From 2a4419b5b2a77f3f4537c14f7ad7df95770655dd Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Wed, 18 Aug 2010 04:37:33 +1000 Subject: fs: fs_struct rwlock to spinlock fs: fs_struct rwlock to spinlock struct fs_struct.lock is an rwlock with the read-side used to protect root and pwd members while taking references to them. Taking a reference to a path typically requires just 2 atomic ops, so the critical section is very small. Parallel read-side operations would have cacheline contention on the lock, the dentry, and the vfsmount cachelines, so the rwlock is unlikely to ever give a real parallelism increase. Replace it with a spinlock to avoid one or two atomic operations in typical path lookup fastpath. Signed-off-by: Nick Piggin Signed-off-by: Al Viro --- kernel/fork.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'kernel/fork.c') diff --git a/kernel/fork.c b/kernel/fork.c index 98b450876f93..856eac3ec52e 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -752,13 +752,13 @@ static int copy_fs(unsigned long clone_flags, struct task_struct *tsk) struct fs_struct *fs = current->fs; if (clone_flags & CLONE_FS) { /* tsk->fs is already what we want */ - write_lock(&fs->lock); + spin_lock(&fs->lock); if (fs->in_exec) { - write_unlock(&fs->lock); + spin_unlock(&fs->lock); return -EAGAIN; } fs->users++; - write_unlock(&fs->lock); + spin_unlock(&fs->lock); return 0; } tsk->fs = copy_fs_struct(fs); @@ -1676,13 +1676,13 @@ SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags) if (new_fs) { fs = current->fs; - write_lock(&fs->lock); + spin_lock(&fs->lock); current->fs = new_fs; if (--fs->users) new_fs = NULL; else new_fs = fs; - write_unlock(&fs->lock); + spin_unlock(&fs->lock); } if (new_mm) { -- cgit v1.2.3 From 297c5eee372478fc32fec5fe8eed711eedb13f3d Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Fri, 20 Aug 2010 16:24:55 -0700 Subject: mm: make the vma list be doubly linked It's a really simple list, and several of the users want to go backwards in it to find the previous vma. So rather than have to look up the previous entry with 'find_vma_prev()' or something similar, just make it doubly linked instead. Tested-by: Ian Campbell Signed-off-by: Linus Torvalds --- kernel/fork.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'kernel/fork.c') diff --git a/kernel/fork.c b/kernel/fork.c index 856eac3ec52e..b7e9d60a675d 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -300,7 +300,7 @@ out: #ifdef CONFIG_MMU static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) { - struct vm_area_struct *mpnt, *tmp, **pprev; + struct vm_area_struct *mpnt, *tmp, *prev, **pprev; struct rb_node **rb_link, *rb_parent; int retval; unsigned long charge; @@ -328,6 +328,7 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) if (retval) goto out; + prev = NULL; for (mpnt = oldmm->mmap; mpnt; mpnt = mpnt->vm_next) { struct file *file; @@ -359,7 +360,7 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) goto fail_nomem_anon_vma_fork; tmp->vm_flags &= ~VM_LOCKED; tmp->vm_mm = mm; - tmp->vm_next = NULL; + tmp->vm_next = tmp->vm_prev = NULL; file = tmp->vm_file; if (file) { struct inode *inode = file->f_path.dentry->d_inode; @@ -392,6 +393,8 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) */ *pprev = tmp; pprev = &tmp->vm_next; + tmp->vm_prev = prev; + prev = tmp; __vma_link_rb(mm, tmp, rb_link, rb_parent); rb_link = &tmp->vm_rb.rb_right; -- cgit v1.2.3 From a247c3a97a0216b18a46243eda26081f1928ec37 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Wed, 22 Sep 2010 13:05:12 -0700 Subject: rmap: fix walk during fork The below bug in fork led to the rmap walk finding the parent huge-pmd twice instead of just once, because the anon_vma_chain objects of the child vma still point to the vma->vm_mm of the parent. The patch fixes it by making the rmap walk accurate during fork. It's not a big deal normally but it worth being accurate considering the cost is the same. Signed-off-by: Andrea Arcangeli Acked-by: Johannes Weiner Acked-by: Rik van Riel Acked-by: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/fork.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/fork.c') diff --git a/kernel/fork.c b/kernel/fork.c index b7e9d60a675d..c445f8cc408d 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -356,10 +356,10 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) if (IS_ERR(pol)) goto fail_nomem_policy; vma_set_policy(tmp, pol); + tmp->vm_mm = mm; if (anon_vma_fork(tmp, mpnt)) goto fail_nomem_anon_vma_fork; tmp->vm_flags &= ~VM_LOCKED; - tmp->vm_mm = mm; tmp->vm_next = tmp->vm_prev = NULL; file = tmp->vm_file; if (file) { -- cgit v1.2.3 From 3d5992d2ac7dc09aed8ab537cba074589f0f0a52 Mon Sep 17 00:00:00 2001 From: Ying Han Date: Tue, 26 Oct 2010 14:21:23 -0700 Subject: oom: add per-mm oom disable count It's pointless to kill a task if another thread sharing its mm cannot be killed to allow future memory freeing. A subsequent