From 39efa3ef3a376a4e53de2f82fc91182459d34200 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 23 Mar 2011 10:37:00 +0100 Subject: signal: Use GROUP_STOP_PENDING to stop once for a single group stop Currently task->signal->group_stop_count is used to decide whether to stop for group stop. However, if there is a task in the group which is taking a long time to stop, other tasks which are continued by ptrace would repeatedly stop for the same group stop until the group stop is complete. Conversely, if a ptraced task is in TASK_TRACED state, the debugger won't get notified of group stops which is inconsistent compared to the ptraced task in any other state. This patch introduces GROUP_STOP_PENDING which tracks whether a task is yet to stop for the group stop in progress. The flag is set when a group stop starts and cleared when the task stops the first time for the group stop, and consulted whenever whether the task should participate in a group stop needs to be determined. Note that now tasks in TASK_TRACED also participate in group stop. This results in the following behavior changes. * For a single group stop, a ptracer would see at most one stop reported. * A ptracee in TASK_TRACED now also participates in group stop and the tracer would get the notification. However, as a ptraced task could be in TASK_STOPPED state or any ptrace trap could consume group stop, the notification may still be missing. These will be addressed with further patches. * A ptracee may start a group stop while one is still in progress if the tracer let it continue with stop signal delivery. Group stop code handles this correctly. Oleg: * Spotted that a task might skip signal check even when its GROUP_STOP_PENDING is set. Fixed by updating recalc_sigpending_tsk() to check GROUP_STOP_PENDING instead of group_stop_count. * Pointed out that task->group_stop should be cleared whenever task->signal->group_stop_count is cleared. Fixed accordingly. * Pointed out the behavior inconsistency between TASK_TRACED and RUNNING and the last behavior change. Signed-off-by: Tejun Heo Acked-by: Oleg Nesterov Cc: Roland McGrath --- fs/exec.c | 1 + 1 file changed, 1 insertion(+) (limited to 'fs/exec.c') diff --git a/fs/exec.c b/fs/exec.c index 5e62d26a4fec..8328beb9016f 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1659,6 +1659,7 @@ static int zap_process(struct task_struct *start, int exit_code) t = start; do { + task_clear_group_stop_pending(t); if (t != current && t->mm) { sigaddset(&t->pending.signal, SIGKILL); signal_wake_up(t, 1); -- cgit v1.3-8-gc7d7 From 1d1dbf8135ab2f3603cc72e39e0f68784f453c39 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Sun, 6 Mar 2011 18:02:21 +0100 Subject: exec: introduce get_user_arg_ptr() helper Introduce get_user_arg_ptr() helper, convert count() and copy_strings() to use it. No functional changes, preparation. This helper is trivial, it just reads the pointer from argv/envp user-space array. Signed-off-by: Oleg Nesterov Reviewed-by: KOSAKI Motohiro Tested-by: KOSAKI Motohiro --- fs/exec.c | 36 +++++++++++++++++++++++++----------- 1 file changed, 25 insertions(+), 11 deletions(-) (limited to 'fs/exec.c') diff --git a/fs/exec.c b/fs/exec.c index 5e62d26a4fec..b12e24fe1c5e 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -398,6 +398,17 @@ err: return err; } +static const char __user * +get_user_arg_ptr(const char __user * const __user *argv, int nr) +{ + const char __user *ptr; + + if (get_user(ptr, argv + nr)) + return ERR_PTR(-EFAULT); + + return ptr; +} + /* * count() counts the number of strings in array ARGV. */ @@ -407,13 +418,14 @@ static int count(const char __user * const __user * argv, int max) if (argv != NULL) { for (;;) { - const char __user * p; + const char __user *p = get_user_arg_ptr(argv, i); - if (get_user(p, argv)) - return -EFAULT; if (!p) break; - argv++; + + if (IS_ERR(p)) + return -EFAULT; + if (i++ >= max) return -E2BIG; @@ -443,16 +455,18 @@ static int copy_strings(int argc, const char __user *const __user *argv, int len; unsigned long pos; - if (get_user(str, argv+argc) || - !(len = strnlen_user(str, MAX_ARG_STRLEN))) { - ret = -EFAULT; + ret = -EFAULT; + str = get_user_arg_ptr(argv, argc); + if (IS_ERR(str)) goto out; - } - if (!valid_arg_len(bprm, len)) { - ret = -E2BIG; + len = strnlen_user(str, MAX_ARG_STRLEN); + if (!len) + goto out; + + ret = -E2BIG; + if (!valid_arg_len(bprm, len)) goto out; - } /* We're going to work our way backwords. */ pos = bprm->p; -- cgit v1.3-8-gc7d7 From ba2d01629d0d167598cfea85adc7926822bbfc45 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Sun, 6 Mar 2011 18:02:37 +0100 Subject: exec: introduce struct user_arg_ptr No functional changes, preparation. Introduce struct user_arg_ptr, change do_execve() paths to use it instead of "char __user * const __user *argv". This makes the argv/envp arguments opaque, we are ready to handle the compat case which needs argv pointing to compat_uptr_t. Suggested-by: Linus Torvalds Signed-off-by: Oleg Nesterov Reviewed-by: KOSAKI Motohiro Tested-by: KOSAKI Motohiro --- fs/exec.c | 42 ++++++++++++++++++++++++++++++------------ 1 file changed, 30 insertions(+), 12 deletions(-) (limited to 'fs/exec.c') diff --git a/fs/exec.c b/fs/exec.c index b12e24fe1c5e..526a0399d963 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -398,12 +398,15 @@ err: return err; } -static const char __user * -get_user_arg_ptr(const char __user * const __user *argv, int nr) +struct user_arg_ptr { + const char __user *const __user *native; +}; + +static const char __user *get_user_arg_ptr(struct user_arg_ptr argv, int nr) { const char __user *ptr; - if (get_user(ptr, argv + nr)) + if (get_user(ptr, argv.native + nr)) return ERR_PTR(-EFAULT); return ptr; @@ -412,11 +415,11 @@ get_user_arg_ptr(const char __user * const __user *argv, int nr) /* * count() counts the number of strings in array ARGV. */ -static int count(const char __user * const __user * argv, int max) +static int count(struct user_arg_ptr argv, int max) { int i = 0; - if (argv != NULL) { + if (argv.native != NULL) { for (;;) { const char __user *p = get_user_arg_ptr(argv, i); @@ -442,7 +445,7 @@ static int count(const char __user * const __user * argv, int max) * processes's memory to the new process's stack. The call to get_user_pages() * ensures the destination page is created and not swapped out. */ -static int copy_strings(int argc, const char __user *const __user *argv, +static int copy_strings(int argc, struct user_arg_ptr argv, struct linux_binprm *bprm) { struct page *kmapped_page = NULL; @@ -533,14 +536,19 @@ out: /* * Like copy_strings, but get argv and its values from kernel memory. */ -int copy_strings_kernel(int argc, const char *const *argv, +int copy_strings_kernel(int argc, const char *const *__argv, struct linux_binprm *bprm) { int r; mm_segment_t oldfs = get_fs(); + struct user_arg_ptr argv = { + .native = (const char __user *const __user *)__argv, + }; + set_fs(KERNEL_DS); - r = copy_strings(argc, (const char __user *const __user *)argv, bprm); + r = copy_strings(argc, argv, bprm); set_fs(oldfs); + return r; } EXPORT_SYMBOL(copy_strings_kernel); @@ -1393,10 +1401,10 @@ EXPORT_SYMBOL(search_binary_handler); /* * sys_execve() executes a new program. */ -int do_execve(const char * filename, - const char __user *const __user *argv, - const char __user *const __user *envp, - struct pt_regs * regs) +static int do_execve_common(const char *filename, + struct user_arg_ptr argv, + struct user_arg_ptr envp, + struct pt_regs *regs) { struct linux_binprm *bprm; struct file *file; @@ -1503,6 +1511,16 @@ out_ret: return retval; } +int do_execve(const char *filename, + const char __user *const __user *__argv, + const char __user *const __user *__envp, + struct pt_regs *regs) +{ + struct user_arg_ptr argv = { .native = __argv }; + struct user_arg_ptr envp = { .native = __envp }; + return do_execve_common(filename, argv, envp, regs); +} + void set_binfmt(struct linux_binfmt *new) { struct mm_struct *mm = current->mm; -- cgit v1.3-8-gc7d7 From 0e028465d18b7c6797fcbdea632299d16097c5cd Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Sun, 6 Mar 2011 18:02:54 +0100 Subject: exec: unify do_execve/compat_do_execve code Add the appropriate members into struct user_arg_ptr and teach get_user_arg_ptr() to handle is_compat = T case correctly. This allows us to remove the compat_do_execve() code from fs/compat.c and reimplement compat_do_execve() as the trivial wrapper on top of do_execve_common(is_compat => true). In fact, this fixes another (minor) bug. "compat_uptr_t str" can overflow after "str += len" in compat_copy_strings() if a 64bit application execs via sys32_execve(). Unexport acct_arg_size() and get_arg_page(), fs/compat.c doesn't need them any longer. Signed-off-by: Oleg Nesterov Reviewed-by: KOSAKI Motohiro Tested-by: KOSAKI Motohiro --- fs/compat.c | 235 ------------------------------------------------ fs/exec.c | 62 ++++++++++--- include/linux/binfmts.h | 4 - 3 files changed, 50 insertions(+), 251 deletions(-) (limited to 'fs/exec.c') diff --git a/fs/compat.c b/fs/compat.c index 72fe6cda9108..0ea00832de23 100644 --- a/fs/compat.c +++ b/fs/compat.c @@ -1306,241 +1306,6 @@ compat_sys_openat(unsigned int dfd, const char __user *filename, int flags, int return do_sys_open(dfd, filename, flags, mode); } -/* - * compat_count() counts the number of arguments/envelopes. It is basically - * a copy of count() from fs/exec.c, except that it works with 32 bit argv - * and envp pointers. - */ -static int compat_count(compat_uptr_t __user *argv, int max) -{ - int i = 0; - - if (argv != NULL) { - for (;;) { - compat_uptr_t p; - - if (get_user(p, argv)) - return -EFAULT; - if (!p) - break; - argv++; - if (i++ >= max) - return -E2BIG; - - if (fatal_signal_pending(current)) - return -ERESTARTNOHAND; - cond_resched(); - } - } - return i; -} - -/* - * compat_copy_strings() is basically a copy of copy_strings() from fs/exec.c - * except that it works with 32 bit argv and envp pointers. - */ -static int compat_copy_strings(int argc, compat_uptr_t __user *argv, - struct linux_binprm *bprm) -{ - struct page *kmapped_page = NULL; - char *kaddr = NULL; - unsigned long kpos = 0; - int ret; - - while (argc-- > 0) { - compat_uptr_t str; - int len; - unsigned long pos; - - if (get_user(str, argv+argc) || - !(len = strnlen_user(compat_ptr(str), MAX_ARG_STRLEN))) { - ret = -EFAULT; - goto out; - } - - if (len > MAX_ARG_STRLEN) { - ret = -E2BIG; - goto out; - } - - /* We're going to work our way backwords. */ - pos = bprm->p; - str += len; - bprm->p -= len; - - while (len > 0) { - int offset, bytes_to_copy; - - if (fatal_signal_pending(current)) { - ret = -ERESTARTNOHAND; - goto out; - } - cond_resched(); - - offset = pos % PAGE_SIZE; - if (offset == 0) - offset = PAGE_SIZE; - - bytes_to_copy = offset; - if (bytes_to_copy > len) - bytes_to_copy = len; - - offset -= bytes_to_copy; - pos -= bytes_to_copy; - str -= bytes_to_copy; - len -= bytes_to_copy; - - if (!kmapped_page || kpos != (pos & PAGE_MASK)) { - struct page *page; - - page = get_arg_page(bprm, pos, 1); - if (!page) { - ret = -E2BIG; - goto out; - } - - if (kmapped_page) { - flush_kernel_dcache_page(kmapped_page); - kunmap(kmapped_page); - put_page(kmapped_page); - } - kmapped_page = page; - kaddr = kmap(kmapped_page); - kpos = pos & PAGE_MASK; - flush_cache_page(bprm->vma, kpos, - page_to_pfn(kmapped_page)); - } - if (copy_from_user(kaddr+offset, compat_ptr(str), - bytes_to_copy)) { - ret = -EFAULT; - goto out; - } - } - } - ret = 0; -out: - if (kmapped_page) { - flush_kernel_dcache_page(kmapped_page); - kunmap(kmapped_page); - put_page(kmapped_page); - } - return ret; -} - -/* - * compat_do_execve() is mostly a copy of do_execve(), with the exception - * that it processes 32 bit argv and envp pointers. - */ -int compat_do_execve(char * filename, - compat_uptr_t __user *argv, - compat_uptr_t __user *envp, - struct pt_regs * regs) -{ - struct linux_binprm *bprm; - struct file *file; - struct files_struct *displaced; - bool clear_in_exec; - int retval; - - retval = unshare_files(&displaced); - if (retval) - goto out_ret; - - retval = -ENOMEM; - bprm = kzalloc(sizeof(*bprm), GFP_KERNEL); - if (!bprm) - goto out_files; - - retval = prepare_bprm_creds(bprm); - if (retval) - goto out_free; - - retval = check_unsafe_exec(bprm); - if (retval < 0) - goto out_free; - clear_in_exec = retval; - current->in_execve = 1; - - file = open_exec(filename); - retval = PTR_ERR(file); - if (IS_ERR(file)) - goto out_unmark; - - sched_exec(); - - bprm->file = file; - bprm->filename = filename; - bprm->interp = filename; - - retval = bprm_mm_init(bprm); - if (retval) - goto out_file; - - bprm->argc = compat_count(argv, MAX_ARG_STRINGS); - if ((retval = bprm->argc) < 0) - goto out; - - bprm->envc = compat_count(envp, MAX_ARG_STRINGS); - if ((retval = bprm->envc) < 0) - goto out; - - retval = prepare_binprm(bprm); - if (retval < 0) - goto out; - - retval = copy_strings_kernel(1, &bprm->filename, bprm); - if (retval < 0) - goto out; - - bprm->exec = bprm->p; - retval = compat_copy_strings(bprm->envc, envp, bprm); - if (retval < 0) - goto out; - - retval = compat_copy_strings(bprm->argc, argv, bprm); - if (retval < 0) - goto out; - - retval = search_binary_handler(bprm, regs); - if (retval < 0) - goto out; - - /* execve succeeded */ - current->fs->in_exec = 0; - current->in_execve = 0; - acct_update_integrals(current); - free_bprm(bprm); - if (displaced) - put_files_struct(displaced); - return retval; - -out: - if (bprm->mm) { - acct_arg_size(bprm, 0); - mmput(bprm->mm); - } - -out_file: - if (bprm->file) { - allow_write_access(bprm->file); - fput(bprm->file); - } - -out_unmark: - if (clear_in_exec) - current->fs->in_exec = 0; - current->in_execve = 0; - -out_free: - free_bprm(bprm); - -out_files: - if (displaced) - reset_files_struct(displaced); -out_ret: - return retval; -} - #define __COMPAT_NFDBITS (8 * sizeof(compat_ulong_t)) static int poll_select_copy_remaining(struct timespec *end_time, void __user *p, diff --git a/fs/exec.c b/fs/exec.c index 526a0399d963..89d788ca7829 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -55,6 +55,7 @@ #include #include #include +#include #include #include @@ -167,7 +168,7 @@ out: #ifdef CONFIG_MMU -void acct_arg_size(struct linux_binprm *bprm, unsigned long pages) +static void acct_arg_size(struct linux_binprm *bprm, unsigned long pages) { struct mm_struct *mm = current->mm; long diff = (long)(pages - bprm->vma_pages); @@ -186,7 +187,7 @@ void acct_arg_size(struct linux_binprm *bprm, unsigned long pages) #endif } -struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos, +static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos, int write) { struct page *page; @@ -305,11 +306,11 @@ static bool valid_arg_len(struct linux_binprm *bprm, long len) #else -void acct_arg_size(struct linux_binprm *bprm, unsigned long pages) +static inline void acct_arg_size(struct linux_binprm *bprm, unsigned long pages) { } -struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos, +static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos, int write) { struct page *page; @@ -399,17 +400,36 @@ err: } struct user_arg_ptr { - const char __user *const __user *native; +#ifdef CONFIG_COMPAT + bool is_compat; +#endif + union { + const char __user *const __user *native; +#ifdef CONFIG_COMPAT + compat_uptr_t __user *compat; +#endif + } ptr; }; static const char __user *get_user_arg_ptr(struct user_arg_ptr argv, int nr) { - const char __user *ptr; + const char __user *native; + +#ifdef CONFIG_COMPAT + if (unlikely(argv.is_compat)) { + compat_uptr_t compat; + + if (get_user(compat, argv.ptr.compat + nr)) + return ERR_PTR(-EFAULT); - if (get_user(ptr, argv.native + nr)) + return compat_ptr(compat); + } +#endif + + if (get_user(native, argv.ptr.native + nr)) return ERR_PTR(-EFAULT); - return ptr; + return native; } /* @@ -419,7 +439,7 @@ static int count(struct user_arg_ptr argv, int max) { int i = 0; - if (argv.native != NULL) { + if (argv.ptr.native != NULL) { for (;;) { const char __user *p = get_user_arg_ptr(argv, i); @@ -542,7 +562,7 @@ int copy_strings_kernel(int argc, const char *const *__argv, int r; mm_segment_t oldfs = get_fs(); struct user_arg_ptr argv = { - .native = (const char __user *const __user *)__argv, + .ptr.native = (const char __user *const __user *)__argv, }; set_fs(KERNEL_DS); @@ -1516,10 +1536,28 @@ int do_execve(const char *filename, const char __user *const __user *__envp, struct pt_regs *regs) { - struct user_arg_ptr argv = { .native = __argv }; - struct user_arg_ptr envp = { .native = __envp }; + struct user_arg_ptr argv = { .ptr.native = __argv }; + struct user_arg_ptr envp = { .ptr.native = __envp }; + return do_execve_common(filename, argv, envp, regs); +} + +#ifdef CONFIG_COMPAT +int compat_do_execve(char *filename, + compat_uptr_t __user *__argv, + compat_uptr_t __user *__envp, + struct pt_regs *regs) +{ + struct user_arg_ptr argv = { + .is_compat = true, + .ptr.compat = __argv, + }; + struct user_arg_ptr envp = { + .is_compat = true, + .ptr.compat = __envp, + }; return do_execve_common(filename, argv, envp, regs); } +#endif void set_binfmt(struct linux_binfmt *new) { diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index c3d6512eded1..8845613fd7e3 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -60,10 +60,6 @@ struct linux_binprm { unsigned long loader, exec; }; -extern void acct_arg_size(struct linux_binprm *bprm, unsigned long pages); -extern struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos, - int write); - #define BINPRM_FLAGS_ENFORCE_NONDUMP_BIT 0 #define BINPRM_FLAGS_ENFORCE_NONDUMP (1 << BINPRM_FLAGS_ENFORCE_NONDUMP_BIT) -- cgit v1.3-8-gc7d7 From ae6b585eeb74670a2dec1fe4394bdfbdb9395cc2 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Sun, 6 Mar 2011 18:03:11 +0100 Subject: exec: document acct_arg_size() Add the comment to explain acct_arg_size(). Signed-off-by: Oleg Nesterov Reviewed-by: KOSAKI Motohiro --- fs/exec.