(void) { if (tick_nohz_full_enabled()) - __tick_nohz_task_switch(tsk); + __tick_nohz_task_switch(); } #endif diff --git a/kernel/include/linux/time64.h b/kernel/include/linux/time64.h index a3831478d..367d5af89 100644 --- a/kernel/include/linux/time64.h +++ b/kernel/include/linux/time64.h @@ -2,6 +2,7 @@ #define _LINUX_TIME64_H #include <uapi/linux/time.h> +#include <linux/math64.h> typedef __s64 time64_t; @@ -11,11 +12,18 @@ typedef __s64 time64_t; */ #if __BITS_PER_LONG == 64 # define timespec64 timespec +#define itimerspec64 itimerspec #else struct timespec64 { time64_t tv_sec; /* seconds */ long tv_nsec; /* nanoseconds */ }; + +struct itimerspec64 { + struct timespec64 it_interval; + struct timespec64 it_value; +}; + #endif /* Parameters used to convert the timespec values: */ @@ -28,6 +36,7 @@ struct timespec64 { #define FSEC_PER_SEC 1000000000000000LL /* Located here for timespec[64]_valid_strict */ +#define TIME64_MAX ((s64)~((u64)1 << 63)) #define KTIME_MAX ((s64)~((u64)1 << 63)) #define KTIME_SEC_MAX (KTIME_MAX / NSEC_PER_SEC) @@ -43,6 +52,16 @@ static inline struct timespec64 timespec_to_timespec64(const struct timespec ts) return ts; } +static inline struct itimerspec itimerspec64_to_itimerspec(struct itimerspec64 *its64) +{ + return *its64; +} + +static inline struct itimerspec64 itimerspec_to_itimerspec64(struct itimerspec *its) +{ + return *its; +} + # define timespec64_equal timespec_equal # define timespec64_compare timespec_compare # define set_normalized_timespec64 set_normalized_timespec @@ -75,6 +94,24 @@ static inline struct timespec64 timespec_to_timespec64(const struct timespec ts) return ret; } +static inline struct itimerspec itimerspec64_to_itimerspec(struct itimerspec64 *its64) +{ + struct itimerspec ret; + + ret.it_interval = timespec64_to_timespec(its64->it_interval); + ret.it_value = timespec64_to_timespec(its64->it_value); + return ret; +} + +static inline struct itimerspec64 itimerspec_to_itimerspec64(struct itimerspec *its) +{ + struct itimerspec64 ret; + + ret.it_interval = timespec_to_timespec64(its->it_interval); + ret.it_value = timespec_to_timespec64(its->it_value); + return ret; +} + static inline int timespec64_equal(const struct timespec64 *a, const struct timespec64 *b) { diff --git a/kernel/include/linux/timekeeper_internal.h b/kernel/include/linux/timekeeper_internal.h index fb8696385..25247220b 100644 --- a/kernel/include/linux/timekeeper_internal.h +++ b/kernel/include/linux/timekeeper_internal.h @@ -49,6 +49,8 @@ struct tk_read_base { * @offs_boot: Offset clock monotonic -> clock boottime * @offs_tai: Offset clock monotonic -> clock tai * @tai_offset: The current UTC to TAI offset in seconds + * @clock_was_set_seq: The sequence number of clock was set events + * @next_leap_ktime: CLOCK_MONOTONIC time value of a pending leap-second * @raw_time: Monotonic raw base time in timespec64 format * @cycle_interval: Number of clock cycles in one NTP interval * @xtime_interval: Number of clock shifted nano seconds in one NTP @@ -60,6 +62,9 @@ struct tk_read_base { * shifted nano seconds. * @ntp_error_shift: Shift conversion between clock shifted nano seconds and * ntp shifted nano seconds. + * @last_warning: Warning ratelimiter (DEBUG_TIMEKEEPING) + * @underflow_seen: Underflow warning flag (DEBUG_TIMEKEEPING) + * @overflow_seen: Overflow warning flag (DEBUG_TIMEKEEPING) * * Note: For timespec(64) based interfaces wall_to_monotonic is what * we need to add to xtime (or xtime corrected for sub jiffie times) @@ -85,6 +90,8 @@ struct timekeeper { ktime_t offs_boot; ktime_t offs_tai; s32 tai_offset; + unsigned int clock_was_set_seq; + ktime_t next_leap_ktime; struct timespec64 raw_time; /* The following members are for timekeeping internal use */ @@ -104,6 +111,18 @@ struct timekeeper { s64 ntp_error; u32 ntp_error_shift; u32 ntp_err_mult; +#ifdef CONFIG_DEBUG_TIMEKEEPING + long last_warning; + /* + * These simple flag variables are managed + * without locks, which is racy, but they are + * ok since we don't really care about being + * super precise about how many events were + * seen, just that a problem was observed. + */ + int underflow_seen; + int overflow_seen; +#endif }; #ifdef CONFIG_GENERIC_TIME_VSYSCALL diff --git a/kernel/include/linux/timekeeping.h b/kernel/include/linux/timekeeping.h index 99176af21..ec89d8463 100644 --- a/kernel/include/linux/timekeeping.h +++ b/kernel/include/linux/timekeeping.h @@ -18,10 +18,17 @@ extern int do_sys_settimeofday(const struct timespec *tv, * Kernel time accessors */ unsigned long get_seconds(void); -struct timespec current_kernel_time(void); +struct timespec64 current_kernel_time64(void); /* does not take xtime_lock */ struct timespec __current_kernel_time(void); +static inline struct timespec current_kernel_time(void) +{ + struct timespec64 now = current_kernel_time64(); + + return timespec64_to_timespec(now); +} + /* * timespec based interfaces */ @@ -145,7 +152,6 @@ static inline void getboottime(struct timespec *ts) } #endif -#define do_posix_clock_monotonic_gettime(ts) ktime_get_ts(ts) #define ktime_get_real_ts64(ts) getnstimeofday64(ts) /* @@ -163,6 +169,7 @@ extern ktime_t ktime_get(void); extern ktime_t ktime_get_with_offset(enum tk_offsets offs); extern ktime_t ktime_mono_to_any(ktime_t tmono, enum tk_offsets offs); extern ktime_t ktime_get_raw(void); +extern u32 ktime_get_resolution_ns(void); /** * ktime_get_real - get the real (wall-) time in ktime_t format @@ -256,8 +263,8 @@ extern void timekeeping_inject_sleeptime64(struct timespec64 *delta); /* * PPS accessor */ -extern void getnstime_raw_and_real(struct timespec *ts_raw, - struct timespec *ts_real); +extern void ktime_get_raw_and_real_ts64(struct timespec64 *ts_raw, + struct timespec64 *ts_real); /* * Persistent clock related interfaces @@ -266,7 +273,6 @@ extern int persistent_clock_is_local; extern void read_persistent_clock(struct timespec *ts); extern void read_persistent_clock64(struct timespec64 *ts); -extern void read_boot_clock(struct timespec *ts); extern void read_boot_clock64(struct timespec64 *ts); extern int update_persistent_clock(struct timespec now); extern int update_persistent_clock64(struct timespec64 now); diff --git a/kernel/include/linux/timer.h b/kernel/include/linux/timer.h index 5fcd72c57..299d2b785 100644 --- a/kernel/include/linux/timer.h +++ b/kernel/include/linux/timer.h @@ -14,27 +14,23 @@ struct timer_list { * All fields that change during normal runtime grouped to the * same cacheline */ - struct list_head entry; - unsigned long expires; - struct tvec_base *base; - - void (*function)(unsigned long); - unsigned long data; - - int slack; + struct hlist_node entry; + unsigned long expires; + void (*function)(unsigned long); + unsigned long data; + u32 flags; + int slack; #ifdef CONFIG_TIMER_STATS - int start_pid; - void *start_site; - char start_comm[16]; + int start_pid; + void *start_site; + char start_comm[16]; #endif #ifdef CONFIG_LOCKDEP - struct lockdep_map lockdep_map; + struct lockdep_map lockdep_map; #endif }; -extern struct tvec_base boot_tvec_bases; - #ifdef CONFIG_LOCKDEP /* * NB: because we have to copy the lockdep_map, setting the lockdep_map key @@ -49,9 +45,6 @@ extern struct tvec_base boot_tvec_bases; #endif /* - * Note that all tvec_bases are at least 4 byte aligned and lower two bits - * of base in timer_list is guaranteed to be zero. Use them for flags. - * * A deferrable timer will work normally when the system is busy, but * will not cause a CPU to come out of idle just to service it; instead, * the timer will be serviced when the CPU eventually wakes up with a @@ -65,17 +58,18 @@ extern struct tvec_base boot_tvec_bases; * workqueue locking issues. It's not meant for executing random crap * with interrupts disabled. Abuse is monitored! */ -#define TIMER_DEFERRABLE 0x1LU -#define TIMER_IRQSAFE 0x2LU - -#define TIMER_FLAG_MASK 0x3LU +#define TIMER_CPUMASK 0x0007FFFF +#define TIMER_MIGRATING 0x00080000 +#define TIMER_BASEMASK (TIMER_CPUMASK | TIMER_MIGRATING) +#define TIMER_DEFERRABLE 0x00100000 +#define TIMER_IRQSAFE 0x00200000 #define __TIMER_INITIALIZER(_function, _expires, _data, _flags) { \ - .entry = { .prev = TIMER_ENTRY_STATIC }, \ + .entry = { .next = TIMER_ENTRY_STATIC }, \ .function = (_function), \ .expires = (_expires), \ .data = (_data), \ - .base = (void *)((unsigned long)&boot_tvec_bases + (_flags)), \ + .flags = (_flags), \ .slack = -1, \ __TIMER_LOCKDEP_MAP_INITIALIZER( \ __FILE__ ":" __stringify(__LINE__)) \ @@ -168,7 +162,7 @@ static inline void init_timer_on_stack_key(struct timer_list *timer, */ static inline int timer_pending(const struct timer_list * timer) { - return timer->entry.next != NULL; + return timer->entry.pprev != NULL; } extern void add_timer_on(struct timer_list *timer, int cpu); @@ -188,26 +182,16 @@ extern void set_timer_slack(struct timer_list *time, int slack_hz); #define NEXT_TIMER_MAX_DELTA ((1UL << 30) - 1) /* - * Return when the next timer-wheel timeout occurs (in absolute jiffies), - * locks the timer base and does the comparison against the given - * jiffie. - */ -extern unsigned long get_next_timer_interrupt(unsigned long now); - -/* * Timer-statistics info: */ #ifdef CONFIG_TIMER_STATS extern int timer_stats_active; -#define TIMER_STATS_FLAG_DEFERRABLE 0x1 - extern void init_timer_stats(void); extern void timer_stats_update_stats(void *timer, pid_t pid, void *startf, - void *timerf, char *comm, - unsigned int timer_flag); + void *timerf, char *comm, u32 flags); extern void __timer_stats_timer_set_start_info(struct timer_list *timer, void *addr); @@ -254,6 +238,15 @@ extern void run_local_timers(void); struct hrtimer; extern enum hrtimer_restart it_real_fn(struct hrtimer *); +#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) +#include <linux/sysctl.h> + +extern unsigned int sysctl_timer_migration; +int timer_migration_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos); +#endif + unsigned long __round_jiffies(unsigned long j, int cpu); unsigned long __round_jiffies_relative(unsigned long j, int cpu); unsigned long round_jiffies(unsigned long j); diff --git a/kernel/include/linux/timerqueue.h b/kernel/include/linux/timerqueue.h index a520fd70a..7eec17ad7 100644 --- a/kernel/include/linux/timerqueue.h +++ b/kernel/include/linux/timerqueue.h @@ -16,10 +16,10 @@ struct timerqueue_head { }; -extern void timerqueue_add(struct timerqueue_head *head, - struct timerqueue_node *node); -extern void timerqueue_del(struct timerqueue_head *head, - struct timerqueue_node *node); +extern bool timerqueue_add(struct timerqueue_head *head, + struct timerqueue_node *node); +extern bool timerqueue_del(struct timerqueue_head *head, + struct timerqueue_node *node); extern struct timerqueue_node *timerqueue_iterate_next( struct timerqueue_node *node); diff --git a/kernel/include/linux/timex.h b/kernel/include/linux/timex.h index 9d3f1a5b6..39c25dbeb 100644 --- a/kernel/include/linux/timex.h +++ b/kernel/include/linux/timex.h @@ -152,7 +152,7 @@ extern unsigned long tick_nsec; /* SHIFTED_HZ period (nsec) */ #define NTP_INTERVAL_LENGTH (NSEC_PER_SEC/NTP_INTERVAL_FREQ) extern int do_adjtimex(struct timex *); -extern void hardpps(const struct timespec *, const struct timespec *); +extern void hardpps(const struct timespec64 *, const struct timespec64 *); int read_current_timer(unsigned long *timer_val); void ntp_notify_cmos_timer(void); diff --git a/kernel/include/linux/topology.h b/kernel/include/linux/topology.h index 909b6e43b..73ddad1e0 100644 --- a/kernel/include/linux/topology.h +++ b/kernel/include/linux/topology.h @@ -191,8 +191,8 @@ static inline int cpu_to_mem(int cpu) #ifndef topology_core_id #define topology_core_id(cpu) ((void)(cpu), 0) #endif -#ifndef topology_thread_cpumask -#define topology_thread_cpumask(cpu) cpumask_of(cpu) +#ifndef topology_sibling_cpumask +#define topology_sibling_cpumask(cpu) cpumask_of(cpu) #endif #ifndef topology_core_cpumask #define topology_core_cpumask(cpu) cpumask_of(cpu) @@ -201,7 +201,7 @@ static inline int cpu_to_mem(int cpu) #ifdef CONFIG_SCHED_SMT static inline const struct cpumask *cpu_smt_mask(int cpu) { - return topology_thread_cpumask(cpu); + return topology_sibling_cpumask(cpu); } #endif diff --git a/kernel/include/linux/tpm.h b/kernel/include/linux/tpm.h index 8350c538b..706e63eea 100644 --- a/kernel/include/linux/tpm.h +++ b/kernel/include/linux/tpm.h @@ -30,6 +30,8 @@ #define TPM_ANY_NUM 0xFFFF struct tpm_chip; +struct trusted_key_payload; +struct trusted_key_options; struct tpm_class_ops { const u8 req_complete_mask; @@ -46,11 +48,22 @@ struct tpm_class_ops { #if defined(CONFIG_TCG_TPM) || defined(CONFIG_TCG_TPM_MODULE) +extern int tpm_is_tpm2(u32 chip_num); extern int tpm_pcr_read(u32 chip_num, int pcr_idx, u8 *res_buf); extern int tpm_pcr_extend(u32 chip_num, int pcr_idx, const u8 *hash); extern int tpm_send(u32 chip_num, void *cmd, size_t buflen); extern int tpm_get_random(u32 chip_num, u8 *data, size_t max); +extern int tpm_seal_trusted(u32 chip_num, + struct trusted_key_payload *payload, + struct trusted_key_options *options); +extern int tpm_unseal_trusted(u32 chip_num, + struct trusted_key_payload *payload, + struct trusted_key_options *options); #else +static inline int tpm_is_tpm2(u32 chip_num) +{ + return -ENODEV; +} static inline int tpm_pcr_read(u32 chip_num, int pcr_idx, u8 *res_buf) { return -ENODEV; } @@ -63,5 +76,18 @@ static inline int tpm_send(u32 chip_num, void *cmd, size_t buflen) { static inline int tpm_get_random(u32 chip_num, u8 *data, size_t max) { return -ENODEV; } + +static inline int tpm_seal_trusted(u32 chip_num, + struct trusted_key_payload *payload, + struct trusted_key_options *options) +{ + return -ENODEV; +} +static inline int tpm_unseal_trusted(u32 chip_num, + struct trusted_key_payload *payload, + struct trusted_key_options *options) +{ + return -ENODEV; +} #endif #endif diff --git a/kernel/include/linux/ftrace_event.h b/kernel/include/linux/trace_events.h index 2ef42aa7e..a591f414d 100644 --- a/kernel/include/linux/ftrace_event.h +++ b/kernel/include/linux/trace_events.h @@ -1,6 +1,6 @@ -#ifndef _LINUX_FTRACE_EVENT_H -#define _LINUX_FTRACE_EVENT_H +#ifndef _LINUX_TRACE_EVENT_H +#define _LINUX_TRACE_EVENT_H #include <linux/ring_buffer.h> #include <linux/trace_seq.h> @@ -25,35 +25,35 @@ struct trace_print_flags_u64 { const char *name; }; -const char *ftrace_print_flags_seq(struct trace_seq *p, const char *delim, - unsigned long flags, - const struct trace_print_flags *flag_array); +const char *trace_print_flags_seq(struct trace_seq *p, const char *delim, + unsigned long flags, + const struct trace_print_flags *flag_array); -const char *ftrace_print_symbols_seq(struct trace_seq *p, unsigned long val, - const struct trace_print_flags *symbol_array); +const char *trace_print_symbols_seq(struct trace_seq *p, unsigned long val, + const struct trace_print_flags *symbol_array); #if BITS_PER_LONG == 32 -const char *ftrace_print_symbols_seq_u64(struct trace_seq *p, - unsigned long long val, - const struct trace_print_flags_u64 +const char *trace_print_symbols_seq_u64(struct trace_seq *p, + unsigned long long val, + const struct trace_print_flags_u64 *symbol_array); #endif -const char *ftrace_print_bitmask_seq(struct trace_seq *p, void *bitmask_ptr, - unsigned int bitmask_size); +const char *trace_print_bitmask_seq(struct trace_seq *p, void *bitmask_ptr, + unsigned int bitmask_size); -const char *ftrace_print_hex_seq(struct trace_seq *p, - const unsigned char *buf, int len); +const char *trace_print_hex_seq(struct trace_seq *p, + const unsigned char *buf, int len); -const char *ftrace_print_array_seq(struct trace_seq *p, +const char *trace_print_array_seq(struct trace_seq *p, const void *buf, int count, size_t el_size); struct trace_iterator; struct trace_event; -int ftrace_raw_output_prep(struct trace_iterator *iter, - struct trace_event *event); +int trace_raw_output_prep(struct trace_iterator *iter, + struct trace_event *event); /* * The trace entry - the most basic unit of tracing. This is what @@ -71,7 +71,7 @@ struct trace_entry { unsigned char preempt_lazy_count; }; -#define FTRACE_MAX_EVENT \ +#define TRACE_EVENT_TYPE_MAX \ ((1 << (sizeof(((struct trace_entry *)0)->type) * 8)) - 1) /* @@ -135,8 +135,8 @@ struct trace_event { struct trace_event_functions *funcs; }; -extern int register_ftrace_event(struct trace_event *event); -extern int unregister_ftrace_event(struct trace_event *event); +extern int register_trace_event(struct trace_event *event); +extern int unregister_trace_event(struct trace_event *event); /* Return values for print_line callback */ enum print_line_t { @@ -160,24 +160,23 @@ static inline enum print_line_t trace_handle_return(struct trace_seq *s) void tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags, int pc); -struct ftrace_event_file; +struct trace_event_file; struct ring_buffer_event * trace_event_buffer_lock_reserve(struct ring_buffer **current_buffer, - struct ftrace_event_file *ftrace_file, + struct trace_event_file *trace_file, int type, unsigned long len, unsigned long flags, int pc); struct ring_buffer_event * trace_current_buffer_lock_reserve(struct ring_buffer **current_buffer, int type, unsigned long len, unsigned long flags, int pc); -void trace_current_buffer_unlock_commit(struct ring_buffer *buffer, - struct ring_buffer_event *event, - unsigned long flags, int pc); -void trace_buffer_unlock_commit(struct ring_buffer *buffer, +void trace_buffer_unlock_commit(struct trace_array *tr, + struct ring_buffer *buffer, struct ring_buffer_event *event, unsigned long flags, int pc); -void trace_buffer_unlock_commit_regs(struct ring_buffer *buffer, +void trace_buffer_unlock_commit_regs(struct trace_array *tr, + struct ring_buffer *buffer, struct ring_buffer_event *event, unsigned long flags, int pc, struct pt_regs *regs); @@ -186,7 +185,7 @@ void trace_current_buffer_discard_commit(struct ring_buffer *buffer, void tracing_record_cmdline(struct task_struct *tsk); -int ftrace_output_call(struct trace_iterator *iter, char *name, char *fmt, ...); +int trace_output_call(struct trace_iterator *iter, char *name, char *fmt, ...); struct event_filter; @@ -203,50 +202,39 @@ enum trace_reg { #endif }; -struct ftrace_event_call; +struct trace_event_call; -struct ftrace_event_class { +struct trace_event_class { const char *system; void *probe; #ifdef CONFIG_PERF_EVENTS void *perf_probe; #endif - int (*reg)(struct ftrace_event_call *event, + int (*reg)(struct trace_event_call *event, enum trace_reg type, void *data); - int (*define_fields)(struct ftrace_event_call *); - struct list_head *(*get_fields)(struct ftrace_event_call *); + int (*define_fields)(struct trace_event_call *); + struct list_head *(*get_fields)(struct trace_event_call *); struct list_head fields; - int (*raw_init)(struct ftrace_event_call *); + int (*raw_init)(struct trace_event_call *); }; -extern int ftrace_event_reg(struct ftrace_event_call *event, +extern int trace_event_reg(struct trace_event_call *event, enum trace_reg type, void *data); -int ftrace_output_event(struct trace_iterator *iter, struct ftrace_event_call *event, - char *fmt, ...); - -int ftrace_event_define_field(struct ftrace_event_call *call, - char *type, int len, char *item, int offset, - int field_size, int sign, int filter); - -struct ftrace_event_buffer { +struct trace_event_buffer { struct ring_buffer *buffer; struct ring_buffer_event *event; - struct ftrace_event_file *ftrace_file; + struct trace_event_file *trace_file; void *entry; unsigned long flags; int pc; }; -void *ftrace_event_buffer_reserve(struct ftrace_event_buffer *fbuffer, - struct ftrace_event_file *ftrace_file, +void *trace_event_buffer_reserve(struct trace_event_buffer *fbuffer, + struct trace_event_file *trace_file, unsigned long len); -void ftrace_event_buffer_commit(struct ftrace_event_buffer *fbuffer); - -int ftrace_event_define_field(struct ftrace_event_call *call, - char *type, int len, char *item, int offset, - int field_size, int sign, int filter); +void trace_event_buffer_commit(struct trace_event_buffer *fbuffer); enum { TRACE_EVENT_FL_FILTERED_BIT, @@ -257,6 +245,7 @@ enum { TRACE_EVENT_FL_USE_CALL_FILTER_BIT, TRACE_EVENT_FL_TRACEPOINT_BIT, TRACE_EVENT_FL_KPROBE_BIT, + TRACE_EVENT_FL_UPROBE_BIT, }; /* @@ -264,13 +253,14 @@ enum { * FILTERED - The event has a filter attached * CAP_ANY - Any user can enable for perf * NO_SET_FILTER - Set when filter has error and is to be ignored - * IGNORE_ENABLE - For ftrace internal events, do not enable with debugfs file + * IGNORE_ENABLE - For trace internal events, do not enable with debugfs file * WAS_ENABLED - Set and stays set when an event was ever enabled * (used for module unloading, if a module event is enabled, * it is best to clear the buffers that used it). - * USE_CALL_FILTER - For ftrace internal events, don't use file filter + * USE_CALL_FILTER - For trace internal events, don't use file filter * TRACEPOINT - Event is a tracepoint * KPROBE - Event is a kprobe + * UPROBE - Event is a uprobe */ enum { TRACE_EVENT_FL_FILTERED = (1 << TRACE_EVENT_FL_FILTERED_BIT), @@ -281,11 +271,14 @@ enum { TRACE_EVENT_FL_USE_CALL_FILTER = (1 << TRACE_EVENT_FL_USE_CALL_FILTER_BIT), TRACE_EVENT_FL_TRACEPOINT = (1 << TRACE_EVENT_FL_TRACEPOINT_BIT), TRACE_EVENT_FL_KPROBE = (1 << TRACE_EVENT_FL_KPROBE_BIT), + TRACE_EVENT_FL_UPROBE = (1 << TRACE_EVENT_FL_UPROBE_BIT), }; -struct ftrace_event_call { +#define TRACE_EVENT_FL_UKPROBE (TRACE_EVENT_FL_KPROBE | TRACE_EVENT_FL_UPROBE) + +struct trace_event_call { struct list_head list; - struct ftrace_event_class *class; + struct trace_event_class *class; union { char *name; /* Set TRACE_EVENT_FL_TRACEPOINT flag when using "tp" */ @@ -300,7 +293,7 @@ struct ftrace_event_call { * bit 0: filter_active * bit 1: allow trace by non root (cap any) * bit 2: failed to apply filter - * bit 3: ftrace internal event (do not enable) + * bit 3: trace internal event (do not enable) * bit 4: Event was enabled by module * bit 5: use call filter rather than file filter * bit 6: Event is a tracepoint @@ -312,13 +305,13 @@ struct ftrace_event_call { struct hlist_head __percpu *perf_events; struct bpf_prog *prog; - int (*perf_perm)(struct ftrace_event_call *, + int (*perf_perm)(struct trace_event_call *, struct perf_event *); #endif }; static inline const char * -ftrace_event_name(struct ftrace_event_call *call) +trace_event_name(struct trace_event_call *call) { if (call->flags & TRACE_EVENT_FL_TRACEPOINT) return call->tp ? call->tp->name : NULL; @@ -327,21 +320,22 @@ ftrace_event_name(struct ftrace_event_call *call) } struct trace_array; -struct ftrace_subsystem_dir; +struct trace_subsystem_dir; enum { - FTRACE_EVENT_FL_ENABLED_BIT, - FTRACE_EVENT_FL_RECORDED_CMD_BIT, - FTRACE_EVENT_FL_FILTERED_BIT, - FTRACE_EVENT_FL_NO_SET_FILTER_BIT, - FTRACE_EVENT_FL_SOFT_MODE_BIT, - FTRACE_EVENT_FL_SOFT_DISABLED_BIT, - FTRACE_EVENT_FL_TRIGGER_MODE_BIT, - FTRACE_EVENT_FL_TRIGGER_COND_BIT, + EVENT_FILE_FL_ENABLED_BIT, + EVENT_FILE_FL_RECORDED_CMD_BIT, + EVENT_FILE_FL_FILTERED_BIT, + EVENT_FILE_FL_NO_SET_FILTER_BIT, + EVENT_FILE_FL_SOFT_MODE_BIT, + EVENT_FILE_FL_SOFT_DISABLED_BIT, + EVENT_FILE_FL_TRIGGER_MODE_BIT, + EVENT_FILE_FL_TRIGGER_COND_BIT, + EVENT_FILE_FL_PID_FILTER_BIT, }; /* - * Ftrace event file flags: + * Event file flags: * ENABLED - The event is enabled * RECORDED_CMD - The comms should be recorded at sched_switch * FILTERED - The event has a filter attached @@ -351,25 +345,27 @@ enum { * tracepoint may be enabled) * TRIGGER_MODE - When set, invoke the triggers associated with the event * TRIGGER_COND - When set, one or more triggers has an associated filter + * PID_FILTER - When set, the event is filtered based on pid */ enum { - FTRACE_EVENT_FL_ENABLED = (1 << FTRACE_EVENT_FL_ENABLED_BIT), - FTRACE_EVENT_FL_RECORDED_CMD = (1 << FTRACE_EVENT_FL_RECORDED_CMD_BIT), - FTRACE_EVENT_FL_FILTERED = (1 << FTRACE_EVENT_FL_FILTERED_BIT), - FTRACE_EVENT_FL_NO_SET_FILTER = (1 << FTRACE_EVENT_FL_NO_SET_FILTER_BIT), - FTRACE_EVENT_FL_SOFT_MODE = (1 << FTRACE_EVENT_FL_SOFT_MODE_BIT), - FTRACE_EVENT_FL_SOFT_DISABLED = (1 << FTRACE_EVENT_FL_SOFT_DISABLED_BIT), - FTRACE_EVENT_FL_TRIGGER_MODE = (1 << FTRACE_EVENT_FL_TRIGGER_MODE_BIT), - FTRACE_EVENT_FL_TRIGGER_COND = (1 << FTRACE_EVENT_FL_TRIGGER_COND_BIT), + EVENT_FILE_FL_ENABLED = (1 << EVENT_FILE_FL_ENABLED_BIT), + EVENT_FILE_FL_RECORDED_CMD = (1 << EVENT_FILE_FL_RECORDED_CMD_BIT), + EVENT_FILE_FL_FILTERED = (1 << EVENT_FILE_FL_FILTERED_BIT), + EVENT_FILE_FL_NO_SET_FILTER = (1 << EVENT_FILE_FL_NO_SET_FILTER_BIT), + EVENT_FILE_FL_SOFT_MODE = (1 << EVENT_FILE_FL_SOFT_MODE_BIT), + EVENT_FILE_FL_SOFT_DISABLED = (1 << EVENT_FILE_FL_SOFT_DISABLED_BIT), + EVENT_FILE_FL_TRIGGER_MODE = (1 << EVENT_FILE_FL_TRIGGER_MODE_BIT), + EVENT_FILE_FL_TRIGGER_COND = (1 << EVENT_FILE_FL_TRIGGER_COND_BIT), + EVENT_FILE_FL_PID_FILTER = (1 << EVENT_FILE_FL_PID_FILTER_BIT), }; -struct ftrace_event_file { +struct trace_event_file { struct list_head list; - struct ftrace_event_call *event_call; + struct trace_event_call *event_call; struct event_filter *filter; struct dentry *dir; struct trace_array *tr; - struct ftrace_subsystem_dir *system; + struct trace_subsystem_dir *system; struct list_head triggers; /* @@ -402,7 +398,7 @@ struct ftrace_event_file { early_initcall(trace_init_flags_##name); #define __TRACE_EVENT_PERF_PERM(name, expr...) \ - static int perf_perm_##name(struct ftrace_event_call *tp_event, \ + static int perf_perm_##name(struct trace_event_call *tp_event, \ struct perf_event *p_event) \ { \ return ({ expr; }); \ @@ -428,19 +424,21 @@ enum event_trigger_type { extern int filter_match_preds(struct event_filter *filter, void *rec); -extern int filter_check_discard(struct ftrace_event_file *file, void *rec, +extern int filter_check_discard(struct trace_event_file *file, void *rec, struct ring_buffer *buffer, struct ring_buffer_event *event); -extern int call_filter_check_discard(struct ftrace_event_call *call, void *rec, +extern int call_filter_check_discard(struct trace_event_call *call, void *rec, struct ring_buffer *buffer, struct ring_buffer_event *event); -extern enum event_trigger_type event_triggers_call(struct ftrace_event_file *file, +extern enum event_trigger_type event_triggers_call(struct trace_event_file *file, void *rec); -extern void event_triggers_post_call(struct ftrace_event_file *file, +extern void event_triggers_post_call(struct trace_event_file *file, enum event_trigger_type tt); +bool trace_event_ignore_this_pid(struct trace_event_file *trace_file); + /** - * ftrace_trigger_soft_disabled - do triggers and test if soft disabled + * trace_trigger_soft_disabled - do triggers and test if soft disabled * @file: The file pointer of the event to test * * If any triggers without filters are attached to this event, they @@ -449,15 +447,17 @@ extern void event_triggers_post_call(struct ftrace_event_file *file, * otherwise false. */ static inline bool -ftrace_trigger_soft_disabled(struct ftrace_event_file *file) +trace_trigger_soft_disabled(struct trace_event_file *file) { unsigned long eflags = file->flags; - if (!(eflags & FTRACE_EVENT_FL_TRIGGER_COND)) { - if (eflags & FTRACE_EVENT_FL_TRIGGER_MODE) + if (!(eflags & EVENT_FILE_FL_TRIGGER_COND)) { + if (eflags & EVENT_FILE_FL_TRIGGER_MODE) event_triggers_call(file, NULL); - if (eflags & FTRACE_EVENT_FL_SOFT_DISABLED) + if (eflags & EVENT_FILE_FL_SOFT_DISABLED) return true; + if (eflags & EVENT_FILE_FL_PID_FILTER) + return trace_event_ignore_this_pid(file); } return false; } @@ -476,7 +476,7 @@ ftrace_trigger_soft_disabled(struct ftrace_event_file *file) * Returns true if the event is discarded, false otherwise. */ static inline bool -__event_trigger_test_discard(struct ftrace_event_file *file, +__event_trigger_test_discard(struct trace_event_file *file, struct ring_buffer *buffer, struct ring_buffer_event *event, void *entry, @@ -484,10 +484,10 @@ __event_trigger_test_discard(struct ftrace_event_file *file, { unsigned long eflags = file->flags; - if (eflags & FTRACE_EVENT_FL_TRIGGER_COND) + if (eflags & EVENT_FILE_FL_TRIGGER_COND) *tt = event_triggers_call(file, entry); - if (test_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, &file->flags)) + if (test_bit(EVENT_FILE_FL_SOFT_DISABLED_BIT, &file->flags)) ring_buffer_discard_commit(buffer, event); else if (!filter_check_discard(file, entry, buffer, event)) return false; @@ -509,7 +509,7 @@ __event_trigger_test_discard(struct ftrace_event_file *file, * if the event is soft disabled and should be discarded. */ static inline void -event_trigger_unlock_commit(struct ftrace_event_file *file, +event_trigger_unlock_commit(struct trace_event_file *file, struct ring_buffer *buffer, struct ring_buffer_event *event, void *entry, unsigned long irq_flags, int pc) @@ -517,7 +517,7 @@ event_trigger_unlock_commit(struct ftrace_event_file *file, enum event_trigger_type tt = ETT_NONE; if (!__event_trigger_test_discard(file, buffer, event, entry, &tt)) - trace_buffer_unlock_commit(buffer, event, irq_flags, pc); + trace_buffer_unlock_commit(file->tr, buffer, event, irq_flags, pc); if (tt) event_triggers_post_call(file, tt); @@ -540,7 +540,7 @@ event_trigger_unlock_commit(struct ftrace_event_file *file, * trace_buffer_unlock_commit_regs() instead of trace_buffer_unlock_commit(). */ static inline void -event_trigger_unlock_commit_regs(struct ftrace_event_file *file, +event_trigger_unlock_commit_regs(struct trace_event_file *file, struct ring_buffer *buffer, struct ring_buffer_event *event, void *entry, unsigned long irq_flags, int pc, @@ -549,14 +549,14 @@ event_trigger_unlock_commit_regs(struct ftrace_event_file *file, enum event_trigger_type tt = ETT_NONE; if (!__event_trigger_test_discard(file, buffer, event, entry, &tt)) - trace_buffer_unlock_commit_regs(buffer, event, + trace_buffer_unlock_commit_regs(file->tr, buffer, event, irq_flags, pc, regs); if (tt) event_triggers_post_call(file, tt); } -#ifdef CONFIG_BPF_SYSCALL +#ifdef CONFIG_BPF_EVENTS unsigned int trace_call_bpf(struct bpf_prog *prog, void *ctx); #else static inline unsigned int trace_call_bpf(struct bpf_prog *prog, void *ctx) @@ -571,14 +571,16 @@ enum { FILTER_DYN_STRING, FILTER_PTR_STRING, FILTER_TRACE_FN, + FILTER_COMM, + FILTER_CPU, }; -extern int trace_event_raw_init(struct ftrace_event_call *call); -extern int trace_define_field(struct ftrace_event_call *call, const char *type, +extern int trace_event_raw_init(struct trace_event_call *call); +extern int trace_define_field(struct trace_event_call *call, const char *type, const char *name, int offset, int size, int is_signed, int filter_type); -extern int trace_add_event_call(struct ftrace_event_call *call); -extern int trace_remove_event_call(struct ftrace_event_call *call); +extern int trace_add_event_call(struct trace_event_call *call); +extern int trace_remove_event_call(struct trace_event_call *call); #define is_signed_type(type) (((type)(-1)) < (type)1) @@ -627,4 +629,4 @@ perf_trace_buf_submit(void *raw_data, int size, int rctx, u64 addr, } #endif -#endif /* _LINUX_FTRACE_EVENT_H */ +#endif /* _LINUX_TRACE_EVENT_H */ diff --git a/kernel/include/linux/tracehook.h b/kernel/include/linux/tracehook.h index 84d497297..26c152122 100644 --- a/kernel/include/linux/tracehook.h +++ b/kernel/include/linux/tracehook.h @@ -50,6 +50,7 @@ #include <linux/ptrace.h> #include <linux/security.h> #include <linux/task_work.h> +#include <linux/memcontrol.h> struct linux_binprm; /* @@ -188,6 +189,8 @@ static inline void tracehook_notify_resume(struct pt_regs *regs) smp_mb__after_atomic(); if (unlikely(current->task_works)) task_work_run(); + + mem_cgroup_handle_over_high(); } #endif /* <linux/tracehook.h> */ diff --git a/kernel/include/linux/tracepoint.h b/kernel/include/linux/tracepoint.h index a5f7f3eca..27e32b2b6 100644 --- a/kernel/include/linux/tracepoint.h +++ b/kernel/include/linux/tracepoint.h @@ -14,8 +14,10 @@ * See the file COPYING for more details. */ +#include <linux/smp.h> #include <linux/errno.h> #include <linux/types.h> +#include <linux/cpumask.h> #include <linux/rcupdate.h> #include <linux/static_key.h> @@ -26,6 +28,7 @@ struct notifier_block; struct tracepoint_func { void *func; void *data; + int prio; }; struct tracepoint { @@ -42,9 +45,14 @@ struct trace_enum_map { unsigned long enum_value; }; +#define TRACEPOINT_DEFAULT_PRIO 10 + extern int tracepoint_probe_register(struct tracepoint *tp, void *probe, void *data); extern int +tracepoint_probe_register_prio(struct tracepoint *tp, void *probe, void *data, + int prio); +extern int tracepoint_probe_unregister(struct tracepoint *tp, void *probe, void *data); extern void for_each_kernel_tracepoint(void (*fct)(struct tracepoint *tp, void *priv), @@ -111,7 +119,18 @@ extern void syscall_unregfunc(void); #define TP_ARGS(args...) args #define TP_CONDITION(args...) args -#ifdef CONFIG_TRACEPOINTS +/* + * Individual subsystem my have a separate configuration to + * enable their tracepoints. By default, this file will create + * the tracepoints if CONFIG_TRACEPOINT is defined. If a subsystem + * wants to be able to disable its tracepoints from being created + * it can define NOTRACE before including the tracepoint headers. + */ +#if defined(CONFIG_TRACEPOINTS) && !defined(NOTRACE) +#define TRACEPOINTS_ENABLED +#endif + +#ifdef TRACEPOINTS_ENABLED /* * it_func[0] is never NULL because there is at least one element in the array @@ -167,10 +186,11 @@ extern void syscall_unregfunc(void); * structure. Force alignment to the same alignment as the section start. * * When lockdep is enabled, we make sure to always do the RCU portions of - * the tracepoint code, regardless of whether tracing is on or we match the - * condition. This lets us find RCU issues triggered with tracepoints even - * when this tracepoint is off. This code has no purpose other than poking - * RCU a bit. + * the tracepoint code, regardless of whether tracing is on. However, + * don't check if the condition is false, due to interaction with idle + * instrumentation. This lets us find RCU issues triggered with tracepoints + * even when this tracepoint is off. This code has no purpose other than + * poking RCU a bit. */ #define __DECLARE_TRACE(name, proto, args, cond, data_proto, data_args) \ extern struct tracepoint __tracepoint_##name; \ @@ -196,6 +216,13 @@ extern void syscall_unregfunc(void); (void *)probe, data); \ } \ static inline int \ + register_trace_prio_##name(void (*probe)(data_proto), void *data,\ + int prio) \ + { \ + return tracepoint_probe_register_prio(&__tracepoint_##name, \ + (void *)probe, data, prio); \ + } \ + static inline int \ unregister_trace_##name(void (*probe)(data_proto), void *data) \ { \ return tracepoint_probe_unregister(&__tracepoint_##name,\ @@ -234,7 +261,7 @@ extern void syscall_unregfunc(void); #define EXPORT_TRACEPOINT_SYMBOL(name) \ EXPORT_SYMBOL(__tracepoint_##name) -#else /* !CONFIG_TRACEPOINTS */ +#else /* !TRACEPOINTS_ENABLED */ #define __DECLARE_TRACE(name, proto, args, cond, data_proto, data_args) \ static inline void trace_##name(proto) \ { } \ @@ -266,7 +293,7 @@ extern void syscall_unregfunc(void); #define EXPORT_TRACEPOINT_SYMBOL_GPL(name) #define EXPORT_TRACEPOINT_SYMBOL(name) -#endif /* CONFIG_TRACEPOINTS */ +#endif /* TRACEPOINTS_ENABLED */ #ifdef CONFIG_TRACING /** @@ -327,15 +354,19 @@ extern void syscall_unregfunc(void); * "void *__data, proto" as the callback prototype. */ #define DECLARE_TRACE_NOARGS(name) \ - __DECLARE_TRACE(name, void, , 1, void *__data, __data) + __DECLARE_TRACE(name, void, , \ + cpu_online(raw_smp_processor_id()), \ + void *__data, __data) #define DECLARE_TRACE(name, proto, args) \ - __DECLARE_TRACE(name, PARAMS(proto), PARAMS(args), 1, \ - PARAMS(void *__data, proto), \ - PARAMS(__data, args)) + __DECLARE_TRACE(name, PARAMS(proto), PARAMS(args), \ + cpu_online(raw_smp_processor_id()), \ + PARAMS(void *__data, proto), \ + PARAMS(__data, args)) #define DECLARE_TRACE_CONDITION(name, proto, args, cond) \ - __DECLARE_TRACE(name, PARAMS(proto), PARAMS(args), PARAMS(cond), \ + __DECLARE_TRACE(name, PARAMS(proto), PARAMS(args), \ + cpu_online(raw_smp_processor_id()) && (PARAMS(cond)), \ PARAMS(void *__data, proto), \ PARAMS(__data, args)) diff --git a/kernel/include/linux/tty.h b/kernel/include/linux/tty.h index d76631f61..6b6e811f4 100644 --- a/kernel/include/linux/tty.h +++ b/kernel/include/linux/tty.h @@ -227,7 +227,6 @@ struct tty_port { int blocked_open; /* Waiting to open */ int count; /* Usage count */ wait_queue_head_t open_wait; /* Open waiters */ - wait_queue_head_t close_wait; /* Close waiters */ wait_queue_head_t delta_msr_wait; /* Modem status change */ unsigned long flags; /* TTY flags ASY_*/ unsigned char console:1, /* port is a console */ @@ -422,8 +421,9 @@ static inline struct tty_struct *tty_kref_get(struct tty_struct *tty) extern int tty_paranoia_check(struct tty_struct *tty, struct inode *inode, const char *routine); -extern char *tty_name(struct tty_struct *tty, char *buf); +extern const char *tty_name(const struct tty_struct *tty); extern void tty_wait_until_sent(struct tty_struct *tty, long timeout); +extern int __tty_check_change(struct tty_struct *tty, int sig); extern int tty_check_change(struct tty_struct *tty); extern void __stop_tty(struct tty_struct *tty); extern void stop_tty(struct tty_struct *tty); @@ -467,6 +467,8 @@ extern void tty_buffer_free_all(struct tty_port *port); extern void tty_buffer_flush(struct tty_struct *tty, struct tty_ldisc *ld); extern void tty_buffer_init(struct tty_port *port); extern void tty_buffer_set_lock_subclass(struct tty_port *port); +extern bool tty_buffer_restart_work(struct tty_port *port); +extern bool tty_buffer_cancel_work(struct tty_port *port); extern speed_t tty_termios_baud_rate(struct ktermios *termios); extern speed_t tty_termios_input_baud_rate(struct ktermios *termios); extern void tty_termios_encode_baud_rate(struct ktermios *termios, @@ -605,7 +607,7 @@ extern void n_tty_inherit_ops(struct tty_ldisc_ops *ops); /* tty_audit.c */ #ifdef CONFIG_AUDIT -extern void tty_audit_add_data(struct tty_struct *tty, unsigned char *data, +extern void tty_audit_add_data(struct tty_struct *tty, const void *data, size_t size, unsigned icanon); extern void tty_audit_exit(void); extern void tty_audit_fork(struct signal_struct *sig); @@ -613,8 +615,8 @@ extern void tty_audit_tiocsti(struct tty_struct *tty, char ch); extern void tty_audit_push(struct tty_struct *tty); extern int tty_audit_push_current(void); #else -static inline void tty_audit_add_data(struct tty_struct *tty, - unsigned char *data, size_t size, unsigned icanon) +static inline void tty_audit_add_data(struct tty_struct *tty, const void *data, + size_t size, unsigned icanon) { } static inline void tty_audit_tiocsti(struct tty_struct *tty, char ch) @@ -652,54 +654,11 @@ extern long vt_compat_ioctl(struct tty_struct *tty, /* tty_mutex.c */ /* functions for preparation of BKL removal */ extern void __lockfunc tty_lock(struct tty_struct *tty); +extern int tty_lock_interruptible(struct tty_struct *tty); extern void __lockfunc tty_unlock(struct tty_struct *tty); extern void __lockfunc tty_lock_slave(struct tty_struct *tty); extern void __lockfunc tty_unlock_slave(struct tty_struct *tty); extern void tty_set_lock_subclass(struct tty_struct *tty); -/* - * this shall be called only from where BTM is held (like close) - * - * We need this to ensure nobody waits for us to finish while we are waiting. - * Without this we were encountering system stalls. - * - * This should be indeed removed with BTM removal later. - * - * Locking: BTM required. Nobody is allowed to hold port->mutex. - */ -static inline void tty_wait_until_sent_from_close(struct tty_struct *tty, - long timeout) -{ - tty_unlock(tty); /* tty->ops->close holds the BTM, drop it while waiting */ - tty_wait_until_sent(tty, timeout); - tty_lock(tty); -} - -/* - * wait_event_interruptible_tty -- wait for a condition with the tty lock held - * - * The condition we are waiting for might take a long time to - * become true, or might depend on another thread taking the - * BTM. In either case, we need to drop the BTM to guarantee - * forward progress. This is a leftover from the conversion - * from the BKL and should eventually get removed as the BTM - * falls out of use. - * - * Do not use in new code. - */ -#define wait_event_interruptible_tty(tty, wq, condition) \ -({ \ - int __ret = 0; \ - if (!(condition)) \ - __ret = __wait_event_interruptible_tty(tty, wq, \ - condition); \ - __ret; \ -}) - -#define __wait_event_interruptible_tty(tty, wq, condition) \ - ___wait_event(wq, condition, TASK_INTERRUPTIBLE, 0, 0, \ - tty_unlock(tty); \ - schedule(); \ - tty_lock(tty)) #ifdef CONFIG_PROC_FS extern void proc_tty_register_driver(struct tty_driver *); @@ -709,4 +668,10 @@ static inline void proc_tty_register_driver(struct tty_driver *d) {} static inline void proc_tty_unregister_driver(struct tty_driver *d) {} #endif +#define tty_debug(tty, f, args...) \ + do { \ + printk(KERN_DEBUG "%s: %s: " f, __func__, \ + tty_name(tty), ##args); \ + } while (0) + #endif diff --git a/kernel/include/linux/tty_driver.h b/kernel/include/linux/tty_driver.h index 92e337c18..161052477 100644 --- a/kernel/include/linux/tty_driver.h +++ b/kernel/include/linux/tty_driver.h @@ -296,7 +296,7 @@ struct tty_operations { struct tty_driver { int magic; /* magic number for this structure */ struct kref kref; /* Reference management */ - struct cdev *cdevs; + struct cdev **cdevs; struct module *owner; const char *driver_name; const char *name; diff --git a/kernel/include/linux/types.h b/kernel/include/linux/types.h index 8715287c3..70dd3dfde 100644 --- a/kernel/include/linux/types.h +++ b/kernel/include/linux/types.h @@ -35,7 +35,7 @@ typedef __kernel_gid16_t gid16_t; typedef unsigned long uintptr_t; -#ifdef CONFIG_UID16 +#ifdef CONFIG_HAVE_UID16 /* This is defined by include/asm-{arch}/posix_types.h */ typedef __kernel_old_uid_t old_uid_t; typedef __kernel_old_gid_t old_gid_t; @@ -205,13 +205,30 @@ struct ustat { * struct callback_head - callback structure for use with RCU and task_work * @next: next update requests in a list * @func: actual update function to call after the grace period. + * + * The struct is aligned to size of pointer. On most architectures it happens + * naturally due ABI requirements, but some architectures (like CRIS) have + * weird ABI and we need to ask it explicitly. + * + * The alignment is required to guarantee that bits 0 and 1 of @next will be + * clear under normal conditions -- as long as we use call_rcu(), + * call_rcu_bh(), call_rcu_sched(), or call_srcu() to queue callback. + * + * This guarantee is important for few reasons: + * - future call_rcu_lazy() will make use of lower bits in the pointer; + * - the structure shares storage spacer in struct page with @compound_head, + * which encode PageTail() in bit 0. The guarantee is needed to avoid + * false-positive PageTail(). */ struct callback_head { struct callback_head *next; void (*func)(struct callback_head *head); -}; +} __attribute__((aligned(sizeof(void *)))); #define rcu_head callback_head +typedef void (*rcu_callback_t)(struct rcu_head *head); +typedef void (*call_rcu_func_t)(struct rcu_head *head, rcu_callback_t func); + /* clocksource cycle base type */ typedef u64 cycle_t; diff --git a/kernel/include/linux/u64_stats_sync.h b/kernel/include/linux/u64_stats_sync.h index 4b4439e75..df89c9bcb 100644 --- a/kernel/include/linux/u64_stats_sync.h +++ b/kernel/include/linux/u64_stats_sync.h @@ -68,11 +68,12 @@ struct u64_stats_sync { }; +static inline void u64_stats_init(struct u64_stats_sync *syncp) +{ #if BITS_PER_LONG == 32 && defined(CONFIG_SMP) -# define u64_stats_init(syncp) seqcount_init(syncp.seq) -#else -# define u64_stats_init(syncp) do { } while (0) + seqcount_init(&syncp->seq); #endif +} static inline void u64_stats_update_begin(struct u64_stats_sync *syncp) { diff --git a/kernel/include/linux/uaccess.h b/kernel/include/linux/uaccess.h index 941b2dab5..cf5c472bb 100644 --- a/kernel/include/linux/uaccess.h +++ b/kernel/include/linux/uaccess.h @@ -77,36 +77,6 @@ static inline unsigned long __copy_from_user_nocache(void *to, #endif /* ARCH_HAS_NOCACHE_UACCESS */ -/** - * probe_kernel_address(): safely attempt to read from a location - * @addr: address to read from - its type is type typeof(retval)* - * @retval: read into this variable - * - * Safely read from address @addr into variable @revtal. If a kernel fault - * happens, handle that and return -EFAULT. - * We ensure that the __get_user() is executed in atomic context so that - * do_page_fault() doesn't attempt to take mmap_sem. This makes - * probe_kernel_address() suitable for use within regions where the caller - * already holds mmap_sem, or other locks which nest inside mmap_sem. - * This must be a macro because __get_user() needs to know the types of the - * args. - * - * We don't include enough header files to be able to do the set_fs(). We - * require that the probe_kernel_address() caller will do that. - */ -#define probe_kernel_address(addr, retval) \ - ({ \ - long ret; \ - mm_segment_t old_fs = get_fs(); \ - \ - set_fs(KERNEL_DS); \ - pagefault_disable(); \ - ret = __copy_from_user_inatomic(&(retval), (__force typeof(retval) __user *)(addr), sizeof(retval)); \ - pagefault_enable(); \ - set_fs(old_fs); \ - ret; \ - }) - /* * probe_kernel_read(): safely attempt to read from a location * @dst: pointer to the buffer that shall take the data @@ -131,4 +101,16 @@ extern long __probe_kernel_read(void *dst, const void *src, size_t size); extern long notrace probe_kernel_write(void *dst, const void *src, size_t size); extern long notrace __probe_kernel_write(void *dst, const void *src, size_t size); +extern long strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count); + +/** + * probe_kernel_address(): safely attempt to read from a location + * @addr: address to read from + * @retval: read into this variable + * + * Returns 0 on success, or -EFAULT. + */ +#define probe_kernel_address(addr, retval) \ + probe_kernel_read(&retval, addr, sizeof(retval)) + #endif /* __LINUX_UACCESS_H__ */ diff --git a/kernel/include/linux/ucs2_string.h b/kernel/include/linux/ucs2_string.h index cbb20afdb..bb679b48f 100644 --- a/kernel/include/linux/ucs2_string.h +++ b/kernel/include/linux/ucs2_string.h @@ -11,4 +11,8 @@ unsigned long ucs2_strlen(const ucs2_char_t *s); unsigned long ucs2_strsize(const ucs2_char_t *data, unsigned long maxlength); int ucs2_strncmp(const ucs2_char_t *a, const ucs2_char_t *b, size_t len); +unsigned long ucs2_utf8size(const ucs2_char_t *src); +unsigned long ucs2_as_utf8(u8 *dest, const ucs2_char_t *src, + unsigned long maxlength); + #endif /* _LINUX_UCS2_STRING_H_ */ diff --git a/kernel/include/linux/ulpi/driver.h b/kernel/include/linux/ulpi/driver.h new file mode 100644 index 000000000..388f6e08b --- /dev/null +++ b/kernel/include/linux/ulpi/driver.h @@ -0,0 +1,60 @@ +#ifndef __LINUX_ULPI_DRIVER_H +#define __LINUX_ULPI_DRIVER_H + +#include <linux/mod_devicetable.h> + +#include <linux/device.h> + +struct ulpi_ops; + +/** + * struct ulpi - describes ULPI PHY device + * @id: vendor and product ids for ULPI device + * @ops: I/O access + * @dev: device interface + */ +struct ulpi { + struct ulpi_device_id id; + struct ulpi_ops *ops; + struct device dev; +}; + +#define to_ulpi_dev(d) container_of(d, struct ulpi, dev) + +static inline void ulpi_set_drvdata(struct ulpi *ulpi, void *data) +{ + dev_set_drvdata(&ulpi->dev, data); +} + +static inline void *ulpi_get_drvdata(struct ulpi *ulpi) +{ + return dev_get_drvdata(&ulpi->dev); +} + +/** + * struct ulpi_driver - describes a ULPI PHY driver + * @id_table: array of device identifiers supported by this driver + * @probe: binds this driver to ULPI device + * @remove: unbinds this driver from ULPI device + * @driver: the name and owner members must be initialized by the drivers + */ +struct ulpi_driver { + const struct ulpi_device_id *id_table; + int (*probe)(struct ulpi *ulpi); + void (*remove)(struct ulpi *ulpi); + struct device_driver driver; +}; + +#define to_ulpi_driver(d) container_of(d, struct ulpi_driver, driver) + +int ulpi_register_driver(struct ulpi_driver *drv); +void ulpi_unregister_driver(struct ulpi_driver *drv); + +#define module_ulpi_driver(__ulpi_driver) \ + module_driver(__ulpi_driver, ulpi_register_driver, \ + ulpi_unregister_driver) + +int ulpi_read(struct ulpi *ulpi, u8 addr); +int ulpi_write(struct ulpi *ulpi, u8 addr, u8 val); + +#endif /* __LINUX_ULPI_DRIVER_H */ diff --git a/kernel/include/linux/ulpi/interface.h b/kernel/include/linux/ulpi/interface.h new file mode 100644 index 000000000..4de8ab491 --- /dev/null +++ b/kernel/include/linux/ulpi/interface.h @@ -0,0 +1,23 @@ +#ifndef __LINUX_ULPI_INTERFACE_H +#define __LINUX_ULPI_INTERFACE_H + +#include <linux/types.h> + +struct ulpi; + +/** + * struct ulpi_ops - ULPI register access + * @dev: the interface provider + * @read: read operation for ULPI register access + * @write: write operation for ULPI register access + */ +struct ulpi_ops { + struct device *dev; + int (*read)(struct ulpi_ops *ops, u8 addr); + int (*write)(struct ulpi_ops *ops, u8 addr, u8 val); +}; + +struct ulpi *ulpi_register_interface(struct device *, struct ulpi_ops *); +void ulpi_unregister_interface(struct ulpi *); + +#endif /* __LINUX_ULPI_INTERFACE_H */ diff --git a/kernel/include/linux/ulpi/regs.h b/kernel/include/linux/ulpi/regs.h new file mode 100644 index 000000000..b5b8b8804 --- /dev/null +++ b/kernel/include/linux/ulpi/regs.h @@ -0,0 +1,130 @@ +#ifndef __LINUX_ULPI_REGS_H +#define __LINUX_ULPI_REGS_H + +/* + * Macros for Set and Clear + * See ULPI 1.1 specification to find the registers with Set and Clear offsets + */ +#define ULPI_SET(a) (a + 1) +#define ULPI_CLR(a) (a + 2) + +/* + * Register Map + */ +#define ULPI_VENDOR_ID_LOW 0x00 +#define ULPI_VENDOR_ID_HIGH 0x01 +#define ULPI_PRODUCT_ID_LOW 0x02 +#define ULPI_PRODUCT_ID_HIGH 0x03 +#define ULPI_FUNC_CTRL 0x04 +#define ULPI_IFC_CTRL 0x07 +#define ULPI_OTG_CTRL 0x0a +#define ULPI_USB_INT_EN_RISE 0x0d +#define ULPI_USB_INT_EN_FALL 0x10 +#define ULPI_USB_INT_STS 0x13 +#define ULPI_USB_INT_LATCH 0x14 +#define ULPI_DEBUG 0x15 +#define ULPI_SCRATCH 0x16 +/* Optional Carkit Registers */ +#define ULPI_CARKIT_CTRL 0x19 +#define ULPI_CARKIT_INT_DELAY 0x1c +#define ULPI_CARKIT_INT_EN 0x1d +#define ULPI_CARKIT_INT_STS 0x20 +#define ULPI_CARKIT_INT_LATCH 0x21 +#define ULPI_CARKIT_PLS_CTRL 0x22 +/* Other Optional Registers */ +#define ULPI_TX_POS_WIDTH 0x25 +#define ULPI_TX_NEG_WIDTH 0x26 +#define ULPI_POLARITY_RECOVERY 0x27 +/* Access Extended Register Set */ +#define ULPI_ACCESS_EXTENDED 0x2f +/* Vendor Specific */ +#define ULPI_VENDOR_SPECIFIC 0x30 +/* Extended Registers */ +#define ULPI_EXT_VENDOR_SPECIFIC 0x80 + +/* + * Register Bits + */ + +/* Function Control */ +#define ULPI_FUNC_CTRL_XCVRSEL BIT(0) +#define ULPI_FUNC_CTRL_XCVRSEL_MASK 0x3 +#define ULPI_FUNC_CTRL_HIGH_SPEED 0x0 +#define ULPI_FUNC_CTRL_FULL_SPEED 0x1 +#define ULPI_FUNC_CTRL_LOW_SPEED 0x2 +#define ULPI_FUNC_CTRL_FS4LS 0x3 +#define ULPI_FUNC_CTRL_TERMSELECT BIT(2) +#define ULPI_FUNC_CTRL_OPMODE BIT(3) +#define ULPI_FUNC_CTRL_OPMODE_MASK (0x3 << 3) +#define ULPI_FUNC_CTRL_OPMODE_NORMAL (0x0 << 3) +#define ULPI_FUNC_CTRL_OPMODE_NONDRIVING (0x1 << 3) +#define ULPI_FUNC_CTRL_OPMODE_DISABLE_NRZI (0x2 << 3) +#define ULPI_FUNC_CTRL_OPMODE_NOSYNC_NOEOP (0x3 << 3) +#define ULPI_FUNC_CTRL_RESET BIT(5) +#define ULPI_FUNC_CTRL_SUSPENDM BIT(6) + +/* Interface Control */ +#define ULPI_IFC_CTRL_6_PIN_SERIAL_MODE BIT(0) +#define ULPI_IFC_CTRL_3_PIN_SERIAL_MODE BIT(1) +#define ULPI_IFC_CTRL_CARKITMODE BIT(2) +#define ULPI_IFC_CTRL_CLOCKSUSPENDM BIT(3) +#define ULPI_IFC_CTRL_AUTORESUME BIT(4) +#define ULPI_IFC_CTRL_EXTERNAL_VBUS BIT(5) +#define ULPI_IFC_CTRL_PASSTHRU BIT(6) +#define ULPI_IFC_CTRL_PROTECT_IFC_DISABLE BIT(7) + +/* OTG Control */ +#define ULPI_OTG_CTRL_ID_PULLUP BIT(0) +#define ULPI_OTG_CTRL_DP_PULLDOWN BIT(1) +#define ULPI_OTG_CTRL_DM_PULLDOWN BIT(2) +#define ULPI_OTG_CTRL_DISCHRGVBUS BIT(3) +#define ULPI_OTG_CTRL_CHRGVBUS BIT(4) +#define ULPI_OTG_CTRL_DRVVBUS BIT(5) +#define ULPI_OTG_CTRL_DRVVBUS_EXT BIT(6) +#define ULPI_OTG_CTRL_EXTVBUSIND BIT(7) + +/* USB Interrupt Enable Rising, + * USB Interrupt Enable Falling, + * USB Interrupt Status and + * USB Interrupt Latch + */ +#define ULPI_INT_HOST_DISCONNECT BIT(0) +#define ULPI_INT_VBUS_VALID BIT(1) +#define ULPI_INT_SESS_VALID BIT(2) +#define ULPI_INT_SESS_END BIT(3) +#define ULPI_INT_IDGRD BIT(4) + +/* Debug */ +#define ULPI_DEBUG_LINESTATE0 BIT(0) +#define ULPI_DEBUG_LINESTATE1 BIT(1) + +/* Carkit Control */ +#define ULPI_CARKIT_CTRL_CARKITPWR BIT(0) +#define ULPI_CARKIT_CTRL_IDGNDDRV BIT(1) +#define ULPI_CARKIT_CTRL_TXDEN BIT(2) +#define ULPI_CARKIT_CTRL_RXDEN BIT(3) +#define ULPI_CARKIT_CTRL_SPKLEFTEN BIT(4) +#define ULPI_CARKIT_CTRL_SPKRIGHTEN BIT(5) +#define ULPI_CARKIT_CTRL_MICEN BIT(6) + +/* Carkit Interrupt Enable */ +#define ULPI_CARKIT_INT_EN_IDFLOAT_RISE BIT(0) +#define ULPI_CARKIT_INT_EN_IDFLOAT_FALL BIT(1) +#define ULPI_CARKIT_INT_EN_CARINTDET BIT(2) +#define ULPI_CARKIT_INT_EN_DP_RISE BIT(3) +#define ULPI_CARKIT_INT_EN_DP_FALL BIT(4) + +/* Carkit Interrupt Status and + * Carkit Interrupt Latch + */ +#define ULPI_CARKIT_INT_IDFLOAT BIT(0) +#define ULPI_CARKIT_INT_CARINTDET BIT(1) +#define ULPI_CARKIT_INT_DP BIT(2) + +/* Carkit Pulse Control*/ +#define ULPI_CARKIT_PLS_CTRL_TXPLSEN BIT(0) +#define ULPI_CARKIT_PLS_CTRL_RXPLSEN BIT(1) +#define ULPI_CARKIT_PLS_CTRL_SPKRLEFT_BIASEN BIT(2) +#define ULPI_CARKIT_PLS_CTRL_SPKRRIGHT_BIASEN BIT(3) + +#endif /* __LINUX_ULPI_REGS_H */ diff --git a/kernel/include/linux/uprobes.h b/kernel/include/linux/uprobes.h index f5a644c64..0a294e950 100644 --- a/kernel/include/linux/uprobes.h +++ b/kernel/include/linux/uprobes.h @@ -21,7 +21,7 @@ * Authors: * Srikar Dronamraju * Jim Keniston - * Copyright (C) 2011-2012 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com> + * Copyright (C) 2011-2012 Red Hat, Inc., Peter Zijlstra */ #include <linux/errno.h> @@ -93,6 +93,22 @@ struct uprobe_task { unsigned int depth; }; +struct return_instance { + struct uprobe *uprobe; + unsigned long func; + unsigned long stack; /* stack pointer */ + unsigned long orig_ret_vaddr; /* original return address */ + bool chained; /* true, if instance is nested */ + + struct return_instance *next; /* keep as stack */ +}; + +enum rp_check { + RP_CHECK_CALL, + RP_CHECK_CHAIN_CALL, + RP_CHECK_RET, +}; + struct xol_area; struct