From e78c3496790ee8a36522a838b59b388e8a709e65 Mon Sep 17 00:00:00 2001 From: Rik van Riel Date: Sat, 16 Aug 2014 13:40:10 -0400 Subject: time, signal: Protect resource use statistics with seqlock Both times() and clock_gettime(CLOCK_PROCESS_CPUTIME_ID) have scalability issues on large systems, due to both functions being serialized with a lock. The lock protects against reporting a wrong value, due to a thread in the task group exiting, its statistics reporting up to the signal struct, and that exited task's statistics being counted twice (or not at all). Protecting that with a lock results in times() and clock_gettime() being completely serialized on large systems. This can be fixed by using a seqlock around the events that gather and propagate statistics. As an additional benefit, the protection code can be moved into thread_group_cputime(), slightly simplifying the calling functions. In the case of posix_cpu_clock_get_task() things can be simplified a lot, because the calling function already ensures that the task sticks around, and the rest is now taken care of in thread_group_cputime(). This way the statistics reporting code can run lockless. Signed-off-by: Rik van Riel Signed-off-by: Peter Zijlstra (Intel) Cc: Alex Thorlton Cc: Andrew Morton Cc: Daeseok Youn Cc: David Rientjes Cc: Dongsheng Yang Cc: Geert Uytterhoeven Cc: Guillaume Morin Cc: Ionut Alexa Cc: Kees Cook Cc: Linus Torvalds Cc: Li Zefan Cc: Michal Hocko Cc: Michal Schmidt Cc: Oleg Nesterov Cc: Vladimir Davydov Cc: umgwanakikbuti@gmail.com Cc: fweisbec@gmail.com Cc: srao@redhat.com Cc: lwoodman@redhat.com Cc: atheurer@redhat.com Link: http://lkml.kernel.org/r/20140816134010.26a9b572@annuminas.surriel.com Signed-off-by: Ingo Molnar --- kernel/fork.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel/fork.c') diff --git a/kernel/fork.c b/kernel/fork.c index 0cf9cdb6e491..9387ae8ab048 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1068,6 +1068,7 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) sig->curr_target = tsk; init_sigpending(&sig->shared_pending); INIT_LIST_HEAD(&sig->posix_timers); + seqlock_init(&sig->stats_lock); hrtimer_init(&sig->real_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); sig->real_timer.function = it_real_fn; -- cgit v1.2.2 From d4311ff1a8da48d609db9500f121c15580dfeeb7 Mon Sep 17 00:00:00 2001 From: Aaron Tomlin Date: Fri, 12 Sep 2014 14:16:17 +0100 Subject: init/main.c: Give init_task a canary Tasks get their end of stack set to STACK_END_MAGIC with the aim to catch stack overruns. Currently this feature does not apply to init_task. This patch removes this restriction. Note that a similar patch was posted by Prarit Bhargava some time ago but was never merged: http://marc.info/?l=linux-kernel&m=127144305403241&w=2 Signed-off-by: Aaron Tomlin Signed-off-by: Peter Zijlstra (Intel) Acked-by: Oleg Nesterov Acked-by: Michael Ellerman Cc: aneesh.kumar@linux.vnet.ibm.com Cc: dzickus@redhat.com Cc: bmr@redhat.com Cc: jcastillo@redhat.com Cc: jgh@redhat.com Cc: minchan@kernel.org Cc: tglx@linutronix.de Cc: hannes@cmpxchg.org Cc: Alex Thorlton Cc: Andrew Morton Cc: Benjamin Herrenschmidt Cc: Daeseok Youn Cc: David Rientjes Cc: Fabian Frederick Cc: Geert Uytterhoeven Cc: Jiri Olsa Cc: Kees Cook Cc: Kirill A. Shutemov Cc: Linus Torvalds Cc: Masami Hiramatsu Cc: Michael Opdenacker Cc: Paul Mackerras Cc: Prarit Bhargava Cc: Rik van Riel Cc: Rusty Russell Cc: Seiji Aguchi Cc: Steven Rostedt Cc: Vladimir Davydov Cc: Yasuaki Ishimatsu Cc: linuxppc-dev@lists.ozlabs.org Link: http://lkml.kernel.org/r/1410527779-8133-2-git-send-email-atomlin@redhat.com Signed-off-by: Ingo Molnar --- kernel/fork.