From d178f27fc5150d680d9df865ea9dfe3269cf00a6 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Mon, 9 Nov 2009 15:58:23 +0000 Subject: ksm: cond_resched in unstable tree KSM needs a cond_resched() for CONFIG_PREEMPT_NONE, in its unbounded search of the unstable tree. The stable tree cases already have one, and originally there was one down inside get_user_pages(); but I missed it when I converted to follow_page() instead. Signed-off-by: Hugh Dickins Acked-by: Izik Eidus Signed-off-by: Linus Torvalds --- mm/ksm.c | 1 + 1 file changed, 1 insertion(+) (limited to 'mm') diff --git a/mm/ksm.c b/mm/ksm.c index bef1af4f77e3..5575f8628fef 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -1012,6 +1012,7 @@ static struct rmap_item *unstable_tree_search_insert(struct page *page, struct rmap_item *tree_rmap_item; int ret; + cond_resched(); tree_rmap_item = rb_entry(*new, struct rmap_item, node); page2[0] = get_mergeable_page(tree_rmap_item); if (!page2[0]) -- cgit v1.2.3 From 5ebd4c22897dce65845807a9bd3a31cc4e142b53 Mon Sep 17 00:00:00 2001 From: Soeren Sandmann Date: Wed, 28 Oct 2009 18:55:36 +0100 Subject: highmem: Fix race in debug_kmap_atomic() which could cause warn_count to underflow debug_kmap_atomic() tries to prevent ever printing more than 10 warnings, but it does so by testing whether an unsigned integer is equal to 0. However, if the warning is caused by a nested IRQ, then this counter may underflow and the stream of warnings will never end. Fix that by using a signed integer instead. Signed-off-by: Soeren Sandmann Pedersen Cc: Linus Torvalds Cc: a.p.zijlstra@chello.nl Cc: # .31.x LKML-Reference: Signed-off-by: Ingo Molnar --- mm/highmem.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'mm') diff --git a/mm/highmem.c b/mm/highmem.c index 25878cc49daa..33587de6b871 100644 --- a/mm/highmem.c +++ b/mm/highmem.c @@ -426,9 +426,9 @@ void __init page_address_init(void) void debug_kmap_atomic(enum km_type type) { - static unsigned warn_count = 10; + static int warn_count = 10; - if (unlikely(warn_count == 0)) + if (unlikely(warn_count < 0)) return; if (unlikely(in_interrupt())) { -- cgit v1.2.3 From d4515646699b6ad7b1a98ceb871296b957f3ef47 Mon Sep 17 00:00:00 2001 From: Soeren Sandmann Date: Wed, 28 Oct 2009 18:56:35 +0100 Subject: highmem: Fix debug_kmap_atomic() to also handle KM_IRQ_PTE, KM_NMI, and KM_NMI_PTE Previously calling debug_kmap_atomic() with these types would cause spurious warnings. (triggered by SysProf using perf events) Signed-off-by: Soeren Sandmann Pedersen Cc: Linus Torvalds Cc: a.p.zijlstra@chello.nl Cc: # .31.x LKML-Reference: Signed-off-by: Ingo Molnar --- mm/highmem.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) (limited to 'mm') diff --git a/mm/highmem.c b/mm/highmem.c index 33587de6b871..9c1e627f282e 100644 --- a/mm/highmem.c +++ b/mm/highmem.c @@ -432,10 +432,15 @@ void debug_kmap_atomic(enum km_type type) return; if (unlikely(in_interrupt())) { - if (in_irq()) { + if (in_nmi()) { + if (type != KM_NMI && type != KM_NMI_PTE) { + WARN_ON(1); + warn_count--; + } + } else if (in_irq()) { if (type != KM_IRQ0 && type != KM_IRQ1 && type != KM_BIO_SRC_IRQ && type != KM_BIO_DST_IRQ && - type != KM_BOUNCE_READ) { + type != KM_BOUNCE_READ && type != KM_IRQ_PTE) { WARN_ON(1); warn_count--; } @@ -452,7 +457,9 @@ void debug_kmap_atomic(enum km_type type) } if (type == KM_IRQ0 || type == KM_IRQ1 || type == KM_BOUNCE_READ || - type == KM_BIO_SRC_IRQ || type == KM_BIO_DST_IRQ) { + type == KM_BIO_SRC_IRQ || type == KM_BIO_DST_IRQ || + type == KM_IRQ_PTE || type == KM_NMI || + type == KM_NMI_PTE ) { if (!irqs_disabled()) { WARN_ON(1); warn_count--; -- cgit v1.2.3 From cc4a6851466039a8a688c843962a05689059ff3b Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 11 Nov 2009 14:26:14 -0800 Subject: page allocator: always wake kswapd when restarting an allocation attempt after direct reclaim failed If a