uprobes_state { @@ -129,6 +145,7 @@ extern bool arch_uprobe_xol_was_trapped(struct task_struct *tsk); extern int arch_uprobe_exception_notify(struct notifier_block *self, unsigned long val, void *data); extern void arch_uprobe_abort_xol(struct arch_uprobe *aup, struct pt_regs *regs); extern unsigned long arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr, struct pt_regs *regs); +extern bool arch_uretprobe_is_alive(struct return_instance *ret, enum rp_check ctx, struct pt_regs *regs); extern bool arch_uprobe_ignore(struct arch_uprobe *aup, struct pt_regs *regs); extern void arch_uprobe_copy_ixol(struct page *page, unsigned long vaddr, void *src, unsigned long len); diff --git a/kernel/include/linux/usb.h b/kernel/include/linux/usb.h index 447fe29b5..b79925dd2 100644 --- a/kernel/include/linux/usb.h +++ b/kernel/include/linux/usb.h @@ -122,6 +122,8 @@ enum usb_interface_condition { * has been deferred. * @needs_binding: flag set when the driver should be re-probed or unbound * following a reset or suspend operation it doesn't support. + * @authorized: This allows to (de)authorize individual interfaces instead + * a whole device in contrast to the device authorization. * @dev: driver model's view of this device * @usb_dev: if an interface is bound to the USB major, this will point * to the sysfs representation for that device. @@ -178,6 +180,7 @@ struct usb_interface { unsigned needs_altsetting0:1; /* switch to altsetting 0 is pending */ unsigned needs_binding:1; /* needs delayed unbind/rebind */ unsigned resetting_device:1; /* true: bandwidth alloc after reset */ + unsigned authorized:1; /* used for interface authorization */ struct device dev; /* interface specific device info */ struct device *usb_dev; @@ -325,6 +328,7 @@ struct usb_host_bos { /* wireless cap descriptor is handled by wusb */ struct usb_ext_cap_descriptor *ext_cap; struct usb_ss_cap_descriptor *ss_cap; + struct usb_ssp_cap_descriptor *ssp_cap; struct usb_ss_container_id_descriptor *ss_id; }; @@ -507,6 +511,8 @@ struct usb3_lpm_parameters { * @usb2_hw_lpm_enabled: USB2 hardware LPM is enabled * @usb2_hw_lpm_allowed: Userspace allows USB 2.0 LPM to be enabled * @usb3_lpm_enabled: USB3 hardware LPM enabled + * @usb3_lpm_u1_enabled: USB3 hardware U1 LPM enabled + * @usb3_lpm_u2_enabled: USB3 hardware U2 LPM enabled * @string_langid: language ID for strings * @product: iProduct string, if present (static) * @manufacturer: iManufacturer string, if present (static) @@ -580,6 +586,8 @@ struct usb_device { unsigned usb2_hw_lpm_enabled:1; unsigned usb2_hw_lpm_allowed:1; unsigned usb3_lpm_enabled:1; + unsigned usb3_lpm_u1_enabled:1; + unsigned usb3_lpm_u2_enabled:1; int string_langid; /* static strings from the device */ diff --git a/kernel/include/linux/usb/cdc.h b/kernel/include/linux/usb/cdc.h new file mode 100644 index 000000000..b5706f94e --- /dev/null +++ b/kernel/include/linux/usb/cdc.h @@ -0,0 +1,51 @@ +/* + * USB CDC common helpers + * + * Copyright (c) 2015 Oliver Neukum <oneukum@suse.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * version 2 as published by the Free Software Foundation. + */ +#ifndef __LINUX_USB_CDC_H +#define __LINUX_USB_CDC_H + +#include <uapi/linux/usb/cdc.h> + +/* + * inofficial magic numbers + */ + +#define CDC_PHONET_MAGIC_NUMBER 0xAB + +/* + * parsing CDC headers + */ + +struct usb_cdc_parsed_header { + struct usb_cdc_union_desc *usb_cdc_union_desc; + struct usb_cdc_header_desc *usb_cdc_header_desc; + + struct usb_cdc_call_mgmt_descriptor *usb_cdc_call_mgmt_descriptor; + struct usb_cdc_acm_descriptor *usb_cdc_acm_descriptor; + struct usb_cdc_country_functional_desc *usb_cdc_country_functional_desc; + struct usb_cdc_network_terminal_desc *usb_cdc_network_terminal_desc; + struct usb_cdc_ether_desc *usb_cdc_ether_desc; + struct usb_cdc_dmm_desc *usb_cdc_dmm_desc; + struct usb_cdc_mdlm_desc *usb_cdc_mdlm_desc; + struct usb_cdc_mdlm_detail_desc *usb_cdc_mdlm_detail_desc; + struct usb_cdc_obex_desc *usb_cdc_obex_desc; + struct usb_cdc_ncm_desc *usb_cdc_ncm_desc; + struct usb_cdc_mbim_desc *usb_cdc_mbim_desc; + struct usb_cdc_mbim_extended_desc *usb_cdc_mbim_extended_desc; + + bool phonet_magic_present; +}; + +struct usb_interface; +int cdc_parse_cdc_header(struct usb_cdc_parsed_header *hdr, + struct usb_interface *intf, + u8 *buffer, + int buflen); + +#endif /* __LINUX_USB_CDC_H */ diff --git a/kernel/include/linux/usb/cdc_ncm.h b/kernel/include/linux/usb/cdc_ncm.h index 7c9b48473..3a375d07d 100644 --- a/kernel/include/linux/usb/cdc_ncm.h +++ b/kernel/include/linux/usb/cdc_ncm.h @@ -80,6 +80,9 @@ #define CDC_NCM_TIMER_INTERVAL_MIN 5UL #define CDC_NCM_TIMER_INTERVAL_MAX (U32_MAX / NSEC_PER_USEC) +/* Driver flags */ +#define CDC_NCM_FLAG_NDP_TO_END 0x02 /* NDP is placed at end of frame */ + #define cdc_ncm_comm_intf_is_mbim(x) ((x)->desc.bInterfaceSubClass == USB_CDC_SUBCLASS_MBIM && \ (x)->desc.bInterfaceProtocol == USB_CDC_PROTO_NONE) #define cdc_ncm_data_intf_is_mbim(x) ((x)->desc.bInterfaceProtocol == USB_CDC_MBIM_PROTO_NTB) @@ -103,9 +106,11 @@ struct cdc_ncm_ctx { spinlock_t mtx; atomic_t stop; + int drvflags; u32 timer_interval; u32 max_ndp_size; + struct usb_cdc_ncm_ndp16 *delayed_ndp16; u32 tx_timer_pending; u32 tx_curr_frame_num; @@ -133,7 +138,8 @@ struct cdc_ncm_ctx { }; u8 cdc_ncm_select_altsetting(struct usb_interface *intf); -int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_altsetting); +int cdc_ncm_change_mtu(struct net_device *net, int new_mtu); +int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_altsetting, int drvflags); void cdc_ncm_unbind(struct usbnet *dev, struct usb_interface *intf); struct sk_buff *cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign); int cdc_ncm_rx_verify_nth16(struct cdc_ncm_ctx *ctx, struct sk_buff *skb_in); diff --git a/kernel/include/linux/usb/ch9.h b/kernel/include/linux/usb/ch9.h index 27603bcbb..6cc96bb12 100644 --- a/kernel/include/linux/usb/ch9.h +++ b/kernel/include/linux/usb/ch9.h @@ -32,9 +32,9 @@ #ifndef __LINUX_USB_CH9_H #define __LINUX_USB_CH9_H +#include <linux/device.h> #include <uapi/linux/usb/ch9.h> - /** * usb_speed_string() - Returns human readable-name of the speed. * @speed: The speed to return human-readable name for. If it's not @@ -43,6 +43,15 @@ */ extern const char *usb_speed_string(enum usb_device_speed speed); +/** + * usb_get_maximum_speed - Get maximum requested speed for a given USB + * controller. + * @dev: Pointer to the given USB controller device + * + * The function gets the maximum speed string from property "maximum-speed", + * and returns the corresponding enum usb_device_speed. + */ +extern enum usb_device_speed usb_get_maximum_speed(struct device *dev); /** * usb_state_string - Returns human readable name for the state. diff --git a/kernel/include/linux/usb/chipidea.h b/kernel/include/linux/usb/chipidea.h index ab94f78c4..5dd75fa47 100644 --- a/kernel/include/linux/usb/chipidea.h +++ b/kernel/include/linux/usb/chipidea.h @@ -5,9 +5,28 @@ #ifndef __LINUX_USB_CHIPIDEA_H #define __LINUX_USB_CHIPIDEA_H +#include <linux/extcon.h> #include <linux/usb/otg.h> struct ci_hdrc; + +/** + * struct ci_hdrc_cable - structure for external connector cable state tracking + * @state: current state of the line + * @changed: set to true when extcon event happen + * @edev: device which generate events + * @ci: driver state of the chipidea device + * @nb: hold event notification callback + * @conn: used for notification registration + */ +struct ci_hdrc_cable { + bool state; + bool changed; + struct extcon_dev *edev; + struct ci_hdrc *ci; + struct notifier_block nb; +}; + struct ci_hdrc_platform_data { const char *name; /* offset of the capability registers */ @@ -19,8 +38,11 @@ struct ci_hdrc_platform_data { enum usb_phy_interface phy_mode; unsigned long flags; #define CI_HDRC_REGS_SHARED BIT(0) +#define CI_HDRC_DISABLE_DEVICE_STREAMING BIT(1) #define CI_HDRC_SUPPORTS_RUNTIME_PM BIT(2) -#define CI_HDRC_DISABLE_STREAMING BIT(3) +#define CI_HDRC_DISABLE_HOST_STREAMING BIT(3) +#define CI_HDRC_DISABLE_STREAMING (CI_HDRC_DISABLE_DEVICE_STREAMING | \ + CI_HDRC_DISABLE_HOST_STREAMING) /* * Only set it when DCCPARAMS.DC==1 and DCCPARAMS.HC==1, * but otg is not supported (no register otgsc). @@ -29,12 +51,27 @@ struct ci_hdrc_platform_data { #define CI_HDRC_IMX28_WRITE_FIX BIT(5) #define CI_HDRC_FORCE_FULLSPEED BIT(6) #define CI_HDRC_TURN_VBUS_EARLY_ON BIT(7) +#define CI_HDRC_SET_NON_ZERO_TTHA BIT(8) +#define CI_HDRC_OVERRIDE_AHB_BURST BIT(9) +#define CI_HDRC_OVERRIDE_TX_BURST BIT(10) +#define CI_HDRC_OVERRIDE_RX_BURST BIT(11) enum usb_dr_mode dr_mode; #define CI_HDRC_CONTROLLER_RESET_EVENT 0 #define CI_HDRC_CONTROLLER_STOPPED_EVENT 1 void (*notify_event) (struct ci_hdrc *ci, unsigned event); struct regulator *reg_vbus; + struct usb_otg_caps ci_otg_caps; bool tpl_support; + /* interrupt threshold setting */ + u32 itc_setting; + u32 ahb_burst_config; + u32 tx_burst_size; + u32 rx_burst_size; + + /* VBUS and ID signal state tracking, using extcon framework */ + struct ci_hdrc_cable vbus_extcon; + struct ci_hdrc_cable id_extcon; + u32 phy_clkgate_delay_us; }; /* Default offset of capability registers */ diff --git a/kernel/include/linux/usb/composite.h b/kernel/include/linux/usb/composite.h index 2511469a9..1074b8921 100644 --- a/kernel/include/linux/usb/composite.h +++ b/kernel/include/linux/usb/composite.h @@ -228,6 +228,8 @@ struct usb_function { struct list_head list; DECLARE_BITMAP(endpoints, 32); const struct usb_function_instance *fi; + + unsigned int bind_deactivated:1; }; int usb_add_function(struct usb_configuration *, struct usb_function *); diff --git a/kernel/include/linux/usb/gadget.h b/kernel/include/linux/usb/gadget.h index 4f3dfb7d0..3d583a10b 100644 --- a/kernel/include/linux/usb/gadget.h +++ b/kernel/include/linux/usb/gadget.h @@ -141,10 +141,49 @@ struct usb_ep_ops { }; /** + * struct usb_ep_caps - endpoint capabilities description + * @type_control:Endpoint supports control type (reserved for ep0). + * @type_iso:Endpoint supports isochronous transfers. + * @type_bulk:Endpoint supports bulk transfers. + * @type_int:Endpoint supports interrupt transfers. + * @dir_in:Endpoint supports IN direction. + * @dir_out:Endpoint supports OUT direction. + */ +struct usb_ep_caps { + unsigned type_control:1; + unsigned type_iso:1; + unsigned type_bulk:1; + unsigned type_int:1; + unsigned dir_in:1; + unsigned dir_out:1; +}; + +#define USB_EP_CAPS_TYPE_CONTROL 0x01 +#define USB_EP_CAPS_TYPE_ISO 0x02 +#define USB_EP_CAPS_TYPE_BULK 0x04 +#define USB_EP_CAPS_TYPE_INT 0x08 +#define USB_EP_CAPS_TYPE_ALL \ + (USB_EP_CAPS_TYPE_ISO | USB_EP_CAPS_TYPE_BULK | USB_EP_CAPS_TYPE_INT) +#define USB_EP_CAPS_DIR_IN 0x01 +#define USB_EP_CAPS_DIR_OUT 0x02 +#define USB_EP_CAPS_DIR_ALL (USB_EP_CAPS_DIR_IN | USB_EP_CAPS_DIR_OUT) + +#define USB_EP_CAPS(_type, _dir) \ + { \ + .type_control = !!(_type & USB_EP_CAPS_TYPE_CONTROL), \ + .type_iso = !!(_type & USB_EP_CAPS_TYPE_ISO), \ + .type_bulk = !!(_type & USB_EP_CAPS_TYPE_BULK), \ + .type_int = !!(_type & USB_EP_CAPS_TYPE_INT), \ + .dir_in = !!(_dir & USB_EP_CAPS_DIR_IN), \ + .dir_out = !!(_dir & USB_EP_CAPS_DIR_OUT), \ + } + +/** * struct usb_ep - device side representation of USB endpoint * @name:identifier for the endpoint, such as "ep-a" or "ep9in-bulk" * @ops: Function pointers used to access hardware-specific operations. * @ep_list:the gadget's ep_list holds all of its endpoints + * @caps:The structure describing types and directions supported by endoint. * @maxpacket:The maximum packet size used on this endpoint. The initial * value can sometimes be reduced (hardware allowing), according to * the endpoint descriptor used to configure the endpoint. @@ -167,12 +206,16 @@ struct usb_ep_ops { * gadget->ep_list. the control endpoint (gadget->ep0) is not in that list, * and is accessed only in response to a driver setup() callback. */ + struct usb_ep { void *driver_data; const char *name; const struct usb_ep_ops *ops; struct list_head ep_list; + struct usb_ep_caps caps; + bool claimed; + bool enabled; unsigned maxpacket:16; unsigned maxpacket_limit:16; unsigned max_streams:16; @@ -222,7 +265,18 @@ static inline void usb_ep_set_maxpacket_limit(struct usb_ep *ep, */ static inline int usb_ep_enable(struct usb_ep *ep) { - return ep->ops->enable(ep, ep->desc); + int ret; + + if (ep->enabled) + return 0; + + ret = ep->ops->enable(ep, ep->desc); + if (ret) + return ret; + + ep->enabled = true; + + return 0; } /** @@ -239,7 +293,18 @@ static inline int usb_ep_enable(struct usb_ep *ep) */ static inline int usb_ep_disable(struct usb_ep *ep) { - return ep->ops->disable(ep); + int ret; + + if (!ep->enabled) + return 0; + + ret = ep->ops->disable(ep); + if (ret) + return ret; + + ep->enabled = false; + + return 0; } /** @@ -492,6 +557,9 @@ struct usb_gadget_ops { int (*udc_start)(struct usb_gadget *, struct usb_gadget_driver *); int (*udc_stop)(struct usb_gadget *); + struct usb_ep *(*match_ep)(struct usb_gadget *, + struct usb_endpoint_descriptor *, + struct usb_ss_ep_comp_descriptor *); }; /** @@ -511,6 +579,7 @@ struct usb_gadget_ops { * @dev: Driver model state for this abstract device. * @out_epnum: last used out ep number * @in_epnum: last used in ep number + * @otg_caps: OTG capabilities of this gadget. * @sg_supported: true if we can handle scatter-gather * @is_otg: True if the USB device port uses a Mini-AB jack, so that the * gadget driver must provide a USB OTG descriptor. @@ -526,6 +595,9 @@ struct usb_gadget_ops { * @quirk_ep_out_aligned_size: epout requires buffer size to be aligned to * MaxPacketSize. * @is_selfpowered: if the gadget is self-powered. + * @deactivated: True if gadget is deactivated - in deactivated state it cannot + * be connected. + * @connected: True if gadget is connected. * * Gadgets have a mostly-portable "gadget driver" implementing device * functions, handling all usb configurations and interfaces. Gadget @@ -559,6 +631,7 @@ struct usb_gadget { struct device dev; unsigned out_epnum; unsigned in_epnum; + struct usb_otg_caps *otg_caps; unsigned sg_supported:1; unsigned is_otg:1; @@ -567,7 +640,12 @@ struct usb_gadget { unsigned a_hnp_support:1; unsigned a_alt_hnp_support:1; unsigned quirk_ep_out_aligned_size:1; + unsigned quirk_altset_not_supp:1; + unsigned quirk_stall_not_supp:1; + unsigned quirk_zlp_not_supp:1; unsigned is_selfpowered:1; + unsigned deactivated:1; + unsigned connected:1; }; #define work_to_gadget(w) (container_of((w), struct usb_gadget, work)) @@ -584,7 +662,6 @@ static inline struct usb_gadget *dev_to_usb_gadget(struct device *dev) #define gadget_for_each_ep(tmp, gadget) \ list_for_each_entry(tmp, &(gadget)->ep_list, ep_list) - /** * usb_ep_align_maybe - returns @len aligned to ep's maxpacketsize if gadget * requires quirk_ep_out_aligned_size, otherwise reguens len. @@ -603,6 +680,34 @@ usb_ep_align_maybe(struct usb_gadget *g, struct usb_ep *ep, size_t len) } /** + * gadget_is_altset_supported - return true iff the hardware supports + * altsettings + * @g: controller to check for quirk + */ +static inline int gadget_is_altset_supported(struct usb_gadget *g) +{ + return !g->quirk_altset_not_supp; +} + +/** + * gadget_is_stall_supported - return true iff the hardware supports stalling + * @g: controller to check for quirk + */ +static inline int gadget_is_stall_supported(struct usb_gadget *g) +{ + return !g->quirk_stall_not_supp; +} + +/** + * gadget_is_zlp_supported - return true iff the hardware supports zlp + * @g: controller to check for quirk + */ +static inline int gadget_is_zlp_supported(struct usb_gadget *g) +{ + return !g->quirk_zlp_not_supp; +} + +/** * gadget_is_dualspeed - return true iff the hardware handles high speed * @g: controller that might support both high and full speeds */ @@ -771,9 +876,24 @@ static inline int usb_gadget_vbus_disconnect(struct usb_gadget *gadget) */ static inline int usb_gadget_connect(struct usb_gadget *gadget) { + int ret; + if (!gadget->ops->pullup) return -EOPNOTSUPP; - return gadget->ops->pullup(gadget, 1); + + if (gadget->deactivated) { + /* + * If gadget is deactivated we only save new state. + * Gadget will be connected automatically after activation. + */ + gadget->connected = true; + return 0; + } + + ret = gadget->ops->pullup(gadget, 1); + if (!ret) + gadget->connected = 1; + return ret; } /** @@ -784,20 +904,88 @@ static inline int usb_gadget_connect(struct usb_gadget *gadget) * as a disconnect (when a VBUS session is active). Not all systems * support software pullup controls. * + * Returns zero on success, else negative errno. + */ +static inline int usb_gadget_disconnect(struct usb_gadget *gadget) +{ + int ret; + + if (!gadget->ops->pullup) + return -EOPNOTSUPP; + + if (gadget->deactivated) { + /* + * If gadget is deactivated we only save new state. + * Gadget will stay disconnected after activation. + */ + gadget->connected = false; + return 0; + } + + ret = gadget->ops->pullup(gadget, 0); + if (!ret) + gadget->connected = 0; + return ret; +} + +/** + * usb_gadget_deactivate - deactivate function which is not ready to work + * @gadget: the peripheral being deactivated + * * This routine may be used during the gadget driver bind() call to prevent * the peripheral from ever being visible to the USB host, unless later - * usb_gadget_connect() is called. For example, user mode components may + * usb_gadget_activate() is called. For example, user mode components may * need to be activated before the system can talk to hosts. * * Returns zero on success, else negative errno. */ -static inline int usb_gadget_disconnect(struct usb_gadget *gadget) +static inline int usb_gadget_deactivate(struct usb_gadget *gadget) { - if (!gadget->ops->pullup) - return -EOPNOTSUPP; - return gadget->ops->pullup(gadget, 0); + int ret; + + if (gadget->deactivated) + return 0; + + if (gadget->connected) { + ret = usb_gadget_disconnect(gadget); + if (ret) + return ret; + /* + * If gadget was being connected before deactivation, we want + * to reconnect it in usb_gadget_activate(). + */ + gadget->connected = true; + } + gadget->deactivated = true; + + return 0; } +/** + * usb_gadget_activate - activate function which is not ready to