diff options
Diffstat (limited to 'kernel/arch/um')
45 files changed, 474 insertions, 583 deletions
diff --git a/kernel/arch/um/Kconfig.um b/kernel/arch/um/Kconfig.um index 6e67847f5..28a9885e3 100644 --- a/kernel/arch/um/Kconfig.um +++ b/kernel/arch/um/Kconfig.um @@ -44,23 +44,9 @@ config HOSTFS If you'd like to be able to work with files stored on the host, say Y or M here; otherwise say N. -config HPPFS - tristate "HoneyPot ProcFS" - depends on PROC_FS - help - hppfs (HoneyPot ProcFS) is a filesystem which allows UML /proc - entries to be overridden, removed, or fabricated from the host. - Its purpose is to allow a UML to appear to be a physical machine - by removing or changing anything in /proc which gives away the - identity of a UML. - - See <http://user-mode-linux.sf.net/old/hppfs.html> for more information. - - You only need this if you are setting up a UML honeypot. Otherwise, - it is safe to say 'N' here. - config MCONSOLE bool "Management console" + depends on PROC_FS default y help The user mode linux management console is a low-level interface to diff --git a/kernel/arch/um/Makefile b/kernel/arch/um/Makefile index 17d4460b1..e3abe6f31 100644 --- a/kernel/arch/um/Makefile +++ b/kernel/arch/um/Makefile @@ -68,9 +68,10 @@ KBUILD_CFLAGS += $(CFLAGS) $(CFLAGS-y) -D__arch_um__ \ KBUILD_AFLAGS += $(ARCH_INCLUDE) -USER_CFLAGS = $(patsubst $(KERNEL_DEFINES),,$(patsubst -D__KERNEL__,,\ - $(patsubst -I%,,$(KBUILD_CFLAGS)))) $(ARCH_INCLUDE) $(MODE_INCLUDE) \ - $(filter -I%,$(CFLAGS)) -D_FILE_OFFSET_BITS=64 -idirafter include +USER_CFLAGS = $(patsubst $(KERNEL_DEFINES),,$(patsubst -I%,,$(KBUILD_CFLAGS))) \ + $(ARCH_INCLUDE) $(MODE_INCLUDE) $(filter -I%,$(CFLAGS)) \ + -D_FILE_OFFSET_BITS=64 -idirafter $(srctree)/include \ + -idirafter $(obj)/include -D__KERNEL__ -D__UM_HOST__ #This will adjust *FLAGS accordingly to the platform. include $(ARCH_DIR)/Makefile-os-$(OS) diff --git a/kernel/arch/um/drivers/harddog_user.c b/kernel/arch/um/drivers/harddog_user.c index f99b32a4d..3aa8b0d52 100644 --- a/kernel/arch/um/drivers/harddog_user.c +++ b/kernel/arch/um/drivers/harddog_user.c @@ -9,8 +9,8 @@ #include <os.h> struct dog_data { - int stdin; - int stdout; + int stdin_fd; + int stdout_fd; int close_me[2]; }; @@ -18,11 +18,11 @@ static void pre_exec(void *d) { struct dog_data *data = d; - dup2(data->stdin, 0); - dup2(data->stdout, 1); - dup2(data->stdout, 2); - close(data->stdin); - close(data->stdout); + dup2(data->stdin_fd, 0); + dup2(data->stdout_fd, 1); + dup2(data->stdout_fd, 2); + close(data->stdin_fd); + close(data->stdout_fd); close(data->close_me[0]); close(data->close_me[1]); } @@ -49,8 +49,8 @@ int start_watchdog(int *in_fd_ret, int *out_fd_ret, char *sock) goto out_close_in; } - data.stdin = out_fds[0]; - data.stdout = in_fds[1]; + data.stdin_fd = out_fds[0]; + data.stdout_fd = in_fds[1]; data.close_me[0] = out_fds[1]; data.close_me[1] = in_fds[0]; diff --git a/kernel/arch/um/drivers/hostaudio_kern.c b/kernel/arch/um/drivers/hostaudio_kern.c index 9b90fdc4b..f6b911cc3 100644 --- a/kernel/arch/um/drivers/hostaudio_kern.c +++ b/kernel/arch/um/drivers/hostaudio_kern.c @@ -185,9 +185,9 @@ static int hostaudio_open(struct inode *inode, struct file *file) int ret; #ifdef DEBUG - kparam_block_sysfs_write(dsp); + kernel_param_lock(THIS_MODULE); printk(KERN_DEBUG "hostaudio: open called (host: %s)\n", dsp); - kparam_unblock_sysfs_write(dsp); + kernel_param_unlock(THIS_MODULE); #endif state = kmalloc(sizeof(struct hostaudio_state), GFP_KERNEL); @@ -199,11 +199,11 @@ static int hostaudio_open(struct inode *inode, struct file *file) if (file->f_mode & FMODE_WRITE) w = 1; - kparam_block_sysfs_write(dsp); + kernel_param_lock(THIS_MODULE); mutex_lock(&hostaudio_mutex); ret = os_open_file(dsp, of_set_rw(OPENFLAGS(), r, w), 0); mutex_unlock(&hostaudio_mutex); - kparam_unblock_sysfs_write(dsp); + kernel_param_unlock(THIS_MODULE); if (ret < 0) { kfree(state); @@ -260,17 +260,17 @@ static int hostmixer_open_mixdev(struct inode *inode, struct file *file) if (file->f_mode & FMODE_WRITE) w = 1; - kparam_block_sysfs_write(mixer); + kernel_param_lock(THIS_MODULE); mutex_lock(&hostaudio_mutex); ret = os_open_file(mixer, of_set_rw(OPENFLAGS(), r, w), 0); mutex_unlock(&hostaudio_mutex); - kparam_unblock_sysfs_write(mixer); + kernel_param_unlock(THIS_MODULE); if (ret < 0) { - kparam_block_sysfs_write(dsp); + kernel_param_lock(THIS_MODULE); printk(KERN_ERR "hostaudio_open_mixdev failed to open '%s', " "err = %d\n", dsp, -ret); - kparam_unblock_sysfs_write(dsp); + kernel_param_unlock(THIS_MODULE); kfree(state); return ret; } @@ -326,10 +326,10 @@ MODULE_LICENSE("GPL"); static int __init hostaudio_init_module(void) { - __kernel_param_lock(); + kernel_param_lock(THIS_MODULE); printk(KERN_INFO "UML Audio Relay (host dsp = %s, host mixer = %s)\n", dsp, mixer); - __kernel_param_unlock(); + kernel_param_unlock(THIS_MODULE); module_data.dev_audio = register_sound_dsp(&hostaudio_fops, -1); if (module_data.dev_audio < 0) { diff --git a/kernel/arch/um/drivers/mconsole.h b/kernel/arch/um/drivers/mconsole.h index 8b22535c6..44af7379e 100644 --- a/kernel/arch/um/drivers/mconsole.h +++ b/kernel/arch/um/drivers/mconsole.h @@ -7,7 +7,7 @@ #ifndef __MCONSOLE_H__ #define __MCONSOLE_H__ -#ifndef __KERNEL__ +#ifdef __UM_HOST__ #include <stdint.h> #define u32 uint32_t #endif diff --git a/kernel/arch/um/drivers/net_kern.c b/kernel/arch/um/drivers/net_kern.c index f70dd5406..9ef669d24 100644 --- a/kernel/arch/um/drivers/net_kern.c +++ b/kernel/arch/um/drivers/net_kern.c @@ -388,7 +388,7 @@ static const struct net_device_ops uml_netdev_ops = { static int driver_registered; static void eth_configure(int n, void *init, char *mac, - struct transport *transport) + struct transport *transport, gfp_t gfp_mask) { struct uml_net *device; struct net_device *dev; @@ -397,7 +397,7 @@ static void eth_configure(int n, void *init, char *mac, size = transport->private_size + sizeof(struct uml_net_private); - device = kzalloc(sizeof(*device), GFP_KERNEL); + device = kzalloc(sizeof(*device), gfp_mask); if (device == NULL) { printk(KERN_ERR "eth_configure failed to allocate struct " "uml_net\n"); @@ -568,7 +568,7 @@ static LIST_HEAD(transports); static LIST_HEAD(eth_cmd_line); static int check_transport(struct transport *transport, char *eth, int n, - void **init_out, char **mac_out) + void **init_out, char **mac_out, gfp_t gfp_mask) { int len; @@ -582,7 +582,7 @@ static int check_transport(struct transport *transport, char *eth, int n, else if (*eth != '\0') return 0; - *init_out = kmalloc(transport->setup_size, GFP_KERNEL); + *init_out = kmalloc(transport->setup_size, gfp_mask); if (*init_out == NULL) return 1; @@ -609,11 +609,11 @@ void register_transport(struct transport *new) list_for_each_safe(ele, next, ð_cmd_line) { eth = list_entry(ele, struct eth_init, list); match = check_transport(new, eth->init, eth->index, &init, - &mac); + &mac, GFP_KERNEL); if (!match) continue; else if (init != NULL) { - eth_configure(eth->index, init, mac, new); + eth_configure(eth->index, init, mac, new, GFP_KERNEL); kfree(init); } list_del(ð->list); @@ -631,10 +631,11 @@ static int eth_setup_common(char *str, int index) spin_lock(&transports_lock); list_for_each(ele, &transports) { transport = list_entry(ele, struct transport, list); - if (!check_transport(transport, str, index, &init, &mac)) + if (!check_transport(transport, str, index, &init, + &mac, GFP_ATOMIC)) continue; if (init != NULL) { - eth_configure(index, init, mac, transport); + eth_configure(index, init, mac, transport, GFP_ATOMIC); kfree(init); } found = 1; diff --git a/kernel/arch/um/drivers/net_user.c b/kernel/arch/um/drivers/net_user.c index cd14157b5..e9f844586 100644 --- a/kernel/arch/um/drivers/net_user.c +++ b/kernel/arch/um/drivers/net_user.c @@ -166,7 +166,7 @@ int net_sendto(int fd, void *buf, int len, void *to, int sock_len) struct change_pre_exec_data { int close_me; - int stdout; + int stdout_fd; }; static void change_pre_exec(void *arg) @@ -174,7 +174,7 @@ static void change_pre_exec(void *arg) struct change_pre_exec_data *data = arg; close(data->close_me); - dup2(data->stdout, 1); + dup2(data->stdout_fd, 1); } static int change_tramp(char **argv, char *output, int output_len) @@ -189,7 +189,7 @@ static int change_tramp(char **argv, char *output, int output_len) return err; } pe_data.close_me = fds[0]; - pe_data.stdout = fds[1]; + pe_data.stdout_fd = fds[1]; pid = run_helper(change_pre_exec, &pe_data, argv); if (pid > 0) /* Avoid hang as we won't get data in failure case. */ @@ -249,21 +249,23 @@ void close_addr(unsigned char *addr, unsigned char *netmask, void *arg) char *split_if_spec(char *str, ...) { - char **arg, *end; + char **arg, *end, *ret = NULL; va_list ap; va_start(ap, str); while ((arg = va_arg(ap, char **)) != NULL) { if (*str == '\0') - return NULL; + goto out; end = strchr(str, ','); if (end != str) *arg = str; if (end == NULL) - return NULL; + goto out; *end++ = '\0'; str = end; } + ret = str; +out: va_end(ap); - return str; + return ret; } diff --git a/kernel/arch/um/drivers/slip_user.c b/kernel/arch/um/drivers/slip_user.c index 55c290d92..0d6b66c64 100644 --- a/kernel/arch/um/drivers/slip_user.c +++ b/kernel/arch/um/drivers/slip_user.c @@ -55,8 +55,8 @@ static int set_up_tty(int fd) } struct slip_pre_exec_data { - int stdin; - int stdout; + int stdin_fd; + int stdout_fd; int close_me; }; @@ -64,9 +64,9 @@ static void slip_pre_exec(void *arg) { struct slip_pre_exec_data *data = arg; - if (data->stdin >= 0) - dup2(data->stdin, 0); - dup2(data->stdout, 1); + if (data->stdin_fd >= 0) + dup2(data->stdin_fd, 0); + dup2(data->stdout_fd, 1); if (data->close_me >= 0) close(data->close_me); } @@ -85,8 +85,8 @@ static int slip_tramp(char **argv, int fd) } err = 0; - pe_data.stdin = fd; - pe_data.stdout = fds[1]; + pe_data.stdin_fd = fd; + pe_data.stdout_fd = fds[1]; pe_data.close_me = fds[0]; err = run_helper(slip_pre_exec, &pe_data, argv); if (err < 0) diff --git a/kernel/arch/um/drivers/slirp_user.c b/kernel/arch/um/drivers/slirp_user.c index c999d187a..98b6a41a2 100644 --- a/kernel/arch/um/drivers/slirp_user.c +++ b/kernel/arch/um/drivers/slirp_user.c @@ -20,18 +20,18 @@ static int slirp_user_init(void *data, void *dev) } struct slirp_pre_exec_data { - int stdin; - int stdout; + int stdin_fd; + int stdout_fd; }; static void slirp_pre_exec(void *arg) { struct slirp_pre_exec_data *data = arg; - if (data->stdin != -1) - dup2(data->stdin, 0); - if (data->stdout != -1) - dup2(data->stdout, 1); + if (data->stdin_fd != -1) + dup2(data->stdin_fd, 0); + if (data->stdout_fd != -1) + dup2(data->stdout_fd, 1); } static int slirp_tramp(char **argv, int fd) @@ -39,8 +39,8 @@ static int slirp_tramp(char **argv, int fd) struct slirp_pre_exec_data pe_data; int pid; - pe_data.stdin = fd; - pe_data.stdout = fd; + pe_data.stdin_fd = fd; + pe_data.stdout_fd = fd; pid = run_helper(slirp_pre_exec, &pe_data, argv); return pid; diff --git a/kernel/arch/um/include/asm/Kbuild b/kernel/arch/um/include/asm/Kbuild index 9176fa11d..904f3ebf4 100644 --- a/kernel/arch/um/include/asm/Kbuild +++ b/kernel/arch/um/include/asm/Kbuild @@ -16,14 +16,14 @@ generic-y += irq_regs.h generic-y += irq_work.h generic-y += kdebug.h generic-y += mcs_spinlock.h +generic-y += mm-arch-hooks.h generic-y += mutex.h generic-y += param.h generic-y += pci.h generic-y += percpu.h generic-y += preempt.h -generic-y += scatterlist.h -generic-y += sections.h generic-y += switch_to.h generic-y += topology.h generic-y += trace_clock.h +generic-y += word-at-a-time.h generic-y += xor.h diff --git a/kernel/arch/um/include/asm/ptrace-generic.h b/kernel/arch/um/include/asm/ptrace-generic.h index cb9b3c47c..5ab20620f 100644 --- a/kernel/arch/um/include/asm/ptrace-generic.h +++ b/kernel/arch/um/include/asm/ptrace-generic.h @@ -8,7 +8,6 @@ #ifndef __ASSEMBLY__ -#include <asm/ptrace-abi.h> #include <sysdep/ptrace.h> struct pt_regs { @@ -28,6 +27,8 @@ struct pt_regs { #define instruction_pointer(regs) PT_REGS_IP(regs) +#define PTRACE_OLDSETOPTIONS 21 + struct task_struct; extern long subarch_ptrace(struct task_struct *child, long request, @@ -37,7 +38,7 @@ extern int putreg(struct task_struct *child, int regno, unsigned long value); extern int arch_copy_tls(struct task_struct *new); extern void clear_flushed_tls(struct task_struct *task); -extern void syscall_trace_enter(struct pt_regs *regs); +extern int syscall_trace_enter(struct pt_regs *regs); extern void syscall_trace_leave(struct pt_regs *regs); #endif diff --git a/kernel/arch/um/include/asm/sections.h b/kernel/arch/um/include/asm/sections.h new file mode 100644 index 000000000..cafcf684d --- /dev/null +++ b/kernel/arch/um/include/asm/sections.h @@ -0,0 +1,9 @@ +#ifndef __UM_SECTIONS_H +#define __UM_SECTIONS_H + +#include <asm-generic/sections.h> + +extern char __binary_start[]; +extern char __syscall_stub_start[], __syscall_stub_end[]; + +#endif diff --git a/kernel/arch/um/include/asm/thread_info.h b/kernel/arch/um/include/asm/thread_info.h index b30c85b14..53968aaf7 100644 --- a/kernel/arch/um/include/asm/thread_info.h +++ b/kernel/arch/um/include/asm/thread_info.h @@ -10,7 +10,7 @@ #include <asm/types.h> #include <asm/page.h> -#include <asm/uaccess.h> +#include <asm/segment.h> struct thread_info { struct task_struct *task; /* main task structure */ diff --git a/kernel/arch/um/include/asm/uaccess.h b/kernel/arch/um/include/asm/uaccess.h index 3f22fbf7c..3705620ca 100644 --- a/kernel/arch/um/include/asm/uaccess.h +++ b/kernel/arch/um/include/asm/uaccess.h @@ -1,178 +1,52 @@ /* * Copyright (C) 2002 Jeff Dike (jdike@karaya.com) + * Copyright (C) 2015 Richard Weinberger (richard@nod.at) * Licensed under the GPL */ #ifndef __UM_UACCESS_H #define __UM_UACCESS_H -/* thread_info has a mm_segment_t in it, so put the definition up here */ -typedef struct { - unsigned long seg; -} mm_segment_t; - -#include <linux/thread_info.h> -#include <linux/errno.h> -#include <asm/processor.h> +#include <asm/thread_info.h> #include <asm/elf.h> -#define VERIFY_READ 0 -#define VERIFY_WRITE 1 - -/* - * The fs value determines whether argument validity checking should be - * performed or not. If get_fs() == USER_DS, checking is performed, with - * get_fs() == KERNEL_DS, checking is bypassed. - * - * For historical reasons, these macros are grossly misnamed. - */ - -#define MAKE_MM_SEG(s) ((mm_segment_t) { (s) }) - -#define KERNEL_DS MAKE_MM_SEG(0xFFFFFFFF) -#define USER_DS MAKE_MM_SEG(TASK_SIZE) - -#define get_ds() (KERNEL_DS) -#define get_fs() (current_thread_info()->addr_limit) -#define set_fs(x) (current_thread_info()->addr_limit = (x)) - -#define segment_eq(a, b) ((a).seg == (b).seg) - #define __under_task_size(addr, size) \ (((unsigned long) (addr) < TASK_SIZE) && \ (((unsigned long) (addr) + (size)) < TASK_SIZE)) -#define __access_ok_vsyscall(type, addr, size) \ - ((type == VERIFY_READ) && \ - ((unsigned long) (addr) >= FIXADDR_USER_START) && \ +#define __access_ok_vsyscall(addr, size) \ + (((unsigned long) (addr) >= FIXADDR_USER_START) && \ ((unsigned long) (addr) + (size) <= FIXADDR_USER_END) && \ ((unsigned long) (addr) + (size) >= (unsigned long)(addr))) #define __addr_range_nowrap(addr, size) \ ((unsigned long) (addr) <= ((unsigned long) (addr) + (size))) -#define access_ok(type, addr, size) \ - (__addr_range_nowrap(addr, size) && \ - (__under_task_size(addr, size) || \ - __access_ok_vsyscall(type, addr, size) || \ - segment_eq(get_fs(), KERNEL_DS))) - -extern int copy_from_user(void *to, const void __user *from, int n); -extern int copy_to_user(void __user *to, const void *from, int n); - -/* - * strncpy_from_user: - Copy a NUL terminated string from userspace. - * @dst: Destination address, in kernel space. This buffer must be at - * least @count bytes long. - * @src: Source address, in user space. - * @count: Maximum number of bytes to copy, including the trailing NUL. - * - * Copies a NUL-terminated string from userspace to kernel space. - * - * On success, returns the length of the string (not including the trailing - * NUL). - * - * If access to userspace fails, returns -EFAULT (some data may have been - * copied). - * - * If @count is smaller than the length of the string, copies @count bytes - * and returns @count. - */ - -extern int strncpy_from_user(char *dst, const char __user *src, int count); - -/* - * __clear_user: - Zero a block of memory in user space, with less checking. - * @to: Destination address, in user space. - * @n: Number of bytes to zero. - * - * Zero a block of memory in user space. Caller must check - * the specified block with access_ok() before calling this function. - * - * Returns number of bytes that could not be cleared. - * On success, this will be zero. - */ -extern int __clear_user(void __user *mem, int len); - -/* - * clear_user: - Zero a block of memory in user space. - * @to: Destination address, in user space. - * @n: Number of bytes to zero. - * - * Zero a block of memory in user space. - * - * Returns number of bytes that could not be cleared. - * On success, this will be zero. - */ -extern int clear_user(void __user *mem, int len); - -/* - * strlen_user: - Get the size of a string in user space. - * @str: The string to measure. - * @n: The maximum valid length - * - * Get the size of a NUL-terminated string in user space. - * - * Returns the size of the string INCLUDING the terminating NUL. - * On exception, returns 0. - * If the string is too long, returns a value greater than @n. - */ -extern int strnlen_user(const void __user *str, int len); - -#define __copy_from_user(to, from, n) copy_from_user(to, from, n) - -#define __copy_to_user(to, from, n) copy_to_user(to, from, n) - +extern long __copy_from_user(void *to, const void __user *from, unsigned long n); +extern long __copy_to_user(void __user *to, const void *from, unsigned long n); +extern long __strncpy_from_user(char *dst, const char __user *src, long count); +extern long __strnlen_user(const void __user *str, long len); +extern unsigned long __clear_user(void __user *mem, unsigned long len); +static inline int __access_ok(unsigned long addr, unsigned long size); + +/* Teach asm-generic/uaccess.h that we have C functions for these. */ +#define __access_ok __access_ok +#define __clear_user __clear_user +#define __copy_to_user __copy_to_user +#define __copy_from_user __copy_from_user +#define __strnlen_user __strnlen_user +#define __strncpy_from_user __strncpy_from_user #define __copy_to_user_inatomic __copy_to_user #define __copy_from_user_inatomic __copy_from_user -#define __get_user(x, ptr) \ -({ \ - const __typeof__(*(ptr)) __user *__private_ptr = (ptr); \ - __typeof__(x) __private_val; \ - int __private_ret = -EFAULT; \ - (x) = (__typeof__(*(__private_ptr)))0; \ - if (__copy_from_user((__force void *)&__private_val, (__private_ptr),\ - sizeof(*(__private_ptr))) == 0) { \ - (x) = (__typeof__(*(__private_ptr))) __private_val; \ - __private_ret = 0; \ - } \ - __private_ret; \ -}) - -#define get_user(x, ptr) \ -({ \ - const __typeof__((*(ptr))) __user *private_ptr = (ptr); \ - (access_ok(VERIFY_READ, private_ptr, sizeof(*private_ptr)) ? \ - __get_user(x, private_ptr) : ((x) = (__typeof__(*ptr))0, -EFAULT)); \ -}) - -#define __put_user(x, ptr) \ -({ \ - __typeof__(*(ptr)) __user *__private_ptr = ptr; \ - __typeof__(*(__private_ptr)) __private_val; \ - int __private_ret = -EFAULT; \ - __private_val = (__typeof__(*(__private_ptr))) (x); \ - if (__copy_to_user((__private_ptr), &__private_val, \ - sizeof(*(__private_ptr))) == 0) { \ - __private_ret = 0; \ - } \ - __private_ret; \ -}) - -#define put_user(x, ptr) \ -({ \ - __typeof__(*(ptr)) __user *private_ptr = (ptr); \ - (access_ok(VERIFY_WRITE, private_ptr, sizeof(*private_ptr)) ? \ - __put_user(x, private_ptr) : -EFAULT); \ -}) - -#define strlen_user(str) strnlen_user(str, ~0U >> 1) +#include <asm-generic/uaccess.h> -struct exception_table_entry +static inline int __access_ok(unsigned long addr, unsigned long size) { - unsigned long insn; - unsigned long fixup; -}; + return __addr_range_nowrap(addr, size) && + (__under_task_size(addr, size) || + __access_ok_vsyscall(addr, size) || + segment_eq(get_fs(), KERNEL_DS)); +} #endif diff --git a/kernel/arch/um/include/shared/init.h b/kernel/arch/um/include/shared/init.h index b3906f860..233e2593e 100644 --- a/kernel/arch/um/include/shared/init.h +++ b/kernel/arch/um/include/shared/init.h @@ -40,28 +40,8 @@ typedef int (*initcall_t)(void); typedef void (*exitcall_t)(void); -#ifndef __KERNEL__ -#ifndef __section -# define __section(S) __attribute__ ((__section__(#S))) -#endif - -#if __GNUC__ == 3 - -#if __GNUC_MINOR__ >= 3 -# define __used __attribute__((__used__)) -#else -# define __used __attribute__((__unused__)) -#endif - -#else -#if __GNUC__ == 4 -# define __used __attribute__((__used__)) -#endif -#endif - -#else #include <linux/compiler.h> -#endif + /* These are for everybody (although not all archs will actually discard it in modules) */ #define __init __section(.init.text) @@ -131,7 +111,7 @@ extern struct uml_param __uml_setup_start, __uml_setup_end; #define __uml_postsetup_call __used __section(.uml.postsetup.init) #define __uml_exit_call __used __section(.uml.exitcall.exit) -#ifndef __KERNEL__ +#ifdef __UM_HOST__ #define __define_initcall(level,fn) \ static initcall_t __initcall_##fn __used \ diff --git a/kernel/arch/um/include/shared/kern_util.h b/kernel/arch/um/include/shared/kern_util.h index 83a91f976..35ab97e4b 100644 --- a/kernel/arch/um/include/shared/kern_util.h +++ b/kernel/arch/um/include/shared/kern_util.h @@ -22,7 +22,8 @@ extern int kmalloc_ok; extern unsigned long alloc_stack(int order, int atomic); extern void free_stack(unsigned long stack, int order); -extern int do_signal(void); +struct pt_regs; +extern void do_signal(struct pt_regs *regs); extern void interrupt_end(void); extern void relay_signal(int sig, struct siginfo *si, struct uml_pt_regs *regs); diff --git a/kernel/arch/um/include/shared/os.h b/kernel/arch/um/include/shared/os.h index d824528f6..868e6c3f8 100644 --- a/kernel/arch/um/include/shared/os.h +++ b/kernel/arch/um/include/shared/os.h @@ -1,4 +1,6 @@ /* + * Copyright (C) 2015 Anton Ivanov (aivanov@{brocade.com,kot-begemot.co.uk}) + * Copyright (C) 2015 Thomas Meyer (thomas@m3y3r.de) * Copyright (C) 2002 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com) * Licensed under the GPL */ @@ -183,6 +185,7 @@ extern int create_mem_file(unsigned long long len); /* process.c */ extern unsigned long os_process_pc(int pid); extern int os_process_parent(int pid); +extern void os_alarm_process(int pid); extern void os_stop_process(int pid); extern void os_kill_process(int pid, int reap_child); extern void os_kill_ptraced_process(int pid, int reap_child); @@ -217,7 +220,7 @@ extern int set_umid(char *name); extern char *get_umid(void); /* signal.c */ -extern void timer_init(void); +extern void timer_set_signal_handler(void); extern void set_sigstack(void *sig_stack, int size); extern void remove_sigstack(void); extern void set_handler(int sig); @@ -227,6 +230,7 @@ extern void unblock_signals(void); extern int get_signals(void); extern int set_signals(int enable); extern int os_is_signal_stack(void); +extern void deliver_alarm(void); /* util.c */ extern void stack_protections(unsigned long address); @@ -238,12 +242,16 @@ extern void um_early_printk(const char *s, unsigned int n); extern void os_fix_helper_signals(void); /* time.c */ -extern void idle_sleep(unsigned long long nsecs); -extern int set_interval(void); -extern int timer_one_shot(int ticks); -extern long long disable_timer(void); +extern void os_idle_sleep(unsigned long long nsecs); +extern int os_timer_create(void* timer); +extern int os_timer_set_interval(void* timer, void* its); +extern int os_timer_one_shot(int ticks); +extern long long os_timer_disable(void); +extern long os_timer_remain(void* timer); extern void uml_idle_timer(void); +extern long long os_persistent_clock_emulation(void); extern long long os_nsecs(void); +extern long long os_vnsecs(void); /* skas/mem.c */ extern long run_syscall_stub(struct mm_id * mm_idp, @@ -274,6 +282,7 @@ extern void initial_thread_cb_skas(void (*proc)(void *), void *arg); extern void halt_skas(void); extern void reboot_skas(void); +extern int get_syscall(struct uml_pt_regs *regs); /* irq.c */ extern int os_waiting_for_events(struct irq_fd *active_fds); @@ -301,4 +310,6 @@ extern int get_pty(void); /* sys-$ARCH/task_size.c */ extern unsigned long os_get_top_address(void); +long syscall(long number, ...); + #endif diff --git a/kernel/arch/um/include/shared/skas/stub-data.h b/kernel/arch/um/include/shared/skas/stub-data.h index f6ed92c37..a9deece95 100644 --- a/kernel/arch/um/include/shared/skas/stub-data.h +++ b/kernel/arch/um/include/shared/skas/stub-data.h @@ -1,4 +1,6 @@ /* + + * Copyright (C) 2015 Thomas Meyer (thomas@m3y3r.de) * Copyright (C) 2005 Jeff Dike (jdike@karaya.com) * Licensed under the GPL */ @@ -6,12 +8,11 @@ #ifndef __STUB_DATA_H #define __STUB_DATA_H -#include <sys/time.h> +#include <time.h> struct stub_data { - long offset; + unsigned long offset; int fd; - struct itimerval timer; long err; }; diff --git a/kernel/arch/um/include/shared/timer-internal.h b/kernel/arch/um/include/shared/timer-internal.h new file mode 100644 index 000000000..03e6f217f --- /dev/null +++ b/kernel/arch/um/include/shared/timer-internal.h @@ -0,0 +1,13 @@ +/* + * Copyright (C) 2012 - 2014 Cisco Systems + * Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com) + * Licensed under the GPL + */ + +#ifndef __TIMER_INTERNAL_H__ +#define __TIMER_INTERNAL_H__ + +#define TIMER_MULTIPLIER 256 +#define TIMER_MIN_DELTA 500 + +#endif diff --git a/kernel/arch/um/include/shared/user.h b/kernel/arch/um/include/shared/user.h index cef068563..4cff19f62 100644 --- a/kernel/arch/um/include/shared/user.h +++ b/kernel/arch/um/include/shared/user.h @@ -17,7 +17,7 @@ #define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) /* This is to get size_t */ -#ifdef __KERNEL__ +#ifndef __UM_HOST__ #include <linux/types.h> #else #include <stddef.h> diff --git a/kernel/arch/um/kernel/ksyms.c b/kernel/arch/um/kernel/ksyms.c index 543c04756..232b22307 100644 --- a/kernel/arch/um/kernel/ksyms.c +++ b/kernel/arch/um/kernel/ksyms.c @@ -42,3 +42,5 @@ EXPORT_SYMBOL(os_makedev); EXPORT_SYMBOL(add_sigio_fd); EXPORT_SYMBOL(ignore_sigio_fd); EXPORT_SYMBOL(sigio_broken); + +EXPORT_SYMBOL(syscall); diff --git a/kernel/arch/um/kernel/physmem.c b/kernel/arch/um/kernel/physmem.c index 9034fc805..4c9861b42 100644 --- a/kernel/arch/um/kernel/physmem.c +++ b/kernel/arch/um/kernel/physmem.c @@ -8,6 +8,7 @@ #include <linux/mm.h> #include <linux/pfn.h> #include <asm/page.h> +#include <asm/sections.h> #include <as-layout.h> #include <init.h> #include <kern.h> @@ -55,8 +56,6 @@ void map_memory(unsigned long virt, unsigned long phys, unsigned long len, } } -extern int __syscall_stub_start; - /** * setup_physmem() - Setup physical memory for UML * @start: Start address of the physical kernel memory, @@ -110,8 +109,8 @@ void __init setup_physmem(unsigned long start, unsigned long reserve_end, * Special kludge - This page will be mapped in to userspace processes * from physmem_fd, so it needs to be written out there. */ - os_seek_file(physmem_fd, __pa(&__syscall_stub_start)); - os_write_file(physmem_fd, &__syscall_stub_start, PAGE_SIZE); + os_seek_file(physmem_fd, __pa(__syscall_stub_start)); + os_write_file(physmem_fd, __syscall_stub_start, PAGE_SIZE); os_fsync_file(physmem_fd); bootmap_size = init_bootmem(pfn, pfn + delta); diff --git a/kernel/arch/um/kernel/process.c b/kernel/arch/um/kernel/process.c index 68b911984..48af59aae 100644 --- a/kernel/arch/um/kernel/process.c +++ b/kernel/arch/um/kernel/process.c @@ -1,4 +1,6 @@ /* + * Copyright (C) 2015 Anton Ivanov (aivanov@{brocade.com,kot-begemot.co.uk}) + * Copyright (C) 2015 Thomas Meyer (thomas@m3y3r.de) * Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com) * Copyright 2003 PathScale, Inc. * Licensed under the GPL @@ -27,6 +29,7 @@ #include <kern_util.h> #include <os.h> #include <skas.h> +#include <timer-internal.h> /* * This is a per-cpu array. A processor only modifies its entry and it only @@ -90,12 +93,14 @@ void *__switch_to(struct task_struct *from, struct task_struct *to) void interrupt_end(void) { + struct pt_regs *regs = ¤t->thread.regs; + if (need_resched()) schedule(); if (test_thread_flag(TIF_SIGPENDING)) - do_signal(); + do_signal(regs); if (test_and_clear_thread_flag(TIF_NOTIFY_RESUME)) - tracehook_notify_resume(¤t->thread.regs); + tracehook_notify_resume(regs); } void exit_thread(void) @@ -201,11 +206,8 @@ void initial_thread_cb(void (*proc)(void *), void *arg) void arch_cpu_idle(void) { - unsigned long long nsecs; - cpu_tasks[current_thread_info()->cpu].pid = os_getpid(); - nsecs = disable_timer(); - idle_sleep(nsecs); + os_idle_sleep(UM_NSEC_PER_SEC); local_irq_enable(); } diff --git a/kernel/arch/um/kernel/ptrace.c b/kernel/arch/um/kernel/ptrace.c index 174ee5017..6a826cbb1 100644 --- a/kernel/arch/um/kernel/ptrace.c +++ b/kernel/arch/um/kernel/ptrace.c @@ -8,6 +8,7 @@ #include <linux/sched.h> #include <linux/tracehook.h> #include <asm/uaccess.h> +#include <asm/ptrace-abi.h> void user_enable_single_step(struct task_struct *child) { @@ -131,7 +132,7 @@ static void send_sigtrap(struct task_struct *tsk, struct uml_pt_regs *regs, * XXX Check PT_DTRACE vs TIF_SINGLESTEP for singlestepping check and * PT_PTRACED vs TIF_SYSCALL_TRACE for syscall tracing check */ -void syscall_trace_enter(struct pt_regs *regs) +int syscall_trace_enter(struct pt_regs *regs) { audit_syscall_entry(UPT_SYSCALL_NR(®s->regs), UPT_SYSCALL_ARG1(®s->regs), @@ -140,9 +141,9 @@ void syscall_trace_enter(struct pt_regs *regs) UPT_SYSCALL_ARG4(®s->regs)); if (!test_thread_flag(TIF_SYSCALL_TRACE)) - return; + return 0; - tracehook_report_syscall_entry(regs); + return tracehook_report_syscall_entry(regs); } void syscall_trace_leave(struct pt_regs *regs) diff --git a/kernel/arch/um/kernel/signal.c b/kernel/arch/um/kernel/signal.c index 4f60e4aad..fc8be0e3a 100644 --- a/kernel/arch/um/kernel/signal.c +++ b/kernel/arch/um/kernel/signal.c @@ -64,12 +64,12 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs) signal_setup_done(err, ksig, singlestep); } -static int kern_do_signal(struct pt_regs *regs) +void do_signal(struct pt_regs *regs) { struct ksignal ksig; int handled_sig = 0; - while (get_signal(&ksig)) { + if (get_signal(&ksig)) { handled_sig = 1; /* Whee! Actually deliver the signal. */ handle_signal(&ksig, regs); @@ -110,10 +110,4 @@ static int kern_do_signal(struct pt_regs *regs) */ if (!handled_sig) restore_saved_sigmask(); - return handled_sig; -} - -int do_signal(void) -{ - return kern_do_signal(¤t->thread.regs); } diff --git a/kernel/arch/um/kernel/skas/clone.c b/kernel/arch/um/kernel/skas/clone.c index 289771dad..0f25d41b1 100644 --- a/kernel/arch/um/kernel/skas/clone.c +++ b/kernel/arch/um/kernel/skas/clone.c @@ -1,4 +1,5 @@ /* + * Copyright (C) 2015 Thomas Meyer (thomas@m3y3r.de) * Copyright (C) 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com) * Licensed under the GPL */ @@ -35,11 +36,6 @@ stub_clone_handler(void) if (err) goto out; - err = stub_syscall3(__NR_setitimer, ITIMER_VIRTUAL, - (long) &data->timer, 0); - if (err) - goto out; - remap_stack(data->fd, data->offset); goto done; diff --git a/kernel/arch/um/kernel/skas/mmu.c b/kernel/arch/um/kernel/skas/mmu.c index 94abdcc1d..9591a66aa 100644 --- a/kernel/arch/um/kernel/skas/mmu.c +++ b/kernel/arch/um/kernel/skas/mmu.c @@ -1,4 +1,5 @@ /* + * Copyright (C) 2015 Thomas Meyer (thomas@m3y3r.de) * Copyright (C) 2002 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com) * Licensed under the GPL */ @@ -8,12 +9,11 @@ #include <linux/slab.h> #include <asm/pgalloc.h> #include <asm/pgtable.h> +#include <asm/sections.h> #include <as-layout.h> #include <os.h> #include <skas.h> -extern int __syscall_stub_start; - static int init_stub_pte(struct mm_struct *mm, unsigned long proc, unsigned long kernel) { @@ -62,10 +62,12 @@ int init_new_context(struct task_struct *task, struct mm_struct *mm) if (current->mm != NULL && current->mm != &init_mm) from_mm = ¤t->mm->context; + block_signals(); if (from_mm) to_mm->id.u.pid = copy_context_skas0(stack, from_mm->id.u.pid); else to_mm->id.u.pid = start_userspace(stack); + unblock_signals(); if (to_mm->id.u.pid < 0) { ret = to_mm->id.u.pid; @@ -93,7 +95,7 @@ void uml_setup_stubs(struct mm_struct *mm) int err, ret; ret = init_stub_pte(mm, STUB_CODE, - (unsigned long) &__syscall_stub_start); + (unsigned long) __syscall_stub_start); if (ret) goto out; @@ -101,7 +103,7 @@ void uml_setup_stubs(struct mm_struct *mm) if (ret) goto out; - mm->context.stub_pages[0] = virt_to_page(&__syscall_stub_start); + mm->context.stub_pages[0] = virt_to_page(__syscall_stub_start); mm->context.stub_pages[1] = virt_to_page(mm->context.id.stack); /* dup_mmap already holds mmap_sem */ diff --git a/kernel/arch/um/kernel/skas/syscall.c b/kernel/arch/um/kernel/skas/syscall.c index c0681e097..1683b8efd 100644 --- a/kernel/arch/um/kernel/skas/syscall.c +++ b/kernel/arch/um/kernel/skas/syscall.c @@ -8,9 +8,7 @@ #include <kern_util.h> #include <sysdep/ptrace.h> #include <sysdep/syscalls.h> - -extern int syscall_table_size; -#define NR_SYSCALLS (syscall_table_size / sizeof(void *)) +#include <os.h> void handle_syscall(struct uml_pt_regs *r) { @@ -18,22 +16,19 @@ void handle_syscall(struct uml_pt_regs *r) long result; int syscall; - syscall_trace_enter(regs); + if (syscall_trace_enter(regs)) { + result = -ENOSYS; + goto out; + } + + syscall = get_syscall(r); - /* - * This should go in the declaration of syscall, but when I do that, - * strace -f -c bash -c 'ls ; ls' breaks, sometimes not tracing - * children at all, sometimes hanging when bash doesn't see the first - * ls exit. - * The assembly looks functionally the same to me. This is - * gcc version 4.0.1 20050727 (Red Hat 4.0.1-5) - * in case it's a compiler bug. - */ - syscall = UPT_SYSCALL_NR(r); - if ((syscall >= NR_SYSCALLS) || (syscall < 0)) + if ((syscall > __NR_syscall_max) || syscall < 0) result = -ENOSYS; - else result = EXECUTE_SYSCALL(syscall, regs); + else + result = EXECUTE_SYSCALL(syscall, regs); +out: PT_REGS_SET_SYSCALL_RETURN(regs, result); syscall_trace_leave(regs); diff --git a/kernel/arch/um/kernel/skas/uaccess.c b/kernel/arch/um/kernel/skas/uaccess.c index 4ffb644d6..85ac8adb0 