From e9959f0f37160e1f5351af828cc981712b5066c1 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Wed, 24 Nov 2010 12:57:09 -0800 Subject: mm/page_alloc.c: fix build_all_zonelist() where percpu_alloc() is wrongly called under stop_machine_run() During memory hotplug, build_allzonelists() may be called under stop_machine_run(). In this function, setup_zone_pageset() is called. But it's bug because it will do page allocation under stop_machine_run(). Here is a report from Alok Kataria. BUG: sleeping function called from invalid context at kernel/mutex.c:94 in_atomic(): 0, irqs_disabled(): 1, pid: 4, name: migration/0 Pid: 4, comm: migration/0 Not tainted 2.6.35.6-45.fc14.x86_64 #1 Call Trace: [] __might_sleep+0xeb/0xf0 [] mutex_lock+0x24/0x50 [] pcpu_alloc+0x6d/0x7ee [] ? load_balance+0xbe/0x60e [] ? rt_se_boosted+0x21/0x2f [] ? dequeue_rt_stack+0x18b/0x1ed [] __alloc_percpu+0x10/0x12 [] setup_zone_pageset+0x38/0xbe [] ? build_zonelists_node.clone.58+0x79/0x8c [] __build_all_zonelists+0x419/0x46c [] ? cpu_stopper_thread+0xb2/0x198 [] stop_machine_cpu_stop+0x8e/0xc5 [] ? stop_machine_cpu_stop+0x0/0xc5 [] cpu_stopper_thread+0x108/0x198 [] ? schedule+0x5b2/0x5cc [] ? cpu_stopper_thread+0x0/0x198 [] kthread+0x7f/0x87 [] kernel_thread_helper+0x4/0x10 [] ? kthread+0x0/0x87 [] ? kernel_thread_helper+0x0/0x10 Built 5 zonelists in Node order, mobility grouping on. Total pages: 289456 Policy zone: Normal This patch tries to fix the issue by moving setup_zone_pageset() out from stop_machine_run(). It's obviously not necessary to be called under stop_machine_run(). [akpm@linux-foundation.org: remove unneeded local] Reported-by: Alok Kataria Signed-off-by: KAMEZAWA Hiroyuki Cc: Tejun Heo Cc: Petr Vandrovec Cc: Pekka Enberg Reviewed-by: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 14 +++++--------- 1 file changed, 5 insertions(+), 9 deletions(-) (limited to 'mm/page_alloc.c') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 07a654486f75..e4092704c1a9 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -3008,14 +3008,6 @@ static __init_refok int __build_all_zonelists(void *data) build_zonelist_cache(pgdat); } -#ifdef CONFIG_MEMORY_HOTPLUG - /* Setup real pagesets for the new zone */ - if (data) { - struct zone *zone = data; - setup_zone_pageset(zone); - } -#endif - /* * Initialize the boot_pagesets that are going to be used * for bootstrapping processors. The real pagesets for @@ -3064,7 +3056,11 @@ void build_all_zonelists(void *data) } else { /* we have to stop all cpus to guarantee there is no user of zonelist */ - stop_machine(__build_all_zonelists, data, NULL); +#ifdef CONFIG_MEMORY_HOTPLUG + if (data) + setup_zone_pageset((struct zone *)data); +#endif + stop_machine(__build_all_zonelists, NULL, NULL); /* cpuset refresh routine should be here */ } vm_total_pages = nr_free_pagecache_pages(); -- cgit v1.2.3-59-g8ed1b From fa9f90be745d3b600a9d97a063be404c5e5d9071 Mon Sep 17 00:00:00 2001 From: Jesper Juhl Date: Sun, 28 Nov 2010 21:39:34 +0100 Subject: Kill off a bunch of warning: ‘inline’ is not at beginning of declaration MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit These warnings are spewed during a build of a 'allnoconfig' kernel (especially the ones from u64_stats_sync.h show up a lot) when building with -Wextra (which I often do).. They are a) annoying b) easy to get rid of. This patch kills them off. include/linux/u64_stats_sync.h:70:1: warning: ‘inline’ is not at beginning of declaration include/linux/u64_stats_sync.h:77:1: warning: ‘inline’ is not at beginning of declaration include/linux/u64_stats_sync.h:84:1: warning: ‘inline’ is not at beginning of declaration include/linux/u64_stats_sync.h:96:1: warning: ‘inline’ is not at beginning of declaration include/linux/u64_stats_sync.h:115:1: warning: ‘inline’ is not at beginning of declaration include/linux/u64_stats_sync.h:127:1: warning: ‘inline’ is not at beginning of declaration kernel/time.c:241:1: warning: ‘inline’ is not at beginning of declaration kernel/time.c:257:1: warning: ‘inline’ is not at beginning of declaration kernel/perf_event.c:4513:1: warning: ‘inline’ is not at beginning of declaration mm/page_alloc.c:4012:1: warning: ‘inline’ is not at beginning of declaration Signed-off-by: Jesper Juhl Signed-off-by: Jiri Kosina --- include/linux/u64_stats_sync.h | 12 ++++++------ kernel/perf_event.c | 2 +- kernel/time.c | 4 ++-- mm/page_alloc.c | 2 +- 4 files changed, 10 insertions(+), 10 deletions(-) (limited to 'mm/page_alloc.c') diff --git a/include/linux/u64_stats_sync.h b/include/linux/u64_stats_sync.h index fa261a0da280..8da8c4e87da3 100644 --- a/include/linux/u64_stats_sync.h +++ b/include/linux/u64_stats_sync.h @@ -67,21 +67,21 @@ struct u64_stats_sync { #endif }; -static void inline u64_stats_update_begin(struct u64_stats_sync *syncp) +static inline void u64_stats_update_begin(struct u64_stats_sync *syncp) { #if BITS_PER_LONG==32 && defined(CONFIG_SMP) write_seqcount_begin(&syncp->seq); #endif } -static void inline u64_stats_update_end(struct u64_stats_sync *syncp) +static inline void u64_stats_update_end(struct u64_stats_sync *syncp) { #if BITS_PER_LONG==32 && defined(CONFIG_SMP) write_seqcount_end(&syncp->seq); #endif } -static unsigned int inline u64_stats_fetch_begin(const struct u64_stats_sync *syncp) +static inline unsigned int u64_stats_fetch_begin(const struct u64_stats_sync *syncp) { #if BITS_PER_LONG==32 && defined(CONFIG_SMP) return read_seqcount_begin(&syncp->seq); @@ -93,7 +93,7 @@ static unsigned int inline u64_stats_fetch_begin(const struct u64_stats_sync *sy #endif } -static bool inline u64_stats_fetch_retry(const struct u64_stats_sync *syncp, +static inline bool u64_stats_fetch_retry(const struct u64_stats_sync *syncp, unsigned int start) { #if BITS_PER_LONG==32 && defined(CONFIG_SMP) @@ -112,7 +112,7 @@ static bool inline u64_stats_fetch_retry(const struct u64_stats_sync *syncp, * - UP 32bit must disable BH. * - 64bit have no problem atomically reading u64 values, irq safe. */ -static unsigned int inline u64_stats_fetch_begin_bh(const struct u64_stats_sync *syncp) +static inline unsigned int u64_stats_fetch_begin_bh(const struct u64_stats_sync *syncp) { #if BITS_PER_LONG==32 && defined(CONFIG_SMP) return read_seqcount_begin(&syncp->seq); @@ -124,7 +124,7 @@ static unsigned int inline u64_stats_fetch_begin_bh(const struct u64_stats_sync #endif } -static bool inline u64_stats_fetch_retry_bh(const struct u64_stats_sync *syncp, +static inline bool u64_stats_fetch_retry_bh(const struct u64_stats_sync *syncp, unsigned int start) { #if BITS_PER_LONG==32 && defined(CONFIG_SMP) diff --git a/kernel/perf_event.c b/kernel/perf_event.c index 517d827f4982..06682e7b12e2 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -4454,7 +4454,7 @@ int perf_swevent_get_recursion_context(void) } EXPORT_SYMBOL_GPL(perf_swevent_get_recursion_context); -void inline perf_swevent_put_recursion_context(int rctx) +inline void perf_swevent_put_recursion_context(int rctx) { struct swevent_htable *swhash = &__get_cpu_var(swevent_htable); diff --git a/kernel/time.c b/kernel/time.c index ba9b338d1835..32174359576f 100644 --- a/kernel/time.c +++ b/kernel/time.c @@ -238,7 +238,7 @@ EXPORT_SYMBOL(current_fs_time); * Avoid