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'fs/exec.c') diff --git a/fs/exec.c b/fs/exec.c index 89d788ca7829..5cb53f0232b1 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -167,7 +167,12 @@ out: } #ifdef CONFIG_MMU - +/* + * The nascent bprm->mm is not visible until exec_mmap() but it can + * use a lot of memory, account these pages in current->mm temporary + * for oom_badness()->get_mm_rss(). Once exec succeeds or fails, we + * change the counter back via acct_arg_size(0). + */ static void acct_arg_size(struct linux_binprm *bprm, unsigned long pages) { struct mm_struct *mm = current->mm; -- cgit v1.3-8-gc7d7 From 7d74f492e4dd0034a61458eb80f70b1d2862ed07 Mon Sep 17 00:00:00 2001 From: J Freyensee Date: Fri, 6 May 2011 16:56:47 -0700 Subject: export kernel call get_task_comm(). This allows drivers who call this function to be compiled modularly. Otherwise, a driver who is interested in this type of functionality has to implement their own get_task_comm() call, causing code duplication in the Linux source tree. Signed-off-by: J Freyensee Acked-by: David Rientjes Signed-off-by: Greg Kroah-Hartman --- fs/exec.c | 1 + 1 file changed, 1 insertion(+) (limited to 'fs/exec.c') diff --git a/fs/exec.c b/fs/exec.c index 5e62d26a4fec..7de94950a5b4 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1004,6 +1004,7 @@ char *get_task_comm(char *buf, struct task_struct *tsk) task_unlock(tsk); return buf; } +EXPORT_SYMBOL_GPL(get_task_comm); void set_task_comm(struct task_struct *tsk, char *buf) { -- cgit v1.3-8-gc7d7 From d05f3169c0fbca16132ec7c2be71685c6de638b5 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Tue, 24 May 2011 17:11:44 -0700 Subject: mm: make expand_downwards() symmetrical with expand_upwards() Currently we have expand_upwards exported while expand_downwards is accessible only via expand_stack or expand_stack_downwards. check_stack_guard_page is a nice example of the asymmetry. It uses expand_stack for VM_GROWSDOWN while expand_upwards is called for VM_GROWSUP case. Let's clean this up by exporting both functions and make those names consistent. Let's use expand_{upwards,downwards} because expanding doesn't always involve stack manipulation (an example is ia64_do_page_fault which uses expand_upwards for registers backing store expansion). expand_downwards has to be defined for both CONFIG_STACK_GROWS{UP,DOWN} because get_arg_page calls the downwards version in the early process initialization phase for growsup configuration. Signed-off-by: Michal Hocko Acked-by: Hugh Dickins Cc: James Bottomley Cc: "Luck, Tony" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/exec.c | 2 +- include/linux/mm.h | 8 +++++--- mm/memory.c | 2 +- mm/mmap.c | 7 +------ 4 files changed, 8 insertions(+), 11 deletions(-) (limited to 'fs/exec.c') diff --git a/fs/exec.c b/fs/exec.c index c1cf372f17a7..e276d5e0abb9 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -200,7 +200,7 @@ static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos, #ifdef CONFIG_STACK_GROWSUP if (write) { - ret = expand_stack_downwards(bprm->vma, pos); + ret = expand_downwards(bprm->vma, pos); if (ret < 0) return NULL; } diff --git a/include/linux/mm.h b/include/linux/mm.h index e173cd297d88..d2948af126ca 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1518,15 +1518,17 @@ unsigned long ra_submit(struct file_ra_state *ra, struct address_space *mapping, struct file *filp); -/* Do stack extension */ +/* Generic expand stack which grows the stack according to GROWS{UP,DOWN} */ extern int expand_stack(struct vm_area_struct *vma, unsigned long address); + +/* CONFIG_STACK_GROWSUP still needs to to grow downwards at some places */ +extern int expand_downwards(struct vm_area_struct *vma, + unsigned long address); #if VM_GROWSUP extern int expand_upwards(struct vm_area_struct *vma, unsigned long address); #else #define expand_upwards(vma, address) do { } while (0) #endif -extern int expand_stack_downwards(struct vm_area_struct *vma, - unsigned long address); /* Look up the first VMA which satisfies addr < vm_end, NULL if none. */ extern struct vm_area_struct * find_vma(struct mm_struct * mm, unsigned long addr); diff --git a/mm/memory.c b/mm/memory.c index 61e66f026563..4c6ea10f3d18 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2966,7 +2966,7 @@ static inline int check_stack_guard_page(struct vm_area_struct *vma, unsigned lo if (prev && prev->vm_end == address) return prev->vm_flags & VM_GROWSDOWN ? 0 : -ENOMEM; - expand_stack(vma, address - PAGE_SIZE); + expand_downwards(vma, address - PAGE_SIZE); } if ((vma->vm_flags & VM_GROWSUP) && address + PAGE_SIZE == vma->vm_end) { struct vm_area_struct *next = vma->vm_next; diff --git a/mm/mmap.c b/mm/mmap.c index e76f8d752884..adb12527fd0e 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1774,7 +1774,7 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address) /* * vma is the first one with address < vma->vm_start. Have to extend vma. */ -static int expand_downwards(struct vm_area_struct *vma, +int expand_downwards(struct vm_area_struct *vma, unsigned long address) { int error; @@ -1821,11 +1821,6 @@ static int expand_downwards(struct vm_area_struct *vma, return error; } -int expand_stack_downwards(struct vm_area_struct *vma, unsigned long address) -{ - return expand_downwards(vma, address); -} - #ifdef CONFIG_STACK_GROWSUP int expand_stack(struct vm_area_struct *vma, unsigned long address) { -- cgit v1.3-8-gc7d7 From d16dfc550f5326a4000f3322582a7c05dec91d7a Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 24 May 2011 17:11:45 -0700 Subject: mm: mmu_gather rework Rework the existing mmu_gather infrastructure. The direct purpose of these patches was to allow preemptible mmu_gather, but even without that I think these patches provide an improvement to the status quo. The first 9 patches rework the mmu_gather infrastructure. For review purpose I've split them into generic and per-arch patches with the last of those a generic cleanup. The next patch provides generic RCU page-table freeing, and the followup is a patch converting s390 to use this. I've also got 4 patches from DaveM lined up (not included in