From e8e3c3d66fd9d1ee2250f68d778cc48c1346d228 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Fri, 25 Nov 2011 23:14:27 +0800 Subject: fs: remove the second argument of k[un]map_atomic() Acked-by: Benjamin LaHaise Signed-off-by: Cong Wang --- fs/exec.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'fs/exec.c') diff --git a/fs/exec.c b/fs/exec.c index 153dee1..1a07d1c 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1339,13 +1339,13 @@ int remove_arg_zero(struct linux_binprm *bprm) ret = -EFAULT; goto out; } - kaddr = kmap_atomic(page, KM_USER0); + kaddr = kmap_atomic(page); for (; offset < PAGE_SIZE && kaddr[offset]; offset++, bprm->p++) ; - kunmap_atomic(kaddr, KM_USER0); + kunmap_atomic(kaddr); put_arg_page(page); if (offset == PAGE_SIZE) -- cgit v1.1 From e636825346b36a07ccfc8e30946d52855e21f681 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Mon, 19 Mar 2012 17:03:22 +0100 Subject: exit_signal: simplify the "we have changed execution domain" logic exit_notify() checks "tsk->self_exec_id != tsk->parent_exec_id" to handle the "we have changed execution domain" case. We can change do_thread() to always set ->exit_signal = SIGCHLD and remove this check to simplify the code. We could change setup_new_exec() instead, this looks more logical because it increments ->self_exec_id. But note that de_thread() already resets ->exit_signal if it changes the leader, let's keep both changes close to each other. Note that we change ->exit_signal lockless, this changes the rules. Thereafter ->exit_signal is not stable under tasklist but this is fine, the only possible change is OLDSIG -> SIGCHLD. This can race with eligible_child() but the race is harmless. We can race with reparent_leader() which changes our ->exit_signal in parallel, but it does the same change to SIGCHLD. The noticeable user-visible change is that the execing task is not "visible" to do_wait()->eligible_child(__WCLONE) right after exec. To me this looks more logical, and this is consistent with mt case. Signed-off-by: Oleg Nesterov Signed-off-by: Linus Torvalds --- fs/exec.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'fs/exec.c') diff --git a/fs/exec.c b/fs/exec.c index b0695a9..1e94d22 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -977,6 +977,9 @@ static int de_thread(struct task_struct *tsk) sig->notify_count = 0; no_thread_group: + /* we have changed execution domain */ + tsk->exit_signal = SIGCHLD; + if (current->mm) setmax_mm_hiwater_rss(&sig->maxrss, current->mm); -- cgit v1.1 From 701085b219016d38f105b031381b9cee6200253a Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Mon, 19 Mar 2012 17:04:01 +0100 Subject: exec: move de_thread()->setmax_mm_hiwater_rss() into exec_mmap() Minor cleanup. de_thread()->setmax_mm_hiwater_rss() looks a bit strange, move it into exec_mmap() which plays with old_mm. Signed-off-by: Oleg Nesterov Signed-off-by: Linus Torvalds --- fs/exec.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'fs/exec.c') diff --git a/fs/exec.c b/fs/exec.c index 1e94d22..95551c6 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -850,6 +850,7 @@ static int exec_mmap(struct mm_struct *mm) if (old_mm) { up_read(&old_mm->mmap_sem); BUG_ON(active_mm != old_mm); + setmax_mm_hiwater_rss(&tsk->signal->maxrss, old_mm); mm_update_next_owner(old_mm); mmput(old_mm); return 0; @@ -980,9 +981,6 @@ no_thread_group: /* we have changed execution domain */ tsk->exit_signal = SIGCHLD; - if (current->mm) - setmax_mm_hiwater_rss(&sig->maxrss, current->mm); - exit_itimers(sig); flush_itimer_signals(); -- cgit v1.1 From 8fc3dc5a3a17aa2b353886422bd89420619af211 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 17 Mar 2012 03:05:16 -0400 Subject: __register_binfmt() made void Just don't pass NULL to it - nobody does, anyway. Signed-off-by: Al Viro --- fs/exec.