work + * @gadget: the peripheral being activated + * + * This routine activates gadget which was previously deactivated with + * usb_gadget_deactivate() call. It calls usb_gadget_connect() if needed. + * + * Returns zero on success, else negative errno. + */ +static inline int usb_gadget_activate(struct usb_gadget *gadget) +{ + if (!gadget->deactivated) + return 0; + + gadget->deactivated = false; + + /* + * If gadget has been connected before deactivation, or became connected + * while it was being deactivated, we call usb_gadget_connect(). + */ + if (gadget->connected) + return usb_gadget_connect(gadget); + + return 0; +} /*-------------------------------------------------------------------------*/ @@ -1002,6 +1190,10 @@ int usb_assign_descriptors(struct usb_function *f, struct usb_descriptor_header **ss); void usb_free_all_descriptors(struct usb_function *f); +struct usb_descriptor_header *usb_otg_descriptor_alloc( + struct usb_gadget *gadget); +int usb_otg_descriptor_init(struct usb_gadget *gadget, + struct usb_descriptor_header *otg_desc); /*-------------------------------------------------------------------------*/ /* utility to simplify map/unmap of usb_requests to/from DMA */ @@ -1034,6 +1226,21 @@ extern void usb_gadget_giveback_request(struct usb_ep *ep, /*-------------------------------------------------------------------------*/ +/* utility to find endpoint by name */ + +extern struct usb_ep *gadget_find_ep_by_name(struct usb_gadget *g, + const char *name); + +/*-------------------------------------------------------------------------*/ + +/* utility to check if endpoint caps match descriptor needs */ + +extern int usb_gadget_ep_match_desc(struct usb_gadget *gadget, + struct usb_ep *ep, struct usb_endpoint_descriptor *desc, + struct usb_ss_ep_comp_descriptor *ep_comp); + +/*-------------------------------------------------------------------------*/ + /* utility to update vbus status for udc core, it may be scheduled */ extern void usb_udc_vbus_handler(struct usb_gadget *gadget, bool status); @@ -1049,6 +1256,8 @@ extern struct usb_ep *usb_ep_autoconfig_ss(struct usb_gadget *, struct usb_endpoint_descriptor *, struct usb_ss_ep_comp_descriptor *); +extern void usb_ep_autoconfig_release(struct usb_ep *); + extern void usb_ep_autoconfig_reset(struct usb_gadget *); #endif /* __LINUX_USB_GADGET_H */ diff --git a/kernel/include/linux/usb/gadget_configfs.h b/kernel/include/linux/usb/gadget_configfs.h index d74c0ae98..c36e95730 100644 --- a/kernel/include/linux/usb/gadget_configfs.h +++ b/kernel/include/linux/usb/gadget_configfs.h @@ -7,9 +7,10 @@ int check_user_usb_string(const char *name, struct usb_gadget_strings *stringtab_dev); #define GS_STRINGS_W(__struct, __name) \ - static ssize_t __struct##_##__name##_store(struct __struct *gs, \ +static ssize_t __struct##_##__name##_store(struct config_item *item, \ const char *page, size_t len) \ { \ + struct __struct *gs = to_##__struct(item); \ int ret; \ \ ret = usb_string_copy(page, &gs->__name); \ @@ -19,30 +20,20 @@ int check_user_usb_string(const char *name, } #define GS_STRINGS_R(__struct, __name) \ - static ssize_t __struct##_##__name##_show(struct __struct *gs, \ - char *page) \ +static ssize_t __struct##_##__name##_show(struct config_item *item, char *page) \ { \ + struct __struct *gs = to_##__struct(item); \ return sprintf(page, "%s\n", gs->__name ?: ""); \ } -#define GS_STRING_ITEM_ATTR(struct_name, name) \ - static struct struct_name##_attribute struct_name##_##name = \ - __CONFIGFS_ATTR(name, S_IRUGO | S_IWUSR, \ - struct_name##_##name##_show, \ - struct_name##_##name##_store) - #define GS_STRINGS_RW(struct_name, _name) \ GS_STRINGS_R(struct_name, _name) \ GS_STRINGS_W(struct_name, _name) \ - GS_STRING_ITEM_ATTR(struct_name, _name) + CONFIGFS_ATTR(struct_name##_, _name) #define USB_CONFIG_STRING_RW_OPS(struct_in) \ - CONFIGFS_ATTR_OPS(struct_in); \ - \ static struct configfs_item_operations struct_in##_langid_item_ops = { \ .release = struct_in##_attr_release, \ - .show_attribute = struct_in##_attr_show, \ - .store_attribute = struct_in##_attr_store, \ }; \ \ static struct config_item_type struct_in##_langid_type = { \ diff --git a/kernel/include/linux/usb/hcd.h b/kernel/include/linux/usb/hcd.h index 68b1e836d..f89c24bd5 100644 --- a/kernel/include/linux/usb/hcd.h +++ b/kernel/include/linux/usb/hcd.h @@ -58,12 +58,6 @@ * * Since "struct usb_bus" is so thin, you can't share much code in it. * This framework is a layer over that, and should be more sharable. - * - * @authorized_default: Specifies if new devices are authorized to - * connect by default or they require explicit - * user space authorization; this bit is settable - * through /sys/class/usb_host/X/authorized_default. - * For the rest is RO, so we don't lock to r/w it. */ /*-------------------------------------------------------------------------*/ @@ -120,6 +114,8 @@ struct usb_hcd { #define HCD_FLAG_WAKEUP_PENDING 4 /* root hub is resuming? */ #define HCD_FLAG_RH_RUNNING 5 /* root hub is running? */ #define HCD_FLAG_DEAD 6 /* controller has died? */ +#define HCD_FLAG_INTF_AUTHORIZED 7 /* authorize interfaces? */ +#define HCD_FLAG_DEV_AUTHORIZED 8 /* authorize devices? */ /* The flags can be tested using these macros; they are likely to * be slightly faster than test_bit(). @@ -131,6 +127,22 @@ struct usb_hcd { #define HCD_RH_RUNNING(hcd) ((hcd)->flags & (1U << HCD_FLAG_RH_RUNNING)) #define HCD_DEAD(hcd) ((hcd)->flags & (1U << HCD_FLAG_DEAD)) + /* + * Specifies if interfaces are authorized by default + * or they require explicit user space authorization; this bit is + * settable through /sys/class/usb_host/X/interface_authorized_default + */ +#define HCD_INTF_AUTHORIZED(hcd) \ + ((hcd)->flags & (1U << HCD_FLAG_INTF_AUTHORIZED)) + + /* + * Specifies if devices are authorized by default + * or they require explicit user space authorization; this bit is + * settable through /sys/class/usb_host/X/authorized_default + */ +#define HCD_DEV_AUTHORIZED(hcd) \ + ((hcd)->flags & (1U << HCD_FLAG_DEV_AUTHORIZED)) + /* Flags that get set only during HCD registration or removal. */ unsigned rh_registered:1;/* is root hub registered? */ unsigned rh_pollable:1; /* may we poll the root hub? */ @@ -141,7 +153,6 @@ struct usb_hcd { * support the new root-hub polling mechanism. */ unsigned uses_new_polling:1; unsigned wireless:1; /* Wireless USB HCD */ - unsigned authorized_default:1; unsigned has_tt:1; /* Integrated TT in root hub */ unsigned amd_resume_bug:1; /* AMD remote wakeup quirk */ unsigned can_do_streams:1; /* HC supports streams */ @@ -239,6 +250,7 @@ struct hc_driver { #define HCD_USB2 0x0020 /* USB 2.0 */ #define HCD_USB25 0x0030 /* Wireless USB 1.0 (USB 2.5)*/ #define HCD_USB3 0x0040 /* USB 3.0 */ +#define HCD_USB31 0x0050 /* USB 3.1 */ #define HCD_MASK 0x0070 #define HCD_BH 0x0100 /* URB complete in BH context */ @@ -564,9 +576,9 @@ extern void usb_ep0_reinit(struct usb_device *); /*-------------------------------------------------------------------------*/ -/* class requests from USB 3.0 hub spec, table 10-5 */ -#define SetHubDepth (0x3000 | HUB_SET_DEPTH) -#define GetPortErrorCount (0x8000 | HUB_GET_PORT_ERR_COUNT) +/* class requests from USB 3.1 hub spec, table 10-7 */ +#define SetHubDepth (0x2000 | HUB_SET_DEPTH) +#define GetPortErrorCount (0xa300 | HUB_GET_PORT_ERR_COUNT) /* * Generic bandwidth allocation constants/support @@ -622,8 +634,6 @@ extern struct list_head usb_bus_list; extern struct mutex usb_bus_list_lock; extern wait_queue_head_t usb_kill_urb_queue; -extern int usb_find_interface_driver(struct usb_device *dev, - struct usb_interface *interface); #define usb_endpoint_out(ep_dir) (!((ep_dir) & USB_DIR_IN)) diff --git a/kernel/include/linux/usb/msm_hsusb.h b/kernel/include/linux/usb/msm_hsusb.h index 7dbecf9a4..8c8f6854c 100644 --- a/kernel/include/linux/usb/msm_hsusb.h +++ b/kernel/include/linux/usb/msm_hsusb.h @@ -18,6 +18,7 @@ #ifndef __ASM_ARCH_MSM_HSUSB_H #define __ASM_ARCH_MSM_HSUSB_H +#include <linux/extcon.h> #include <linux/types.h> #include <linux/usb/otg.h> #include <linux/clk.h> @@ -120,6 +121,17 @@ struct msm_otg_platform_data { }; /** + * struct msm_usb_cable - structure for exteternal connector cable + * state tracking + * @nb: hold event notification callback + * @conn: used for notification registration + */ +struct msm_usb_cable { + struct notifier_block nb; + struct extcon_dev *extcon; +}; + +/** * struct msm_otg: OTG driver data. Shared by HCD and DCD. * @otg: USB OTG Transceiver structure. * @pdata: otg device platform data. @@ -138,6 +150,15 @@ struct msm_otg_platform_data { * @chg_type: The type of charger attached. * @dcd_retires: The retry count used to track Data contact * detection process. + * @manual_pullup: true if VBUS is not routed to USB controller/phy + * and controller driver therefore enables pull-up explicitly before + * starting controller using usbcmd run/stop bit. + * @vbus: VBUS signal state trakining, using extcon framework + * @id: ID signal state trakining, using extcon framework + * @switch_gpio: Descriptor for GPIO used to control external Dual + * SPDT USB Switch. + * @reboot: Used to inform the driver to route USB D+/D- line to Device + * connector */ struct msm_otg { struct usb_phy phy; @@ -166,6 +187,14 @@ struct msm_otg { struct reset_control *phy_rst; struct reset_control *link_rst; int vdd_levels[3]; + + bool manual_pullup; + + struct msm_usb_cable vbus; + struct msm_usb_cable id; + + struct gpio_desc *switch_gpio; + struct notifier_block reboot; }; #endif diff --git a/kernel/include/linux/usb/msm_hsusb_hw.h b/kernel/include/linux/usb/msm_hsusb_hw.h index a29f6030a..e159b39f6 100644 --- a/kernel/include/linux/usb/msm_hsusb_hw.h +++ b/kernel/include/linux/usb/msm_hsusb_hw.h @@ -21,6 +21,8 @@ #define USB_AHBBURST (MSM_USB_BASE + 0x0090) #define USB_AHBMODE (MSM_USB_BASE + 0x0098) +#define USB_GENCONFIG_2 (MSM_USB_BASE + 0x00a0) + #define USB_CAPLENGTH (MSM_USB_BASE + 0x0100) /* 8 bit */ #define USB_USBCMD (MSM_USB_BASE + 0x0140) @@ -30,6 +32,9 @@ #define USB_PHY_CTRL (MSM_USB_BASE + 0x0240) #define USB_PHY_CTRL2 (MSM_USB_BASE + 0x0278) +#define GENCONFIG_2_SESS_VLD_CTRL_EN BIT(7) +#define USBCMD_SESS_VLD_CTRL BIT(25) + #define USBCMD_RESET 2 #define USB_USBINTR (MSM_USB_BASE + 0x0148) @@ -50,6 +55,10 @@ #define ULPI_PWR_CLK_MNG_REG 0x88 #define OTG_COMP_DISABLE BIT(0) +#define ULPI_MISC_A 0x96 +#define ULPI_MISC_A_VBUSVLDEXTSEL BIT(1) +#define ULPI_MISC_A_VBUSVLDEXT BIT(0) + #define ASYNC_INTR_CTRL (1 << 29) /* Enable async interrupt */ #define ULPI_STP_CTRL (1 << 30) /* Block communication with PHY */ #define PHY_RETEN (1 << 1) /* PHY retention enable/disable */ diff --git a/kernel/include/linux/usb/musb.h b/kernel/include/linux/usb/musb.h index a4ee1b582..fa6dc132b 100644 --- a/kernel/include/linux/usb/musb.h +++ b/kernel/include/linux/usb/musb.h @@ -95,7 +95,7 @@ struct musb_hdrc_config { /* musb CLKIN in Blackfin in MHZ */ unsigned char clkin; #endif - + u32 maximum_speed; }; struct musb_hdrc_platform_data { diff --git a/kernel/include/linux/usb/net2280.h b/kernel/include/linux/usb/net2280.h index 148b8fa5b..725120224 100644 --- a/kernel/include/linux/usb/net2280.h +++ b/kernel/include/linux/usb/net2280.h @@ -168,6 +168,9 @@ struct net2280_regs { #define ENDPOINT_B_INTERRUPT 2 #define ENDPOINT_A_INTERRUPT 1 #define ENDPOINT_0_INTERRUPT 0 +#define USB3380_IRQSTAT0_EP_INTR_MASK_IN (0xF << 17) +#define USB3380_IRQSTAT0_EP_INTR_MASK_OUT (0xF << 1) + u32 irqstat1; #define POWER_STATE_CHANGE_INTERRUPT 27 #define PCI_ARBITER_TIMEOUT_INTERRUPT 26 diff --git a/kernel/include/linux/usb/of.h b/kernel/include/linux/usb/of.h index cfe0528cd..c3fe9e48c 100644 --- a/kernel/include/linux/usb/of.h +++ b/kernel/include/linux/usb/of.h @@ -12,24 +12,19 @@ #include <linux/usb/phy.h> #if IS_ENABLED(CONFIG_OF) -enum usb_dr_mode of_usb_get_dr_mode(struct device_node *np); -enum usb_device_speed of_usb_get_maximum_speed(struct device_node *np); bool of_usb_host_tpl_support(struct device_node *np); +int of_usb_update_otg_caps(struct device_node *np, + struct usb_otg_caps *otg_caps); #else -static inline enum usb_dr_mode of_usb_get_dr_mode(struct device_node *np) -{ - return USB_DR_MODE_UNKNOWN; -} - -static inline enum usb_device_speed -of_usb_get_maximum_speed(struct device_node *np) -{ - return USB_SPEED_UNKNOWN; -} static inline bool of_usb_host_tpl_support(struct device_node *np) { return false; } +static inline int of_usb_update_otg_caps(struct device_node *np, + struct usb_otg_caps *otg_caps) +{ + return 0; +} #endif #if IS_ENABLED(CONFIG_OF) && IS_ENABLED(CONFIG_USB_SUPPORT) diff --git a/kernel/include/linux/usb/otg.h b/kernel/include/linux/usb/otg.h index 52661c5da..67929df86 100644 --- a/kernel/include/linux/usb/otg.h +++ b/kernel/include/linux/usb/otg.h @@ -41,6 +41,21 @@ struct usb_otg { }; +/** + * struct usb_otg_caps - describes the otg capabilities of the device + * @otg_rev: The OTG revision number the device is compliant with, it's + * in binary-coded decimal (i.e. 2.0 is 0200H). + * @hnp_support: Indicates if the device supports HNP. + * @srp_support: Indicates if the device supports SRP. + * @adp_support: Indicates if the device supports ADP. + */ +struct usb_otg_caps { + u16 otg_rev; + bool hnp_support; + bool srp_support; + bool adp_support; +}; + extern const char *usb_otg_state_string(enum usb_otg_state state); /* Context: can sleep */ @@ -104,4 +119,13 @@ enum usb_dr_mode { USB_DR_MODE_OTG, }; +/** + * usb_get_dr_mode - Get dual role mode for given device + * @dev: Pointer to the given device + * + * The function gets phy interface string from property 'dr_mode', + * and returns the correspondig enum usb_dr_mode + */ +extern enum usb_dr_mode usb_get_dr_mode(struct device *dev); + #endif /* __LINUX_USB_OTG_H */ diff --git a/kernel/include/linux/usb/phy.h b/kernel/include/linux/usb/phy.h index bc91b5d38..31a8068c4 100644 --- a/kernel/include/linux/usb/phy.h +++ b/kernel/include/linux/usb/phy.h @@ -63,7 +63,7 @@ enum usb_otg_state { struct usb_phy; struct usb_otg; -/* for transceivers connected thru an ULPI interface, the user must +/* for phys connected thru an ULPI interface, the user must * provide access ops */ struct usb_phy_io_ops { @@ -92,10 +92,10 @@ struct usb_phy { u16 port_status; u16 port_change; - /* to support controllers that have multiple transceivers */ + /* to support controllers that have multiple phys */ struct list_head head; - /* initialize/shutdown the OTG controller */ + /* initialize/shutdown the phy */ int (*init)(struct usb_phy *x); void (*shutdown)(struct usb_phy *x); @@ -106,7 +106,7 @@ struct usb_phy { int (*set_power)(struct usb_phy *x, unsigned mA); - /* Set transceiver into suspend mode */ + /* Set phy into suspend mode */ int (*set_suspend)(struct usb_phy *x, int suspend); @@ -205,6 +205,8 @@ extern struct usb_phy *usb_get_phy_dev(struct device *dev, u8 index); extern struct usb_phy *devm_usb_get_phy_dev(struct device *dev, u8 index); extern struct usb_phy *devm_usb_get_phy_by_phandle(struct device *dev, const char *phandle, u8 index); +extern struct usb_phy *devm_usb_get_phy_by_node(struct device *dev, + struct device_node *node, struct notifier_block *nb); extern void usb_put_phy(struct usb_phy *); extern void devm_usb_put_phy(struct device *dev, struct usb_phy *x); extern int usb_bind_phy(const char *dev_name, u8 index, @@ -238,6 +240,12 @@ static inline struct usb_phy *devm_usb_get_phy_by_phandle(struct device *dev, return ERR_PTR(-ENXIO); } +static inline struct usb_phy *devm_usb_get_phy_by_node(struct device *dev, + struct device_node *node, struct notifier_block *nb) +{ + return ERR_PTR(-ENXIO); +} + static inline void usb_put_phy(struct usb_phy *x) { } diff --git a/kernel/include/linux/usb/quirks.h b/kernel/include/linux/usb/quirks.h index 9948c874e..1d0043dc3 100644 --- a/kernel/include/linux/usb/quirks.h +++ b/kernel/include/linux/usb/quirks.h @@ -47,4 +47,7 @@ /* device generates spurious wakeup, ignore remote wakeup capability */ #define USB_QUIRK_IGNORE_REMOTE_WAKEUP BIT(9) +/* device can't handle Link Power Management */ +#define USB_QUIRK_NO_LPM BIT(10) + #endif /* __LINUX_USB_QUIRKS_H */ diff --git a/kernel/include/linux/usb/renesas_usbhs.h b/kernel/include/linux/usb/renesas_usbhs.h index f06529c14..bfb74723f 100644 --- a/kernel/include/linux/usb/renesas_usbhs.h +++ b/kernel/include/linux/usb/renesas_usbhs.h @@ -157,7 +157,7 @@ struct renesas_usbhs_driver_param { */ int pio_dma_border; /* default is 64byte */ - u32 type; + uintptr_t type; u32 enable_gpio; /* @@ -169,8 +169,7 @@ struct renesas_usbhs_driver_param { #define USBHS_USB_DMAC_XFER_SIZE 32 /* hardcode the xfer size */ }; -#define USBHS_TYPE_R8A7790 1 -#define USBHS_TYPE_R8A7791 2 +#define USBHS_TYPE_RCAR_GEN2 1 /* * option: diff --git a/kernel/include/linux/usb/ulpi.h b/kernel/include/linux/usb/ulpi.h index 5c295c26a..5f07407a3 100644 --- a/kernel/include/linux/usb/ulpi.h +++ b/kernel/include/linux/usb/ulpi.h @@ -12,6 +12,8 @@ #define __LINUX_USB_ULPI_H #include <linux/usb/otg.h> +#include <linux/ulpi/regs.h> + /*-------------------------------------------------------------------------*/ /* @@ -49,138 +51,6 @@ /*-------------------------------------------------------------------------*/ -/* - * Macros for Set and Clear - * See ULPI 1.1 specification to find the registers with Set and Clear offsets - */ -#define ULPI_SET(a) (a + 1) -#define ULPI_CLR(a) (a + 2) - -/*-------------------------------------------------------------------------*/ - -/* - * Register Map - */ -#define ULPI_VENDOR_ID_LOW 0x00 -#define ULPI_VENDOR_ID_HIGH 0x01 -#define ULPI_PRODUCT_ID_LOW 0x02 -#define ULPI_PRODUCT_ID_HIGH 0x03 -#define ULPI_FUNC_CTRL 0x04 -#define ULPI_IFC_CTRL 0x07 -#define ULPI_OTG_CTRL 0x0a -#define ULPI_USB_INT_EN_RISE 0x0d -#define ULPI_USB_INT_EN_FALL 0x10 -#define ULPI_USB_INT_STS 0x13 -#define ULPI_USB_INT_LATCH 0x14 -#define ULPI_DEBUG 0x15 -#define ULPI_SCRATCH 0x16 -/* Optional Carkit Registers */ -#define ULPI_CARCIT_CTRL 0x19 -#define ULPI_CARCIT_INT_DELAY 0x1c -#define ULPI_CARCIT_INT_EN 0x1d -#define ULPI_CARCIT_INT_STS 0x20 -#define ULPI_CARCIT_INT_LATCH 0x21 -#define ULPI_CARCIT_PLS_CTRL 0x22 -/* Other