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) (limited to 'kernel/fork.c') diff --git a/kernel/fork.c b/kernel/fork.c index 9387ae8ab048..ad64248c4b18 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -294,11 +294,18 @@ int __weak arch_dup_task_struct(struct task_struct *dst, return 0; } +void set_task_stack_end_magic(struct task_struct *tsk) +{ + unsigned long *stackend; + + stackend = end_of_stack(tsk); + *stackend = STACK_END_MAGIC; /* for overflow detection */ +} + static struct task_struct *dup_task_struct(struct task_struct *orig) { struct task_struct *tsk; struct thread_info *ti; - unsigned long *stackend; int node = tsk_fork_get_node(orig); int err; @@ -328,8 +335,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig) setup_thread_stack(tsk, orig); clear_user_return_notifier(tsk); clear_tsk_need_resched(tsk); - stackend = end_of_stack(tsk); - *stackend = STACK_END_MAGIC; /* for overflow detection */ + set_task_stack_end_magic(tsk); #ifdef CONFIG_CC_STACKPROTECTOR tsk->stack_canary = get_random_int(); -- cgit v1.2.2 From 96dad67ff244e797c4bc3e4f7f0fdaa0cfdf0a7d Mon Sep 17 00:00:00 2001 From: Sasha Levin Date: Thu, 9 Oct 2014 15:28:39 -0700 Subject: mm: use VM_BUG_ON_MM where possible Dump the contents of the relevant struct_mm when we hit the bug condition. Signed-off-by: Sasha Levin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/fork.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'kernel/fork.c') diff --git a/kernel/fork.c b/kernel/fork.c index a91e47d86de2..8c162d102740 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -601,9 +601,8 @@ static void check_mm(struct mm_struct *mm) printk(KERN_ALERT "BUG: Bad rss-counter state " "mm:%p idx:%d val:%ld\n", mm, i, x); } - #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS - VM_BUG_ON(mm->pmd_huge_pte); + VM_BUG_ON_MM(mm->pmd_huge_pte, mm); #endif } -- cgit v1.2.2 From 392809b25833548ccfc55e61b76c8451a5073216 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Sun, 28 Sep 2014 23:44:18 +0200 Subject: signal: Document the RCU protection of ->sighand __cleanup_sighand() frees sighand without RCU grace period. This is correct but this looks "obviously buggy" and constantly confuses the readers, add the comments to explain how this works. Signed-off-by: Oleg Nesterov Reviewed-by: Steven Rostedt Reviewed-by: Rik van Riel Signed-off-by: Paul E. McKenney Reviewed-by: Pranith Kumar --- kernel/fork.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'kernel/fork.c') diff --git a/kernel/fork.c b/kernel/fork.c index 9b7d746d6d62..9ca84189cfc2 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1022,11 +1022,14 @@ void __cleanup_sighand(struct sighand_struct *sighand) { if (atomic_dec_and_test(&sighand->count)) { signalfd_cleanup(sighand); + /* + * sighand_cachep is SLAB_DESTROY_BY_RCU so we can free it + * without an RCU grace period, see __lock_task_sighand(). + */ kmem_cache_free(sighand_cachep, sighand); } } - /* * Initialize POSIX timer handling for a thread group. */ -- cgit v1.2.2 From 83cde9e8ba95d180eaefefe834958fbf7008cf39 Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Fri, 12 Dec 2014 16:54:21 -0800 Subject: mm: use new helper functions around the i_mmap_mutex Convert all open coded mutex_lock/unlock calls to the i_mmap_[lock/unlock]_write() helpers. Signed-off-by: Davidlohr Bueso Acked-by: Rik van Riel Acked-by: "Kirill A. Shutemov" Acked-by: Hugh Dickins Cc: Oleg Nesterov Acked-by: Peter Zijlstra (Intel) Cc: Srikar Dronamraju Acked-by: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/fork.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel/fork.c') diff --git a/kernel/fork.c b/kernel/fork.c index 9ca84189cfc2..4dc2ddade9f1 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -433,7 +433,7 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) get_file(file); if (tmp->vm_flags & VM_DENYWRITE) atomic_dec(&inode->i_writecount); - mutex_lock(&mapping->i_mmap_mutex); + i_mmap_lock_write(mapping); if (tmp->vm_flags & VM_SHARED) atomic_inc(&mapping->i_mmap_writable); flush_dcache_mmap_lock(mapping); @@ -445,7 +445,7 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) vma_interval_tree_insert_after(tmp, mpnt, &mapping->i_mmap); flush_dcache_mmap_unlock(mapping); - mutex_unlock(&mapping->i_mmap_mutex); + i_mmap_unlock_write(mapping); } /* -- cgit v1.2.2