this series) that uses this to implement gup_fast() for sparc64. Then there is one patch that extends the generic mmu_gather batching. After that follow the mm preemptibility patches, these make part of the mm a lot more preemptible. It converts i_mmap_lock and anon_vma->lock to mutexes which together with the mmu_gather rework makes mmu_gather preemptible as well. Making i_mmap_lock a mutex also enables a clean-up of the truncate code. This also allows for preemptible mmu_notifiers, something that XPMEM I think wants. Furthermore, it removes the new and universially detested unmap_mutex. This patch: Remove the first obstacle towards a fully preemptible mmu_gather. The current scheme assumes mmu_gather is always done with preemption disabled and uses per-cpu storage for the page batches. Change this to try and allocate a page for batching and in case of failure, use a small on-stack array to make some progress. Preemptible mmu_gather is desired in general and usable once i_mmap_lock becomes a mutex. Doing it before the mutex conversion saves us from having to rework the code by moving the mmu_gather bits inside the pte_lock. Also avoid flushing the tlb batches from under the pte lock, this is useful even without the i_mmap_lock conversion as it significantly reduces pte lock hold times. [akpm@linux-foundation.org: fix comment tpyo] Signed-off-by: Peter Zijlstra Cc: Benjamin Herrenschmidt Cc: David Miller Cc: Martin Schwidefsky Cc: Russell King Cc: Paul Mundt Cc: Jeff Dike Cc: Richard Weinberger Cc: Tony Luck Reviewed-by: KAMEZAWA Hiroyuki Acked-by: Hugh Dickins Acked-by: Mel Gorman Cc: KOSAKI Motohiro Cc: Nick Piggin Cc: Namhyung Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/exec.c | 10 ++--- include/asm-generic/tlb.h | 96 ++++++++++++++++++++++++++++++++++------------- include/linux/mm.h | 2 +- mm/memory.c | 46 +++++++++++------------ mm/mmap.c | 18 ++++----- 5 files changed, 107 insertions(+), 65 deletions(-) (limited to 'fs/exec.c') diff --git a/fs/exec.c b/fs/exec.c index e276d5e0abb9..936f5776655c 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -600,7 +600,7 @@ static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift) unsigned long length = old_end - old_start; unsigned long new_start = old_start - shift; unsigned long new_end = old_end - shift; - struct mmu_gather *tlb; + struct mmu_gather tlb; BUG_ON(new_start > new_end); @@ -626,12 +626,12 @@ static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift) return -ENOMEM; lru_add_drain(); - tlb = tlb_gather_mmu(mm, 0); + tlb_gather_mmu(&tlb, mm, 0); if (new_end > old_start) { /* * when the old and new regions overlap clear from new_end. */ - free_pgd_range(tlb, new_end, old_end, new_end, + free_pgd_range(&tlb, new_end, old_end, new_end, vma->vm_next ? vma->vm_next->vm_start : 0); } else { /* @@ -640,10 +640,10 @@ static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift) * have constraints on va-space that make this illegal (IA64) - * for the others its just a little faster. */ - free_pgd_range(tlb, old_start, old_end, new_end, + free_pgd_range(&tlb, old_start, old_end, new_end, vma->vm_next ? vma->vm_next->vm_start : 0); } - tlb_finish_mmu(tlb, new_end, old_end); + tlb_finish_mmu(&tlb, new_end, old_end); /* * Shrink the vma to just the new range. Always succeeds. diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index e43f9766259f..2d3547c84235 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -5,6 +5,8 @@ * Copyright 2001 Red Hat, Inc. * Based on code from mm/memory.c Copyright Linus Torvalds and others. * + * Copyright 2011 Red Hat, Inc., Peter Zijlstra + * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License * as published by the Free Software Foundation; either version @@ -22,51 +24,71 @@ * and page free order so much.. */ #ifdef CONFIG_SMP - #ifdef ARCH_FREE_PTR_NR - #define FREE_PTR_NR ARCH_FREE_PTR_NR - #else - #define FREE_PTE_NR 506 - #endif #define tlb_fast_mode(tlb) ((tlb)->nr == ~0U) #else - #define FREE_PTE_NR 1 #define tlb_fast_mode(tlb) 1 #endif +/* + * If we can't allocate a page to make a big batch of page pointers + * to work on, then just handle a few from the on-stack structure. + */ +#define MMU_GATHER_BUNDLE 8 + /* struct mmu_gather is an opaque type used by the mm code for passing around * any data needed by arch specific code for tlb_remove_page. */ struct mmu_gather { struct mm_struct *mm; unsigned int nr; /* set to ~0U means fast mode */ + unsigned int max; /* nr < max */ unsigned int need_flush;/* Really unmapped some ptes? */ unsigned int fullmm; /* non-zero means full mm flush */ - struct page * pages[FREE_PTE_NR]; +#ifdef HAVE_ARCH_MMU_GATHER + struct arch_mmu_gather arch; +#endif + struct page **pages; + struct page *local[MMU_GATHER_BUNDLE]; }; -/* Users of the generic TLB shootdown code must declare this storage space. */ -DECLARE_PER_CPU(struct mmu_gather, mmu_gathers); +static inline void __tlb_alloc_page(struct mmu_gather *tlb) +{ + unsigned long addr = __get_free_pages(GFP_NOWAIT | __GFP_NOWARN, 0); + + if (addr) { + tlb->pages = (void *)addr; + tlb->max = PAGE_SIZE / sizeof(struct page *); + } +} /* tlb_gather_mmu - * Return a pointer to an initialized struct mmu_gather. + * Called to initialize an (on-stack) mmu_gather structure for page-table + * tear-down from @mm. The @fullmm argument is used when @mm is without + * users and we're going to destroy the full address space (exit/execve). */ -static inline struct mmu_gather * -tlb_gather_mmu(struct mm_struct *mm, unsigned int full_mm_flush) +static inline void +tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, bool fullmm) { - struct mmu_gather *tlb = &get_cpu_var(mmu_gathers); - tlb->mm = mm; - /* Use fast mode if only one CPU is online */ - tlb->nr = num_online_cpus() > 1 ? 