From 8afb1474db4701d1ab80cd8251137a3260e6913e Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Tue, 10 Sep 2013 11:43:37 +0800 Subject: slub: Fix calculation of cpu slabs /sys/kernel/slab/:t-0000048 # cat cpu_slabs 231 N0=16 N1=215 /sys/kernel/slab/:t-0000048 # cat slabs 145 N0=36 N1=109 See, the number of slabs is smaller than that of cpu slabs. The bug was introduced by commit 49e2258586b423684f03c278149ab46d8f8b6700 ("slub: per cpu cache for partial pages"). We should use page->pages instead of page->pobjects when calculating the number of cpu partial slabs. This also fixes the mapping of slabs and nodes. As there's no variable storing the number of total/active objects in cpu partial slabs, and we don't have user interfaces requiring those statistics, I just add WARN_ON for those cases. Cc: # 3.2+ Acked-by: Christoph Lameter Reviewed-by: Wanpeng Li Signed-off-by: Li Zefan Signed-off-by: Pekka Enberg --- mm/slub.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/slub.c b/mm/slub.c index 545a170ebf9f..89490d9d91e0 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -4299,7 +4299,13 @@ static ssize_t show_slab_objects(struct kmem_cache *s, page = ACCESS_ONCE(c->partial); if (page) { - x = page->pobjects; + node = page_to_nid(page); + if (flags & SO_TOTAL) + WARN_ON_ONCE(1); + else if (flags & SO_OBJECTS) + WARN_ON_ONCE(1); + else + x = page->pages; total += x; nodes[node] += x; } -- cgit v1.2.3 From c65c1877bd6826ce0d9713d76e30a7bed8e49f38 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 10 Jan 2014 13:23:49 +0100 Subject: slub: use lockdep_assert_held Instead of using comments in an attempt at getting the locking right, use proper assertions that actively warn you if you got it wrong. Also add extra braces in a few sites to comply with coding-style. Signed-off-by: Peter Zijlstra Signed-off-by: Pekka Enberg --- mm/slub.c | 40 ++++++++++++++++++++-------------------- 1 file changed, 20 insertions(+), 20 deletions(-) (limited to 'mm') diff --git a/mm/slub.c b/mm/slub.c index 89490d9d91e0..367b224f2aa5 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -985,23 +985,22 @@ static inline void slab_free_hook(struct kmem_cache *s, void *x) /* * Tracking of fully allocated slabs for debugging purposes. - * - * list_lock must be held. */ static void add_full(struct kmem_cache *s, struct kmem_cache_node *n, struct page *page) { + lockdep_assert_held(&n->list_lock); + if (!(s->flags & SLAB_STORE_USER)) return; list_add(&page->lru, &n->full); } -/* - * list_lock must be held. - */ -static void remove_full(struct kmem_cache *s, struct page *page) +static void remove_full(struct kmem_cache *s, struct kmem_cache_node *n, struct page *page) { + lockdep_assert_held(&n->list_lock); + if (!(s->flags & SLAB_STORE_USER)) return; @@ -1250,7 +1249,8 @@ static inline int check_object(struct kmem_cache *s, struct page *page, void *object, u8 val) { return 1; } static inline void add_full(struct kmem_cache *s, struct kmem_cache_node *n, struct page *page) {} -static inline void remove_full(struct kmem_cache *s, struct page *page) {} +static inline void remove_full(struct kmem_cache *s, struct kmem_cache_node *n, + struct page *page) {} static inline unsigned long kmem_cache_flags(unsigned long object_size, unsigned long flags, const char *name, void (*ctor)(void *)) @@ -1504,12 +1504,12 @@ static void discard_slab(struct kmem_cache *s, struct page *page) /* * Management of partially allocated slabs. - * - * list_lock must be held. */ static inline void add_partial(struct kmem_cache_node *n, struct page *page, int tail) { + lockdep_assert_held(&n->list_lock); + n->nr_partial++; if (tail == DEACTIVATE_TO_TAIL) list_add_tail(&page->lru, &n->partial); @@ -1517,12 +1517,11 @@ static inline void add_partial(struct kmem_cache_node *n, list_add(&page->lru, &n->partial); } -/* - * list_lock must be held. - */ static inline void remove_partial(struct kmem_cache_node *n, struct page *page) { + lockdep_assert_held(&n->list_lock); + list_del(&page->lru); n->nr_partial--; } @@ -1532,8 +1531,6 @@ static inline void remove_partial(struct kmem_cache_node *n, * return the pointer to the freelist. * * Returns a list of objects or NULL if it fails. - * - * Must hold list_lock since we modify the partial list. */ static inline void *acquire_slab(struct kmem_cache *s, struct kmem_cache_node *n, struct page *page, @@ -1543,6 +1540,8 @@ static inline void *acquire_slab(struct kmem_cache *s, unsigned long counters; struct page new; + lockdep_assert_held(&n->list_lock); + /* * Zap the freelist and set the frozen bit. * The old freelist is the list of objects for the @@ -1887,7 +1886,7 @@ redo: else if (l == M_FULL) - remove_full(s, page); + remove_full(s, n, page); if (m == M_PARTIAL) { @@ -2541,7 +2540,7 @@ static void __slab_free(struct kmem_cache *s, struct page *page, new.inuse--; if ((!new.inuse || !prior) && !was_frozen) { - if (kmem_cache_has_cpu_partial(s) && !prior) + if (kmem_cache_has_cpu_partial(s) && !prior) { /* * Slab was on no list before and will be @@ -2551,7 +2550,7 @@ static void __slab_free(struct kmem_cache *s, struct page *page, */ new.frozen = 1; - else { /* Needs to be taken off a list */ + } else { /* Needs to be taken off a list */ n = get_node(s, page_to_nid(page)); /* @@ -2600,7 +2599,7 @@ static void __slab_free(struct kmem_cache *s, struct page *page, */ if (!kmem_cache_has_cpu_partial(s) && unlikely(!prior)) { if (kmem_cache_debug(s)) - remove_full(s, page); + remove_full(s, n, page); add_partial(n, page, DEACTIVATE_TO_TAIL); stat(s, FREE_ADD_PARTIAL); } @@ -2614,9 +2613,10 @@ slab_empty: */ remove_partial(n, page); stat(s, FREE_REMOVE_PARTIAL); - } else + } else { /* Slab must be on the full list */ - remove_full(s, page); + remove_full(s, n, page); + } spin_unlock_irqrestore(&n->list_lock, flags); stat(s, FREE_SLAB); -- cgit v1.2.3 From 26e4f2057516f1c457e0e95346a00303f983ad53 Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Sat, 4 Jan 2014 16:32:31 +0900 Subject: slub: Fix possible format string bug. The "name" is determined at runtime and is parsed as format string. Acked-by: David Rientjes Signed-off-by: Tetsuo Handa Signed-off-by: Pekka Enberg --- mm/slub.