100644 --- a/kernel/arch/um/kernel/skas/uaccess.c +++ b/kernel/arch/um/kernel/skas/uaccess.c @@ -87,10 +87,10 @@ static int do_op_one_page(unsigned long addr, int len, int is_write, return n; } -static int buffer_op(unsigned long addr, int len, int is_write, - int (*op)(unsigned long, int, void *), void *arg) +static long buffer_op(unsigned long addr, int len, int is_write, + int (*op)(unsigned long, int, void *), void *arg) { - int size, remain, n; + long size, remain, n; size = min(PAGE_ALIGN(addr) - addr, (unsigned long) len); remain = len; @@ -139,18 +139,16 @@ static int copy_chunk_from_user(unsigned long from, int len, void *arg) return 0; } -int copy_from_user(void *to, const void __user *from, int n) +long __copy_from_user(void *to, const void __user *from, unsigned long n) { if (segment_eq(get_fs(), KERNEL_DS)) { memcpy(to, (__force void*)from, n); return 0; } - return access_ok(VERIFY_READ, from, n) ? - buffer_op((unsigned long) from, n, 0, copy_chunk_from_user, &to): - n; + return buffer_op((unsigned long) from, n, 0, copy_chunk_from_user, &to); } -EXPORT_SYMBOL(copy_from_user); +EXPORT_SYMBOL(__copy_from_user); static int copy_chunk_to_user(unsigned long to, int len, void *arg) { @@ -161,18 +159,16 @@ static int copy_chunk_to_user(unsigned long to, int len, void *arg) return 0; } -int copy_to_user(void __user *to, const void *from, int n) +long __copy_to_user(void __user *to, const void *from, unsigned long n) { if (segment_eq(get_fs(), KERNEL_DS)) { memcpy((__force void *) to, from, n); return 0; } - return access_ok(VERIFY_WRITE, to, n) ? - buffer_op((unsigned long) to, n, 1, copy_chunk_to_user, &from) : - n; + return buffer_op((unsigned long) to, n, 1, copy_chunk_to_user, &from); } -EXPORT_SYMBOL(copy_to_user); +EXPORT_SYMBOL(__copy_to_user); static int strncpy_chunk_from_user(unsigned long from, int len, void *arg) { @@ -188,9 +184,9 @@ static int strncpy_chunk_from_user(unsigned long from, int len, void *arg) return 0; } -int strncpy_from_user(char *dst, const char __user *src, int count) +long __strncpy_from_user(char *dst, const char __user *src, long count) { - int n; + long n; char *ptr = dst; if (segment_eq(get_fs(), KERNEL_DS)) { @@ -198,16 +194,13 @@ int strncpy_from_user(char *dst, const char __user *src, int count) return strnlen(dst, count); } - if (!access_ok(VERIFY_READ, src, 1)) - return -EFAULT; - n = buffer_op((unsigned long) src, count, 0, strncpy_chunk_from_user, &ptr); if (n != 0) return -EFAULT; return strnlen(dst, count); } -EXPORT_SYMBOL(strncpy_from_user); +EXPORT_SYMBOL(__strncpy_from_user); static int clear_chunk(unsigned long addr, int len, void *unused) { @@ -215,22 +208,16 @@ static int clear_chunk(unsigned long addr, int len, void *unused) return 0; } -int __clear_user(void __user *mem, int len) -{ - return buffer_op((unsigned long) mem, len, 1, clear_chunk, NULL); -} - -int clear_user(void __user *mem, int len) +unsigned long __clear_user(void __user *mem, unsigned long len) { if (segment_eq(get_fs(), KERNEL_DS)) { memset((__force void*)mem, 0, len); return 0; } - return access_ok(VERIFY_WRITE, mem, len) ? - buffer_op((unsigned long) mem, len, 1, clear_chunk, NULL) : len; + return buffer_op((unsigned long) mem, len, 1, clear_chunk, NULL); } -EXPORT_SYMBOL(clear_user); +EXPORT_SYMBOL(__clear_user); static int strnlen_chunk(unsigned long str, int len, void *arg) { @@ -244,7 +231,7 @@ static int strnlen_chunk(unsigned long str, int len, void *arg) return 0; } -int strnlen_user(const void __user *str, int len) +long __strnlen_user(const void __user *str, long len) { int count = 0, n; @@ -256,4 +243,4 @@ int strnlen_user(const void __user *str, int len) return count + 1; return 0; } -EXPORT_SYMBOL(strnlen_user); +EXPORT_SYMBOL(__strnlen_user); diff --git a/kernel/arch/um/kernel/time.c b/kernel/arch/um/kernel/time.c index 117568d4f..25c23666d 100644 --- a/kernel/arch/um/kernel/time.c +++ b/kernel/arch/um/kernel/time.c @@ -1,4 +1,7 @@ /* + * Copyright (C) 2015 Anton Ivanov (aivanov@{brocade.com,kot-begemot.co.uk}) + * Copyright (C) 2015 Thomas Meyer (thomas@m3y3r.de) + * Copyright (C) 2012-2014 Cisco Systems * Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com) * Licensed under the GPL */ @@ -7,11 +10,15 @@ #include <linux/init.h> #include <linux/interrupt.h> #include <linux/jiffies.h> +#include <linux/mm.h> +#include <linux/sched.h> +#include <linux/spinlock.h> #include <linux/threads.h> #include <asm/irq.h> #include <asm/param.h> #include <kern_util.h> #include <os.h> +#include <timer-internal.h> void timer_handler(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs) { @@ -22,87 +29,99 @@ void timer_handler(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs) local_irq_restore(flags); } -static void itimer_set_mode(enum clock_event_mode mode, - struct clock_event_device *evt) +static int itimer_shutdown(struct clock_event_device *evt) { - switch (mode) { - case CLOCK_EVT_MODE_PERIODIC: - set_interval(); - break; - - case CLOCK_EVT_MODE_SHUTDOWN: - case CLOCK_EVT_MODE_UNUSED: - case CLOCK_EVT_MODE_ONESHOT: - disable_timer(); - break; - - case CLOCK_EVT_MODE_RESUME: - break; - } + os_timer_disable(); + return 0; +} + +static int itimer_set_periodic(struct clock_event_device *evt) +{ + os_timer_set_interval(NULL, NULL); + return 0; } static int itimer_next_event(unsigned long delta, struct clock_event_device *evt) { - return timer_one_shot(delta + 1); + return os_timer_one_shot(delta); +} + +static int itimer_one_shot(struct clock_event_device *evt) +{ + os_timer_one_shot(1); + return 0; } -static struct clock_event_device itimer_clockevent = { - .name = "itimer", - .rating = 250, - .cpumask = cpu_all_mask, - .features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT, - .set_mode = itimer_set_mode, - .set_next_event = itimer_next_event, - .shift = 32, - .irq = 0, +static struct clock_event_device timer_clockevent = { + .name = "posix-timer", + .rating = 250, + .cpumask = cpu_all_mask, + .features = CLOCK_EVT_FEAT_PERIODIC | + CLOCK_EVT_FEAT_ONESHOT, + .set_state_shutdown = itimer_shutdown, + .set_state_periodic = itimer_set_periodic, + .set_state_oneshot = itimer_one_shot, + .set_next_event = itimer_next_event, + .shift = 0, + .max_delta_ns = 0xffffffff, + .min_delta_ns = TIMER_MIN_DELTA, //microsecond resolution should be enough for anyone, same as 640K RAM + .irq = 0, + .mult = 1, }; static irqreturn_t um_timer(int irq, void *dev) { - (*itimer_clockevent.event_handler)(&itimer_clockevent); + if (get_current()->mm != NULL) + { + /* userspace - relay signal, results in correct userspace timers */ + os_alarm_process(get_current()->mm->context.id.u.pid); + } + + (*timer_clockevent.event_handler)(&timer_clockevent); return IRQ_HANDLED; } -static cycle_t itimer_read(struct clocksource *cs) +static cycle_t timer_read(struct clocksource *cs) { - return os_nsecs() / 1000; + return os_nsecs() / TIMER_MULTIPLIER; } -static struct clocksource itimer_clocksource = { - .name = "itimer", +static struct clocksource timer_clocksource = { + .name = "timer", .rating = 300, - .read = itimer_read, + .read = timer_read, .mask = CLOCKSOURCE_MASK(64), .flags = CLOCK_SOURCE_IS_CONTINUOUS, }; -static void __init setup_itimer(void) +static void __init timer_setup(void) { int err; - err = request_irq(TIMER_IRQ, um_timer, 0, "timer", NULL); + err = request_irq(TIMER_IRQ, um_timer, IRQF_TIMER, "hr timer", NULL); if (err != 0) printk(KERN_ERR "register_timer : request_irq failed - " "errno = %d\n", -err); - itimer_clockevent.mult = div_sc(HZ, NSEC_PER_SEC, 32); - itimer_clockevent.max_delta_ns = - clockevent_delta2ns(60 * HZ, &itimer_clockevent); - itimer_clockevent.min_delta_ns = - clockevent_delta2ns(1, &itimer_clockevent); - err = clocksource_register_hz(&itimer_clocksource, USEC_PER_SEC); + err = os_timer_create(NULL); + if (err != 0) { + printk(KERN_ERR "creation of timer failed - errno = %d\n", -err); + return; + } + + err = clocksource_register_hz(&timer_clocksource, NSEC_PER_SEC/TIMER_MULTIPLIER); if (err) { printk(KERN_ERR "clocksource_register_hz returned %d\n", err); return; } - clockevents_register_device(&itimer_clockevent); + clockevents_register_device(&timer_clockevent); } void read_persistent_clock(struct timespec *ts) { - long long nsecs = os_nsecs(); + long long nsecs = os_persistent_clock_emulation(); set_normalized_timespec(ts, nsecs / NSEC_PER_SEC, nsecs % NSEC_PER_SEC); @@ -110,6 +129,6 @@ void read_persistent_clock(struct timespec *ts) void __init time_init(void) { - timer_init(); - late_time_init = setup_itimer; + timer_set_signal_handler(); + late_time_init = timer_setup; } diff --git a/kernel/arch/um/kernel/tlb.c b/kernel/arch/um/kernel/tlb.c index f1b3eb14b..3777b8275 100644 --- a/kernel/arch/um/kernel/tlb.c +++ b/kernel/arch/um/kernel/tlb.c @@ -50,6 +50,13 @@ struct host_vm_change { .index = 0, \ .force = force }) +static void report_enomem(void) +{ + printk(KERN_ERR "UML ran out of memory on the host side! " + "This can happen due to a memory limitation or " + "vm.max_map_count has been reached.