Optional Registers */ -#define ULPI_TX_POS_WIDTH 0x25 -#define ULPI_TX_NEG_WIDTH 0x26 -#define ULPI_POLARITY_RECOVERY 0x27 -/* Access Extended Register Set */ -#define ULPI_ACCESS_EXTENDED 0x2f -/* Vendor Specific */ -#define ULPI_VENDOR_SPECIFIC 0x30 -/* Extended Registers */ -#define ULPI_EXT_VENDOR_SPECIFIC 0x80 - -/*-------------------------------------------------------------------------*/ - -/* - * Register Bits - */ - -/* Function Control */ -#define ULPI_FUNC_CTRL_XCVRSEL (1 << 0) -#define ULPI_FUNC_CTRL_XCVRSEL_MASK (3 << 0) -#define ULPI_FUNC_CTRL_HIGH_SPEED (0 << 0) -#define ULPI_FUNC_CTRL_FULL_SPEED (1 << 0) -#define ULPI_FUNC_CTRL_LOW_SPEED (2 << 0) -#define ULPI_FUNC_CTRL_FS4LS (3 << 0) -#define ULPI_FUNC_CTRL_TERMSELECT (1 << 2) -#define ULPI_FUNC_CTRL_OPMODE (1 << 3) -#define ULPI_FUNC_CTRL_OPMODE_MASK (3 << 3) -#define ULPI_FUNC_CTRL_OPMODE_NORMAL (0 << 3) -#define ULPI_FUNC_CTRL_OPMODE_NONDRIVING (1 << 3) -#define ULPI_FUNC_CTRL_OPMODE_DISABLE_NRZI (2 << 3) -#define ULPI_FUNC_CTRL_OPMODE_NOSYNC_NOEOP (3 << 3) -#define ULPI_FUNC_CTRL_RESET (1 << 5) -#define ULPI_FUNC_CTRL_SUSPENDM (1 << 6) - -/* Interface Control */ -#define ULPI_IFC_CTRL_6_PIN_SERIAL_MODE (1 << 0) -#define ULPI_IFC_CTRL_3_PIN_SERIAL_MODE (1 << 1) -#define ULPI_IFC_CTRL_CARKITMODE (1 << 2) -#define ULPI_IFC_CTRL_CLOCKSUSPENDM (1 << 3) -#define ULPI_IFC_CTRL_AUTORESUME (1 << 4) -#define ULPI_IFC_CTRL_EXTERNAL_VBUS (1 << 5) -#define ULPI_IFC_CTRL_PASSTHRU (1 << 6) -#define ULPI_IFC_CTRL_PROTECT_IFC_DISABLE (1 << 7) - -/* OTG Control */ -#define ULPI_OTG_CTRL_ID_PULLUP (1 << 0) -#define ULPI_OTG_CTRL_DP_PULLDOWN (1 << 1) -#define ULPI_OTG_CTRL_DM_PULLDOWN (1 << 2) -#define ULPI_OTG_CTRL_DISCHRGVBUS (1 << 3) -#define ULPI_OTG_CTRL_CHRGVBUS (1 << 4) -#define ULPI_OTG_CTRL_DRVVBUS (1 << 5) -#define ULPI_OTG_CTRL_DRVVBUS_EXT (1 << 6) -#define ULPI_OTG_CTRL_EXTVBUSIND (1 << 7) - -/* USB Interrupt Enable Rising, - * USB Interrupt Enable Falling, - * USB Interrupt Status and - * USB Interrupt Latch - */ -#define ULPI_INT_HOST_DISCONNECT (1 << 0) -#define ULPI_INT_VBUS_VALID (1 << 1) -#define ULPI_INT_SESS_VALID (1 << 2) -#define ULPI_INT_SESS_END (1 << 3) -#define ULPI_INT_IDGRD (1 << 4) - -/* Debug */ -#define ULPI_DEBUG_LINESTATE0 (1 << 0) -#define ULPI_DEBUG_LINESTATE1 (1 << 1) - -/* Carkit Control */ -#define ULPI_CARKIT_CTRL_CARKITPWR (1 << 0) -#define ULPI_CARKIT_CTRL_IDGNDDRV (1 << 1) -#define ULPI_CARKIT_CTRL_TXDEN (1 << 2) -#define ULPI_CARKIT_CTRL_RXDEN (1 << 3) -#define ULPI_CARKIT_CTRL_SPKLEFTEN (1 << 4) -#define ULPI_CARKIT_CTRL_SPKRIGHTEN (1 << 5) -#define ULPI_CARKIT_CTRL_MICEN (1 << 6) - -/* Carkit Interrupt Enable */ -#define ULPI_CARKIT_INT_EN_IDFLOAT_RISE (1 << 0) -#define ULPI_CARKIT_INT_EN_IDFLOAT_FALL (1 << 1) -#define ULPI_CARKIT_INT_EN_CARINTDET (1 << 2) -#define ULPI_CARKIT_INT_EN_DP_RISE (1 << 3) -#define ULPI_CARKIT_INT_EN_DP_FALL (1 << 4) - -/* Carkit Interrupt Status and - * Carkit Interrupt Latch - */ -#define ULPI_CARKIT_INT_IDFLOAT (1 << 0) -#define ULPI_CARKIT_INT_CARINTDET (1 << 1) -#define ULPI_CARKIT_INT_DP (1 << 2) - -/* Carkit Pulse Control*/ -#define ULPI_CARKIT_PLS_CTRL_TXPLSEN (1 << 0) -#define ULPI_CARKIT_PLS_CTRL_RXPLSEN (1 << 1) -#define ULPI_CARKIT_PLS_CTRL_SPKRLEFT_BIASEN (1 << 2) -#define ULPI_CARKIT_PLS_CTRL_SPKRRIGHT_BIASEN (1 << 3) - -/*-------------------------------------------------------------------------*/ - #if IS_ENABLED(CONFIG_USB_ULPI) struct usb_phy *otg_ulpi_create(struct usb_phy_io_ops *ops, unsigned int flags); diff --git a/kernel/include/linux/usb/usb338x.h b/kernel/include/linux/usb/usb338x.h index f92eb635b..11525d8d8 100644 --- a/kernel/include/linux/usb/usb338x.h +++ b/kernel/include/linux/usb/usb338x.h @@ -43,6 +43,10 @@ #define IN_ENDPOINT_TYPE 12 #define OUT_ENDPOINT_ENABLE 10 #define OUT_ENDPOINT_TYPE 8 +#define USB3380_EP_CFG_MASK_IN ((0x3 << IN_ENDPOINT_TYPE) | \ + BIT(IN_ENDPOINT_ENABLE)) +#define USB3380_EP_CFG_MASK_OUT ((0x3 << OUT_ENDPOINT_TYPE) | \ + BIT(OUT_ENDPOINT_ENABLE)) struct usb338x_usb_ext_regs { u32 usbclass; diff --git a/kernel/include/linux/userfaultfd_k.h b/kernel/include/linux/userfaultfd_k.h new file mode 100644 index 000000000..587480ad4 --- /dev/null +++ b/kernel/include/linux/userfaultfd_k.h @@ -0,0 +1,85 @@ +/* + * include/linux/userfaultfd_k.h + * + * Copyright (C) 2015 Red Hat, Inc. + * + */ + +#ifndef _LINUX_USERFAULTFD_K_H +#define _LINUX_USERFAULTFD_K_H + +#ifdef CONFIG_USERFAULTFD + +#include <linux/userfaultfd.h> /* linux/include/uapi/linux/userfaultfd.h */ + +#include <linux/fcntl.h> + +/* + * CAREFUL: Check include/uapi/asm-generic/fcntl.h when defining + * new flags, since they might collide with O_* ones. We want + * to re-use O_* flags that couldn't possibly have a meaning + * from userfaultfd, in order to leave a free define-space for + * shared O_* flags. + */ +#define UFFD_CLOEXEC O_CLOEXEC +#define UFFD_NONBLOCK O_NONBLOCK + +#define UFFD_SHARED_FCNTL_FLAGS (O_CLOEXEC | O_NONBLOCK) +#define UFFD_FLAGS_SET (EFD_SHARED_FCNTL_FLAGS) + +extern int handle_userfault(struct vm_area_struct *vma, unsigned long address, + unsigned int flags, unsigned long reason); + +extern ssize_t mcopy_atomic(struct mm_struct *dst_mm, unsigned long dst_start, + unsigned long src_start, unsigned long len); +extern ssize_t mfill_zeropage(struct mm_struct *dst_mm, + unsigned long dst_start, + unsigned long len); + +/* mm helpers */ +static inline bool is_mergeable_vm_userfaultfd_ctx(struct vm_area_struct *vma, + struct vm_userfaultfd_ctx vm_ctx) +{ + return vma->vm_userfaultfd_ctx.ctx == vm_ctx.ctx; +} + +static inline bool userfaultfd_missing(struct vm_area_struct *vma) +{ + return vma->vm_flags & VM_UFFD_MISSING; +} + +static inline bool userfaultfd_armed(struct vm_area_struct *vma) +{ + return vma->vm_flags & (VM_UFFD_MISSING | VM_UFFD_WP); +} + +#else /* CONFIG_USERFAULTFD */ + +/* mm helpers */ +static inline int handle_userfault(struct vm_area_struct *vma, + unsigned long address, + unsigned int flags, + unsigned long reason) +{ + return VM_FAULT_SIGBUS; +} + +static inline bool is_mergeable_vm_userfaultfd_ctx(struct vm_area_struct *vma, + struct vm_userfaultfd_ctx vm_ctx) +{ + return true; +} + +static inline bool userfaultfd_missing(struct vm_area_struct *vma) +{ + return false; +} + +static inline bool userfaultfd_armed(struct vm_area_struct *vma) +{ + return false; +} + +#endif /* CONFIG_USERFAULTFD */ + +#endif /* _LINUX_USERFAULTFD_K_H */ diff --git a/kernel/include/linux/verify_pefile.h b/kernel/include/linux/verify_pefile.h index ac3481921..da2049b51 100644 --- a/kernel/include/linux/verify_pefile.h +++ b/kernel/include/linux/verify_pefile.h @@ -12,7 +12,11 @@ #ifndef _LINUX_VERIFY_PEFILE_H #define _LINUX_VERIFY_PEFILE_H +#include <crypto/public_key.h> + extern int verify_pefile_signature(const void *pebuf, unsigned pelen, - struct key *trusted_keyring, bool *_trusted); + struct key *trusted_keyring, + enum key_being_used_for usage, + bool *_trusted); #endif /* _LINUX_VERIFY_PEFILE_H */ diff --git a/kernel/include/linux/vga_switcheroo.h b/kernel/include/linux/vga_switcheroo.h index b483abd34..69e1d4a1f 100644 --- a/kernel/include/linux/vga_switcheroo.h +++ b/kernel/include/linux/vga_switcheroo.h @@ -1,10 +1,31 @@ /* + * vga_switcheroo.h - Support for laptop with dual GPU using one set of outputs + * * Copyright (c) 2010 Red Hat Inc. * Author : Dave Airlie <airlied@redhat.com> * - * Licensed under GPLv2 + * Copyright (c) 2015 Lukas Wunner <lukas@wunner.de> + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice (including the next + * paragraph) shall be included in all copies or substantial portions of the + * Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER + * DEALINGS + * IN THE SOFTWARE. * - * vga_switcheroo.h - Support for laptop with dual GPU using one set of outputs */ #ifndef _LINUX_VGA_SWITCHEROO_H_ @@ -14,28 +35,85 @@ struct pci_dev; +/** + * enum vga_switcheroo_state - client power state + * @VGA_SWITCHEROO_OFF: off + * @VGA_SWITCHEROO_ON: on + * @VGA_SWITCHEROO_NOT_FOUND: client has not registered with vga_switcheroo. + * Only used in vga_switcheroo_get_client_state() which in turn is only + * called from hda_intel.c + * + * Client power state. + */ enum vga_switcheroo_state { VGA_SWITCHEROO_OFF, VGA_SWITCHEROO_ON, /* below are referred only from vga_switcheroo_get_client_state() */ - VGA_SWITCHEROO_INIT, VGA_SWITCHEROO_NOT_FOUND, }; +/** + * enum vga_switcheroo_client_id - client identifier + * @VGA_SWITCHEROO_UNKNOWN_ID: initial identifier assigned to vga clients. + * Determining the id requires the handler, so GPUs are given their + * true id in a delayed fashion in vga_switcheroo_enable() + * @VGA_SWITCHEROO_IGD: integrated graphics device + * @VGA_SWITCHEROO_DIS: discrete graphics device + * @VGA_SWITCHEROO_MAX_CLIENTS: currently no more than two GPUs are supported + * + * Client identifier. Audio clients use the same identifier & 0x100. + */ enum vga_switcheroo_client_id { + VGA_SWITCHEROO_UNKNOWN_ID = -1, VGA_SWITCHEROO_IGD, VGA_SWITCHEROO_DIS, VGA_SWITCHEROO_MAX_CLIENTS, }; +/** + * struct vga_switcheroo_handler - handler callbacks + * @init: initialize handler. + * Optional. This gets called when vga_switcheroo is enabled, i.e. when + * two vga clients have registered. It allows the handler to perform + * some delayed initialization that depends on the existence of the + * vga clients. Currently only the radeon and amdgpu drivers use this. + * The return value is ignored + * @switchto: switch outputs to given client. + * Mandatory. For muxless machines this should be a no-op. Returning 0 + * denotes success, anything else failure (in which case the switch is + * aborted) + * @power_state: cut or reinstate power of given client. + * Optional. The return value is ignored + * @get_client_id: determine if given pci device is integrated or discrete GPU. + * Mandatory + * + * Handler callbacks. The multiplexer itself. The @switchto and @get_client_id + * methods are mandatory, all others may be set to NULL. + */ struct vga_switcheroo_handler { + int (*init)(void); int (*switchto)(enum vga_switcheroo_client_id id); int (*power_state)(enum vga_switcheroo_client_id id, enum vga_switcheroo_state state); - int (*init)(void); - int (*get_client_id)(struct pci_dev *pdev); + enum vga_switcheroo_client_id (*get_client_id)(struct pci_dev *pdev); }; +/** + * struct vga_switcheroo_client_ops - client callbacks + * @set_gpu_state: do the equivalent of suspend/resume for the card. + * Mandatory. This should not cut power to the discrete GPU, + * which is the job of the handler + * @reprobe: poll outputs. + * Optional. This gets called after waking the GPU and switching + * the outputs to it + * @can_switch: check if the device is in a position to switch now. + * Mandatory. The client should return false if a user space process + * has one of its device files open + * + * Client callbacks. A client can be either a GPU or an audio device on a GPU. + * The @set_gpu_state and @can_switch methods are mandatory, @reprobe may be + * set to NULL. For audio clients, the @reprobe member is bogus. + */ struct vga_switcheroo_client_ops { void (*set_gpu_state)(struct pci_dev *dev, enum vga_switcheroo_state); void (*reprobe)(struct pci_dev *dev); @@ -49,17 +127,17 @@ int vga_switcheroo_register_client(struct pci_dev *dev, bool driver_power_control); int vga_switcheroo_register_audio_client(struct pci_dev *pdev, const struct vga_switcheroo_client_ops *ops, - int id, bool active); + enum vga_switcheroo_client_id id); void vga_switcheroo_client_fb_set(struct pci_dev *dev, struct fb_info *info); -int vga_switcheroo_register_handler(struct vga_switcheroo_handler *handler); +int vga_switcheroo_register_handler(const struct vga_switcheroo_handler *handler); void vga_switcheroo_unregister_handler(void); int vga_switcheroo_process_delayed_switch(void); -int vga_switcheroo_get_client_state(struct pci_dev *dev); +enum vga_switcheroo_state vga_switcheroo_get_client_state(struct pci_dev *dev); void vga_switcheroo_set_dynamic_switch(struct pci_dev *pdev, enum vga_switcheroo_state dynamic); @@ -72,13 +150,13 @@ static inline void vga_switcheroo_unregister_client(struct pci_dev *dev) {} static inline int vga_switcheroo_register_client(struct pci_dev *dev, const struct vga_switcheroo_client_ops *ops, bool driver_power_control) { return 0; } static inline void vga_switcheroo_client_fb_set(struct pci_dev *dev, struct fb_info *info) {} -static inline int vga_switcheroo_register_handler(struct vga_switcheroo_handler *handler) { return 0; } +static inline int vga_switcheroo_register_handler(const struct vga_switcheroo_handler *handler) { return 0; } static inline int vga_switcheroo_register_audio_client(struct pci_dev *pdev, const struct vga_switcheroo_client_ops *ops, - int id, bool active) { return 0; } + enum vga_switcheroo_client_id id) { return 0; } static inline void vga_switcheroo_unregister_handler(void) {} static inline int vga_switcheroo_process_delayed_switch(void) { return 0; } -static inline int vga_switcheroo_get_client_state(struct pci_dev *dev) { return VGA_SWITCHEROO_ON; } +static inline enum vga_switcheroo_state vga_switcheroo_get_client_state(struct pci_dev *dev) { return VGA_SWITCHEROO_ON; } static inline void vga_switcheroo_set_dynamic_switch(struct pci_dev *pdev, enum vga_switcheroo_state dynamic) {} diff --git a/kernel/include/linux/virtio_byteorder.h b/kernel/include/linux/virtio_byteorder.h index 51865d05b..ce63a2c3a 100644 --- a/kernel/include/linux/virtio_byteorder.h +++ b/kernel/include/linux/virtio_byteorder.h @@ -3,17 +3,21 @@ #include <linux/types.h> #include <uapi/linux/virtio_types.h> -/* - * Low-level memory accessors for handling virtio in modern little endian and in - * compatibility native endian format. - */ +static inline bool virtio_legacy_is_little_endian(void) +{ +#ifdef __LITTLE_ENDIAN + return true; +#else + return false; +#endif +} static inline u16 __virtio16_to_cpu(bool little_endian, __virtio16 val) { if (little_endian) return le16_to_cpu((__force __le16)val); else - return (__force u16)val; + return be16_to_cpu((__force __be16)val); } static inline __virtio16 __cpu_to_virtio16(bool little_endian, u16 val) @@ -21,7 +25,7 @@ static inline __virtio16 __cpu_to_virtio16(bool little_endian, u16 val) if (little_endian) return (__force __virtio16)cpu_to_le16(val); else - return (__force __virtio16)val; + return (__force __virtio16)cpu_to_be16(val); } static inline u32 __virtio32_to_cpu(bool little_endian, __virtio32 val) @@ -29,7 +33,7 @@ static inline u32 __virtio32_to_cpu(bool little_endian, __virtio32 val) if (little_endian) return le32_to_cpu((__force __le32)val); else - return (__force u32)val; + return be32_to_cpu((__force __be32)val); } static inline __virtio32 __cpu_to_virtio32(bool little_endian, u32 val) @@ -37,7 +41,7 @@ static inline __virtio32 __cpu_to_virtio32(bool little_endian, u32 val) if (little_endian) return (__force __virtio32)cpu_to_le32(val); else - return (__force __virtio32)val; + return (__force __virtio32)cpu_to_be32(val); } static inline u64 __virtio64_to_cpu(bool little_endian, __virtio64 val) @@ -45,7 +49,7 @@ static inline u64 __virtio64_to_cpu(bool little_endian, __virtio64 val) if (little_endian) return le64_to_cpu((__force __le64)val); else - return (__force u64)val; + return be64_to_cpu((__force __be64)val); } static inline __virtio64 __cpu_to_virtio64(bool little_endian, u64 val) @@ -53,7 +57,7 @@ static inline __virtio64 __cpu_to_virtio64(bool little_endian, u64 val) if (little_endian) return (__force __virtio64)cpu_to_le64(val); else - return (__force __virtio64)val; + return (__force __virtio64)cpu_to_be64(val); } #endif /* _LINUX_VIRTIO_BYTEORDER */ diff --git a/kernel/include/linux/virtio_config.h b/kernel/include/linux/virtio_config.h index 1e306f727..e5ce8ab0b 100644 --- a/kernel/include/linux/virtio_config.h +++ b/kernel/include/linux/virtio_config.h @@ -205,35 +205,41 @@ int virtqueue_set_affinity(struct virtqueue *vq, int cpu) return 0; } +static inline bool virtio_is_little_endian(struct virtio_device *vdev) +{ + return virtio_has_feature(vdev, VIRTIO_F_VERSION_1) || + virtio_legacy_is_little_endian(); +} + /* Memory accessors */ static inline u16 virtio16_to_cpu(struct virtio_device *vdev, __virtio16 val) { - return __virtio16_to_cpu(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val); + return __virtio16_to_cpu(virtio_is_little_endian(vdev), val); } static inline __virtio16 cpu_to_virtio16(struct virtio_device *vdev, u16 val) { - return __cpu_to_virtio16(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val); + return __cpu_to_virtio16(virtio_is_little_endian(vdev), val); } static inline u32 virtio32_to_cpu(struct virtio_device *vdev, __virtio32 val) { - return __virtio32_to_cpu(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val); + return __virtio32_to_cpu(virtio_is_little_endian(vdev), val); } static inline __virtio32 cpu_to_virtio32(struct virtio_device *vdev, u32 val) { - return __cpu_to_virtio32(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val); + return __cpu_to_virtio32(virtio_is_little_endian(vdev), val); } static inline u64 virtio64_to_cpu(struct virtio_device *vdev, __virtio64 val) { - return __virtio64_to_cpu(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val); + return __virtio64_to_cpu(virtio_is_little_endian(vdev), val); } static inline __virtio64 cpu_to_virtio64(struct virtio_device *vdev, u64 val) { - return __cpu_to_virtio64(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val); + return __cpu_to_virtio64(virtio_is_little_endian(vdev), val); } /* Config space accessors. */ diff --git a/kernel/include/linux/vm_event_item.h b/kernel/include/linux/vm_event_item.h index 9246d32dc..e623d392d 100644 --- a/kernel/include/linux/vm_event_item.h +++ b/kernel/include/linux/vm_event_item.h @@ -14,12 +14,12 @@ #endif #ifdef CONFIG_HIGHMEM -#define HIGHMEM_ZONE(xx) , xx##_HIGH +#define HIGHMEM_ZONE(xx) xx##_HIGH, #else #define HIGHMEM_ZONE(xx) #endif -#define FOR_ALL_ZONES(xx) DMA_ZONE(xx) DMA32_ZONE(xx) xx##_NORMAL HIGHMEM_ZONE(xx) , xx##_MOVABLE +#define FOR_ALL_ZONES(xx) DMA_ZONE(xx) DMA32_ZONE(xx) xx##_NORMAL, HIGHMEM_ZONE(xx) xx##_MOVABLE enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, FOR_ALL_ZONES(PGALLOC), diff --git a/kernel/include/linux/vmalloc.h b/kernel/include/linux/vmalloc.h index 0ec598381..3bff87a25 100644 --- a/kernel/include/linux/vmalloc.h +++ b/kernel/include/linux/vmalloc.h @@ -182,22 +182,10 @@ pcpu_free_vm_areas(struct vm_struct **vms, int nr_vms) # endif #endif -struct vmalloc_info { - unsigned long used; - unsigned long largest_chunk; -}; - #ifdef CONFIG_MMU #define VMALLOC_TOTAL (VMALLOC_END - VMALLOC_START) -extern void get_vmalloc_info(struct vmalloc_info *vmi); #else - #define VMALLOC_TOTAL 0UL -#define get_vmalloc_info(vmi) \ -do { \ - (vmi)->used = 0; \ - (vmi)->largest_chunk = 0; \ -} while (0) #endif #endif /* _LINUX_VMALLOC_H */ diff --git a/kernel/include/linux/vme.h b/kernel/include/linux/vme.h index 79242e9c0..71e4a6dec 100644 --- a/kernel/include/linux/vme.h +++ b/kernel/include/linux/vme.h @@ -81,6 +81,9 @@ struct vme_resource { extern struct bus_type vme_bus_type; +/* Number of VME interrupt vectors */ +#define VME_NUM_STATUSID 256 + /* VME_MAX_BRIDGES comes from the type of vme_bus_numbers */ #define VME_MAX_BRIDGES (sizeof(unsigned int)*8) #define VME_MAX_SLOTS 32 @@ -120,6 +123,8 @@ void vme_free_consistent(struct vme_resource *, size_t, void *, dma_addr_t); size_t vme_get_size(struct vme_resource *); +int vme_check_window(u32 aspace, unsigned long long vme_base, + unsigned long long size); struct vme_resource *vme_slave_request(struct vme_dev *, u32, u32); int vme_slave_set(struct vme_resource *, int, unsigned long long, diff --git a/kernel/include/linux/vmstat.h b/kernel/include/linux/vmstat.h index 3feaf770a..7eaa847cd 100644 --- a/kernel/include/linux/vmstat.h +++ b/kernel/include/linux/vmstat.h @@ -165,30 +165,8 @@ static inline unsigned long zone_page_state_snapshot(struct zone *zone, } #ifdef CONFIG_NUMA -/* - * Determine the per node value of a stat item. This function - * is called frequently in a NUMA machine, so try to be as - * frugal as possible. - */ -static inline unsigned long node_page_state(int node, - enum zone_stat_item item) -{ - struct zone *zones = NODE_DATA(node)->node_zones; - - return -#ifdef CONFIG_ZONE_DMA - zone_page_state(&zones[ZONE_DMA], item) + -#endif -#ifdef CONFIG_ZONE_DMA32 - zone_page_state(&zones[ZONE_DMA32], item) + -#endif -#ifdef CONFIG_HIGHMEM - zone_page_state(&zones[ZONE_HIGHMEM], item) + -#endif - zone_page_state(&zones[ZONE_NORMAL], item) + - zone_page_state(&zones[ZONE_MOVABLE], item); -} +extern unsigned long node_page_state(int node, enum zone_stat_item item); extern void zone_statistics(struct zone *, struct zone *, gfp_t gfp); #else @@ -202,11 +180,11 @@ extern void zone_statistics(struct zone *, struct zone *, gfp_t gfp); #define sub_zone_page_state(__z, __i, __d) mod_zone_page_state(__z, __i, -(__d)) #ifdef CONFIG_SMP -void __mod_zone_page_state(struct zone *, enum zone_stat_item item, int); +void __mod_zone_page_state(struct zone *, enum zone_stat_item item, long); void __inc_zone_page_state(struct page *, enum zone_stat_item); void __dec_zone_page_state(struct page *, enum zone_stat_item); -void mod_zone_page_state(struct zone *, enum zone_stat_item, int); +void mod_zone_page_state(struct zone *, enum zone_stat_item, long); void inc_zone_page_state(struct page *, enum zone_stat_item); void dec_zone_page_state(struct page *, enum zone_stat_item); @@ -231,7 +209,7 @@ void set_pgdat_percpu_threshold(pg_data_t *pgdat, * The functions directly modify the zone and global counters. */ static inline void __mod_zone_page_state(struct zone *zone, - enum zone_stat_item item, int delta) + enum zone_stat_item item, long delta) { zone_page_state_add(delta, zone, item); } @@ -273,7 +251,6 @@ static inline void __dec_zone_page_state(struct page *page, #define set_pgdat_percpu_threshold(pgdat, callback) { } -static inline void refresh_cpu_vm_stats(int cpu) { } static inline void refresh_zone_stat_thresholds(void) { } static inline void cpu_vm_stats_fold(int cpu) { } diff --git a/kernel/include/linux/vringh.h b/kernel/include/linux/vringh.h index a3fa537e7..bc6c28d04 100644 --- a/kernel/include/linux/vringh.h +++ b/kernel/include/linux/vringh.h @@ -226,33 +226,39 @@ static inline void vringh_notify(struct vringh *vrh) vrh->notify(vrh); } +static inline bool vringh_is_little_endian(const struct vringh *vrh) +{ + return vrh->little_endian || + virtio_legacy_is_little_endian(); +} + static inline u16 vringh16_to_cpu(const struct vringh *vrh, __virtio16 val) { - return __virtio16_to_cpu(vrh->little_endian, val); + return __virtio16_to_cpu(vringh_is_little_endian(vrh), val); } static inline __virtio16 cpu_to_vringh16(const struct vringh *vrh, u16 val) { - return __cpu_to_virtio16(vrh->little_endian, val); + return __cpu_to_virtio16(vringh_is_little_endian(vrh), val); } static inline u32 vringh32_to_cpu(const struct vringh *vrh, __virtio32 val) { - return __virtio32_to_cpu(vrh->little_endian, val); + return __virtio32_to_cpu(vringh_is_little_endian(vrh), val); } static inline __virtio32 cpu_to_vringh32(const struct vringh *vrh, u32 val) { - return __cpu_to_virtio32(vrh->little_endian, val); + return __cpu_to_virtio32(vringh_is_little_endian(vrh), val); } static inline u64 vringh64_to_cpu(const struct vringh *vrh, __virtio64 val) { - return __virtio64_to_cpu(vrh->little_endian, val); + return __virtio64_to_cpu(vringh_is_little_endian(vrh), val); } static inline __virtio64 cpu_to_vringh64(const struct vringh *vrh, u64 val) { - return __cpu_to_virtio64(vrh->little_endian, val); + return __cpu_to_virtio64(vringh_is_little_endian(vrh), val); } #endif /* _LINUX_VRINGH_H */ diff --git a/kernel/include/linux/wait-simple.h b/kernel/include/linux/wait-simple.h deleted file mode 100644 index f86bca2c4..000000000 --- a/kernel/include/linux/wait-simple.h +++ /dev/null @@ -1,207 +0,0 @@ -#ifndef _LINUX_WAIT_SIMPLE_H -#define _LINUX_WAIT_SIMPLE_H - -#include <linux/spinlock.h> -#include <linux/list.h> - -#include <asm/current.h> - -struct swaiter { - struct task_struct *task; - struct list_head node; -}; - -#define DEFINE_SWAITER(name) \ - struct swaiter name = { \ - .task = current, \ - .node = LIST_HEAD_INIT((name).node), \ - } - -struct swait_head { - raw_spinlock_t lock; - struct list_head list; -}; - -#define SWAIT_HEAD_INITIALIZER(name) { \ - .lock = __RAW_SPIN_LOCK_UNLOCKED(name.lock), \ - .list = LIST_HEAD_INIT((name).list), \ - } - -#define DEFINE_SWAIT_HEAD(name) \ - struct swait_head name = SWAIT_HEAD_INITIALIZER(name) - -extern void __init_swait_head(struct swait_head *h, struct lock_class_key *key); - -#define init_swait_head(swh) \ - do { \ - static struct lock_class_key __key; \ - \ - __init_swait_head((swh), &__key); \ - } while (0) - -/* - * Waiter functions - */ -extern void swait_prepare_locked(struct swait_head *head, struct swaiter *w); -extern void swait_prepare(struct swait_head *head, struct swaiter *w, int state); -extern void swait_finish_locked(struct swait_head *head, struct swaiter *w); -extern void swait_finish(struct swait_head *head, struct swaiter *w); - -/* Check whether a head has waiters enqueued */ -static inline bool swaitqueue_active(struct swait_head *h) -{ - /* Make sure the condition is visible before checking list_empty() */ - smp_mb(); - return !list_empty(&h->list); -} - -/* - * Wakeup functions - */ -extern unsigned int __swait_wake(struct swait_head *head, unsigned int state, unsigned int num); -extern unsigned int __swait_wake_locked(struct swait_head *head, unsigned int state, unsigned int num); - -#define swait_wake(head) __swait_wake(head, TASK_NORMAL, 1) -#define swait_wake_interruptible(head) __swait_wake(head, TASK_INTERRUPTIBLE, 1) -#define swait_wake_all(head) __swait_wake(head, TASK_NORMAL, 0) -#define swait_wake_all_interruptible(head) __swait_wake(head, TASK_INTERRUPTIBLE, 0) - -/* - * Event API - */ -#define __swait_event(wq, condition) \ -do { \ - DEFINE_SWAITER(__wait); \ - \ - for (;;) { \ - swait_prepare(&wq, &__wait, TASK_UNINTERRUPTIBLE); \ - if (condition) \ - break; \ - schedule(); \ - } \ - swait_finish(&wq, &__wait); \ -} while (0) - -/** - * swait_event - sleep until a condition gets true - * @wq: the waitqueue to wait on - * @condition: a C expression for the event to wait for - * - * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the - * @condition evaluates to true. The @condition is checked each time - * the waitqueue @wq is woken up. - * - * wake_up() has to be called after changing any variable that could - * change the result of the wait condition. - */ -#define swait_event(wq, condition) \ -do { \ - if (condition) \ - break; \ - __swait_event(wq, condition); \ -} while (0) - -#define __swait_event_interruptible(wq, condition, ret) \ -do { \ - DEFINE_SWAITER(__wait); \ - \ - for (;;) { \ - swait_prepare(&wq, &__wait, TASK_INTERRUPTIBLE); \ - if (condition) \ - break; \ - if (signal_pending(current)) { \ - ret = -ERESTARTSYS; \ - break; \ - } \ - schedule(); \ - } \ - swait_finish(&wq, &__wait); \ -} while (0) - -#define __swait_event_interruptible_timeout(wq, condition, ret) \ -do { \ - DEFINE_SWAITER(__wait); \ - \ - for (;;) { \ - swait_prepare(&wq, &__wait, TASK_INTERRUPTIBLE); \ - if (condition) \ - break; \ - if (signal_pending(current)) { \ - ret = -ERESTARTSYS; \ - break; \ - } \ - ret = schedule_timeout(ret); \ - if (!ret) \ - break; \ - } \ - swait_finish(&wq, &__wait); \ -} while (0) - -/** - * swait_event_interruptible - sleep until a condition gets true - * @wq: the waitqueue to wait on - * @condition: a C expression for the event to wait for - * - * The process is put to sleep (TASK_INTERRUPTIBLE) until the - * @condition evaluates to true. The @condition is checked each time - * the waitqueue @wq is woken up. - * - * wake_up() has to be called after changing any variable that could - * change the result of the wait condition. - */ -#define swait_event_interruptible(wq, condition) \ -({ \ - int __ret = 0; \ - if (!(condition)) \ - __swait_event_interruptible(wq, condition, __ret); \ - __ret; \ -}) - -#define swait_event_interruptible_timeout(wq, condition, timeout) \ -({ \ - int __ret = timeout; \ - if (!(condition)) \ - __swait_event_interruptible_timeout(wq, condition, __ret); \ - __ret; \ -}) - -#define __swait_event_timeout(wq, condition, ret) \ -do { \ - DEFINE_SWAITER(__wait); \ - \ - for (;;) { \ - swait_prepare(&wq, &__wait, TASK_UNINTERRUPTIBLE); \ - if (condition) \ - break; \ - ret = schedule_timeout(ret); \ - if (!ret) \ - break; \ - } \ - swait_finish(&wq, &__wait); \ -} while (0) - -/** - * swait_event_timeout - sleep until a condition gets true or a timeout elapses - * @wq: the waitqueue to wait on - * @condition: a C expression for the event to wait for - * @timeout: timeout, in jiffies - * - * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the - * @condition evaluates to true. The @condition is checked each time - * the waitqueue @wq is woken up. - * - * wake_up() has to be called after changing any variable that could - * change the result of the wait condition. - * - * The function returns 0 if the @timeout elapsed, and the remaining - * jiffies if the condition evaluated to true before the timeout elapsed. - */ -#define swait_event_timeout(wq, condition, timeout) \ -({ \ - long __ret = timeout; \ - if (!(condition)) \ - __swait_event_timeout(wq, condition, __ret); \ - __ret; \ -}) - -#endif diff --git a/kernel/include/linux/wait.h b/kernel/include/linux/wait.h index b3b54c26b..981c8a840 100644 --- a/kernel/include/linux/wait.h +++ b/kernel/include/linux/wait.h @@ -146,7 +146,7 @@ __remove_wait_queue(wait_queue_head_t *head, wait_queue_t *old) list_del(&old->task_list); } -typedef int wait_bit_action_f(struct wait_bit_key *); +typedef int wait_bit_action_f(struct wait_bit_key *, int mode); void __wake_up(wait_queue_head_t *q, unsigned int mode, int nr, void *key); void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key); void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode, int nr, void *key); @@ -359,6 +359,19 @@ do { \ __ret; \ }) +#define __wait_event_exclusive_cmd(wq, condition, cmd1, cmd2) \ + (void)___wait_event(wq, condition, TASK_UNINTERRUPTIBLE, 1, 0, \ + cmd1; schedule(); cmd2) +/* + * Just like wait_event_cmd(), except it sets exclusive flag + */ +#define wait_event_exclusive_cmd(wq, condition, cmd1, cmd2) \ +do { \ + if (condition) \ + break; \ + __wait_event_exclusive_cmd(wq, condition, cmd1, cmd2); \ +} while (0) + #define __wait_event_cmd(wq, condition, cmd1, cmd2) \ (void)___wait_event(wq, condition, TASK_UNINTERRUPTIBLE, 0, 0, \ cmd1; schedule(); cmd2) @@ -948,10 +961,10 @@ int wake_bit_function(wait_queue_t *wait, unsigned mode, int sync, void *key); } while (0) -extern int bit_wait(struct wait_bit_key *); -extern int bit_wait_io(struct wait_bit_key *); -extern int bit_wait_timeout(struct wait_bit_key *); -extern int bit_wait_io_timeout(struct wait_bit_key *); +extern int bit_wait(struct wait_bit_key *, int); +extern int bit_wait_io(struct wait_bit_key *, int); +extern int bit_wait_timeout(struct wait_bit_key *, int); +extern int bit_wait_io_timeout(struct wait_bit_key *, int); /** * wait_on_bit - wait for a bit to be cleared @@ -970,7 +983,7 @@ extern int bit_wait_io_timeout(struct wait_bit_key *); * on that signal. */ static inline int -wait_on_bit(void *word, int bit, unsigned mode) +wait_on_bit(unsigned long *word, int bit, unsigned mode) { might_sleep(); if (!test_bit(bit, word)) @@ -995,7 +1008,7 @@ wait_on_bit(void *word, int bit, unsigned mode) * on that signal. */ static inline int -wait_on_bit_io(void *word, int bit, unsigned mode) +wait_on_bit_io(unsigned long *word, int bit, unsigned mode) { might_sleep(); if (!test_bit(bit, word)) @@ -1021,7 +1034,8 @@ wait_on_bit_io(void *word, int bit, unsigned mode) * received a signal and the mode permitted wakeup on that signal. */ static inline int -wait_on_bit_timeout(void *word, int bit, unsigned mode, unsigned long timeout) +wait_on_bit_timeout(unsigned long *word, int bit, unsigned mode, + unsigned long timeout) { might_sleep(); if (!test_bit(bit, word)) @@ -1048,7 +1062,8 @@ wait_on_bit_timeout(void *word, int bit, unsigned mode, unsigned long timeout) * on that signal. */ static inline int -wait_on_bit_action(void *word, int bit, wait_bit_action_f *action, unsigned mode) +wait_on_bit_action(unsigned long *word, int bit, wait_bit_action_f *action, + unsigned mode) { might_sleep(); if (!test_bit(bit, word)) @@ -1076,7 +1091,7 @@ wait_on_bit_action(void *word, int bit, wait_bit_action_f *action, unsigned mode * the @mode allows that signal to wake the process. */ static inline int -wait_on_bit_lock(void *word, int bit, unsigned mode) +wait_on_bit_lock(unsigned long *word, int bit, unsigned mode) { might_sleep(); if (!test_and_set_bit(bit, word)) @@ -1100,7 +1115,7 @@ wait_on_bit_lock(void *word, int bit, unsigned mode) * the @mode allows that signal to wake the process. */ static inline int -wait_on_bit_lock_io(void *word, int bit, unsigned mode) +wait_on_bit_lock_io(unsigned long *word, int bit, unsigned mode) { might_sleep(); if (!test_and_set_bit(bit, word)) @@ -1126,7 +1141,8 @@ wait_on_bit_lock_io(void *word, int bit, unsigned mode) * the @mode allows that signal to wake the process. */ static inline int -wait_on_bit_lock_action(void *word, int bit, wait_bit_action_f *action, unsigned mode) +wait_on_bit_lock_action(unsigned long *word, int bit, wait_bit_action_f *action, + unsigned mode) { might_sleep(); if (!test_and_set_bit(bit, word)) diff --git a/kernel/include/linux/watchdog.h b/kernel/include/linux/watchdog.h index a746bf521..027b1f43f 100644 --- a/kernel/include/linux/watchdog.h +++ b/kernel/include/linux/watchdog.h @@ -24,8 +24,8 @@ struct watchdog_device; * @stop: The routine for stopping the watchdog device. * @ping: The routine that sends a keepalive ping to the watchdog device. * @status: The routine that shows the status of the watchdog device. - * @set_timeout:The routine for setting the watchdog devices timeout value. - * @get_timeleft:The routine that get's the time that's left before a reset. + * @set_timeout:The routine for setting the watchdog devices timeout value (in seconds). + * @get_timeleft:The routine that gets the time left before a reset (in seconds). * @ref: The ref operation for dyn. allocated watchdog_device structs * @unref: The unref operation for dyn. allocated watchdog_device structs * @ioctl: The routines that handles extra ioctl calls. @@ -33,7 +33,7 @@ struct watchdog_device; * The watchdog_ops structure contains a list of low-level operations * that control a watchdog device. It also contains the module that owns * these operations. The start and stop function are mandatory, all other - * functions are optonal. + * functions are optional. */ struct watchdog_ops { struct module *owner; @@ -59,12 +59,14 @@ struct watchdog_ops { * @info: Pointer to a watchdog_info structure. * @ops: Pointer to the list of watchdog operations. * @bootstatus: Status of the watchdog device at boot. - * @timeout: The watchdog devices timeout value. - * @min_timeout:The watchdog devices minimum timeout value. - * @max_timeout:The watchdog devices maximum timeout value. + * @timeout: The watchdog devices timeout value (in seconds). + * @min_timeout:The watchdog devices minimum timeout value (in seconds). + * @max_timeout:The watchdog devices maximum timeout value (in seconds). * @driver-data:Pointer to the drivers private data. * @lock: Lock for watchdog core internal use only. * @status: Field that contains the devices internal status bits. + * @deferred: entry in wtd_deferred_reg_list which is used to + * register early initialized watchdogs. * * The watchdog_device structure contains all information about a * watchdog timer device. @@ -95,6 +97,7 @@ struct watchdog_device { #define WDOG_ALLOW_RELEASE 2 /* Did we receive the magic char ? */ #define WDOG_NO_WAY_OUT 3 /* Is 'nowayout' feature set ? */ #define WDOG_UNREGISTERED 4 /* Has the device been unregistered */ + struct list_head deferred; }; #define WATCHDOG_NOWAYOUT IS_BUILTIN(CONFIG_WATCHDOG_NOWAYOUT) @@ -116,8 +119,15 @@ static inline void watchdog_set_nowayout(struct