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/slub.c b/mm/slub.c index 367b224f2aa5..a99e9e67c60e 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -5169,7 +5169,7 @@ static int sysfs_slab_add(struct kmem_cache *s) } s->kobj.kset = slab_kset; - err = kobject_init_and_add(&s->kobj, &slab_ktype, NULL, name); + err = kobject_init_and_add(&s->kobj, &slab_ktype, NULL, "%s", name); if (err) { kobject_put(&s->kobj); return err; -- cgit v1.2.3 From ec65993443736a5091b68e80ff1734548944a4b8 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Tue, 21 Jan 2014 14:33:16 -0800 Subject: mm, x86: Account for TLB flushes only when debugging Bisection between 3.11 and 3.12 fingered commit 9824cf97 ("mm: vmstats: tlb flush counters") to cause overhead problems. The counters are undeniably useful but how often do we really need to debug TLB flush related issues? It does not justify taking the penalty everywhere so make it a debugging option. Signed-off-by: Mel Gorman Tested-by: Davidlohr Bueso Reviewed-by: Rik van Riel Signed-off-by: Andrew Morton Cc: Hugh Dickins Cc: Alex Shi Cc: Linus Torvalds Cc: Peter Zijlstra Link: http://lkml.kernel.org/n/tip-XzxjntugxuwpxXhcrxqqh53b@git.kernel.org Signed-off-by: Ingo Molnar --- arch/x86/include/asm/tlbflush.h | 6 +++--- arch/x86/kernel/cpu/mtrr/generic.c | 4 ++-- arch/x86/mm/tlb.c | 14 +++++++------- include/linux/vm_event_item.h | 4 +++- include/linux/vmstat.h | 8 ++++++++ mm/vmstat.c | 4 +++- 6 files changed, 26 insertions(+), 14 deletions(-) (limited to 'mm') diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index e6d90babc245..04905bfc508b 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -62,7 +62,7 @@ static inline void __flush_tlb_all(void) static inline void __flush_tlb_one(unsigned long addr) { - count_vm_event(NR_TLB_LOCAL_FLUSH_ONE); + count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ONE); __flush_tlb_single(addr); } @@ -93,13 +93,13 @@ static inline void __flush_tlb_one(unsigned long addr) */ static inline void __flush_tlb_up(void) { - count_vm_event(NR_TLB_LOCAL_FLUSH_ALL); + count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); __flush_tlb(); } static inline void flush_tlb_all(void) { - count_vm_event(NR_TLB_LOCAL_FLUSH_ALL); + count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); __flush_tlb_all(); } diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index ce2d0a2c3e4f..0e25a1bc5ab5 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -683,7 +683,7 @@ static void prepare_set(void) __acquires(set_atomicity_lock) } /* Flush all TLBs via a mov %cr3, %reg; mov %reg, %cr3 */ - count_vm_event(NR_TLB_LOCAL_FLUSH_ALL); + count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); __flush_tlb(); /* Save MTRR state */ @@ -697,7 +697,7 @@ static void prepare_set(void) __acquires(set_atomicity_lock) static void post_set(void) __releases(set_atomicity_lock) { /* Flush TLBs (no need to flush caches - they are disabled) */ - count_vm_event(NR_TLB_LOCAL_FLUSH_ALL); + count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); __flush_tlb(); /* Intel (P6) standard MTRRs */ diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index ae699b3bbac8..05446c1cccfe 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -103,7 +103,7 @@ static void flush_tlb_func(void *info) if (f->flush_mm != this_cpu_read(cpu_tlbstate.active_mm)) return; - count_vm_event(NR_TLB_REMOTE_FLUSH_RECEIVED); + count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED); if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK) { if (f->flush_end == TLB_FLUSH_ALL) local_flush_tlb(); @@ -131,7 +131,7 @@ void native_flush_tlb_others(const struct cpumask *cpumask, info.flush_start = start; info.flush_end = end; - count_vm_event(NR_TLB_REMOTE_FLUSH); + count_vm_tlb_event(NR_TLB_REMOTE_FLUSH); if (is_uv_system()) { unsigned int cpu; @@ -151,7 +151,7 @@ void flush_tlb_current_task(void) preempt_disable(); - count_vm_event(NR_TLB_LOCAL_FLUSH_ALL); + count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); local_flush_tlb(); if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids) flush_tlb_others(mm_cpumask(mm), mm, 0UL, TLB_FLUSH_ALL); @@ -215,7 +215,7 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, /* tlb_flushall_shift is on balance point, details in commit log */ if ((end - start) >> PAGE_SHIFT > act_entries >> tlb_flushall_shift) { - count_vm_event(NR_TLB_LOCAL_FLUSH_ALL); + count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); local_flush_tlb(); } else { if (has_large_page(mm, start, end)) { @@ -224,7 +224,7 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, } /* flush range by one by one 'invlpg' */ for (addr = start; addr < end; addr += PAGE_SIZE) { - count_vm_event(NR_TLB_LOCAL_FLUSH_ONE); + count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ONE); __flush_tlb_single(addr); } @@ -262,7 +262,7 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long start) static void do_flush_tlb_all(void *info) { - count_vm_event(NR_TLB_REMOTE_FLUSH_RECEIVED); + count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED); __flush_tlb_all(); if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_LAZY) leave_mm(smp_processor_id()); @@ -270,7 +270,7 @@ static void do_flush_tlb_all(void *info) void flush_tlb_all(void) { - count_vm_event(NR_TLB_REMOTE_FLUSH); + count_vm_tlb_event(NR_TLB_REMOTE_FLUSH); on_each_cpu(do_flush_tlb_all, NULL, 1); } diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index c557c6d096de..3a712e2e7d76 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -71,12 +71,14 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, THP_ZERO_PAGE_ALLOC, THP_ZERO_PAGE_ALLOC_FAILED, #endif +#ifdef CONFIG_DEBUG_TLBFLUSH #ifdef CONFIG_SMP NR_TLB_REMOTE_FLUSH, /* cpu tried to flush others' tlbs */ NR_TLB_REMOTE_FLUSH_RECEIVED,/* cpu received ipi for flush */ -#endif +#endif /* CONFIG_SMP */ NR_TLB_LOCAL_FLUSH_ALL, NR_TLB_LOCAL_FLUSH_ONE, +#endif /* CONFIG_DEBUG_TLBFLUSH */ NR_VM_EVENT_ITEMS }; diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index e4b948080d20..80ebba9c2e87 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -83,6 +83,14 @@ static inline void vm_events_fold_cpu(int