\n"); +} + static int do_ops(struct host_vm_change *hvc, int end, int finished) { @@ -81,6 +88,9 @@ static int do_ops(struct host_vm_change *hvc, int end, } } + if (ret == -ENOMEM) + report_enomem(); + return ret; } @@ -291,7 +301,7 @@ void fix_range_common(struct mm_struct *mm, unsigned long start_addr, /* We are under mmap_sem, release it such that current can terminate */ up_write(¤t->mm->mmap_sem); force_sig(SIGKILL, current); - do_signal(); + do_signal(¤t->thread.regs); } } @@ -433,8 +443,12 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long address) else if (pte_newprot(*pte)) err = protect(mm_id, address, PAGE_SIZE, prot, 1, &flush); - if (err) + if (err) { + if (err == -ENOMEM) + report_enomem(); + goto kill; + } *pte = pte_mkuptodate(*pte); diff --git a/kernel/arch/um/kernel/trap.c b/kernel/arch/um/kernel/trap.c index f9c9e5a6b..98783dd0f 100644 --- a/kernel/arch/um/kernel/trap.c +++ b/kernel/arch/um/kernel/trap.c @@ -7,6 +7,7 @@ #include <linux/sched.h> #include <linux/hardirq.h> #include <linux/module.h> +#include <linux/uaccess.h> #include <asm/current.h> #include <asm/pgtable.h> #include <asm/tlbflush.h> @@ -172,7 +173,7 @@ static void bad_segv(struct faultinfo fi, unsigned long ip) void fatal_sigsegv(void) { force_sigsegv(SIGSEGV, current); - do_signal(); + do_signal(¤t->thread.regs); /* * This is to tell gcc that we're not returning - do_signal * can, in general, return, but in this case, it's not, since @@ -219,6 +220,11 @@ unsigned long segv(struct faultinfo fi, unsigned long ip, int is_user, show_regs(container_of(regs, struct pt_regs, regs)); panic("Segfault with no mm"); } + else if (!is_user && address > PAGE_SIZE && address < TASK_SIZE) { + show_regs(container_of(regs, struct pt_regs, regs)); + panic("Kernel tried to access user memory at addr 0x%lx, ip 0x%lx", + address, ip); + } if (SEGV_IS_FIXABLE(&fi)) err = handle_page_fault(address, ip, is_write, is_user, diff --git a/kernel/arch/um/kernel/um_arch.c b/kernel/arch/um/kernel/um_arch.c index 07f798f4b..16630e75f 100644 --- a/kernel/arch/um/kernel/um_arch.c +++ b/kernel/arch/um/kernel/um_arch.c @@ -248,8 +248,6 @@ EXPORT_SYMBOL(end_iomem); #define MIN_VMALLOC (32 * 1024 * 1024) -extern char __binary_start; - int __init linux_main(int argc, char **argv) { unsigned long avail, diff; @@ -294,7 +292,7 @@ int __init linux_main(int argc, char **argv) physmem_size += UML_ROUND_UP(brk_start) - UML_ROUND_UP(&_end); } - uml_physmem = (unsigned long) &__binary_start & PAGE_MASK; + uml_physmem = (unsigned long) __binary_start & PAGE_MASK; /* Reserve up to 4M after the current brk */ uml_reserved = ROUND_4M(brk_start) + (1 << 22); diff --git a/kernel/arch/um/os-Linux/drivers/ethertap_user.c b/kernel/arch/um/os-Linux/drivers/ethertap_user.c index b39b6696a..6d4918246 100644 --- a/kernel/arch/um/os-Linux/drivers/ethertap_user.c +++ b/kernel/arch/um/os-Linux/drivers/ethertap_user.c @@ -105,7 +105,7 @@ static int etap_tramp(char *dev, char *gate, int control_me, sprintf(data_fd_buf, "%d", data_remote); sprintf(version_buf, "%d", UML_NET_VERSION); if (gate != NULL) { - strcpy(gate_buf, gate); + strncpy(gate_buf, gate, 15); args = setup_args; } else args = nosetup_args; diff --git a/kernel/arch/um/os-Linux/drivers/tuntap_user.c b/kernel/arch/um/os-Linux/drivers/tuntap_user.c index 14126d917..c2e6e1dad 100644 --- a/kernel/arch/um/os-Linux/drivers/tuntap_user.c +++ b/kernel/arch/um/os-Linux/drivers/tuntap_user.c @@ -47,7 +47,7 @@ static void tuntap_del_addr(unsigned char *addr, unsigned char *netmask, } struct tuntap_pre_exec_data { - int stdout; + int stdout_fd; int close_me; }; @@ -55,7 +55,7 @@ static void tuntap_pre_exec(void *arg) { struct tuntap_pre_exec_data *data = arg; - dup2(data->stdout, 1); + dup2(data->stdout_fd, 1); close(data->close_me); } @@ -74,7 +74,7 @@ static int tuntap_open_tramp(char *gate, int *fd_out, int me, int remote, sprintf(version_buf, "%d", UML_NET_VERSION); - data.stdout = remote; + data.stdout_fd = remote; data.close_me = me; pid = run_helper(tuntap_pre_exec, &data, argv); diff --git a/kernel/arch/um/os-Linux/file.c b/kernel/arch/um/os-Linux/file.c index 08d90fba9..26e016489 100644 --- a/kernel/arch/um/os-Linux/file.c +++ b/kernel/arch/um/os-Linux/file.c @@ -13,6 +13,7 @@ #include <sys/socket.h> #include <sys/stat.h> #include <sys/un.h> +#include <sys/types.h> #include <os.h> static void copy_stat(struct uml_stat *dst, const struct stat64 *src) diff --git a/kernel/arch/um/os-Linux/helper.c b/kernel/arch/um/os-Linux/helper.c index e3ee4a51e..3f02d4232 100644 --- a/kernel/arch/um/os-Linux/helper.c +++ b/kernel/arch/um/os-Linux/helper.c @@ -96,7 +96,7 @@ int run_helper(void (*pre_exec)(void *), void *pre_data, char **argv) "ret = %d\n", -n); ret = n; } - CATCH_EINTR(waitpid(pid, NULL, __WCLONE)); + CATCH_EINTR(waitpid(pid, NULL, __WALL)); } out_free2: @@ -129,7 +129,7 @@ int run_helper_thread(int (*proc)(void *), void *arg, unsigned int flags, return err; } if (stack_out == NULL) { - CATCH_EINTR(pid = waitpid(pid, &status, __WCLONE)); + CATCH_EINTR(pid = waitpid(pid, &status, __WALL)); if (pid < 0) { err = -errno; printk(UM_KERN_ERR "run_helper_thread - wait failed, " @@ -148,7 +148,7 @@ int run_helper_thread(int (*proc)(void *), void *arg, unsigned int flags, int helper_wait(int pid) { int ret, status; - int wflags = __WCLONE; + int wflags = __WALL; CATCH_EINTR(ret = waitpid(pid, &status, wflags)); if (ret < 0) { diff --git a/kernel/arch/um/os-Linux/internal.h b/kernel/arch/um/os-Linux/internal.h deleted file mode 100644 index 0dc2c9f13..000000000 --- a/kernel/arch/um/os-Linux/internal.h +++ /dev/null @@ -1 +0,0 @@ -void alarm_handler(int sig, struct siginfo *unused_si, mcontext_t *mc); diff --git a/kernel/arch/um/os-Linux/main.c b/kernel/arch/um/os-Linux/main.c index df9191acd..9d499de87 100644 --- a/kernel/arch/um/os-Linux/main.c +++ b/kernel/arch/um/os-Linux/main.c @@ -1,4 +1,5 @@ /* + * Copyright (C) 2015 Thomas Meyer (thomas@m3y3r.de) * Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com) * Licensed under the GPL */ @@ -163,13 +164,13 @@ int __init main(int argc, char **argv, char **envp) /* * This signal stuff used to be in the reboot case. However, - * sometimes a SIGVTALRM can come in when we're halting (reproducably + * sometimes a timer signal can come in when we're halting (reproducably * when writing out gcov information, presumably because that takes * some time) and cause a segfault. */ - /* stop timers and set SIGVTALRM to be ignored */ - disable_timer(); + /* stop timers and set timer signal to be ignored */ + os_timer_disable(); /* disable SIGIO for the fds and set SIGIO to be ignored */ err = deactivate_all_fds(); diff --git a/kernel/arch/um/os-Linux/process.c b/kernel/arch/um/os-Linux/process.c index 8408aba91..b3e0d4093 100644 --- a/kernel/arch/um/os-Linux/process.c +++ b/kernel/arch/um/os-Linux/process.c @@ -1,4 +1,5 @@ /* + * Copyright (C) 2015 Thomas Meyer (thomas@m3y3r.de) * Copyright (C) 2002 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com) * Licensed under the GPL */ @@ -89,6 +90,11 @@ int os_process_parent(int pid) return parent; } +void os_alarm_process(int pid) +{ + kill(pid, SIGALRM); +} + void os_stop_process(int pid) { kill(pid, SIGSTOP); diff --git a/kernel/arch/um/os-Linux/signal.c b/kernel/arch/um/os-Linux/signal.c index 7b605e4df..c211153ca 100644 --- a/kernel/arch/um/os-Linux/signal.c +++ b/kernel/arch/um/os-Linux/signal.c @@ -1,4 +1,6 @@ /* + * Copyright (C) 2015 Anton Ivanov (aivanov@{brocade.com,kot-begemot.co.uk}) + * Copyright (C) 2015 Thomas Meyer (thomas@m3y3r.de) * Copyright (C) 2004 PathScale, Inc * Copyright (C) 2004 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com) * Licensed under the GPL @@ -13,7 +15,6 @@ #include <kern_util.h> #include <os.h> #include <sysdep/mcontext.h> -#include "internal.h" void (*sig_info[NSIG])(int, struct siginfo *, struct uml_pt_regs *) = { [SIGTRAP] = relay_signal, @@ -23,7 +24,8 @@ void (*sig_info[NSIG])(int, struct siginfo *, struct uml_pt_regs *) = { [SIGBUS] = bus_handler, [SIGSEGV] = segv_handler, [SIGIO] = sigio_handler, - [SIGVTALRM] = timer_handler }; + [SIGALRM] = timer_handler +}; static void sig_handler_common(int