watchdog_device *wdd, bool noway /* Use the following function to check if a timeout value is invalid */ static inline bool watchdog_timeout_invalid(struct watchdog_device *wdd, unsigned int t) { - return ((wdd->max_timeout != 0) && - (t < wdd->min_timeout || t > wdd->max_timeout)); + /* + * The timeout is invalid if + * - the requested value is smaller than the configured minimum timeout, + * or + * - a maximum timeout is configured, and the requested value is larger + * than the maximum timeout. + */ + return t < wdd->min_timeout || + (wdd->max_timeout && t > wdd->max_timeout); } /* Use the following functions to manipulate watchdog driver specific data */ @@ -137,12 +147,4 @@ extern int watchdog_init_timeout(struct watchdog_device *wdd, extern int watchdog_register_device(struct watchdog_device *); extern void watchdog_unregister_device(struct watchdog_device *); -#ifdef CONFIG_HARDLOCKUP_DETECTOR -void watchdog_nmi_disable_all(void); -void watchdog_nmi_enable_all(void); -#else -static inline void watchdog_nmi_disable_all(void) {} -static inline void watchdog_nmi_enable_all(void) {} -#endif - #endif /* ifndef _LINUX_WATCHDOG_H */ diff --git a/kernel/include/linux/workqueue.h b/kernel/include/linux/workqueue.h index deee212af..0197358f1 100644 --- a/kernel/include/linux/workqueue.h +++ b/kernel/include/linux/workqueue.h @@ -265,7 +265,7 @@ static inline unsigned int work_static(struct work_struct *work) { return 0; } /** * delayed_work_pending - Find out whether a delayable work item is currently * pending - * @work: The work item in question + * @w: The work item in question */ #define delayed_work_pending(w) \ work_pending(&(w)->work) @@ -366,7 +366,7 @@ __alloc_workqueue_key(const char *fmt, unsigned int flags, int max_active, * @fmt: printf format for the name of the workqueue * @flags: WQ_* flags * @max_active: max in-flight work items, 0 for default - * @args: args for @fmt + * @args...: args for @fmt * * Allocate a workqueue with the specified parameters. For detailed * information on WQ_* flags, please refer to Documentation/workqueue.txt. @@ -398,7 +398,7 @@ __alloc_workqueue_key(const char *fmt, unsigned int flags, int max_active, * alloc_ordered_workqueue - allocate an ordered workqueue * @fmt: printf format for the name of the workqueue * @flags: WQ_* flags (only WQ_FREEZABLE and WQ_MEM_RECLAIM are meaningful) - * @args: args for @fmt + * @args...: args for @fmt * * Allocate an ordered workqueue. An ordered workqueue executes at * most one work item at any given time in the queued order. They are @@ -424,6 +424,7 @@ struct workqueue_attrs *alloc_workqueue_attrs(gfp_t gfp_mask); void free_workqueue_attrs(struct workqueue_attrs *attrs); int apply_workqueue_attrs(struct workqueue_struct *wq, const struct workqueue_attrs *attrs); +int workqueue_set_unbound_cpumask(cpumask_var_t cpumask); extern bool queue_work_on(int cpu, struct workqueue_struct *wq, struct work_struct *work); @@ -434,7 +435,6 @@ extern bool mod_delayed_work_on(int cpu, struct workqueue_struct *wq, extern void flush_workqueue(struct workqueue_struct *wq); extern void drain_workqueue(struct workqueue_struct *wq); -extern void flush_scheduled_work(void); extern int schedule_on_each_cpu(work_func_t func); @@ -531,6 +531,35 @@ static inline bool schedule_work(struct work_struct *work) } /** + * flush_scheduled_work - ensure that any scheduled work has run to completion. + * + * Forces execution of the kernel-global workqueue and blocks until its + * completion. + * + * Think twice before calling this function! It's very easy to get into + * trouble if you don't take great care. Either of the following situations + * will lead to deadlock: + * + * One of the work items currently on the workqueue needs to acquire + * a lock held by your code or its caller. + * + * Your code is running in the context of a work routine. + * + * They will be detected by lockdep when they occur, but the first might not + * occur very often. It depends on what work items are on the workqueue and + * what locks they need, which you have no control over. + * + * In most situations flushing the entire workqueue is overkill; you merely + * need to know that a particular work item isn't queued and isn't running. + * In such cases you should use cancel_delayed_work_sync() or + * cancel_work_sync() instead. + */ +static inline void flush_scheduled_work(void) +{ + flush_workqueue(system_wq); +} + +/** * schedule_delayed_work_on - queue work in global workqueue on CPU after delay * @cpu: cpu to use * @dwork: job to be done diff --git a/kernel/include/linux/writeback.h b/kernel/include/linux/writeback.h index b2dd371ec..d0b5ca5d4 100644 --- a/kernel/include/linux/writeback.h +++ b/kernel/include/linux/writeback.h @@ -7,6 +7,8 @@ #include <linux/sched.h> #include <linux/workqueue.h> #include <linux/fs.h> +#include <linux/flex_proportions.h> +#include <linux/backing-dev-defs.h> DECLARE_PER_CPU(int, dirty_throttle_leaks); @@ -84,8 +86,85 @@ struct writeback_control { unsigned for_reclaim:1; /* Invoked from the page allocator */ unsigned range_cyclic:1; /* range_start is cyclic */ unsigned for_sync:1; /* sync(2) WB_SYNC_ALL writeback */ +#ifdef CONFIG_CGROUP_WRITEBACK + struct bdi_writeback *wb; /* wb this writeback is issued under */ + struct inode *inode; /* inode being written out */ + + /* foreign inode detection, see wbc_detach_inode() */ + int wb_id; /* current wb id */ + int wb_lcand_id; /* last foreign candidate wb id */ + int wb_tcand_id; /* this foreign candidate wb id */ + size_t wb_bytes; /* bytes written by current wb */ + size_t wb_lcand_bytes; /* bytes written by last candidate */ + size_t wb_tcand_bytes; /* bytes written by this candidate */ +#endif +}; + +/* + * A wb_domain represents a domain that wb's (bdi_writeback's) belong to + * and are measured against each other in. There always is one global + * domain, global_wb_domain, that every wb in the system is a member of. + * This allows measuring the relative bandwidth of each wb to distribute + * dirtyable memory accordingly. + */ +struct wb_domain { + spinlock_t lock; + + /* + * Scale the writeback cache size proportional to the relative + * writeout speed. + * + * We do this by keeping a floating proportion between BDIs, based + * on page writeback completions [end_page_writeback()]. Those + * devices that write out pages fastest will get the larger share, + * while the slower will get a smaller share. + * + * We use page writeout completions because we are interested in + * getting rid of dirty pages. Having them written out is the + * primary goal. + * + * We introduce a concept of time, a period over which we measure + * these events, because demand can/will vary over time. The length + * of this period itself is measured in page writeback completions. + */ + struct fprop_global completions; + struct timer_list period_timer; /* timer for aging of completions */ + unsigned long period_time; + + /* + * The dirtyable memory and dirty threshold could be suddenly + * knocked down by a large amount (eg. on the startup of KVM in a + * swapless system). This may throw the system into deep dirty + * exceeded state and throttle heavy/light dirtiers alike. To + * retain good responsiveness, maintain global_dirty_limit for + * tracking slowly down to the knocked down dirty threshold. + * + * Both fields are protected by ->lock. + */ + unsigned long dirty_limit_tstamp; + unsigned long dirty_limit; }; +/** + * wb_domain_size_changed - memory available to a wb_domain has changed + * @dom: wb_domain of interest + * + * This function should be called when the amount of memory available to + * @dom has changed. It resets @dom's dirty limit parameters to prevent + * the past values which don't match the current configuration from skewing + * dirty throttling. Without this, when memory size of a wb_domain is + * greatly reduced, the dirty throttling logic may allow too many pages to + * be dirtied leading to consecutive unnecessary OOMs and may get stuck in + * that situation. + */ +static inline void wb_domain_size_changed(struct wb_domain *dom) +{ + spin_lock(&dom->lock); + dom->dirty_limit_tstamp = jiffies; + dom->dirty_limit = 0; + spin_unlock(&dom->lock); +} + /* * fs/fs-writeback.c */ @@ -93,9 +172,9 @@ struct bdi_writeback; void writeback_inodes_sb(struct super_block *, enum wb_reason reason); void writeback_inodes_sb_nr(struct super_block *, unsigned long nr, enum wb_reason reason); -int try_to_writeback_inodes_sb(struct super_block *, enum wb_reason reason); -int try_to_writeback_inodes_sb_nr(struct super_block *, unsigned long nr, - enum wb_reason reason); +bool try_to_writeback_inodes_sb(struct super_block *, enum wb_reason reason); +bool try_to_writeback_inodes_sb_nr(struct super_block *, unsigned long nr, + enum wb_reason reason); void sync_inodes_sb(struct super_block *); void wakeup_flusher_threads(long nr_pages, enum wb_reason reason); void inode_wait_for_writeback(struct inode *inode); @@ -107,6 +186,128 @@ static inline void wait_on_inode(struct inode *inode) wait_on_bit(&inode->i_state, __I_NEW, TASK_UNINTERRUPTIBLE); } +#ifdef CONFIG_CGROUP_WRITEBACK + +#include <linux/cgroup.h> +#include <linux/bio.h> + +void __inode_attach_wb(struct inode *inode, struct page *page); +void wbc_attach_and_unlock_inode(struct writeback_control *wbc, + struct inode *inode) + __releases(&inode->i_lock); +void wbc_detach_inode(struct writeback_control *wbc); +void wbc_account_io(struct writeback_control *wbc, struct page *page, + size_t bytes); +void cgroup_writeback_umount(void); + +/** + * inode_attach_wb - associate an inode with its wb + * @inode: inode of interest + * @page: page being dirtied (may be NULL) + * + * If @inode doesn't have its wb, associate it with the wb matching the + * memcg of @page or, if @page is NULL, %current. May be called w/ or w/o + * @inode->i_lock. + */ +static inline void inode_attach_wb(struct inode *inode, struct page *page) +{ + if (!inode->i_wb) + __inode_attach_wb(inode, page); +} + +/** + * inode_detach_wb - disassociate an inode from its wb + * @inode: inode of interest + * + * @inode is being freed. Detach from its wb. + */ +static inline void inode_detach_wb(struct inode *inode) +{ + if (inode->i_wb) { + wb_put(inode->i_wb); + inode->i_wb = NULL; + } +} + +/** + * wbc_attach_fdatawrite_inode - associate wbc and inode for fdatawrite + * @wbc: writeback_control of interest + * @inode: target inode + * + * This function is to be used by __filemap_fdatawrite_range(), which is an + * alternative entry point into writeback code, and first ensures @inode is + * associated with a bdi_writeback and attaches it to @wbc. + */ +static inline void wbc_attach_fdatawrite_inode(struct writeback_control *wbc, + struct inode *inode) +{ + spin_lock(&inode->i_lock); + inode_attach_wb(inode, NULL); + wbc_attach_and_unlock_inode(wbc, inode); +} + +/** + * wbc_init_bio - writeback specific initializtion of bio + * @wbc: writeback_control for the writeback in progress + * @bio: bio to be initialized + * + * @bio is a part of the writeback in progress controlled by @wbc. Perform + * writeback specific initialization. This is used to apply the cgroup + * writeback context. + */ +static inline void wbc_init_bio(struct writeback_control *wbc, struct bio *bio) +{ + /* + * pageout() path doesn't attach @wbc to the inode being written + * out. This is intentional as we don't want the function to block + * behind a slow cgroup. Ultimately, we want pageout() to kick off + * regular writeback instead of writing things out itself. + */ + if (wbc->wb) + bio_associate_blkcg(bio, wbc->wb->blkcg_css); +} + +#else /* CONFIG_CGROUP_WRITEBACK */ + +static inline void inode_attach_wb(struct inode *inode, struct page *page) +{ +} + +static inline void inode_detach_wb(struct inode *inode) +{ +} + +static inline void wbc_attach_and_unlock_inode(struct writeback_control *wbc, + struct inode *inode) + __releases(&inode->i_lock) +{ + spin_unlock(&inode->i_lock); +} + +static inline void wbc_attach_fdatawrite_inode(struct writeback_control *wbc, + struct inode *inode) +{ +} + +static inline void wbc_detach_inode(struct writeback_control *wbc) +{ +} + +static inline void wbc_init_bio(struct writeback_control *wbc, struct bio *bio) +{ +} + +static inline void wbc_account_io(struct writeback_control *wbc, + struct page *page, size_t bytes) +{ +} + +static inline void cgroup_writeback_umount(void) +{ +} + +#endif /* CONFIG_CGROUP_WRITEBACK */ + /* * mm/page-writeback.c */ @@ -120,8 +321,12 @@ static inline void laptop_sync_completion(void) { } #endif void throttle_vm_writeout(gfp_t gfp_mask); bool zone_dirty_ok(struct zone *zone); +int wb_domain_init(struct wb_domain *dom, gfp_t gfp); +#ifdef CONFIG_CGROUP_WRITEBACK +void wb_domain_exit(struct wb_domain *dom); +#endif -extern unsigned long global_dirty_limit; +extern struct wb_domain global_wb_domain; /* These are exported to sysctl. */ extern int dirty_background_ratio; @@ -155,19 +360,12 @@ int dirty_writeback_centisecs_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty); -unsigned long bdi_dirty_limit(struct backing_dev_info *bdi, - unsigned long dirty); - -void __bdi_update_bandwidth(struct backing_dev_info *bdi, - unsigned long thresh, - unsigned long bg_thresh, - unsigned long dirty, - unsigned long bdi_thresh, - unsigned long bdi_dirty, - unsigned long start_time); +unsigned long wb_calc_thresh(struct bdi_writeback *wb, unsigned long thresh); +void wb_update_bandwidth(struct bdi_writeback *wb, unsigned long start_time); void page_writeback_init(void); void balance_dirty_pages_ratelimited(struct address_space *mapping); +bool wb_over_bg_thresh(struct bdi_writeback *wb); typedef int (*writepage_t)(struct page *page, struct writeback_control *wbc, void *data); diff --git a/kernel/include/linux/xattr.h b/kernel/include/linux/xattr.h index 91b0a68d3..89474b9d2 100644 --- a/kernel/include/linux/xattr.h +++ b/kernel/include/linux/xattr.h @@ -21,15 +21,19 @@ struct dentry; struct xattr_handler { const char *prefix; - int flags; /* fs private flags passed back to the handlers */ - size_t (*list)(struct dentry *dentry, char *list, size_t list_size, - const char *name, size_t name_len, int handler_flags); - int (*get)(struct dentry *dentry, const char *name, void *buffer, - size_t size, int handler_flags); - int (*set)(struct dentry *dentry, const char *name, const void *buffer, - size_t size, int flags, int handler_flags); + int flags; /* fs private flags */ + size_t (*list)(const struct xattr_handler *, struct dentry *dentry, + char *list, size_t list_size, const char *name, + size_t name_len); + int (*get)(const struct xattr_handler *, struct dentry *dentry, + const char *name, void *buffer, size_t size); + int (*set)(const struct xattr_handler *, struct dentry *dentry, + const char *name, const void *buffer, size_t size, + int flags); }; +const char *xattr_full_name(const struct xattr_handler *, const char *); + struct xattr { const char *name; void *value; diff --git a/kernel/include/linux/zbud.h b/kernel/include/linux/zbud.h index f9d41a6e3..e183a0a65 100644 --- a/kernel/include/linux/zbud.h +++ b/kernel/include/linux/zbud.h @@ -9,7 +9,7 @@ struct zbud_ops { int (*evict)(struct zbud_pool *pool, unsigned long handle); }; -struct zbud_pool *zbud_create_pool(gfp_t gfp, struct zbud_ops *ops); +struct zbud_pool *zbud_create_pool(gfp_t gfp, const struct zbud_ops *ops); void zbud_destroy_pool(struct zbud_pool *pool); int zbud_alloc(struct zbud_pool *pool, size_t size, gfp_t gfp, unsigned long *handle); diff --git a/kernel/include/linux/zpool.h b/kernel/include/linux/zpool.h index 56529b34d..2e97b7707 100644 --- a/kernel/include/linux/zpool.h +++ b/kernel/include/linux/zpool.h @@ -36,10 +36,12 @@ enum zpool_mapmode { ZPOOL_MM_DEFAULT = ZPOOL_MM_RW }; -struct zpool *zpool_create_pool(char *type, char *name, - gfp_t gfp, struct zpool_ops *ops); +bool zpool_has_pool(char *type); -char *zpool_get_type(struct zpool *pool); +struct zpool *zpool_create_pool(const char *type, const char *name, + gfp_t gfp, const struct zpool_ops *ops); + +const char *zpool_get_type(struct zpool *pool); void zpool_destroy_pool(struct zpool *pool); @@ -81,7 +83,10 @@ struct zpool_driver { atomic_t refcount; struct list_head list; - void *(*create)(char *name, gfp_t gfp, struct zpool_ops *ops); + void *(*create)(const char *name, + gfp_t gfp, + const struct zpool_ops *ops, + struct zpool *zpool); void (*destroy)(void *pool); int (*malloc)(void *pool, size_t size, gfp_t gfp, @@ -102,6 +107,4 @@ void zpool_register_driver(struct zpool_driver *driver); int zpool_unregister_driver(struct zpool_driver *driver); -int zpool_evict(void *pool, unsigned long handle); - #endif diff --git a/kernel/include/linux/zsmalloc.h b/kernel/include/linux/zsmalloc.h index 1338190b5..34eb16098 100644 --- a/kernel/include/linux/zsmalloc.h +++ b/kernel/include/linux/zsmalloc.h @@ -34,9 +34,14 @@ enum zs_mapmode { */ }; +struct zs_pool_stats { + /* How many pages were migrated (freed) */ + unsigned long pages_compacted; +}; + struct zs_pool; -struct zs_pool *zs_create_pool(char *name, gfp_t flags); +struct zs_pool *zs_create_pool(const char *name, gfp_t flags); void zs_destroy_pool(struct zs_pool *pool); unsigned long zs_malloc(struct zs_pool *pool, size_t size); @@ -49,4 +54,5 @@ void zs_unmap_object(struct zs_pool *pool, unsigned long handle); unsigned long zs_get_total_pages(struct zs_pool *pool); unsigned long zs_compact(struct zs_pool *pool); +void zs_pool_stats(struct zs_pool *pool, struct zs_pool_stats *stats); #endif diff --git a/kernel/include/linux/zutil.h b/kernel/include/linux/zutil.h index 6adfa9a6f..663689521 100644 --- a/kernel/include/linux/zutil.h +++ b/kernel/include/linux/zutil.h @@ -68,10 +68,10 @@ typedef uLong (*check_func) (uLong check, const Byte *buf, An Adler-32 checksum is almost as reliable as a CRC32 but can be computed much faster. Usage example: - uLong adler = adler32(0L, NULL, 0); + uLong adler = zlib_adler32(0L, NULL, 0); while (read_buffer(buffer, length) != EOF) { - adler = adler32(adler, buffer, length); + adler = zlib_adler32(adler, buffer, length); } if (adler != original_adler) error(); */ |