cpu) #define count_vm_numa_events(x, y) do { (void)(y); } while (0) #endif /* CONFIG_NUMA_BALANCING */ +#ifdef CONFIG_DEBUG_TLBFLUSH +#define count_vm_tlb_event(x) count_vm_event(x) +#define count_vm_tlb_events(x, y) count_vm_events(x, y) +#else +#define count_vm_tlb_event(x) do {} while (0) +#define count_vm_tlb_events(x, y) do { (void)(y); } while (0) +#endif + #define __count_zone_vm_events(item, zone, delta) \ __count_vm_events(item##_NORMAL - ZONE_NORMAL + \ zone_idx(zone), delta) diff --git a/mm/vmstat.c b/mm/vmstat.c index 72496140ac08..def5dd2fbe61 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -851,12 +851,14 @@ const char * const vmstat_text[] = { "thp_zero_page_alloc", "thp_zero_page_alloc_failed", #endif +#ifdef CONFIG_DEBUG_TLBFLUSH #ifdef CONFIG_SMP "nr_tlb_remote_flush", "nr_tlb_remote_flush_received", -#endif +#endif /* CONFIG_SMP */ "nr_tlb_local_flush_all", "nr_tlb_local_flush_one", +#endif /* CONFIG_DEBUG_TLBFLUSH */ #endif /* CONFIG_VM_EVENTS_COUNTERS */ }; -- cgit v1.2.3 From 67b6c900dc6dce65478d6fe37b60cd1e65bb80c2 Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Fri, 24 Jan 2014 07:20:23 -0800 Subject: mm: slub: work around unneeded lockdep warning The slub code does some setup during early boot in early_kmem_cache_node_alloc() with some local data. There is no possible way that another CPU can see this data, so the slub code doesn't unnecessarily lock it. However, some new lockdep asserts check to make sure that add_partial() _always_ has the list_lock held. Just add the locking, even though it is technically unnecessary. Cc: Peter Zijlstra Cc: Russell King Acked-by: David Rientjes Signed-off-by: Dave Hansen Signed-off-by: Pekka Enberg --- mm/slub.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'mm') diff --git a/mm/slub.c b/mm/slub.c index a99e9e67c60e..432bddf484bb 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -2890,7 +2890,13 @@ static void early_kmem_cache_node_alloc(int node) init_kmem_cache_node(n); inc_slabs_node(kmem_cache_node, node, page->objects); + /* + * the lock is for lockdep's sake, not for any actual + * race protection + */ + spin_lock(&n->list_lock); add_partial(n, page, DEACTIVATE_TO_HEAD); + spin_unlock(&n->list_lock); } static void free_kmem_cache_nodes(struct kmem_cache *s) -- cgit v1.2.3 From cb8ee1a3d429f8898972c869dd4792afb04e961a Mon Sep 17 00:00:00 2001 From: Masanari Iida Date: Tue, 28 Jan 2014 02:57:08 +0900 Subject: mm: Fix warning on make htmldocs caused by slab.c This patch fixed following errors while make htmldocs Warning(/mm/slab.c:1956): No description found for parameter 'page' Warning(/mm/slab.c:1956): Excess function parameter 'slabp' description in 'slab_destroy' Incorrect function parameter "slabp" was set instead of "page" Acked-by: Christoph Lameter Signed-off-by: Masanari Iida Signed-off-by: Pekka Enberg --- mm/slab.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/slab.c b/mm/slab.c index eb043bf05f4c..b264214c77ea 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -1946,7 +1946,7 @@ static void slab_destroy_debugcheck(struct kmem_cache *cachep, /** * slab_destroy - destroy and release all objects in a slab * @cachep: cache pointer being destroyed - * @slabp: slab pointer being destroyed + * @page: page pointer being destroyed * * Destroy all the objs in a slab, and release the mem back to the system. * Before calling the slab must have been unlinked from the cache. The -- cgit v1.2.3 From 1ff6bbfd13ca2c114a5cb58e1a92d1e5d68ce0b7 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 28 Jan 2014 18:10:37 -0500 Subject: arm, pm, vmpressure: add missing slab.h includes arch/arm/mach-tegra/pm.c, kernel/power/console.c and mm/vmpressure.c were somehow getting slab.h indirectly through cgroup.h which in turn was getting it indirectly through xattr.h. A scheduled cgroup change drops xattr.h inclusion from cgroup.h and breaks compilation of these three files. Add explicit slab.h includes to the three files. A pending cgroup patch depends on this change and it'd be great if this can be routed through cgroup/for-3.14-fixes branch. Signed-off-by: Tejun Heo Acked-by: Stephen Warren Cc: Thierry Reding Cc: linux-tegra@vger.kernel.org Cc: "Rafael J. Wysocki" Cc: linux-pm@vger.kernel.org Cc: Johannes Weiner Cc: Michal Hocko Cc: Balbir Singh Cc: KAMEZAWA Hiroyuki Cc: cgroups@vger.kernel.org --- arch/arm/mach-tegra/pm.c | 1 + kernel/power/console.c | 1 + mm/vmpressure.c | 1 + 3 files changed, 3 insertions(+) (limited to 'mm') diff --git a/arch/arm/mach-tegra/pm.c b/arch/arm/mach-tegra/pm.c index 4ae0286b468d..f55b05a29b55 100644 --- a/arch/arm/mach-tegra/pm.c +++ b/arch/arm/mach-tegra/pm.c @@ -24,6 +24,7 @@ #include #include #include +#include #include #include diff --git a/kernel/power/console.c b/kernel/power/console.c index eacb8bd8cab4..aba9c545a0e3 100644 --- a/kernel/power/console.c +++ b/kernel/power/console.c @@ -9,6 +9,7 @@ #include #include #include +#include #include "power.h" #define SUSPEND_CONSOLE (MAX_NR_CONSOLES-1) diff --git a/mm/vmpressure.c b/mm/vmpressure.c index 196970a4541f..d4042e75f7c7 100644 --- a/mm/vmpressure.c +++ b/mm/vmpressure.c @@ -19,6 +19,7 @@ #include #include #include +#include #include #include #include -- cgit v1.2.3 From 579f82901f6f41256642936d7e632f3979ad76d4 Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Thu, 6 Feb 2014 12:04:21 -0800 Subject: swap: add a simple detector for inappropriate swapin readahead This is a patch to improve swap readahead algorithm. It's from Hugh and I slightly changed it. Hugh's original changelog: swapin readahead does a blind readahead, whether or not the swapin is sequential. This may be ok on harddisk, because large reads have relatively small costs, and if the readahead pages are unneeded they can be reclaimed easily - though, what if their allocation forced reclaim of useful pages? But on SSD devices large reads are more expensive than small ones: if the readahead pages are unneeded, reading them in caused significant overhead. This patch adds very simplistic random read detection. Stealing the PageReadahead technique from Konstantin Khlebnikov's patch, avoiding the vma/anon_vma sophistications of