From 9ca8dbcc65cfc63d6f5ef3312a33184e1d726e00 Mon Sep 17 00:00:00 2001 From: Yunhong Jiang Date: Tue, 4 Aug 2015 12:17:53 -0700 Subject: Add the rt linux 4.1.3-rt3 as base Import the rt linux 4.1.3-rt3 as OPNFV kvm base. It's from git://git.kernel.org/pub/scm/linux/kernel/git/rt/linux-rt-devel.git linux-4.1.y-rt and the base is: commit 0917f823c59692d751951bf5ea699a2d1e2f26a2 Author: Sebastian Andrzej Siewior Date: Sat Jul 25 12:13:34 2015 +0200 Prepare v4.1.3-rt3 Signed-off-by: Sebastian Andrzej Siewior We lose all the git history this way and it's not good. We should apply another opnfv project repo in future. Change-Id: I87543d81c9df70d99c5001fbdf646b202c19f423 Signed-off-by: Yunhong Jiang --- kernel/arch/arm/xen/Makefile | 1 + kernel/arch/arm/xen/enlighten.c | 290 ++++++++++++++++++++++++++++++++++++++ kernel/arch/arm/xen/grant-table.c | 51 +++++++ kernel/arch/arm/xen/hypercall.S | 105 ++++++++++++++ kernel/arch/arm/xen/mm.c | 201 ++++++++++++++++++++++++++ kernel/arch/arm/xen/p2m.c | 177 +++++++++++++++++++++++ 6 files changed, 825 insertions(+) create mode 100644 kernel/arch/arm/xen/Makefile create mode 100644 kernel/arch/arm/xen/enlighten.c create mode 100644 kernel/arch/arm/xen/grant-table.c create mode 100644 kernel/arch/arm/xen/hypercall.S create mode 100644 kernel/arch/arm/xen/mm.c create mode 100644 kernel/arch/arm/xen/p2m.c (limited to 'kernel/arch/arm/xen') diff --git a/kernel/arch/arm/xen/Makefile b/kernel/arch/arm/xen/Makefile new file mode 100644 index 000000000..129695234 --- /dev/null +++ b/kernel/arch/arm/xen/Makefile @@ -0,0 +1 @@ +obj-y := enlighten.o hypercall.o grant-table.o p2m.o mm.o diff --git a/kernel/arch/arm/xen/enlighten.c b/kernel/arch/arm/xen/enlighten.c new file mode 100644 index 000000000..7d0f07020 --- /dev/null +++ b/kernel/arch/arm/xen/enlighten.c @@ -0,0 +1,290 @@ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +struct start_info _xen_start_info; +struct start_info *xen_start_info = &_xen_start_info; +EXPORT_SYMBOL(xen_start_info); + +enum xen_domain_type xen_domain_type = XEN_NATIVE; +EXPORT_SYMBOL(xen_domain_type); + +struct shared_info xen_dummy_shared_info; +struct shared_info *HYPERVISOR_shared_info = (void *)&xen_dummy_shared_info; + +DEFINE_PER_CPU(struct vcpu_info *, xen_vcpu); +static struct vcpu_info __percpu *xen_vcpu_info; + +/* These are unused until we support booting "pre-ballooned" */ +unsigned long xen_released_pages; +struct xen_memory_region xen_extra_mem[XEN_EXTRA_MEM_MAX_REGIONS] __initdata; + +/* TODO: to be removed */ +__read_mostly int xen_have_vector_callback; +EXPORT_SYMBOL_GPL(xen_have_vector_callback); + +int xen_platform_pci_unplug = XEN_UNPLUG_ALL; +EXPORT_SYMBOL_GPL(xen_platform_pci_unplug); + +static __read_mostly int xen_events_irq = -1; + +int xen_remap_domain_mfn_array(struct vm_area_struct *vma, + unsigned long addr, + xen_pfn_t *mfn, int nr, + int *err_ptr, pgprot_t prot, + unsigned domid, + struct page **pages) +{ + return xen_xlate_remap_gfn_array(vma, addr, mfn, nr, err_ptr, + prot, domid, pages); +} +EXPORT_SYMBOL_GPL(xen_remap_domain_mfn_array); + +/* Not