sig, struct siginfo *si, mcontext_t *mc) { @@ -38,7 +40,7 @@ static void sig_handler_common(int sig, struct siginfo *si, mcontext_t *mc) } /* enable signals if sig isn't IRQ signal */ - if ((sig != SIGIO) && (sig != SIGWINCH) && (sig != SIGVTALRM)) + if ((sig != SIGIO) && (sig != SIGWINCH) && (sig != SIGALRM)) unblock_signals(); (*sig_info[sig])(sig, si, &r); @@ -55,8 +57,8 @@ static void sig_handler_common(int sig, struct siginfo *si, mcontext_t *mc) #define SIGIO_BIT 0 #define SIGIO_MASK (1 << SIGIO_BIT) -#define SIGVTALRM_BIT 1 -#define SIGVTALRM_MASK (1 << SIGVTALRM_BIT) +#define SIGALRM_BIT 1 +#define SIGALRM_MASK (1 << SIGALRM_BIT) static int signals_enabled; static unsigned int signals_pending; @@ -78,43 +80,47 @@ void sig_handler(int sig, struct siginfo *si, mcontext_t *mc) set_signals(enabled); } -static void real_alarm_handler(mcontext_t *mc) +static void timer_real_alarm_handler(mcontext_t *mc) { struct uml_pt_regs regs; if (mc != NULL) get_regs_from_mc(®s, mc); - regs.is_user = 0; - unblock_signals(); - timer_handler(SIGVTALRM, NULL, ®s); + timer_handler(SIGALRM, NULL, ®s); } -void alarm_handler(int sig, struct siginfo *unused_si, mcontext_t *mc) +void timer_alarm_handler(int sig, struct siginfo *unused_si, mcontext_t *mc) { int enabled; enabled = signals_enabled; if (!signals_enabled) { - signals_pending |= SIGVTALRM_MASK; + signals_pending |= SIGALRM_MASK; return; } block_signals(); - real_alarm_handler(mc); + timer_real_alarm_handler(mc); set_signals(enabled); } -void timer_init(void) +void deliver_alarm(void) { + timer_alarm_handler(SIGALRM, NULL, NULL); +} + +void timer_set_signal_handler(void) { - set_handler(SIGVTALRM); + set_handler(SIGALRM); } void set_sigstack(void *sig_stack, int size) { - stack_t stack = ((stack_t) { .ss_flags = 0, - .ss_sp = (__ptr_t) sig_stack, - .ss_size = size - sizeof(void *) }); + stack_t stack = { + .ss_flags = 0, + .ss_sp = sig_stack, + .ss_size = size - sizeof(void *) + }; if (sigaltstack(&stack, NULL) != 0) panic("enabling signal stack failed, errno = %d\n", errno); @@ -129,10 +135,9 @@ static void (*handlers[_NSIG])(int sig, struct siginfo *si, mcontext_t *mc) = { [SIGIO] = sig_handler, [SIGWINCH] = sig_handler, - [SIGVTALRM] = alarm_handler + [SIGALRM] = timer_alarm_handler }; - static void hard_handler(int sig, siginfo_t *si, void *p) { struct ucontext *uc = p; @@ -186,9 +191,9 @@ void set_handler(int sig) /* block irq ones */ sigemptyset(&action.sa_mask); - sigaddset(&action.sa_mask, SIGVTALRM); sigaddset(&action.sa_mask, SIGIO); sigaddset(&action.sa_mask, SIGWINCH); + sigaddset(&action.sa_mask, SIGALRM); if (sig == SIGSEGV) flags |= SA_NODEFER; @@ -281,8 +286,8 @@ void unblock_signals(void) if (save_pending & SIGIO_MASK) sig_handler_common(SIGIO, NULL, NULL); - if (save_pending & SIGVTALRM_MASK) - real_alarm_handler(NULL); + if (save_pending & SIGALRM_MASK) + timer_real_alarm_handler(NULL); } } diff --git a/kernel/arch/um/os-Linux/skas/mem.c b/kernel/arch/um/os-Linux/skas/mem.c index e7f8c945a..35015e3e1 100644 --- a/kernel/arch/um/os-Linux/skas/mem.c +++ b/kernel/arch/um/os-Linux/skas/mem.c @@ -18,7 +18,7 @@ #include <sysdep/ptrace.h> #include <sysdep/stub.h> -extern unsigned long batch_syscall_stub, __syscall_stub_start; +extern char batch_syscall_stub[], __syscall_stub_start[]; extern void wait_stub_done(int pid); @@ -38,8 +38,8 @@ static int __init init_syscall_regs(void) { get_safe_registers(syscall_regs, NULL); syscall_regs[REGS_IP_INDEX] = STUB_CODE + - ((unsigned long) &batch_syscall_stub - - (unsigned long) &__syscall_stub_start); + ((unsigned long) batch_syscall_stub - + (unsigned long) __syscall_stub_start); return 0; } diff --git a/kernel/arch/um/os-Linux/skas/process.c b/kernel/arch/um/os-Linux/skas/process.c index 7a9777570..b856c66eb 100644 --- a/kernel/arch/um/os-Linux/skas/process.c +++ b/kernel/arch/um/os-Linux/skas/process.c @@ -1,4 +1,5 @@ /* + * Copyright (C) 2015 Thomas Meyer (thomas@m3y3r.de) * Copyright (C) 2002- 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com) * Licensed under the GPL */ @@ -45,7 +46,7 @@ static int ptrace_dump_regs(int pid) * Signals that are OK to receive in the stub - we'll just continue it. * SIGWINCH will happen when UML is inside a detached screen. */ -#define STUB_SIG_MASK ((1 << SIGVTALRM) | (1 << SIGWINCH)) +#define STUB_SIG_MASK ((1 << SIGALRM) | (1 << SIGWINCH)) /* Signals that the stub will finish with - anything else is an error */ #define STUB_DONE_MASK (1 << SIGTRAP) @@ -137,9 +138,6 @@ static void handle_trap(int pid, struct uml_pt_regs *regs, if ((UPT_IP(regs) >= STUB_START) && (UPT_IP(regs) < STUB_END)) fatal_sigsegv(); - /* Mark this as a syscall */ - UPT_SYSCALL_NR(regs) = PT_SYSCALL_NR(regs->gp); - if (!local_using_sysemu) { err = ptrace(PTRACE_POKEUSER, pid, PT_SYSCALL_NR_OFFSET, @@ -174,30 +172,31 @@ static void handle_trap(int pid, struct uml_pt_regs *regs, handle_syscall(regs); } -extern int __syscall_stub_start; +int get_syscall(struct uml_pt_regs *regs) +{ + UPT_SYSCALL_NR(regs) = PT_SYSCALL_NR(regs->gp); + + return UPT_SYSCALL_NR(regs); +} + +extern char __syscall_stub_start[]; static int userspace_tramp(void *stack) { void *addr; - int err, fd; + int fd; unsigned long long offset; ptrace(PTRACE_TRACEME, 0, 0, 0); signal(SIGTERM, SIG_DFL); signal(SIGWINCH, SIG_IGN); - err = set_interval(); - if (err) { - printk(UM_KERN_ERR "userspace_tramp - setting timer failed, " - "errno = %d\n", err); - exit(1); - } /* * This has a pte, but it can't be mapped in with the usual * tlb_flush mechanism because this is part of that mechanism */ - fd = phys_mapping(to_phys(&__syscall_stub_start), &offset); + fd = phys_mapping(to_phys(__syscall_stub_start), &offset); addr = mmap64((void *) STUB_CODE, UM_KERN_PAGE_SIZE, PROT_EXEC, MAP_FIXED | MAP_PRIVATE, fd, offset); if (addr == MAP_FAILED) { @@ -223,7 +222,7 @@ static int userspace_tramp(void *stack) unsigned long v = STUB_CODE + (unsigned long) stub_segv_handler - - (unsigned long) &__syscall_stub_start; + (unsigned long) __syscall_stub_start; set_sigstack((void *) STUB_DATA, UM_KERN_PAGE_SIZE); sigemptyset(&sa.sa_mask); @@ -282,7 +281,7 @@ int start_userspace(unsigned long stub_stack) "errno = %d\n", errno); goto out_kill; } - } while (WIFSTOPPED(status) && (WSTOPSIG(status) == SIGVTALRM)); + } while (WIFSTOPPED(status) && (WSTOPSIG(status) == SIGALRM)); if (!WIFSTOPPED(status) || (WSTOPSIG(status) != SIGSTOP)) { err = -EINVAL; @@ -315,8 +314,6 @@ int start_userspace(unsigned long stub_stack) void userspace(struct uml_pt_regs *regs) { - struct itimerval timer; - unsigned long long nsecs, now; int err, status, op, pid = userspace_pid[0]; /* To prevent races if using_sysemu changes under us.*/ int local_using_sysemu; @@ -325,13 +322,8 @@ void userspace(struct uml_pt_regs *regs) /* Handle any immediate reschedules or signals */ interrupt_end(); - if (getitimer(ITIMER_VIRTUAL, &timer)) - printk(UM_KERN_ERR "Failed to get itimer, errno = %d\n", errno); - nsecs = timer.it_value.tv_sec * UM_NSEC_PER_SEC + - timer.it_value.tv_usec * UM_NSEC_PER_USEC; - nsecs += os_nsecs(); - while (1) { + /* * This can legitimately fail if the process loads a * bogus value into a segment register. It will @@ -401,18 +393,7 @@ void userspace(struct uml_pt_regs *regs) case SIGTRAP: relay_signal(SIGTRAP, (struct siginfo *)&si, regs); break; - case SIGVTALRM: - now = os_nsecs(); - if (now < nsecs) - break; - block_signals(); - (*sig_info[sig])(sig, (struct siginfo *)&si, regs); - unblock_signals(); - nsecs = timer.it_value.tv_sec * - UM_NSEC_PER_SEC + - timer.it_value.tv_usec * - UM_NSEC_PER_USEC; - nsecs += os_nsecs(); + case SIGALRM: break; case SIGIO: case SIGILL: @@ -447,7 +428,7 @@ static int __init init_thread_regs(void) /* Set parent's instruction pointer to start of clone-stub */ thread_regs[REGS_IP_INDEX] = STUB_CODE + (unsigned long) stub_clone_handler - - (unsigned long) &__syscall_stub_start; + (unsigned long) __syscall_stub_start; thread_regs[REGS_SP_INDEX] = STUB_DATA + UM_KERN_PAGE_SIZE - sizeof(void *); #ifdef __SIGNAL_FRAMESIZE @@ -460,7 +441,6 @@ __initcall(init_thread_regs); int copy_context_skas0(unsigned long new_stack, int pid) { - struct timeval tv = { .tv_sec = 0, .tv_usec = UM_USEC_PER_SEC / UM_HZ }; int err; unsigned long current_stack = current_stub_stack(); struct stub_data *data = (struct stub_data *) current_stack; @@ -472,11 +452,10 @@ int copy_context_skas0(unsigned long new_stack, int pid) * prepare offset and fd of child's stack as argument for parent's * and child's mmap2 calls */ - *data = ((struct stub_data) { .offset = MMAP_OFFSET(new_offset), - .fd = new_fd, - .timer = ((struct itimerval) - { .it_value = tv, - .it_interval = tv }) }); + *data = ((struct stub_data) { + .offset = MMAP_OFFSET(new_offset), + .fd = new_fd + }); err = ptrace_setregs(pid, thread_regs); if (err < 0) { diff --git a/kernel/arch/um/os-Linux/start_up.c b/kernel/arch/um/os-Linux/start_up.c index 47f1ff056..22a358ef1 100644 --- a/kernel/arch/um/os-Linux/start_up.c +++ b/kernel/arch/um/os-Linux/start_up.c @@ -94,6 +94,8 @@ static int start_ptraced_child(void) { int pid, n, status; + fflush(stdout); + pid = fork(); if (pid == 0) ptrace_child(); diff --git a/kernel/arch/um/os-Linux/time.c b/kernel/arch/um/os-Linux/time.c index e9824d5dd..0e39b9978 100644 --- a/kernel/arch/um/os-Linux/time.c +++ b/kernel/arch/um/os-Linux/time.c @@ -1,4 +1,7 @@ /* + * Copyright (C) 2015 Anton Ivanov (aivanov@{brocade.com,kot-begemot.co.uk}) + * Copyright (C) 2015 Thomas Meyer (thomas@m3y3r.de) + * Copyright (C) 2012-2014 Cisco Systems * Copyright (C) 2000 - 2007 Jeff Dike (jdike{addtoit,linux.intel}.com) * Licensed under the GPL */ @@ -10,177 +13,177 @@ #include <sys/time.h> #include <kern_util.h> #include <os.h> -#include "internal.h" +#include <string.h> +#include <timer-internal.h> -int set_interval(void) -{ - int usec = UM_USEC_PER_SEC / UM_HZ; - struct itimerval interval = ((struct itimerval) { { 0, usec }, - { 0, usec } }); - - if (setitimer(ITIMER_VIRTUAL, &interval, NULL) == -1) - return -errno; +static timer_t event_high_res_timer = 0; - return 0; +static inline long long timeval_to_ns(const struct timeval *tv) +{ + return ((long long) tv->tv_sec * UM_NSEC_PER_SEC) + + tv->tv_usec * UM_NSEC_PER_USEC; } -int timer_one_shot(int ticks) +static inline long long timespec_to_ns(const struct timespec *ts) { - unsigned long usec = ticks * UM_USEC_PER_SEC / UM_HZ; - unsigned long sec = usec / UM_USEC_PER_SEC; - struct itimerval interval; - - usec %= UM_USEC_PER_SEC; - interval = ((struct itimerval) { { 0, 0 }, { sec, usec } }); + return ((long long) ts->tv_sec * UM_NSEC_PER_SEC) + + ts->tv_nsec; +} - if (setitimer(ITIMER_VIRTUAL, &interval, NULL) == -1) - return -errno; +long long os_persistent_clock_emulation (void) { + struct timespec realtime_tp; - return 0; + clock_gettime(CLOCK_REALTIME, &realtime_tp); + return timespec_to_ns(&realtime_tp); } /** - * timeval_to_ns - Convert timeval to nanoseconds - * @ts: pointer to the timeval variable to be converted - * - * Returns the scalar nanosecond representation of the timeval - * parameter. - * - * Ripped from linux/time.h because it's a kernel header, and thus - * unusable from here. + * os_timer_create() - create an new posix (interval) timer */ -static inline long long timeval_to_ns(const struct timeval *tv) -{ - return ((long long) tv->tv_sec * UM_NSEC_PER_SEC) + - tv->tv_usec * UM_NSEC_PER_USEC; +int os_timer_create(void* timer) { + + timer_t* t = timer; + + if(t == NULL) { + t = &event_high_res_timer; + } + + if (timer_create( + CLOCK_MONOTONIC, + NULL, + t) == -1) { + return -1; + } + return 0; } -long long disable_timer(void) +int os_timer_set_interval(void* timer, void* i) { - struct itimerval time = ((struct itimerval) { { 0, 0 }, { 0, 0 } }); - long long remain, max = UM_NSEC_PER_SEC / UM_HZ; + struct itimerspec its; + unsigned long long nsec; + timer_t* t = timer; + struct itimerspec* its_in = i; - if (setitimer(ITIMER_VIRTUAL, &time, &time) < 0) - printk(UM_KERN_ERR "disable_timer - setitimer failed, " - "errno = %d\n", errno); + if(t == NULL) { + t = &event_high_res_timer; + } - remain = timeval_to_ns(&time.it_value); - if (remain > max) - remain = max; + nsec = UM_NSEC_PER_SEC / UM_HZ; - return remain; -} + if(its_in != NULL) { + its.it_value.tv_sec = its_in->it_value.tv_sec; + its.it_value.tv_nsec = its_in->it_value.tv_nsec; + } else { + its.it_value.tv_sec = 0; + its.it_value.tv_nsec = nsec; + } -long long os_nsecs(void) -{ - struct timeval tv; + its.it_interval.tv_sec = 0; + its.it_interval.tv_nsec = nsec; - gettimeofday(&tv, NULL); - return timeval_to_ns(&tv); -} + if(timer_settime(*t, 0, &its, NULL) == -1) { + return -errno; + } -#ifdef UML_CONFIG_NO_HZ_COMMON -static int after_sleep_interval(struct timespec *ts) -{ return 0; } -static void deliver_alarm(void) +/** + * os_timer_remain() - returns the remaining nano seconds of the given interval + * timer + * Because this is the remaining time of an interval timer, which correspondends + * to HZ, this value can never be bigger than one second. Just + * the nanosecond part of the timer is returned. + * The returned time is relative to the start time of the interval timer. + * Return an negative value in an error case. + */ +long os_timer_remain(void* timer) { - alarm_handler(SIGVTALRM, NULL, NULL); -} + struct itimerspec its; + timer_t* t = timer; -static unsigned long long sleep_time(unsigned long long nsecs) -{ - return nsecs; -} + if(t == NULL) { + t = &event_high_res_timer; + } -#else -unsigned long long last_tick; -unsigned long long skew; + if(timer_gettime(t, &its) == -1) { + return -errno; + } -static void deliver_alarm(void) -{ - unsigned long long this_tick = os_nsecs(); - int one_tick = UM_NSEC_PER_SEC / UM_HZ; + return its.it_value.tv_nsec; +} - /* Protection against the host's time going backwards */ - if ((last_tick != 0) && (this_tick < last_tick)) - this_tick = last_tick; +int os_timer_one_shot(int ticks) +{ + struct itimerspec its; + unsigned long long nsec; + unsigned long sec; - if (last_tick == 0) - last_tick = this_tick - one_tick; + nsec = (ticks + 1); + sec = nsec / UM_NSEC_PER_SEC; + nsec = nsec % UM_NSEC_PER_SEC; - skew += this_tick - last_tick; + its.it_value.tv_sec = nsec / UM_NSEC_PER_SEC; + its.it_value.tv_nsec = nsec; - while (skew >= one_tick) { - alarm_handler(SIGVTALRM, NULL, NULL); - skew -= one_tick; - } + its.it_interval.tv_sec = 0; + its.it_interval.tv_nsec = 0; // we cheat here - last_tick = this_tick; + timer_settime(event_high_res_timer, 0, &its, NULL); + return 0; } -static unsigned long long sleep_time(unsigned long long nsecs) +/** + * os_timer_disable() - disable the posix (interval) timer + * Returns the remaining interval timer time in nanoseconds + */ +long long os_timer_disable(void) { - return nsecs > skew ? nsecs - skew : 0; -} + struct itimerspec its; -static inline long long timespec_to_us(const struct timespec *ts) -{ - return ((long long) ts->tv_sec * UM_USEC_PER_SEC) + - ts->tv_nsec / UM_NSEC_PER_USEC; + memset(&its, 0, sizeof(struct itimerspec)); + timer_settime(event_high_res_timer, 0, &its, &its); + + return its.it_value.tv_sec * UM_NSEC_PER_SEC + its.it_value.tv_nsec; } -static int after_sleep_interval(struct timespec *ts) +long long os_vnsecs(void) { - int usec = UM_USEC_PER_SEC / UM_HZ; - long long start_usecs = timespec_to_us(ts); - struct timeval tv; - struct itimerval interval; - - /* - * It seems that rounding can increase the value returned from - * setitimer to larger than the one passed in. Over time, - * this will cause the remaining time to be greater than the - * tick interval. If this happens, then just reduce the first - * tick to the interval value. - */ - if (start_usecs > usec) - start_usecs = usec; - - start_usecs -= skew / UM_NSEC_PER_USEC; - if (start_usecs < 0) - start_usecs = 0; + struct timespec ts; - tv = ((struct timeval) { .tv_sec = start_usecs / UM_USEC_PER_SEC, - .tv_usec = start_usecs % UM_USEC_PER_SEC }); - interval = ((struct itimerval) { { 0, usec }, tv }); + clock_gettime(CLOCK_PROCESS_CPUTIME_ID,&ts); + return timespec_to_ns(&ts); +} - if (setitimer(ITIMER_VIRTUAL, &interval, NULL) == -1) - return -errno; +long long os_nsecs(void) +{ + struct timespec ts; - return 0; + clock_gettime(CLOCK_MONOTONIC,&ts); + return timespec_to_ns(&ts); } -#endif -void idle_sleep(unsigned long long nsecs) +/** + * os_idle_sleep() - sleep for a given time of nsecs + * @nsecs: nanoseconds to sleep + */ +void os_idle_sleep(unsigned long long nsecs) { struct timespec ts; - /* - * nsecs can come in as zero, in which case, this starts a - * busy loop. To prevent this, reset nsecs to the tick - * interval if it is zero. - */ - if (nsecs == 0) - nsecs = UM_NSEC_PER_SEC / UM_HZ; + if (nsecs <= 0) { + return; + } - nsecs = sleep_time(nsecs); - ts = ((struct timespec) { .tv_sec = nsecs / UM_NSEC_PER_SEC, - .tv_nsec = nsecs % UM_NSEC_PER_SEC }); + ts = ((struct timespec) { + .tv_sec = nsecs / UM_NSEC_PER_SEC, + .tv_nsec = nsecs % UM_NSEC_PER_SEC + }); - if (nanosleep(&ts, &ts) == 0) + /* + * Relay the signal if clock_nanosleep is interrupted. + */ + if (clock_nanosleep(CLOCK_MONOTONIC, 0, &ts, NULL)) { deliver_alarm(); - after_sleep_interval(&ts); + } } |