unnecessary multiplications/divisions in the * two most common HZ cases: */ -unsigned int inline jiffies_to_msecs(const unsigned long j) +inline unsigned int jiffies_to_msecs(const unsigned long j) { #if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ) return (MSEC_PER_SEC / HZ) * j; @@ -254,7 +254,7 @@ unsigned int inline jiffies_to_msecs(const unsigned long j) } EXPORT_SYMBOL(jiffies_to_msecs); -unsigned int inline jiffies_to_usecs(const unsigned long j) +inline unsigned int jiffies_to_usecs(const unsigned long j) { #if HZ <= USEC_PER_SEC && !(USEC_PER_SEC % HZ) return (USEC_PER_SEC / HZ) * j; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 07a654486f75..f823ee192e94 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -4013,7 +4013,7 @@ static void __init setup_usemap(struct pglist_data *pgdat, zone->pageblock_flags = alloc_bootmem_node(pgdat, usemapsize); } #else -static void inline setup_usemap(struct pglist_data *pgdat, +static inline void setup_usemap(struct pglist_data *pgdat, struct zone *zone, unsigned long zonesize) {} #endif /* CONFIG_SPARSEMEM */ -- cgit v1.2.3-59-g8ed1b From c9e664f1fdf34aa8cede047b206deaa8f1945af0 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Fri, 3 Dec 2010 22:57:45 +0100 Subject: PM / Hibernate: Fix memory corruption related to swap There is a problem that swap pages allocated before the creation of a hibernation image can be released and used for storing the contents of different memory pages while the image is being saved. Since the kernel stored in the image doesn't know of that, it causes memory corruption to occur after resume from hibernation, especially on systems with relatively small RAM that need to swap often. This issue can be addressed by keeping the GFP_IOFS bits clear in gfp_allowed_mask during the entire hibernation, including the saving of the image, until the system is finally turned off or the hibernation is aborted. Unfortunately, for this purpose it's necessary to rework the way in which the hibernate and suspend code manipulates gfp_allowed_mask. This change is based on an earlier patch from Hugh Dickins. Signed-off-by: Rafael J. Wysocki Reported-by: Ondrej Zary Acked-by: Hugh Dickins Reviewed-by: KAMEZAWA Hiroyuki Cc: stable@kernel.org --- include/linux/gfp.h | 4 ++-- kernel/power/hibernate.c | 22 ++++++++++++---------- kernel/power/suspend.c | 5 ++--- kernel/power/user.c | 2 ++ mm/page_alloc.c | 19 ++++++++++++------- 5 files changed, 30 insertions(+), 22 deletions(-) (limited to 'mm/page_alloc.c') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index e8713d55360a..f54adfcbec9c 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -360,7 +360,7 @@ void drain_local_pages(void *dummy); extern gfp_t gfp_allowed_mask; -extern void set_gfp_allowed_mask(gfp_t mask); -extern gfp_t clear_gfp_allowed_mask(gfp_t mask); +extern void pm_restrict_gfp_mask(void); +extern void pm_restore_gfp_mask(void); #endif /* __LINUX_GFP_H */ diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index 657272e91d0a..048d0b514831 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -327,7 +327,6 @@ static int create_image(int platform_mode) int hibernation_snapshot(int platform_mode) { int error; - gfp_t saved_mask; error = platform_begin(platform_mode); if (error) @@ -339,7 +338,7 @@ int hibernation_snapshot(int platform_mode) goto Close; suspend_console(); - saved_mask = clear_gfp_allowed_mask(GFP_IOFS); + pm_restrict_gfp_mask(); error = dpm_suspend_start(PMSG_FREEZE); if (error) goto Recover_platform; @@ -348,7 +347,10 @@ int hibernation_snapshot(int platform_mode) goto