used by XENFEAT_auto_translated guests. */ +int xen_remap_domain_mfn_range(struct vm_area_struct *vma, + unsigned long addr, + xen_pfn_t mfn, int nr, + pgprot_t prot, unsigned domid, + struct page **pages) +{ + return -ENOSYS; +} +EXPORT_SYMBOL_GPL(xen_remap_domain_mfn_range); + +int xen_unmap_domain_mfn_range(struct vm_area_struct *vma, + int nr, struct page **pages) +{ + return xen_xlate_unmap_gfn_range(vma, nr, pages); +} +EXPORT_SYMBOL_GPL(xen_unmap_domain_mfn_range); + +static void xen_percpu_init(void) +{ + struct vcpu_register_vcpu_info info; + struct vcpu_info *vcpup; + int err; + int cpu = get_cpu(); + + pr_info("Xen: initializing cpu%d\n", cpu); + vcpup = per_cpu_ptr(xen_vcpu_info, cpu); + + info.mfn = __pa(vcpup) >> PAGE_SHIFT; + info.offset = offset_in_page(vcpup); + + err = HYPERVISOR_vcpu_op(VCPUOP_register_vcpu_info, cpu, &info); + BUG_ON(err); + per_cpu(xen_vcpu, cpu) = vcpup; + + enable_percpu_irq(xen_events_irq, 0); + put_cpu(); +} + +static void xen_restart(enum reboot_mode reboot_mode, const char *cmd) +{ + struct sched_shutdown r = { .reason = SHUTDOWN_reboot }; + int rc; + rc = HYPERVISOR_sched_op(SCHEDOP_shutdown, &r); + BUG_ON(rc); +} + +static void xen_power_off(void) +{ + struct sched_shutdown r = { .reason = SHUTDOWN_poweroff }; + int rc; + rc = HYPERVISOR_sched_op(SCHEDOP_shutdown, &r); + BUG_ON(rc); +} + +static int xen_cpu_notification(struct notifier_block *self, + unsigned long action, + void *hcpu) +{ + switch (action) { + case CPU_STARTING: + xen_percpu_init(); + break; + default: + break; + } + + return NOTIFY_OK; +} + +static struct notifier_block xen_cpu_notifier = { + .notifier_call = xen_cpu_notification, +}; + +static irqreturn_t xen_arm_callback(int irq, void *arg) +{ + xen_hvm_evtchn_do_upcall(); + return IRQ_HANDLED; +} + +/* + * see Documentation/devicetree/bindings/arm/xen.txt for the + * documentation of the Xen Device Tree format. + */ +#define GRANT_TABLE_PHYSADDR 0 +static int __init xen_guest_init(void) +{ + struct xen_add_to_physmap xatp; + static struct shared_info *shared_info_page = 0; + struct device_node *node; + int len; + const char *s = NULL; + const char *version = NULL; + const char *xen_prefix = "xen,xen-"; + struct resource res; + phys_addr_t grant_frames; + + node = of_find_compatible_node(NULL, NULL, "xen,xen"); + if (!node) { + pr_debug("No Xen support\n"); + return 0; + } + s = of_get_property(node, "compatible", &len); + if (strlen(xen_prefix) + 3 < len && + !strncmp(xen_prefix, s, strlen(xen_prefix))) + version = s + strlen(xen_prefix); + if (version == NULL) { + pr_debug("Xen version not found\n"); + return 0; + } + if (of_address_to_resource(node, GRANT_TABLE_PHYSADDR, &res)) + return 0; + grant_frames = res.start; + xen_events_irq = irq_of_parse_and_map(node, 0); + pr_info("Xen %s support found, events_irq=%d gnttab_frame=%pa\n", + version, xen_events_irq, &grant_frames); + + if (xen_events_irq < 0) + return -ENODEV; + + xen_domain_type = XEN_HVM_DOMAIN; + + xen_setup_features(); + + if (xen_feature(XENFEAT_dom0)) + xen_start_info->flags |= SIF_INITDOMAIN|SIF_PRIVILEGED; + else + xen_start_info->flags &= ~(SIF_INITDOMAIN|SIF_PRIVILEGED); + + if (!shared_info_page) + shared_info_page = (struct shared_info *) + get_zeroed_page(GFP_KERNEL); + if (!shared_info_page) { + pr_err("not enough memory\n"); + return -ENOMEM; + } + xatp.domid = DOMID_SELF; + xatp.idx = 0; + xatp.space = XENMAPSPACE_shared_info; + xatp.gpfn = __pa(shared_info_page) >> PAGE_SHIFT; + if (HYPERVISOR_memory_op(XENMEM_add_to_physmap, &xatp)) + BUG(); + + HYPERVISOR_shared_info = (struct shared_info *)shared_info_page; + + /* xen_vcpu is a pointer to the vcpu_info struct in the shared_info + * page, we use it in the event channel upcall and in some pvclock + * related functions. + * The shared info contains exactly 1 CPU (the boot CPU). The guest + * is required to use VCPUOP_register_vcpu_info to place vcpu info + * for secondary CPUs as they are brought up. + * For uniformity we use VCPUOP_register_vcpu_info even on cpu0. + */ + xen_vcpu_info = __alloc_percpu(sizeof(struct vcpu_info), + sizeof(struct vcpu_info)); + if (xen_vcpu_info == NULL) + return -ENOMEM; + + if (gnttab_setup_auto_xlat_frames(grant_frames)) { + free_percpu(xen_vcpu_info); + return -ENOMEM; + } + gnttab_init(); + if (!xen_initial_domain()) + xenbus_probe(NULL); + + /* + * Making sure board specific code will not set up ops for + * cpu idle and cpu freq. + */ + disable_cpuidle(); + disable_cpufreq(); + + xen_init_IRQ(); + + if (request_percpu_irq(xen_events_irq, xen_arm_callback, + "events", &xen_vcpu)) { + pr_err("Error request IRQ %d\n", xen_events_irq); + return -EINVAL; + } + + xen_percpu_init(); + + register_cpu_notifier(&xen_cpu_notifier); + + return 0; +} +early_initcall(xen_guest_init); + +static int __init xen_pm_init(void) +{ + if (!xen_domain()) + return -ENODEV; + + pm_power_off = xen_power_off; + arm_pm_restart = xen_restart; + + return 0; +} +late_initcall(xen_pm_init); + + +/* empty stubs */ +void xen_arch_pre_suspend(void) { } +void xen_arch_post_suspend(int suspend_cancelled) { } +void xen_timer_resume(void) { } +void xen_arch_resume(void) { } +void xen_arch_suspend(void) { } + + +/* In the hypervisor.S file. */ +EXPORT_SYMBOL_GPL(HYPERVISOR_event_channel_op); +EXPORT_SYMBOL_GPL(HYPERVISOR_grant_table_op); +EXPORT_SYMBOL_GPL(HYPERVISOR_xen_version); +EXPORT_SYMBOL_GPL(HYPERVISOR_console_io); +EXPORT_SYMBOL_GPL(HYPERVISOR_sched_op); +EXPORT_SYMBOL_GPL(HYPERVISOR_hvm_op); +EXPORT_SYMBOL_GPL(HYPERVISOR_memory_op); +EXPORT_SYMBOL_GPL(HYPERVISOR_physdev_op); +EXPORT_SYMBOL_GPL(HYPERVISOR_vcpu_op); +EXPORT_SYMBOL_GPL(HYPERVISOR_tmem_op); +EXPORT_SYMBOL_GPL(HYPERVISOR_multicall); +EXPORT_SYMBOL_GPL(privcmd_call); diff --git a/kernel/arch/arm/xen/grant-table.c b/kernel/arch/arm/xen/grant-table.c new file mode 100644 index 000000000..e43791829 --- /dev/null +++ b/kernel/arch/arm/xen/grant-table.c @@ -0,0 +1,51 @@ +/****************************************************************************** + * grant_table.c + * ARM specific part + * + * Granting foreign access to our memory reservation. + * + * 