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'fs/exec.c') diff --git a/fs/exec.c b/fs/exec.c index 153dee1..2c5ae33 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -79,15 +79,13 @@ static atomic_t call_count = ATOMIC_INIT(1); static LIST_HEAD(formats); static DEFINE_RWLOCK(binfmt_lock); -int __register_binfmt(struct linux_binfmt * fmt, int insert) +void __register_binfmt(struct linux_binfmt * fmt, int insert) { - if (!fmt) - return -EINVAL; + BUG_ON(!fmt); write_lock(&binfmt_lock); insert ? list_add(&fmt->lh, &formats) : list_add_tail(&fmt->lh, &formats); write_unlock(&binfmt_lock); - return 0; } EXPORT_SYMBOL(__register_binfmt); -- cgit v1.1 From 19e5109fef2c368ab3f8a5157270f87f4a7c0326 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 23 Feb 2012 22:29:17 -0500 Subject: take removal of PF_FORKNOEXEC to flush_old_exec() Signed-off-by: Al Viro --- fs/exec.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs/exec.c') diff --git a/fs/exec.c b/fs/exec.c index 2c5ae33..60478a0 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1110,7 +1110,7 @@ int flush_old_exec(struct linux_binprm * bprm) bprm->mm = NULL; /* We're using it now */ set_fs(USER_DS); - current->flags &= ~(PF_RANDOMIZE | PF_KTHREAD); + current->flags &= ~(PF_RANDOMIZE | PF_FORKNOEXEC | PF_KTHREAD); flush_thread(); current->personality &= ~bprm->per_clear; -- cgit v1.1 From 05af2e104a0c282dcd9303431e1360750ba76de6 Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Wed, 21 Mar 2012 16:34:13 -0700 Subject: mm, counters: remove task argument to sync_mm_rss() and __sync_task_rss_stat() sync_mm_rss() can only be used for current to avoid race conditions in iterating and clearing its per-task counters. Remove the task argument for it and its helper function, __sync_task_rss_stat(), to avoid thinking it can be used safely for anything other than current. Signed-off-by: David Rientjes Acked-by: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/exec.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs/exec.c') diff --git a/fs/exec.c b/fs/exec.c index 3908544..6ed164d 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -824,7 +824,7 @@ static int exec_mmap(struct mm_struct *mm) /* Notify parent that we're no longer interested in the old VM */ tsk = current; old_mm = current->mm; - sync_mm_rss(tsk, old_mm); + sync_mm_rss(old_mm); mm_release(tsk, old_mm); if (old_mm) { -- cgit v1.1 From 6308191f6f55d3629c7dbe72dfb856ad9fa560fd Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Fri, 30 Mar 2012 18:26:36 +0200 Subject: tracing, sched, vfs: Fix 'old_pid' usage in trace_sched_process_exec() 1. TRACE_EVENT(sched_process_exec) forgets to actually use the old pid argument, it sets ->old_pid = p->pid. 2. search_binary_handler() uses the wrong pid number. tracepoint needs the global pid_t from the root namespace, while old_pid is the virtual pid number as it seen by the tracer/parent. With this patch we have two pid_t's in search_binary_handler(), not really nice. Perhaps we should switch to "struct pid*", but in this case it would be better to cleanup the current code first and move the "depth == 0" code outside. Signed-off-by: Oleg Nesterov Cc: David Smith Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Denys Vlasenko Link: http://lkml.kernel.org/r/20120330162636.GA4857@redhat.com Signed-off-by: Ingo Molnar --- fs/exec.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'fs/exec.c') diff --git a/fs/exec.c b/fs/exec.c index 23559c2..644f6c4 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1370,7 +1370,7 @@ int search_binary_handler(struct linux_binprm *bprm,struct pt_regs *regs) unsigned int depth = bprm->recursion_depth; int try,retval; struct linux_binfmt *fmt; - pid_t old_pid; + pid_t old_pid, old_vpid; retval = security_bprm_check(bprm); if (retval) @@ -1381,8 +1381,9 @@ int search_binary_handler(struct linux_binprm *bprm,struct pt_regs *regs) return retval; /* Need to fetch pid before load_binary changes it */ + old_pid = current->pid; rcu_read_lock(); - old_pid = task_pid_nr_ns(current, task_active_pid_ns(current->parent)); + old_vpid = task_pid_nr_ns(current, task_active_pid_ns(current->parent)); rcu_read_unlock(); retval = -ENOENT; @@ -1405,7 +1406,7 @@ int search_binary_handler(struct linux_binprm *bprm,struct pt_regs *regs) if (retval >= 0) { if (depth == 0) { trace_sched_process_exec(current, old_pid, bprm); - ptrace_event(PTRACE_EVENT_EXEC, old_pid); + ptrace_event(PTRACE_EVENT_EXEC, old_vpid); } put_binfmt(fmt); allow_write_access(bprm->file); -- cgit v1.1