0U : ~0U; + tlb->max = ARRAY_SIZE(tlb->local); + tlb->pages = tlb->local; + + if (num_online_cpus() > 1) { + tlb->nr = 0; + __tlb_alloc_page(tlb); + } else /* Use fast mode if only one CPU is online */ + tlb->nr = ~0U; - tlb->fullmm = full_mm_flush; + tlb->fullmm = fullmm; - return tlb; +#ifdef HAVE_ARCH_MMU_GATHER + tlb->arch = ARCH_MMU_GATHER_INIT; +#endif } static inline void -tlb_flush_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end) +tlb_flush_mmu(struct mmu_gather *tlb) { if (!tlb->need_flush) return; @@ -75,6 +97,13 @@ tlb_flush_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end) if (!tlb_fast_mode(tlb)) { free_pages_and_swap_cache(tlb->pages, tlb->nr); tlb->nr = 0; + /* + * If we are using the local on-stack array of pages for MMU + * gather, try allocating an off-stack array again as we have + * recently freed pages. + */ + if (tlb->pages == tlb->local) + __tlb_alloc_page(tlb); } } @@ -85,29 +114,42 @@ tlb_flush_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end) static inline void tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end) { - tlb_flush_mmu(tlb, start, end); + tlb_flush_mmu(tlb); /* keep the page table cache within bounds */ check_pgt_cache(); - put_cpu_var(mmu_gathers); + if (tlb->pages != tlb->local) + free_pages((unsigned long)tlb->pages, 0); } -/* tlb_remove_page +/* __tlb_remove_page * Must perform the equivalent to __free_pte(pte_get_and_clear(ptep)), while * handling the additional races in SMP caused by other CPUs caching valid - * mappings in their TLBs. + * mappings in their TLBs. Returns the number of free page slots left. + * When out of page slots we must call tlb_flush_mmu(). */ -static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page) +static inline int __tlb_remove_page(struct mmu_gather *tlb, struct page *page) { tlb->need_flush = 1; if (tlb_fast_mode(tlb)) { free_page_and_swap_cache(page); - return; + return 1; /* avoid calling tlb_flush_mmu() */ } tlb->pages[tlb->nr++] = page; - if (tlb->nr >= FREE_PTE_NR) - tlb_flush_mmu(tlb, 0, 0); + VM_BUG_ON(tlb->nr > tlb->max); + + return tlb->max - tlb->nr; +} + +/* tlb_remove_page + * Similar to __tlb_remove_page but will call tlb_flush_mmu() itself when + * required. + */ +static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page) +{ + if (!__tlb_remove_page(tlb, page)) + tlb_flush_mmu(tlb); } /** diff --git a/include/linux/mm.h b/include/linux/mm.h index d2948af126ca..ffcce9bf2b54 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -906,7 +906,7 @@ int zap_vma_ptes(struct vm_area_struct *vma, unsigned long address, unsigned long size); unsigned long zap_page_range(struct vm_area_struct *vma, unsigned long address, unsigned long size, struct zap_details *); -unsigned long unmap_vmas(struct mmu_gather **tlb, +unsigned long unmap_vmas(struct mmu_gather *tlb, struct vm_area_struct *start_vma, unsigned long start_addr, unsigned long end_addr, unsigned long *nr_accounted, struct zap_details *); diff --git a/mm/memory.c b/mm/memory.c index 4c6ea10f3d18..19b2d44de9f0 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -912,12 +912,13 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb, long *zap_work, struct zap_details *details) { struct mm_struct *mm = tlb->mm; + int force_flush = 0; pte_t *pte; spinlock_t *ptl; int rss[NR_MM_COUNTERS]; init_rss_vec(rss); - +again: pte = pte_offset_map_lock(mm, pmd, addr, &ptl); arch_enter_lazy_mmu_mode(); do { @@ -974,7 +975,9 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb, page_remove_rmap(page); if (unlikely(page_mapcount(page) < 0)) print_bad_pte(vma, addr, ptent, page); - tlb_remove_page(tlb, page); + force_flush = !__tlb_remove_page(tlb, page); + if (force_flush) + break; continue; } /* @@ -1001,6 +1004,18 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb, arch_leave_lazy_mmu_mode(); pte_unmap_unlock(pte - 1, ptl); + /* + * mmu_gather ran out of room to batch pages, we break out of + * the PTE lock to avoid doing the potential expensive TLB invalidate + * and page-free while holding it. + */ + if (force_flush) { + force_flush = 0; + tlb_flush_mmu(tlb); + if (addr != end) + goto again; + } + return addr; } @@ -1121,17 +1136,14 @@ static unsigned long unmap_page_range(struct mmu_gather *tlb, * ensure that any thus-far unmapped pages are flushed before unmap_vmas() * drops the lock and schedules. */ -unsigned long unmap_vmas(struct mmu_gather **tlbp, +unsigned long unmap_vmas(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start_addr, unsigned long end_addr, unsigned long *nr_accounted, struct zap_details *details) { long zap_work = ZAP_BLOCK_SIZE; - unsigned long tlb_start = 0; /* For tlb_finish_mmu */ - int tlb_start_valid = 0; unsigned long start = start_addr; spinlock_t *i_mmap_lock = details? details->i_mmap_lock: NULL; - int fullmm = (*tlbp)->fullmm; struct mm_struct *mm = vma->vm_mm; mmu_notifier_invalidate_range_start(mm, start_addr, end_addr); @@ -1152,11 +1164,6 @@ unsigned long unmap_vmas(struct mmu_gather **tlbp, untrack_pfn_vma(vma, 0, 0); while (start != end) { - if (!tlb_start_valid) { - tlb_start = start; - tlb_start_valid = 1; - } - if (unlikely(is_vm_hugetlb_page(vma))) { /* * It is undesirable to test vma->vm_file as it @@ -1177,7 +1184,7 @@ unsigned long unmap_vmas(struct mmu_gather **tlbp, start = end; } else - start = unmap_page_range(*tlbp, vma, + start = unmap_page_range(tlb, vma, start, end, &zap_work, details); if (zap_work > 0) { @@ -1185,19 +1192,13 @@ unsigned long unmap_vmas(struct mmu_gather **tlbp, break; } - tlb_finish_mmu(*tlbp, tlb_start, start); - if (need_resched() || (i_mmap_lock && spin_needbreak(i_mmap_lock))) { - if (i_mmap_lock) { - *tlbp = NULL; + if (i_mmap_lock) goto out; - } cond_resched(); } - *tlbp = tlb_gather_mmu(vma->vm_mm, fullmm); - tlb_start_valid = 0; zap_work = ZAP_BLOCK_SIZE; } } @@ -1217,16 +1218,15 @@ unsigned long zap_page_range(struct vm_area_struct *vma, unsigned long address, unsigned long size, struct zap_details *details) { struct mm_struct *mm = vma->vm_mm; - struct mmu_gather *tlb; + struct mmu_gather tlb; unsigned long end = address + size; unsigned long nr_accounted = 0; lru_add_drain(); - tlb = tlb_gather_mmu(mm, 0); + tlb_gather_mmu(&tlb, mm, 0); update_hiwater_rss(mm); end = unmap_vmas(&tlb, vma, address, end, &nr_accounted, details); - if (tlb) - tlb_finish_mmu(tlb, address, end); + tlb_finish_mmu(&tlb, address, end); return end; } diff --git a/mm/mmap.c b/mm/mmap.c index adb12527fd0e..40d49986e714 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1903,17 +1903,17 @@ static void unmap_region(struct mm_struct *mm, unsigned long start, unsigned long end) { struct vm_area_struct *next = prev? prev->vm_next: mm->mmap; - struct mmu_gather *tlb; + struct mmu_gather tlb; unsigned long nr_accounted = 0; lru_add_drain(); - tlb = tlb_gather_mmu(mm, 0); + tlb_gather_mmu(&tlb, mm, 0); update_hiwater_rss(mm); unmap_vmas(&tlb, vma, start, end, &nr_accounted, NULL); vm_unacct_memory(nr_accounted); - free_pgtables(tlb, vma, prev? prev->vm_end: FIRST_USER_ADDRESS, - next? next->vm_start: 0); - tlb_finish_mmu(tlb, start, end); + free_pgtables(&tlb, vma, prev ? prev->vm_end : FIRST_USER_ADDRESS, + next ? next->vm_start : 0); + tlb_finish_mmu(&tlb, start, end); } /* @@ -2255,7 +2255,7 @@ EXPORT_SYMBOL(do_brk); /* Release all mmaps. */ void exit_mmap(struct mm_struct *mm) { - struct mmu_gather *tlb; + struct mmu_gather tlb; struct vm_area_struct *vma; unsigned long nr_accounted = 0; unsigned long end; @@ -2280,14 +2280,14 @@ void exit_mmap(struct mm_struct *mm) lru_add_drain(); flush_cache_mm(mm); - tlb = tlb_gather_mmu(mm, 1); + tlb_gather_mmu(&tlb, mm, 1); /* update_hiwater_rss(mm) here? but nobody should be looking */ /* Use -1 here to ensure all VMAs in the mm are unmapped */ end = unmap_vmas(&tlb, vma, 0, -1, &nr_accounted, NULL); vm_unacct_memory(nr_accounted); - free_pgtables(tlb, vma, FIRST_USER_ADDRESS, 0); - tlb_finish_mmu(tlb, 0, end); + free_pgtables(&tlb, vma, FIRST_USER_ADDRESS, 0); + tlb_finish_mmu(&tlb, 0, end); /* * Walk the list again, actually closing and freeing it, -- cgit v1.3-8-gc7d7 From 3864601387cf4196371e3c1897fdffa5228296f9 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Thu, 26 May 2011 16:25:46 -0700 Subject: mm: extract exe_file handling from procfs Setup and cleanup of mm_struct->exe_file is currently done in fs/proc/. This was because exe_file was needed only for /proc//exe. Since we will need the exe_file functionality also for core dumps (so core name can contain full binary path), built this functionality always into the kernel. To achieve that move that out of proc FS to the kernel/ where in fact it should belong. By doing that we can make dup_mm_exe_file static. Also we can drop linux/proc_fs.h inclusion in fs/exec.c and kernel/fork.c. Signed-off-by: Jiri Slaby Cc: Alexander Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/exec.c | 1 - fs/proc/base.c | 51 ----------------------------------------------- include/linux/mm.h | 10 ++-------- include/linux/mm_types.h | 2 -- include/linux/proc_fs.h | 19 ------------------ kernel/fork.c | 52 +++++++++++++++++++++++++++++++++++++++++++++++- 6 files changed, 53 insertions(+), 82 deletions(-) (limited to 'fs/exec.c') diff --git a/fs/exec.c b/fs/exec.c index 936f5776655c..88a16c572282 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -42,7 +42,6 @@ #include #include #include -#include #include #include #include diff --git a/fs/proc/base.c b/fs/proc/base.c index dc8bca72b002..c2ac2fb123c8 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -1576,57 +1576,6 @@ static const struct file_operations proc_pid_set_comm_operations = { .release = single_release, }; -/* - * We added or removed a vma mapping the executable. The vmas are only mapped - * during exec and are not mapped with the mmap system call. - * Callers must hold down_write() on the mm's mmap_sem for these - */ -void added_exe_file_vma(struct mm_struct *mm) -{ - mm->num_exe_file_vmas++; -} - -void removed_exe_file_vma(struct mm_struct *mm) -{ - mm->num_exe_file_vmas--; - if ((mm->num_exe_file_vmas == 0) && mm->exe_file){ - fput(mm->exe_file); - mm->exe_file = NULL; - } - -} - -void set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file) -{ - if (new_exe_file) - get_file(new_exe_file); - if (mm->exe_file) - fput(mm->exe_file); - mm->exe_file = new_exe_file; - mm->num_exe_file_vmas = 0; -} - -struct file *get_mm_exe_file(struct mm_struct *mm) -{ - struct file *exe_file; - - /* We need mmap_sem to protect against races with removal of - * VM_EXECUTABLE vmas */ - down_read(&mm->mmap_sem); - exe_file = mm->exe_file; - if (exe_file) - get_file(exe_file); - up_read(&mm->mmap_sem); - return exe_file; -} - -void dup_mm_exe_file(struct mm_struct *oldmm, struct mm_struct *newmm) -{ - /* It's safe to write the exe_file pointer without exe_file_lock because - * this is called during fork when the task is not yet in /proc */ - newmm->exe_file = get_mm_exe_file(oldmm); -} - static int proc_exe_link(struct inode *inode, struct path *exe_path) { struct task_struct *task; diff --git a/include/linux/mm.h b/include/linux/mm.h index fb8e814f78dc..9670f71d7be9 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1408,17 +1408,11 @@ extern void exit_mmap(struct mm_struct *); extern int mm_take_all_locks(struct mm_struct *mm); extern void mm_drop_all_locks(struct mm_struct *mm); -#ifdef CONFIG_PROC_FS /* From fs/proc/base.c. callers must _not_ hold the mm's exe_file_lock */ extern void added_exe_file_vma(struct mm_struct *mm); extern void removed_exe_file_vma(struct mm_struct *mm); -#else -static inline void added_exe_file_vma(struct mm_struct *mm) -{} - -static inline void removed_exe_file_vma(struct mm_struct *mm) -{} -#endif /* CONFIG_PROC_FS */ +extern void set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file); +extern struct file *get_mm_exe_file(struct mm_struct *mm); extern int may_expand_vm(struct mm_struct *mm, unsigned long npages); extern int install_special_mapping(struct mm_struct *mm, diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 6fe96c19f85e..2a78aae78c69 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -302,11 +302,9 @@ struct mm_struct { struct task_struct __rcu *owner; #endif -#ifdef CONFIG_PROC_FS /* store ref to file /proc//exe symlink points to */ struct file *exe_file; unsigned long num_exe_file_vmas; -#endif #ifdef CONFIG_MMU_NOTIFIER struct mmu_notifier_mm *mmu_notifier_mm; #endif diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 648c9c58add7..e7576cf9e32d 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -173,12 +173,6 @@ extern void proc_net_remove(struct net *net, const char *name); extern struct proc_dir_entry *proc_net_mkdir(struct net *net, const char *name, struct proc_dir_entry *parent); -/* While the {get|set|dup}_mm_exe_file functions are for mm_structs, they are - * only needed to implement /proc/|self/exe so we define them here. */ -extern void set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file); -extern struct file *get_mm_exe_file(struct mm_struct *mm); -extern void dup_mm_exe_file(struct mm_struct *oldmm, struct mm_struct *newmm); - extern struct file *proc_ns_fget(int fd); #else @@ -230,19 +224,6 @@ static inline void pid_ns_release_proc(struct pid_namespace *ns) { } -static inline void set_mm_exe_file(struct mm_struct *mm, - struct file *new_exe_file) -{} - -static inline struct file *get_mm_exe_file(struct mm_struct *mm) -{ - return NULL; -} - -static inline void dup_mm_exe_file(struct mm_struct *oldmm, - struct mm_struct *newmm) -{} - static inline struct file *proc_ns_fget(int fd) { return ERR_PTR(-EINVAL); diff --git a/kernel/fork.c b/kernel/fork.c index 1f84099ecce6..ca406d916713 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -59,7 +59,6 @@ #include #include #include -#include #include #include #include @@ -597,6 +596,57 @@ void mmput(struct mm_struct *mm) } EXPORT_SYMBOL_GPL(mmput); +/* + * We added or removed a vma mapping the executable. The vmas are only mapped + * during exec and are not mapped with the mmap system call. + * Callers must hold down_write() on the mm's mmap_sem for these + */ +void added_exe_file_vma(struct mm_struct *mm) +{ + mm->num_exe_file_vmas++; +} + +void removed_exe_file_vma(struct mm_struct *mm) +{ + mm->num_exe_file_vmas--; + if ((mm->num_exe_file_vmas == 0) && mm->exe_file){ + fput(mm->exe_file); + mm->exe_file = NULL; + } + +} + +void set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file) +{ + if (new_exe_file) + get_file(new_exe_file); + if (mm->exe_file) + fput(mm->exe_file); + mm->exe_file = new_exe_file; + mm->num_exe_file_vmas = 0; +} + +struct file *get_mm_exe_file(struct mm_struct *mm) +{ + struct file *exe_file; + + /* We need mmap_sem to protect against races with removal of + * VM_EXECUTABLE vmas */ + down_read(&mm->mmap_sem); + exe_file = mm->exe_file; + if (exe_file) + get_file(exe_file); + up_read(&mm->mmap_sem); + return exe_file; +} + +static void dup_mm_exe_file(struct mm_struct *oldmm, struct mm_struct *newmm) +{ + /* It's safe to write the exe_file pointer without exe_file_lock because + * this is called during fork when the task is not yet in /proc */ + newmm->exe_file = get_mm_exe_file(oldmm); +} + /** * get_task_mm - acquire a reference to the task's mm * -- cgit v1.3-8-gc7d7 From 57cc083ad9e1bfeeb4a0ee831e7bb008c8865bf0 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Thu, 26 May 2011 16:25:46 -0700 Subject: coredump: add support for exe_file in core name Now, exe_file is not proc FS dependent, so we can use it to name core file. So we add %E pattern for core file name cration which extract path from mm_struct->exe_file. Then it converts slashes to exclamation marks and pastes the result to the core file name itself. This is useful for environments where binary names are longer than 16 character (the current->comm limitation). Also where there are binaries with same name but in a different path. Further in case the binery itself changes its current->comm after exec. So by doing (s/$/#/ -- # is treated as git comment): $ sysctl kernel.core_pattern='core.%p.%e.%E' $ ln /bin/cat cat45678901234567890 $ ./cat45678901234567890 ^Z $ rm cat45678901234567890 $ fg ^\Quit (core dumped) $ ls core* we now get: core.2434.cat456789012345.!root!cat45678901234567890 (deleted) Signed-off-by: Jiri Slaby Cc: Al Viro Cc: Alan Cox Reviewed-by: Andi Kleen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/sysctl/kernel.txt | 3 ++- fs/exec.c | 38 ++++++++++++++++++++++++++++++++++++++ 2 files changed, 40 insertions(+), 1 deletion(-) (limited to 'fs/exec.c') diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt index 36f007514db3..5e7cb39ad195 100644 --- a/Documentation/sysctl/kernel.txt +++ b/Documentation/sysctl/kernel.txt @@ -161,7 +161,8 @@ core_pattern is used to specify a core dumpfile pattern name. %s signal number %t UNIX time of dump %h hostname - %e executable filename + %e executable filename (may be shortened) + %E executable path % both are dropped . If the first character of the pattern is a '|', the kernel will treat the rest of the pattern as a command to run. The core dump will be diff --git a/fs/exec.c b/fs/exec.c index 88a16c572282..ea5f748906a8 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1623,6 +1623,41 @@ expand_fail: return ret; } +static int cn_print_exe_file(struct core_name *cn) +{ + struct file *exe_file; + char *pathbuf, *path, *p; + int ret; + + exe_file = get_mm_exe_file(current->mm); + if (!exe_file) + return cn_printf(cn, "(unknown)"); + + pathbuf = kmalloc(PATH_MAX, GFP_TEMPORARY); + if (!pathbuf) { + ret = -ENOMEM; + goto put_exe_file; + } + + path = d_path(&exe_file->f_path, pathbuf, PATH_MAX); + if (IS_ERR(path)) { + ret = PTR_ERR(path); + goto free_buf; + } + + for (p = path; *p; p++) + if (*p == '/') + *p = '!'; + + ret = cn_printf(cn, "%s", path); + +free_buf: + kfree(pathbuf); +put_exe_file: + fput(exe_file); + return ret; +} + /* format_corename will inspect the pattern parameter, and output a * name into corename, which must have space for at least * CORENAME_MAX_SIZE bytes plus one byte for the zero terminator. @@ -1694,6 +1729,9 @@ static int format_corename(struct core_name *cn, long signr) case 'e': err = cn_printf(cn, "%s", current->comm); break; + case 'E': + err = cn_print_exe_file(cn); + break; /* core limit size */ case 'c': err = cn_printf(cn, "%lu", -- cgit v1.3-8-gc7d7