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; or, when distributed + * separately from the Linux kernel or incorporated into other + * software packages, subject to the following license: + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this source file (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 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. + */ + +#include +#include +#include + +int arch_gnttab_map_shared(xen_pfn_t *frames, unsigned long nr_gframes, + unsigned long max_nr_gframes, + void **__shared) +{ + return -ENOSYS; +} + +void arch_gnttab_unmap(void *shared, unsigned long nr_gframes) +{ + return; +} + +int arch_gnttab_init(unsigned long nr_shared) +{ + return 0; +} diff --git a/kernel/arch/arm/xen/hypercall.S b/kernel/arch/arm/xen/hypercall.S new file mode 100644 index 000000000..f00e08075 --- /dev/null +++ b/kernel/arch/arm/xen/hypercall.S @@ -0,0 +1,105 @@ +/****************************************************************************** + * hypercall.S + * + * Xen hypercall wrappers + * + * Stefano Stabellini , Citrix, 2012 + * + * 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; or, when distributed + * separately from the Linux kernel or incorporated into other + * software packages, subject to the following license: + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this source file (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 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. + */ + +/* + * The Xen hypercall calling convention is very similar to the ARM + * procedure calling convention: the first paramter is passed in r0, the + * second in r1, the third in r2 and the fourth in r3. Considering that + * Xen hypercalls have 5 arguments at most, the fifth paramter is passed + * in r4, differently from the procedure calling convention of using the + * stack for that case. + * + * The hypercall number is passed in r12. + * + * The return value is in r0. + * + * The hvc ISS is required to be 0xEA1, that is the Xen specific ARM + * hypercall tag. + */ + +#include +#include +#include +#include + + +#define XEN_IMM 0xEA1 + +#define HYPERCALL_SIMPLE(hypercall) \ +ENTRY(HYPERVISOR_##hypercall) \ + mov r12, #__HYPERVISOR_##hypercall; \ + __HVC(XEN_IMM); \ + ret lr; \ +ENDPROC(HYPERVISOR_##hypercall) + +#define HYPERCALL0 HYPERCALL_SIMPLE +#define HYPERCALL1 HYPERCALL_SIMPLE +#define HYPERCALL2 HYPERCALL_SIMPLE +#define HYPERCALL3 HYPERCALL_SIMPLE +#define HYPERCALL4 HYPERCALL_SIMPLE + +#define HYPERCALL5(hypercall) \ +ENTRY(HYPERVISOR_##hypercall) \ + stmdb sp!, {r4} \ + ldr r4, [sp, #4] \ + mov r12, #__HYPERVISOR_##hypercall; \ + __HVC(XEN_IMM); \ + ldm sp!, {r4} \ + ret lr \ +ENDPROC(HYPERVISOR_##hypercall) + + .text + +HYPERCALL2(xen_version); +HYPERCALL3(console_io); +HYPERCALL3(grant_table_op); +HYPERCALL2(sched_op); +HYPERCALL2(event_channel_op); +HYPERCALL2(hvm_op); +HYPERCALL2(memory_op); +HYPERCALL2(physdev_op); +HYPERCALL3(vcpu_op); +HYPERCALL1(tmem_op); +HYPERCALL2(multicall); + +ENTRY(privcmd_call) + stmdb sp!, {r4} + mov r12, r0 + mov r0, r1 + mov r1, r2 + mov r2, r3 + ldr