patch will prevent kills in such cases, but first it's necessary to have a way to flag a task that shares memory with an OOM_DISABLE task that doesn't incur an additional tasklist scan, which would make select_bad_process() an O(n^2) function. This patch adds an atomic counter to struct mm_struct that follows how many threads attached to it have an oom_score_adj of OOM_SCORE_ADJ_MIN. They cannot be killed by the kernel, so their memory cannot be freed in oom conditions. This only requires task_lock() on the task that we're operating on, it does not require mm->mmap_sem since task_lock() pins the mm and the operation is atomic. [rientjes@google.com: changelog and sys_unshare() code] [rientjes@google.com: protect oom_disable_count with task_lock in fork] [rientjes@google.com: use old_mm for oom_disable_count in exec] Signed-off-by: Ying Han Signed-off-by: David Rientjes Cc: KAMEZAWA Hiroyuki Cc: KOSAKI Motohiro Cc: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/fork.c | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) (limited to 'kernel/fork.c') diff --git a/kernel/fork.c b/kernel/fork.c index c445f8cc408d..e87aaaaf5131 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -65,6 +65,7 @@ #include #include #include +#include #include #include @@ -488,6 +489,7 @@ static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p) mm->cached_hole_size = ~0UL; mm_init_aio(mm); mm_init_owner(mm, p); + atomic_set(&mm->oom_disable_count, 0); if (likely(!mm_alloc_pgd(mm))) { mm->def_flags = 0; @@ -741,6 +743,8 @@ good_mm: /* Initializing for Swap token stuff */ mm->token_priority = 0; mm->last_interval = 0; + if (tsk->signal->oom_score_adj == OOM_SCORE_ADJ_MIN) + atomic_inc(&mm->oom_disable_count); tsk->mm = mm; tsk->active_mm = mm; @@ -1299,8 +1303,13 @@ bad_fork_cleanup_io: bad_fork_cleanup_namespaces: exit_task_namespaces(p); bad_fork_cleanup_mm: - if (p->mm) + if (p->mm) { + task_lock(p); + if (p->signal->oom_score_adj == OOM_SCORE_ADJ_MIN) + atomic_dec(&p->mm->oom_disable_count); + task_unlock(p); mmput(p->mm); + } bad_fork_cleanup_signal: if (!(clone_flags & CLONE_THREAD)) free_signal_struct(p->signal); @@ -1693,6 +1702,10 @@ SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags) active_mm = current->active_mm; current->mm = new_mm; current->active_mm = new_mm; + if (current->signal->oom_score_adj == OOM_SCORE_ADJ_MIN) { + atomic_dec(&mm->oom_disable_count); + atomic_inc(&new_mm->oom_disable_count); + } activate_mm(active_mm, new_mm); new_mm = mm; } -- cgit v1.2.3 From 9b1bf12d5d51bca178dea21b04a0805e29d60cf1 Mon Sep 17 00:00:00 2001 From: KOSAKI Motohiro Date: Wed, 27 Oct 2010 15:34:08 -0700 Subject: signals: move cred_guard_mutex from task_struct to signal_struct Oleg Nesterov pointed out we have to prevent multiple-threads-inside-exec itself and we can reuse ->cred_guard_mutex for it. Yes, concurrent execve() has no worth. Let's move ->cred_guard_mutex from task_struct to signal_struct. It naturally prevent multiple-threads-inside-exec. Signed-off-by: KOSAKI Motohiro Reviewed-by: Oleg Nesterov Acked-by: Roland McGrath Acked-by: David Howells Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/fork.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel/fork.c') diff --git a/kernel/fork.c b/kernel/fork.c index e87aaaaf5131..3b159c5991b7 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -908,6 +908,8 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) sig->oom_adj = current->signal->oom_adj; sig->oom_score_adj = current->signal->oom_score_adj; + mutex_init(&sig->cred_guard_mutex); + return 0; } -- cgit v1.2.3 From f26f9aff6aaf67e9a430d16c266f91b13a5bff64 Mon Sep 17 00:00:00 2001 From: Mike Galbraith Date: Wed, 8 Dec 2010 11:05:42 +0100 Subject: Sched: fix skip_clock_update optimization idle_balance() drops/retakes rq->lock, leaving the previous task vulnerable to set_tsk_need_resched(). Clear it after we return from balancing instead, and in setup_thread_stack() as well, so no successfully descheduled or never scheduled task has it set. Need resched confused the skip_clock_update logic, which assumes that the next call to update_rq_clock() will come nearly immediately after being set. Make the optimization robust against the waking a sleeper before it sucessfully deschedules case by checking that the current task has not been dequeued before setting the flag, since it is that useless clock update we're trying to save, and clear unconditionally in schedule() proper instead of conditionally in put_prev_task(). Signed-off-by: Mike Galbraith Reported-by: Bjoern B. Brandenburg Tested-by: Yong Zhang Signed-off-by: Peter Zijlstra Cc: stable@kernel.org LKML-Reference: <1291802742.1417.9.camel@marge.simson.net> 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 3b159c5991b7..5447dc7defa9 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -273,6 +273,7 @@ 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 */ -- cgit v1.2.3