Shaohua Li's patch, swapin_nr_pages() simply looks at readahead's current success rate, and narrows or widens its readahead window accordingly. There is little science to its heuristic: it's about as stupid as can be whilst remaining effective. The table below shows elapsed times (in centiseconds) when running a single repetitive swapping load across a 1000MB mapping in 900MB ram with 1GB swap (the harddisk tests had taken painfully too long when I used mem=500M, but SSD shows similar results for that). Vanilla is the 3.6-rc7 kernel on which I started; Shaohua denotes his Sep 3 patch in mmotm and linux-next; HughOld denotes my Oct 1 patch which Shaohua showed to be defective; HughNew this Nov 14 patch, with page_cluster as usual at default of 3 (8-page reads); HughPC4 this same patch with page_cluster 4 (16-page reads); HughPC0 with page_cluster 0 (1-page reads: no readahead). HDD for swapping to harddisk, SSD for swapping to VertexII SSD. Seq for sequential access to the mapping, cycling five times around; Rand for the same number of random touches. Anon for a MAP_PRIVATE anon mapping; Shmem for a MAP_SHARED anon mapping, equivalent to tmpfs. One weakness of Shaohua's vma/anon_vma approach was that it did not optimize Shmem: seen below. Konstantin's approach was perhaps mistuned, 50% slower on Seq: did not compete and is not shown below. HDD Vanilla Shaohua HughOld HughNew HughPC4 HughPC0 Seq Anon 73921 76210 75611 76904 78191 121542 Seq Shmem 73601 73176 73855 72947 74543 118322 Rand Anon 895392 831243 871569 845197 846496 841680 Rand Shmem 1058375 1053486 827935 764955 764376 756489 SSD Vanilla Shaohua HughOld HughNew HughPC4 HughPC0 Seq Anon 24634 24198 24673 25107 21614 70018 Seq Shmem 24959 24932 25052 25703 22030 69678 Rand Anon 43014 26146 28075 25989 26935 25901 Rand Shmem 45349 45215 28249 24268 24138 24332 These tests are, of course, two extremes of a very simple case: under heavier mixed loads I've not yet observed any consistent improvement or degradation, and wider testing would be welcome. Shaohua Li: Test shows Vanilla is slightly better in sequential workload than Hugh's patch. I observed with Hugh's patch sometimes the readahead size is shrinked too fast (from 8 to 1 immediately) in sequential workload if there is no hit. And in such case, continuing doing readahead is good actually. I don't prepare a sophisticated algorithm for the sequential workload because so far we can't guarantee sequential accessed pages are swap out sequentially. So I slightly change Hugh's heuristic - don't shrink readahead size too fast. Here is my test result (unit second, 3 runs average): Vanilla Hugh New Seq 356 370 360 Random 4525 2447 2444 Attached graph is the swapin/swapout throughput I collected with 'vmstat 2'. The first part is running a random workload (till around 1200 of the x-axis) and the second part is running a sequential workload. swapin and swapout throughput are almost identical in steady state in both workloads. These are expected behavior. while in Vanilla, swapin is much bigger than swapout especially in random workload (because wrong readahead). Original patches by: Shaohua Li and Konstantin Khlebnikov. [fengguang.wu@intel.com: swapin_nr_pages() can be static] Signed-off-by: Hugh Dickins Signed-off-by: Shaohua Li Signed-off-by: Fengguang Wu Cc: Rik van Riel Cc: Wu Fengguang Cc: Minchan Kim Cc: Konstantin Khlebnikov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page-flags.h | 4 +-- mm/swap_state.c | 63 +++++++++++++++++++++++++++++++++++++++++++--- 2 files changed, 62 insertions(+), 5 deletions(-) (limited to 'mm') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index e464b4e987e8..d1fe1a761047 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -228,9 +228,9 @@ PAGEFLAG(OwnerPriv1, owner_priv_1) TESTCLEARFLAG(OwnerPriv1, owner_priv_1) TESTPAGEFLAG(Writeback, writeback) TESTSCFLAG(Writeback, writeback) PAGEFLAG(MappedToDisk, mappedtodisk) -/* PG_readahead is only used for file reads; PG_reclaim is only for writes */ +/* PG_readahead is only used for reads; PG_reclaim is only for writes */ PAGEFLAG(Reclaim, reclaim) TESTCLEARFLAG(Reclaim, reclaim) -PAGEFLAG(Readahead, reclaim) /* Reminder to do async read-ahead */ +PAGEFLAG(Readahead, reclaim) TESTCLEARFLAG(Readahead, reclaim) #ifdef CONFIG_HIGHMEM /* diff --git a/mm/swap_state.c b/mm/swap_state.c index 98e85e9c2b2d..e76ace30d436 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -63,6 +63,8 @@ unsigned long total_swapcache_pages(void) return ret; } +static atomic_t swapin_readahead_hits = ATOMIC_INIT(4); + void show_swap_cache_info(void) { printk("%lu pages in swap cache\n", total_swapcache_pages()); @@ -286,8 +288,11 @@ struct page * lookup_swap_cache(swp_entry_t entry) page = find_get_page(swap_address_space(entry), entry.val); - if (page) + if (page) { INC_CACHE_INFO(find_success); + if (TestClearPageReadahead(page)) + atomic_inc(&swapin_readahead_hits); + } INC_CACHE_INFO(find_total); return page; @@ -389,6 +394,50 @@ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, return found_page; } +static unsigned long swapin_nr_pages(unsigned long offset) +{ + static unsigned long prev_offset; + unsigned int pages, max_pages, last_ra; + static atomic_t last_readahead_pages; + + max_pages = 1 << ACCESS_ONCE(page_cluster); + if (max_pages <= 1) + return 1; + + /* + * This heuristic has been found to work well on both sequential and + * random loads, swapping to hard disk or to SSD: please don't ask + * what the "+ 2" means, it just happens to work well, that's all. + */ + pages = atomic_xchg(&swapin_readahead_hits, 0) + 2; + if (pages == 2) { + /* + * We can have no readahead hits to judge by: but must not get + * stuck here forever, so check for an adjacent offset instead + * (and don't even bother to check whether swap type is same). + */ + if (offset != prev_offset + 1 && offset != prev_offset - 1) + pages = 1; + prev_offset = offset; + } else { + unsigned int roundup = 4; + while (roundup < pages) + roundup <<= 1; + pages = roundup; + } + + if (pages > max_pages) + pages = max_pages; + + /* Don't shrink readahead too fast */ + last_ra = atomic_read(&last_readahead_pages) / 2; + if (pages < last_ra) + pages = last_ra; + atomic_set(&last_readahead_pages, pages); + + return pages; +} + /** * swapin_readahead - swap in pages in hope we need them soon * @entry: swap entry of this memory @@ -412,11 +461,16 @@ struct page *swapin_readahead(swp_entry_t entry, gfp_t gfp_mask, struct vm_area_struct *vma, unsigned long addr) { struct page *page; - unsigned long offset = swp_offset(entry); + unsigned long entry_offset = swp_offset(entry); + unsigned long offset = entry_offset; unsigned long start_offset, end_offset; - unsigned long mask = (1UL << page_cluster) - 1; + unsigned long mask; struct blk_plug plug; + mask = swapin_nr_pages(offset) - 1; + if (!mask) + goto skip; + /* Read a page_cluster sized and aligned cluster around offset. */ start_offset = offset & ~mask; end_offset = offset | mask; @@ -430,10 +484,13 @@ struct page *swapin_readahead(swp_entry_t entry, gfp_t gfp_mask, gfp_mask, vma, addr); if (!page) continue; + if (offset != entry_offset) + SetPageReadahead(page); page_cache_release(page); } blk_finish_plug(&plug); lru_add_drain(); /* Push any new pages onto the LRU now */ +skip: return read_swap_cache_async(entry, gfp_mask, vma, addr); } -- cgit v1.2.3 From f893ab41e4dae2fe8991faf5d86d029068d1ef3a Mon Sep 17 00:00:00 2001 From: Weijie Yang Date: Thu, 6 Feb 2014 12:04:23 -0800 Subject: mm/swap: fix race on swap_info reuse between swapoff and swapon swapoff clear swap_info's SWP_USED flag prematurely and free its resources after that. A concurrent swapon will reuse this swap_info while its previous resources are not cleared completely. These late freed resources are: - p->percpu_cluster - swap_cgroup_ctrl[type] - block_device setting - inode->i_flags &= ~S_SWAPFILE This patch clears the SWP_USED flag after all its resources are freed, so that swapon can reuse this swap_info by alloc_swap_info() safely. [akpm@linux-foundation.org: tidy up code comment] Signed-off-by: Weijie Yang Acked-by: Hugh Dickins Cc: Krzysztof Kozlowski Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/swapfile.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/swapfile.c b/mm/swapfile.c index c6c13b050a58..4a7f7e6992b6 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1923,7 +1923,6 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) p->swap_map = NULL; cluster_info = p->cluster_info; p->cluster_info = NULL; - p->flags = 0; frontswap_map = frontswap_map_get(p); spin_unlock(&p->lock); spin_unlock(&swap_lock); @@ -1949,6 +1948,16 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) mutex_unlock(&inode->i_mutex); } filp_close(swap_file, NULL); + + /* + * Clear the SWP_USED flag after all resources are freed so that swapon + * can reuse this swap_info in alloc_swap_info() safely. It is ok to + * not hold p->lock after we cleared its SWP_WRITEOK. + */ + spin_lock(&swap_lock); + p->flags = 0; + spin_unlock(&swap_lock); + err = 0; atomic_inc(&proc_poll_event); wake_up_interruptible(&proc_poll_wait); -- cgit v1.2.3 From a85d9df1ea1d23682a0ed1e100e6965006595d06 Mon Sep 17 00:00:00 2001 From: KOSAKI Motohiro Date: Thu, 6 Feb 2014 12:04:24 -0800 Subject: mm: __set_page_dirty_nobuffers() uses spin_lock_irqsave() instead of spin_lock_irq() During aio stress test, we observed the following lockdep warning. This mean AIO+numa_balancing is currently deadlockable. The problem is, aio_migratepage disable interrupt, but __set_page_dirty_nobuffers unintentionally enable it again. Generally, all helper function should use spin_lock_irqsave() instead of spin_lock_irq() because they don't know caller at all. other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(&(&ctx->completion_lock)->rlock); lock(&(&ctx->completion_lock)->rlock); *** DEADLOCK *** dump_stack+0x19/0x1b print_usage_bug+0x1f7/0x208 mark_lock+0x21d/0x2a0 mark_held_locks+0xb9/0x140 trace_hardirqs_on_caller+0x105/0x1d0 trace_hardirqs_on+0xd/0x10 _raw_spin_unlock_irq+0x2c/0x50 __set_page_dirty_nobuffers+0x8c/0xf0 migrate_page_copy+0x434/0x540 aio_migratepage+0xb1/0x140 move_to_new_page+0x7d/0x230 migrate_pages+0x5e5/0x700 migrate_misplaced_page+0xbc/0xf0 do_numa_page+0x102/0x190 handle_pte_fault+0x241/0x970 handle_mm_fault+0x265/0x370 __do_page_fault+0x172/0x5a0 do_page_fault+0x1a/0x70 page_fault+0x28/0x30 Signed-off-by: KOSAKI Motohiro Cc: Larry Woodman Cc: Rik van Riel Cc: Johannes Weiner Acked-by: David Rientjes Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page-writeback.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'mm') diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 2d30e2cfe804..7106cb1aca8e 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2173,11 +2173,12 @@ int __set_page_dirty_nobuffers(struct page *page) if (!TestSetPageDirty(page)) { struct address_space *mapping = page_mapping(page); struct address_space *mapping2; + unsigned long flags; if (!mapping) return 1; - spin_lock_irq(&mapping->tree_lock); + spin_lock_irqsave(&mapping->tree_lock, flags); mapping2 = page_mapping(page); if (mapping2) { /* Race with truncate? */ BUG_ON(mapping2 != mapping); @@ -2186,7 +2187,7 @@ int __set_page_dirty_nobuffers(struct page *page) radix_tree_tag_set(&mapping->page_tree, page_index(page), PAGECACHE_TAG_DIRTY); } - spin_unlock_irq(&mapping->tree_lock); + spin_unlock_irqrestore(&mapping->tree_lock, flags); if (mapping->host) { /* !PageAnon && !swapper_space */ __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); -- cgit v1.2.3 From d311d79de305f1ada47cadd672e6ed1b28a949eb Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 9 Feb 2014 15:18:09 -0500 Subject: fix O_SYNC|O_APPEND syncing the wrong range on write() It actually goes back to 2004 ([PATCH] Concurrent O_SYNC write support) when sync_page_range() had been introduced; generic_file_write{,v}() correctly synced pos_after_write - written .. pos_after_write - 1 but generic_file_aio_write() synced pos_before_write .. pos_before_write + written - 1 instead. Which is not the same thing with O_APPEND, obviously. A couple of years later correct variant had been killed off when everything switched to use of generic_file_aio_write(). All users of generic_file_aio_write() are affected, and the same bug has been copied into other