direct reclaim makes no forward progress, it considers whether it should go OOM or not. Whether OOM is triggered or not, it may retry the allocation afterwards. In times past, this would always wake kswapd as well but currently, kswapd is not woken up after direct reclaim fails. For order-0 allocations, this makes little difference but if there is a heavy mix of higher-order allocations that direct reclaim is failing for, it might mean that kswapd is not rewoken for higher orders as much as it did previously. This patch wakes up kswapd when an allocation is being retried after a direct reclaim failure. It would be expected that kswapd is already awake, but this has the effect of telling kswapd to reclaim at the higher order as well. Signed-off-by: Mel Gorman Reviewed-by: Christoph Lameter Reviewed-by: Pekka Enberg Reviewed-by: KOSAKI Motohiro Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index cdcedf661616..250d0552a92d 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1817,9 +1817,9 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, if (NUMA_BUILD && (gfp_mask & GFP_THISNODE) == GFP_THISNODE) goto nopage; +restart: wake_all_kswapd(order, zonelist, high_zoneidx); -restart: /* * OK, we're below the kswapd watermark and have kicked background * reclaim. Now things get more complex, so set up alloc_flags according -- cgit v1.2.3 From 9d0ed60fe9cd1fbf57f755cd27a23ae9114d7210 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 11 Nov 2009 14:26:17 -0800 Subject: page allocator: Do not allow interrupts to use ALLOC_HARDER Commit 341ce06f69abfafa31b9468410a13dbd60e2b237 ("page allocator: calculate the alloc_flags for allocation only once") altered watermark logic slightly by allowing rt_tasks that are handling an interrupt to set ALLOC_HARDER. This patch brings the watermark logic more in line with 2.6.30. This change results in a reduction of the number high-order GFP_ATOMIC allocation failures reported. See http://www.gossamer-threads.com/lists/linux/kernel/1144153 [rientjes@google.com: Spotted the problem] Signed-off-by: Mel Gorman Reviewed-by: Pekka Enberg Reviewed-by: Rik van Riel Reviewed-by: KOSAKI Motohiro Cc: David Rientjes Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 250d0552a92d..2bc2ac63f41e 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1769,7 +1769,7 @@ gfp_to_alloc_flags(gfp_t gfp_mask) * See also cpuset_zone_allowed() comment in kernel/cpuset.c. */ alloc_flags &= ~ALLOC_CPUSET; - } else if (unlikely(rt_task(p))) + } else if (unlikely(rt_task(p)) && !in_interrupt()) alloc_flags |= ALLOC_HARDER; if (likely(!(gfp_mask & __GFP_NOMEMALLOC))) { -- cgit v1.2.3 From e00e431612c3a6e437a01f2129fd3843da0c982a Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Wed, 11 Nov 2009 14:26:26 -0800 Subject: memcg: fix wrong pointer initialization at page migration when memcg is disabled. Lee Schermerhorn reported that he saw bad pointer dereference in mem_cgroup_end_migration() when he disabled memcg by boot option. memcg's page migration logic works as mem_cgroup_prepare_migration(page, &ptr); do page migration mem_cgroup_end_migration(page, ptr); Now, ptr is not initialized in prepare_migration when memcg is disabled by boot option. This causes panic in end_migration. This patch fixes it. Reported-by: Lee Schermerhorn Cc: Balbir Singh Signed-off-by: KAMEZAWA Hiroyuki Reviewed-by: Daisuke Nishimura Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/migrate.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/migrate.c b/mm/migrate.c index 1a4bf4813780..7dbcb22316d2 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -602,7 +602,7 @@ static int unmap_and_move(new_page_t get_new_page, unsigned long private, struct page *newpage = get_new_page(page, private, &result); int rcu_locked = 0; int charge = 0; - struct mem_cgroup *mem; + struct mem_cgroup *mem = NULL; if (!newpage) return -ENOMEM; -- cgit v1.2.3