From b726b7dfb400c937546fa91cf8523dcb1aa2fc6e Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Mon, 7 Oct 2013 11:28:53 +0100 Subject: Revert "mm: sched: numa: Delay PTE scanning until a task is scheduled on a new node" PTE scanning and NUMA hinting fault handling is expensive so commit 5bca2303 ("mm: sched: numa: Delay PTE scanning until a task is scheduled on a new node") deferred the PTE scan until a task had been scheduled on another node. The problem is that in the purely shared memory case that this may never happen and no NUMA hinting fault information will be captured. We are not ruling out the possibility that something better can be done here but for now, this patch needs to be reverted and depend entirely on the scan_delay to avoid punishing short-lived processes. Signed-off-by: Mel Gorman Reviewed-by: Rik van Riel Cc: Andrea Arcangeli Cc: Johannes Weiner Cc: Srikar Dronamraju Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/1381141781-10992-16-git-send-email-mgorman@suse.de Signed-off-by: Ingo Molnar --- kernel/fork.c | 3 --- 1 file changed, 3 deletions(-) (limited to 'kernel/fork.c') diff --git a/kernel/fork.c b/kernel/fork.c index 086fe73ad6bd..7192d91b5415 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -816,9 +816,6 @@ struct mm_struct *dup_mm(struct task_struct *tsk) #ifdef CONFIG_TRANSPARENT_HUGEPAGE mm->pmd_huge_pte = NULL; -#endif -#ifdef CONFIG_NUMA_BALANCING - mm->first_nid = NUMA_PTE_SCAN_INIT; #endif if (!mm_init(mm, tsk)) goto fail_nomem; -- cgit v1.2.3 From 5e1576ed0e54d419286a8096133029062b6ad456 Mon Sep 17 00:00:00 2001 From: Rik van Riel Date: Mon, 7 Oct 2013 11:29:26 +0100 Subject: sched/numa: Stay on the same node if CLONE_VM A newly spawned thread inside a process should stay on the same NUMA node as its parent. This prevents processes from being "torn" across multiple NUMA nodes every time they spawn a new thread. Signed-off-by: Rik van Riel Signed-off-by: Mel Gorman Cc: Andrea Arcangeli Cc: Johannes Weiner Cc: Srikar Dronamraju Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/1381141781-10992-49-git-send-email-mgorman@suse.de Signed-off-by: Ingo Molnar --- 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 7192d91b5415..c93be06dee87 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1310,7 +1310,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, #endif /* Perform scheduler related setup. Assign this task to a CPU. */ - sched_fork(p); + sched_fork(clone_flags, p); retval = perf_event_init_task(p); if (retval) -- cgit v1.2.3 From b68e0749100e1b901bf11330f149b321c082178e Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Sun, 13 Oct 2013 21:18:31 +0200 Subject: uprobes: Change the callsite of uprobe_copy_process() Preparation for the next patches. Move the callsite of uprobe_copy_process() in copy_process() down to the succesfull return. We do not care if copy_process() fails, uprobe_free_utask() won't be called in this case so the wrong ->utask != NULL doesn't matter. OTOH, with this change we know that copy_process() can't fail when uprobe_copy_process() is called, the new task should either return to user-mode or call do_exit(). This way uprobe_copy_process() can: 1. setup p->utask != NULL if necessary 2. setup uprobes_state.xol_area 3. use task_work_add(p) Also, move the definition of uprobe_copy_process() down so that it can see get_utask(). Signed-off-by: Oleg Nesterov Acked-by: Srikar Dronamraju --- 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 086fe73ad6bd..d3603b81246b 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1373,7 +1373,6 @@ static struct task_struct *copy_process(unsigned long clone_flags, INIT_LIST_HEAD(&p->pi_state_list); p->pi_state_cache = NULL; #endif - uprobe_copy_process(p); /* * sigaltstack should be cleared when sharing the same VM */ @@ -1490,6 +1489,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, perf_event_fork(p); trace_task_newtask(p, clone_flags); + uprobe_copy_process(p); return p; -- cgit v1.2.3 From 3ab679661721b1ec2aaad99a801870ed59ab1110 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Wed, 16 Oct 2013 19:39:37 +0200 Subject: uprobes: Teach uprobe_copy_process() to handle CLONE_VFORK uprobe_copy_process() does nothing if the child shares ->mm with the forking