instances of ->aio_write(). The fix is trivial; the only subtle point is that generic_write_sync() ought to be inlined to avoid calculations useless for the majority of calls. Signed-off-by: Al Viro --- fs/cifs/file.c | 4 ++-- fs/ext4/file.c | 2 +- fs/ntfs/file.c | 2 +- fs/sync.c | 17 ----------------- fs/xfs/xfs_file.c | 2 +- include/linux/fs.h | 8 +++++++- mm/filemap.c | 4 ++-- 7 files changed, 14 insertions(+), 25 deletions(-) (limited to 'mm') diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 853d6d1cc822..a7eda8ebfacc 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -2559,8 +2559,8 @@ cifs_writev(struct kiocb *iocb, const struct iovec *iov, if (rc > 0) { ssize_t err; - err = generic_write_sync(file, pos, rc); - if (err < 0 && rc > 0) + err = generic_write_sync(file, iocb->ki_pos - rc, rc); + if (err < 0) rc = err; } diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 43e64f6022eb..1a5073959f32 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -152,7 +152,7 @@ ext4_file_dio_write(struct kiocb *iocb, const struct iovec *iov, if (ret > 0) { ssize_t err; - err = generic_write_sync(file, pos, ret); + err = generic_write_sync(file, iocb->ki_pos - ret, ret); if (err < 0 && ret > 0) ret = err; } diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c index ea4ba9daeb47..db9bd8a31725 100644 --- a/fs/ntfs/file.c +++ b/fs/ntfs/file.c @@ -2134,7 +2134,7 @@ static ssize_t ntfs_file_aio_write(struct kiocb *iocb, const struct iovec *iov, ret = ntfs_file_aio_write_nolock(iocb, iov, nr_segs, &iocb->ki_pos); mutex_unlock(&inode->i_mutex); if (ret > 0) { - int err = generic_write_sync(file, pos, ret); + int err = generic_write_sync(file, iocb->ki_pos - ret, ret); if (err < 0) ret = err; } diff --git a/fs/sync.c b/fs/sync.c index f15537452231..e8ba024a055b 100644 --- a/fs/sync.c +++ b/fs/sync.c @@ -222,23 +222,6 @@ SYSCALL_DEFINE1(fdatasync, unsigned int, fd) return do_fsync(fd, 1); } -/** - * generic_write_sync - perform syncing after a write if file / inode is sync - * @file: file to which the write happened - * @pos: offset where the write started - * @count: length of the write - * - * This is just a simple wrapper about our general syncing function. - */ -int generic_write_sync(struct file *file, loff_t pos, loff_t count) -{ - if (!(file->f_flags & O_DSYNC) && !IS_SYNC(file->f_mapping->host)) - return 0; - return vfs_fsync_range(file, pos, pos + count - 1, - (file->f_flags & __O_SYNC) ? 0 : 1); -} -EXPORT_SYMBOL(generic_write_sync); - /* * sys_sync_file_range() permits finely controlled syncing over a segment of * a file in the range offset .. (offset+nbytes-1) inclusive. If nbytes is diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 2e7989e3a2d6..64b48eade91d 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -799,7 +799,7 @@ xfs_file_aio_write( XFS_STATS_ADD(xs_write_bytes, ret); /* Handle various SYNC-type writes */ - err = generic_write_sync(file, pos, ret); + err = generic_write_sync(file, iocb->ki_pos - ret, ret); if (err < 0) ret = err; } diff --git a/include/linux/fs.h b/include/linux/fs.h index 09f553c59813..75ff961be051 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2273,7 +2273,13 @@ extern int filemap_fdatawrite_range(struct address_space *mapping, extern int vfs_fsync_range(struct file *file, loff_t start, loff_t end, int datasync); extern int vfs_fsync(struct file *file, int datasync); -extern int generic_write_sync(struct file *file, loff_t pos, loff_t count); +static inline int generic_write_sync(struct file *file, loff_t pos, loff_t count) +{ + if (!(file->f_flags & O_DSYNC) && !IS_SYNC(file->f_mapping->host)) + return 0; + return vfs_fsync_range(file, pos, pos + count - 1, + (file->f_flags & __O_SYNC) ? 0 : 1); +} extern void emergency_sync(void); extern void emergency_remount(void); #ifdef CONFIG_BLOCK diff --git a/mm/filemap.c b/mm/filemap.c index d56d3c145b9f..7a13f6ac5421 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2553,8 +2553,8 @@ ssize_t generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, if (ret > 0) { ssize_t err; - err = generic_write_sync(file, pos, ret); - if (err < 0 && ret > 0) + err = generic_write_sync(file, iocb->ki_pos - ret, ret); + if (err < 0) ret = err; } return ret; -- cgit v1.2.3 From 255d0884f5635122adb23866b242b4ca112f4bc8 Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Mon, 10 Feb 2014 14:25:39 -0800 Subject: mm/slub.c: list_lock may not be held in some circumstances Commit c65c1877bd68 ("slub: use lockdep_assert_held") incorrectly required that add_full() and remove_full() hold n->list_lock. The lock is only taken when kmem_cache_debug(s), since that's the only time it actually does anything. Require that the lock only be taken under such a condition. Reported-by: Larry Finger Tested-by: Larry Finger Tested-by: Paul E. McKenney Acked-by: Christoph Lameter Cc: Pekka Enberg Signed-off-by: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/slub.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'mm') diff --git a/mm/slub.c b/mm/slub.c index 7e3e0458bce4..3d3a8a7a0f8c 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -1004,21 +1004,19 @@ static inline void slab_free_hook(struct kmem_cache *s, void *x) static void add_full(struct kmem_cache *s, struct kmem_cache_node *n, struct page *page) { - lockdep_assert_held(&n->list_lock); - if (!(s->flags & SLAB_STORE_USER)) return; + lockdep_assert_held(&n->list_lock); list_add(&page->lru, &n->full); } static void remove_full(struct kmem_cache *s, struct kmem_cache_node *n, struct page *page) { - lockdep_assert_held(&n->list_lock); - if (!