r3, [sp, #8] + ldr r4, [sp, #4] + __HVC(XEN_IMM) + ldm sp!, {r4} + ret lr +ENDPROC(privcmd_call); diff --git a/kernel/arch/arm/xen/mm.c b/kernel/arch/arm/xen/mm.c new file mode 100644 index 000000000..498325074 --- /dev/null +++ b/kernel/arch/arm/xen/mm.c @@ -0,0 +1,201 @@ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include + +#include +#include +#include +#include + +unsigned long xen_get_swiotlb_free_pages(unsigned int order) +{ + struct memblock_region *reg; + gfp_t flags = __GFP_NOWARN; + + for_each_memblock(memory, reg) { + if (reg->base < (phys_addr_t)0xffffffff) { + flags |= __GFP_DMA; + break; + } + } + return __get_free_pages(flags, order); +} + +enum dma_cache_op { + DMA_UNMAP, + DMA_MAP, +}; +static bool hypercall_cflush = false; + +/* functions called by SWIOTLB */ + +static void dma_cache_maint(dma_addr_t handle, unsigned long offset, + size_t size, enum dma_data_direction dir, enum dma_cache_op op) +{ + struct gnttab_cache_flush cflush; + unsigned long pfn; + size_t left = size; + + pfn = (handle >> PAGE_SHIFT) + offset / PAGE_SIZE; + offset %= PAGE_SIZE; + + do { + size_t len = left; + + /* buffers in highmem or foreign pages cannot cross page + * boundaries */ + if (len + offset > PAGE_SIZE) + len = PAGE_SIZE - offset; + + cflush.op = 0; + cflush.a.dev_bus_addr = pfn << PAGE_SHIFT; + cflush.offset = offset; + cflush.length = len; + + if (op == DMA_UNMAP && dir != DMA_TO_DEVICE) + cflush.op = GNTTAB_CACHE_INVAL; + if (op == DMA_MAP) { + if (dir == DMA_FROM_DEVICE) + cflush.op = GNTTAB_CACHE_INVAL; + else + cflush.op = GNTTAB_CACHE_CLEAN; + } + if (cflush.op) + HYPERVISOR_grant_table_op(GNTTABOP_cache_flush, &cflush, 1); + + offset = 0; + pfn++; + left -= len; + } while (left); +} + +static void __xen_dma_page_dev_to_cpu(struct device *hwdev, dma_addr_t handle, + size_t size, enum dma_data_direction dir) +{ + dma_cache_maint(handle & PAGE_MASK, handle & ~PAGE_MASK, size, dir, DMA_UNMAP); +} + +static void __xen_dma_page_cpu_to_dev(struct device *hwdev, dma_addr_t handle, + size_t size, enum dma_data_direction dir) +{ + dma_cache_maint(handle & PAGE_MASK, handle & ~PAGE_MASK, size, dir, DMA_MAP); +} + +void __xen_dma_map_page(struct device *hwdev, struct page *page, + dma_addr_t dev_addr, unsigned long offset, size_t size, + enum dma_data_direction dir, struct dma_attrs *attrs) +{ + if (is_device_dma_coherent(hwdev)) + return; + if (dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs)) + return; + + __xen_dma_page_cpu_to_dev(hwdev, dev_addr, size, dir); +} + +void __xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle, + size_t size, enum dma_data_direction dir, + struct dma_attrs *attrs) + +{ + if (is_device_dma_coherent(hwdev)) + return; + if (dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs)) + return; + + __xen_dma_page_dev_to_cpu(hwdev, handle, size, dir); +} + +void __xen_dma_sync_single_for_cpu(struct device *hwdev, + dma_addr_t handle, size_t size, enum dma_data_direction dir) +{ + if (is_device_dma_coherent(hwdev)) + return; + __xen_dma_page_dev_to_cpu(hwdev, handle, size, dir); +} + +void __xen_dma_sync_single_for_device(struct device *hwdev, + dma_addr_t handle, size_t size, enum dma_data_direction dir) +{ + if (is_device_dma_coherent(hwdev)) + return; + __xen_dma_page_cpu_to_dev(hwdev, handle, size, dir); +} + +bool xen_arch_need_swiotlb(struct device *dev, + unsigned long pfn, + unsigned long mfn) +{ + return (!hypercall_cflush && (pfn != mfn) && !is_device_dma_coherent(dev)); +} + +int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order, + unsigned int address_bits, + dma_addr_t *dma_handle) +{ + if (!xen_initial_domain()) + return -EINVAL; + + /* we assume that dom0 is mapped 1:1 for now */ + *dma_handle = pstart; + return 0; +} +EXPORT_SYMBOL_GPL(xen_create_contiguous_region); + +void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order) +{ + return; +} +EXPORT_SYMBOL_GPL(xen_destroy_contiguous_region); + +struct dma_map_ops *xen_dma_ops; +EXPORT_SYMBOL(xen_dma_ops); + +static struct dma_map_ops xen_swiotlb_dma_ops = { + .mapping_error = xen_swiotlb_dma_mapping_error, + .alloc = xen_swiotlb_alloc_coherent, + .free = xen_swiotlb_free_coherent, + .sync_single_for_cpu = xen_swiotlb_sync_single_for_cpu, + .sync_single_for_device = xen_swiotlb_sync_single_for_device, + .sync_sg_for_cpu = xen_swiotlb_sync_sg_for_cpu, + .sync_sg_for_device = xen_swiotlb_sync_sg_for_device, + .map_sg = xen_swiotlb_map_sg_attrs, + .unmap_sg = xen_swiotlb_unmap_sg_attrs, + .map_page = xen_swiotlb_map_page, + .unmap_page = xen_swiotlb_unmap_page, + .dma_supported = xen_swiotlb_dma_supported, + .set_dma_mask = xen_swiotlb_set_dma_mask, +}; + +int __init xen_mm_init(void) +{ + struct gnttab_cache_flush cflush; + if (!xen_initial_domain()) + return 0; + xen_swiotlb_init(1, false); + xen_dma_ops = &xen_swiotlb_dma_ops; + + cflush.op = 0; + cflush.a.dev_bus_addr = 0; + cflush.offset = 0; + cflush.length = 0; + if (HYPERVISOR_grant_table_op(GNTTABOP_cache_flush, &cflush, 1) != -ENOSYS) + hypercall_cflush = true; + return 0; +} +arch_initcall(xen_mm_init); diff --git a/kernel/arch/arm/xen/p2m.c b/kernel/arch/arm/xen/p2m.c new file mode 100644 index 000000000..cb7a14c5c --- /dev/null +++ b/kernel/arch/arm/xen/p2m.c @@ -0,0 +1,177 @@ +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include + +#include +#include +#include +#include + +struct xen_p2m_entry { + unsigned long pfn; + unsigned long mfn; + unsigned long nr_pages; + struct rb_node rbnode_phys; +}; + +static rwlock_t p2m_lock; +struct rb_root phys_to_mach = RB_ROOT; +EXPORT_SYMBOL_GPL(phys_to_mach); + +static int xen_add_phys_to_mach_entry(struct xen_p2m_entry *new) +{ + struct rb_node **link = &phys_to_mach.rb_node; + struct rb_node *parent = NULL; + struct xen_p2m_entry *entry; + int rc = 0; + + while (*link) { + parent = *link; + entry = rb_entry(parent, struct xen_p2m_entry, rbnode_phys); + + if (new->pfn == entry->pfn) + goto err_out; + + if (new->pfn < entry->pfn) + link = &(*link)->rb_left; + else + link = &(*link)->rb_right; + } + rb_link_node(&new->rbnode_phys, parent, link); + rb_insert_color(&new->rbnode_phys, &phys_to_mach); + goto out; + +err_out: + rc = -EINVAL; + pr_warn("%s: cannot add pfn=%pa -> mfn=%pa: pfn=%pa -> mfn=%pa already exists\n", + __func__, &new->pfn, &new->mfn, &entry->pfn, &entry->mfn); +out: + return rc; +} + +unsigned long __pfn_to_mfn(unsigned long pfn) +{ + struct rb_node *n = phys_to_mach.rb_node; + struct xen_p2m_entry *entry; + unsigned long irqflags; + + read_lock_irqsave(&p2m_lock, irqflags); + while (n) { + entry = rb_entry(n, struct xen_p2m_entry, rbnode_phys); + if (entry->pfn <= pfn && + entry->pfn + entry->nr_pages > pfn) { + read_unlock_irqrestore(&p2m_lock, irqflags); + return entry->mfn + (pfn - entry->pfn); + } + if (pfn < entry->pfn) + n = n->rb_left; + else + n = n->rb_right; + } + read_unlock_irqrestore(&p2m_lock, irqflags); + + return INVALID_P2M_ENTRY; +} +EXPORT_SYMBOL_GPL(__pfn_to_mfn); + +int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops, + struct gnttab_map_grant_ref *kmap_ops, + struct page **pages, unsigned int count) +{ + int i; + + for (i = 0; i < count; i++) { + if (map_ops[i].status) + continue; + set_phys_to_machine(map_ops[i].host_addr >> PAGE_SHIFT, + map_ops[i].dev_bus_addr >> PAGE_SHIFT); + } + + return 0; +} +EXPORT_SYMBOL_GPL(set_foreign_p2m_mapping); + +int clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops, + struct gnttab_unmap_grant_ref *kunmap_ops, + struct page **pages, unsigned int count) +{ + int i; + + for (i = 0; i < count; i++) { + set_phys_to_machine(unmap_ops[i].host_addr >> PAGE_SHIFT, + INVALID_P2M_ENTRY); + } + + return 0; +} +EXPORT_SYMBOL_GPL(clear_foreign_p2m_mapping); + +bool __set_phys_to_machine_multi(unsigned long pfn, + unsigned long mfn, unsigned long nr_pages) +{ + int rc; + unsigned long irqflags; + struct xen_p2m_entry *p2m_entry; + struct rb_node *n = phys_to_mach.rb_node; + + if (mfn == INVALID_P2M_ENTRY) { + write_lock_irqsave(&p2m_lock, irqflags); + while (n) { + p2m_entry = rb_entry(n, struct xen_p2m_entry, rbnode_phys); + if (p2m_entry->pfn <= pfn && + p2m_entry->pfn + p2m_entry->nr_pages > pfn) { + rb_erase(&p2m_entry->rbnode_phys, &phys_to_mach); + write_unlock_irqrestore(&p2m_lock, irqflags); + kfree(p2m_entry); + return true; + } + if (pfn < p2m_entry->pfn) + n = n->rb_left; + else + n = n->rb_right; + } + write_unlock_irqrestore(&p2m_lock, irqflags); + return true; + } + + p2m_entry = kzalloc(sizeof(struct xen_p2m_entry), GFP_NOWAIT); + if (!p2m_entry) { + pr_warn("cannot allocate xen_p2m_entry\n"); + return false; + } + p2m_entry->pfn = pfn; + p2m_entry->nr_pages = nr_pages; + p2m_entry->mfn = mfn; + + write_lock_irqsave(&p2m_lock, irqflags); + if ((rc = xen_add_phys_to_mach_entry(p2m_entry)) < 0) { + write_unlock_irqrestore(&p2m_lock, irqflags); + return false; + } + write_unlock_irqrestore(&p2m_lock, irqflags); + return true; +} +EXPORT_SYMBOL_GPL(__set_phys_to_machine_multi); + +bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn) +{ + return __set_phys_to_machine_multi(pfn, mfn, 1); +} +EXPORT_SYMBOL_GPL(__set_phys_to_machine); + +static int p2m_init(void) +{ + rwlock_init(&p2m_lock); + return 0; +} +arch_initcall(p2m_init); -- cgit 1.2.3-korg