process, but there is a special case: CLONE_VFORK. In this case it would be more correct to do dup_utask() but avoid dup_xol(). This is not that important, the child should not unwind its stack too much, this can corrupt the parent's stack, but at least we need this to allow to ret-probe __vfork() itself. Note: in theory, it would be better to check task_pt_regs(p)->sp instead of CLONE_VFORK, we need to dup_utask() if and only if the child can return from the function called by the parent. But this needs the arch-dependant helper, and I think that nobody actually does clone(same_stack, CLONE_VM). Reported-by: Martin Cermak Reported-by: David Smith Signed-off-by: Oleg Nesterov --- 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 d3603b81246b..8531609b6a82 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1489,7 +1489,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, perf_event_fork(p); trace_task_newtask(p, clone_flags); - uprobe_copy_process(p); + uprobe_copy_process(p, clone_flags); return p; -- cgit v1.2.3 From e1f56c89b040134add93f686931cc266541d239a Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Thu, 14 Nov 2013 14:30:48 -0800 Subject: mm: convert mm->nr_ptes to atomic_long_t With split page table lock for PMD level we can't hold mm->page_table_lock while updating nr_ptes. Let's convert it to atomic_long_t to avoid races. Signed-off-by: Kirill A. Shutemov Tested-by: Alex Thorlton Cc: Ingo Molnar Cc: Naoya Horiguchi Cc: "Eric W . Biederman" Cc: "Paul E . McKenney" Cc: Al Viro Cc: Andi Kleen Cc: Andrea Arcangeli Cc: Dave Hansen Cc: Dave Jones Cc: David Howells Cc: Frederic Weisbecker Cc: Johannes Weiner Cc: Kees Cook Cc: Mel Gorman Cc: Michael Kerrisk Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Rik van Riel Cc: Robin Holt Cc: Sedat Dilek Cc: Srikar Dronamraju Cc: Thomas Gleixner Cc: 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 f6d11fc67f72..e2520756e005 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -532,7 +532,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p) mm->flags = (current->mm) ? (current->mm->flags & MMF_INIT_MASK) : default_dump_filter; mm->core_state = NULL; - mm->nr_ptes = 0; + atomic_long_set(&mm->nr_ptes, 0); memset(&mm->rss_stat, 0, sizeof(mm->rss_stat)); spin_lock_init(&mm->page_table_lock); mm_init_aio(mm); -- cgit v1.2.3 From e009bb30c8df8a52a9622b616b67436b6a03a0cd Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Thu, 14 Nov 2013 14:31:07 -0800 Subject: mm: implement split page table lock for PMD level The basic idea is the same as with PTE level: the lock is embedded into struct page of table's page. We can't use mm->pmd_huge_pte to store pgtables for THP, since we don't take mm->page_table_lock anymore. Let's reuse page->lru of table's page for that. pgtable_pmd_page_ctor() returns true, if initialization is successful and false otherwise. Current implementation never fails, but assumption that constructor can fail will help to port it to -rt where spinlock_t is rather huge and cannot be embedded into struct page -- dynamic allocation is required. Signed-off-by: Naoya Horiguchi Signed-off-by: Kirill A. Shutemov Tested-by: Alex Thorlton Cc: Ingo Molnar Cc: "Eric W . Biederman" Cc: "Paul E . McKenney" Cc: Al Viro Cc: Andi Kleen Cc: Andrea Arcangeli Cc: Dave Hansen Cc: Dave Jones Cc: David Howells Cc: Frederic Weisbecker Cc: Johannes Weiner Cc: Kees Cook Cc: Mel Gorman Cc: Michael Kerrisk Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Rik van Riel Cc: Robin Holt Cc: Sedat Dilek Cc: Srikar Dronamraju Cc: Thomas Gleixner Cc: Hugh Dickins Reviewed-by: Steven Rostedt 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 e2520756e005..728d5be9548c 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -560,7 +560,7 @@ static void check_mm(struct mm_struct *mm) "mm:%p idx:%d val:%ld\n", mm, i, x); } -#ifdef CONFIG_TRANSPARENT_HUGEPAGE +#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS VM_BUG_ON(mm->pmd_huge_pte); #endif } @@ -814,7 +814,7 @@ struct mm_struct *dup_mm(struct task_struct *tsk) memcpy(mm, oldmm, sizeof(*mm)); mm_init_cpumask(mm); -#ifdef CONFIG_TRANSPARENT_HUGEPAGE +#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS mm->pmd_huge_pte = NULL; #endif if (!mm_init(mm, tsk)) -- cgit v1.2.3