(s->flags & SLAB_STORE_USER)) return; + lockdep_assert_held(&n->list_lock); list_del(&page->lru); } -- cgit v1.2.3 From 1e4dd9461fabfbc780cdfaf103cec790f3a53325 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 10 Feb 2014 14:25:46 -0800 Subject: slub: do not assert not having lock in removing freed partial Vladimir reported the following issue: Commit c65c1877bd68 ("slub: use lockdep_assert_held") requires remove_partial() to be called with n->list_lock held, but free_partial() called from kmem_cache_close() on cache destruction does not follow this rule, leading to a warning: WARNING: CPU: 0 PID: 2787 at mm/slub.c:1536 __kmem_cache_shutdown+0x1b2/0x1f0() Modules linked in: CPU: 0 PID: 2787 Comm: modprobe Tainted: G W 3.14.0-rc1-mm1+ #1 Hardware name: 0000000000000600 ffff88003ae1dde8 ffffffff816d9583 0000000000000600 0000000000000000 ffff88003ae1de28 ffffffff8107c107 0000000000000000 ffff880037ab2b00 ffff88007c240d30 ffffea0001ee5280 ffffea0001ee52a0 Call Trace: __kmem_cache_shutdown+0x1b2/0x1f0 kmem_cache_destroy+0x43/0xf0 xfs_destroy_zones+0x103/0x110 [xfs] exit_xfs_fs+0x38/0x4e4 [xfs] SyS_delete_module+0x19a/0x1f0 system_call_fastpath+0x16/0x1b His solution was to add a spinlock in order to quiet lockdep. Although there would be no contention to adding the lock, that lock also requires disabling of interrupts which will have a larger impact on the system. Instead of adding a spinlock to a location where it is not needed for lockdep, make a __remove_partial() function that does not test if the list_lock is held, as no one should have it due to it being freed. Also added a __add_partial() function that does not do the lock validation either, as it is not needed for the creation of the cache. Signed-off-by: Steven Rostedt Reported-by: Vladimir Davydov Suggested-by: David Rientjes Acked-by: David Rientjes Acked-by: Vladimir Davydov Acked-by: Christoph Lameter Cc: Pekka Enberg Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/slub.c | 32 ++++++++++++++++++++------------ 1 file changed, 20 insertions(+), 12 deletions(-) (limited to 'mm') diff --git a/mm/slub.c b/mm/slub.c index 3d3a8a7a0f8c..25f14ad8f817 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -1518,11 +1518,9 @@ static void discard_slab(struct kmem_cache *s, struct page *page) /* * Management of partially allocated slabs. */ -static inline void add_partial(struct kmem_cache_node *n, - struct page *page, int tail) +static inline void +__add_partial(struct kmem_cache_node *n, struct page *page, int tail) { - lockdep_assert_held(&n->list_lock); - n->nr_partial++; if (tail == DEACTIVATE_TO_TAIL) list_add_tail(&page->lru, &n->partial); @@ -1530,15 +1528,27 @@ static inline void add_partial(struct kmem_cache_node *n, list_add(&page->lru, &n->partial); } -static inline void remove_partial(struct kmem_cache_node *n, - struct page *page) +static inline void add_partial(struct kmem_cache_node *n, + struct page *page, int tail) { lockdep_assert_held(&n->list_lock); + __add_partial(n, page, tail); +} +static inline void +__remove_partial(struct kmem_cache_node *n, struct page *page) +{ list_del(&page->lru); n->nr_partial--; } +static inline void remove_partial(struct kmem_cache_node *n, + struct page *page) +{ + lockdep_assert_held(&n->list_lock); + __remove_partial(n, page); +} + /* * Remove slab from the partial list, freeze it and * return the pointer to the freelist. @@ -2904,12 +2914,10 @@ static void early_kmem_cache_node_alloc(int node) inc_slabs_node(kmem_cache_node, node, page->objects); /* - * the lock is for lockdep's sake, not for any actual - * race protection + * No locks need to be taken here as it has just been + * initialized and there is no concurrent access. */ - spin_lock(&n->list_lock); - add_partial(n, page, DEACTIVATE_TO_HEAD); - spin_unlock(&n->list_lock); + __add_partial(n, page, DEACTIVATE_TO_HEAD); } static void free_kmem_cache_nodes(struct kmem_cache *s) @@ -3195,7 +3203,7 @@ static void free_partial(struct kmem_cache *s, struct kmem_cache_node *n) list_for_each_entry_safe(page, h, &n->partial, lru) { if (!page->inuse) { - remove_partial(n, page); + __remove_partial(n, page); discard_slab(s, page); } else { list_slab_objects(s, page, -- cgit v1.2.3 From 8d547ff4ac5927245e0833ac18528f939da0ee0e Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Mon, 10 Feb 2014 14:25:50 -0800 Subject: mm/memory-failure.c: move refcount only in !MF_COUNT_INCREASED mce-test detected a test failure when injecting error to a thp tail page. This is because we take page refcount of the tail page in madvise_hwpoison() while the fix in commit a3e0f9e47d5e ("mm/memory-failure.c: transfer page count from head page to tail page after split thp") assumes that we always take refcount on the head page. When a real memory error happens we take refcount on the head page where memory_failure() is called without MF_COUNT_INCREASED set, so it seems to me that testing memory error on thp tail page using madvise makes little sense. This patch cancels moving refcount in !MF_COUNT_INCREASED for valid testing. [akpm@linux-foundation.org: s/&&/&/] Signed-off-by: Naoya Horiguchi Cc: Andi Kleen Cc: Wanpeng Li Cc: Chen Gong Cc: [3.9+: a3e0f9e47d5e] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory-failure.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'mm') diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 4f08a2d61487..2f2f34a4e77d 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -945,8 +945,10 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn, * to it. Similarly, page lock is shifted. */ if (hpage != p) { - put_page(hpage); - get_page(p); + if (!(flags & MF_COUNT_INCREASED)) { + put_page(hpage); + get_page(p); + } lock_page(p); unlock_page(hpage); *hpagep = p; -- cgit v1.2.3 From 9d85d5863fa4818eb7fa306563bf830c0210c3a6 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Wed, 12 Feb 2014 09:13:37 +0530 Subject: mm: Dirty accountable change only apply to non prot numa case So move it within the if loop Acked-by: Mel Gorman Reviewed-by: Rik van Riel Signed-off-by: Aneesh Kumar K.V Signed-off-by: Benjamin Herrenschmidt --- mm/mprotect.c | 21 +++++++-------------- 1 file changed, 7 insertions(+), 14 deletions(-) (limited to 'mm') diff --git a/mm/mprotect.c b/mm/mprotect.c index 7332c1785744..33eab902f10e 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -58,6 +58,13 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, if (pte_numa(ptent)) ptent = pte_mknonnuma(ptent); ptent = pte_modify(ptent, newprot); + /* + * Avoid taking write faults for pages we + * know to be dirty. + */ + if (dirty_accountable && pte_dirty(ptent)) + ptent = pte_mkwrite(ptent); + ptep_modify_prot_commit(mm, addr, pte, ptent); updated = true; } else { struct page *page; @@ -72,22 +79,8 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, } } } - - /* - * Avoid taking write faults for pages we know to be - * dirty. - */ - if (dirty_accountable && pte_dirty(ptent)) { - ptent = pte_mkwrite(ptent); - updated = true; - } - if (updated) pages++; - - /* Only !prot_numa always clears the pte */ - if (!prot_numa) - ptep_modify_prot_commit(mm, addr, pte, ptent); } else if (IS_ENABLED(CONFIG_MIGRATION) && !pte_file(oldpte)) { swp_entry_t entry = pte_to_swp_entry(oldpte); -- cgit v1.2.3 From 56eecdb912b536a4fa97fb5bfe5a940a54d79be6 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Wed, 12 Feb 2014 09:13:38 +0530 Subject: mm: Use ptep/pmdp_set_numa() for updating _PAGE_NUMA bit Archs like ppc64 doesn't do tlb flush in set_pte/pmd functions when using a hash table MMU for various reasons (the flush is handled as part of the PTE modification when necessary). ppc64 thus doesn't implement flush_tlb_range for hash based MMUs. Additionally ppc64 require the tlb flushing to be batched within ptl locks. The reason to do that is to ensure that the hash page table is in sync with linux page table. We track the hpte index in linux pte and if we clear them without flushing hash and drop the ptl lock, we can have another cpu update the pte and can end up with duplicate entry in the hash table, which is fatal. We also want to keep set_pte_at simpler by not requiring them to do hash flush for performance reason. We do that by assuming that set_pte_at() is never *ever* called on a PTE that is already valid. This was the case until the NUMA code went in which broke that assumption. Fix that by introducing a new pair of helpers to set _PAGE_NUMA in a way similar to ptep/pmdp_set_wrprotect(), with a generic implementation using set_pte_at() and a powerpc specific one using the appropriate mechanism needed to keep the hash table in sync. Acked-by: Mel Gorman Reviewed-by: Rik van Riel Signed-off-by: Aneesh Kumar K.V Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/pgtable.h | 22 +++++++++++++++++++++ include/asm-generic/pgtable.h | 39 ++++++++++++++++++++++++++++++++++++++ mm/huge_memory.c | 9 ++------- mm/mprotect.c | 4 +--- 4 files changed, 64 insertions(+), 10 deletions(-) (limited to 'mm') diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h index f83b6f3e1b39..3ebb188c3ff5 100644 --- a/arch/powerpc/include/asm/pgtable.h +++ b/arch/powerpc/include/asm/pgtable.h @@ -75,12 +75,34 @@ static inline pte_t pte_mknuma(pte_t pte) return pte; } +#define ptep_set_numa ptep_set_numa +static inline void ptep_set_numa(struct mm_struct *mm, unsigned long addr, + pte_t *ptep) +{ + if ((pte_val(*ptep) & _PAGE_PRESENT) == 0) + VM_BUG_ON(1); + + pte_update(mm, addr, ptep, _PAGE_PRESENT, _PAGE_NUMA, 0); + return; +} + #define pmd_numa pmd_numa static inline int pmd_numa(pmd_t pmd) { return pte_numa(pmd_pte(pmd)); } +#define pmdp_set_numa pmdp_set_numa +static inline void pmdp_set_numa(struct mm_struct *mm, unsigned long addr, + pmd_t *pmdp) +{ + if ((pmd_val(*pmdp) & _PAGE_PRESENT) == 0) + VM_BUG_ON(1); + + pmd_hugepage_update(mm, addr, pmdp, _PAGE_PRESENT, _PAGE_NUMA); + return; +} + #define pmd_mknonnuma pmd_mknonnuma static inline pmd_t pmd_mknonnuma(pmd_t pmd) { diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index 8e4f41d9af4d..34c7bdc06014 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -701,6 +701,18 @@ static inline pte_t pte_mknuma(pte_t pte) } #endif +#ifndef ptep_set_numa +static inline void ptep_set_numa(struct mm_struct *mm, unsigned long addr, + pte_t *ptep) +{ + pte_t ptent = *ptep; + + ptent = pte_mknuma(ptent); + set_pte_at(mm, addr, ptep, ptent); + return; +} +#endif + #ifndef pmd_mknuma static inline pmd_t pmd_mknuma(pmd_t pmd) { @@ -708,6 +720,18 @@ static inline pmd_t pmd_mknuma(pmd_t pmd) return pmd_clear_flags(pmd, _PAGE_PRESENT); } #endif + +#ifndef pmdp_set_numa +static inline void pmdp_set_numa(struct mm_struct *mm, unsigned long addr, + pmd_t *pmdp) +{ + pmd_t pmd = *pmdp; + + pmd = pmd_mknuma(pmd); + set_pmd_at(mm, addr, pmdp, pmd); + return; +} +#endif #else extern int pte_numa(pte_t pte); extern int pmd_numa(pmd_t pmd); @@ -715,6 +739,8 @@ extern pte_t pte_mknonnuma(pte_t pte); extern pmd_t pmd_mknonnuma(pmd_t pmd); extern pte_t pte_mknuma(pte_t pte); extern pmd_t pmd_mknuma(pmd_t pmd); +extern void ptep_set_numa(struct mm_struct *mm, unsigned long addr, pte_t *ptep); +extern void pmdp_set_numa(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp); #endif /* CONFIG_ARCH_USES_NUMA_PROT_NONE */ #else static inline int pmd_numa(pmd_t pmd) @@ -742,10 +768,23 @@ static inline pte_t pte_mknuma(pte_t pte) return pte; } +static inline void ptep_set_numa(struct mm_struct *mm, unsigned long addr, + pte_t *ptep) +{ + return; +} + + static inline pmd_t pmd_mknuma(pmd_t pmd) { return pmd; } + +static inline void pmdp_set_numa(struct mm_struct *mm, unsigned long addr, + pmd_t *pmdp) +{ + return ; +} #endif /* CONFIG_NUMA_BALANCING */ #endif /* CONFIG_MMU */ diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 82166bf974e1..da23eb96779f 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1545,6 +1545,7 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, entry = pmd_mknonnuma(entry); entry = pmd_modify(entry, newprot); ret = HPAGE_PMD_NR; + set_pmd_at(mm, addr, pmd, entry); BUG_ON(pmd_write(entry)); } else { struct page *page = pmd_page(*pmd); @@ -1557,16 +1558,10 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, */ if (!is_huge_zero_page(page) && !pmd_numa(*pmd)) { - entry = *pmd; - entry = pmd_mknuma(entry); + pmdp_set_numa(mm, addr, pmd); ret = HPAGE_PMD_NR; } } - - /* Set PMD if cleared earlier */ - if (ret == HPAGE_PMD_NR) - set_pmd_at(mm, addr, pmd, entry); - spin_unlock(ptl); } diff --git a/mm/mprotect.c b/mm/mprotect.c index 33eab902f10e..769a67a15803 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -69,12 +69,10 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, } else { struct page *page; - ptent = *pte; page = vm_normal_page(vma, addr, oldpte); if (page && !PageKsm(page)) { if (!pte_numa(oldpte)) { - ptent = pte_mknuma(ptent); - set_pte_at(mm, addr, pte, ptent); + ptep_set_numa(mm, addr, pte); updated = true; } } -- cgit v1.2.3