Recover_platform; error = create_image(platform_mode); - /* Control returns here after successful restore */ + /* + * Control returns here (1) after the image has been created or the + * image creation has failed and (2) after a successful restore. + */ Resume_devices: /* We may need to release the preallocated image pages here. */ @@ -357,7 +359,10 @@ int hibernation_snapshot(int platform_mode) dpm_resume_end(in_suspend ? (error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE); - set_gfp_allowed_mask(saved_mask); + + if (error || !in_suspend) + pm_restore_gfp_mask(); + resume_console(); Close: platform_end(platform_mode); @@ -452,17 +457,16 @@ static int resume_target_kernel(bool platform_mode) int hibernation_restore(int platform_mode) { int error; - gfp_t saved_mask; pm_prepare_console(); suspend_console(); - saved_mask = clear_gfp_allowed_mask(GFP_IOFS); + pm_restrict_gfp_mask(); error = dpm_suspend_start(PMSG_QUIESCE); if (!error) { error = resume_target_kernel(platform_mode); dpm_resume_end(PMSG_RECOVER); } - set_gfp_allowed_mask(saved_mask); + pm_restore_gfp_mask(); resume_console(); pm_restore_console(); return error; @@ -476,7 +480,6 @@ int hibernation_restore(int platform_mode) int hibernation_platform_enter(void) { int error; - gfp_t saved_mask; if (!hibernation_ops) return -ENOSYS; @@ -492,7 +495,6 @@ int hibernation_platform_enter(void) entering_platform_hibernation = true; suspend_console(); - saved_mask = clear_gfp_allowed_mask(GFP_IOFS); error = dpm_suspend_start(PMSG_HIBERNATE); if (error) { if (hibernation_ops->recover) @@ -536,7 +538,6 @@ int hibernation_platform_enter(void) Resume_devices: entering_platform_hibernation = false; dpm_resume_end(PMSG_RESTORE); - set_gfp_allowed_mask(saved_mask); resume_console(); Close: @@ -646,6 +647,7 @@ int hibernate(void) swsusp_free(); if (!error) power_down(); + pm_restore_gfp_mask(); } else { pr_debug("PM: Image restored successfully.\n"); } diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index 7335952ee473..ecf770509d0d 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -197,7 +197,6 @@ static int suspend_enter(suspend_state_t state) int suspend_devices_and_enter(suspend_state_t state) { int error; - gfp_t saved_mask; if (!suspend_ops) return -ENOSYS; @@ -208,7 +207,7 @@ int suspend_devices_and_enter(suspend_state_t state) goto Close; } suspend_console(); - saved_mask = clear_gfp_allowed_mask(GFP_IOFS); + pm_restrict_gfp_mask(); suspend_test_start(); error = dpm_suspend_start(PMSG_SUSPEND); if (error) { @@ -225,7 +224,7 @@ int suspend_devices_and_enter(suspend_state_t state) suspend_test_start(); dpm_resume_end(PMSG_RESUME); suspend_test_finish("resume devices"); - set_gfp_allowed_mask(saved_mask); + pm_restore_gfp_mask(); resume_console(); Close: if (suspend_ops->end) diff --git a/kernel/power/user.c b/kernel/power/user.c index e819e17877ca..1b2ea31e6bd8 100644 --- a/kernel/power/user.c +++ b/kernel/power/user.c @@ -263,6 +263,7 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd, case SNAPSHOT_UNFREEZE: if (!data->frozen || data->ready) break; + pm_restore_gfp_mask(); thaw_processes(); usermodehelper_enable(); data->frozen = 0; @@ -275,6 +276,7 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd, error = -EPERM; break; } + pm_restore_gfp_mask(); error = hibernation_snapshot(data->platform_support); if (!error) error = put_user(in_suspend, (int __user *)arg); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index e4092704c1a9..ff7e15872398 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -104,19 +104,24 @@ gfp_t gfp_allowed_mask __read_mostly = GFP_BOOT_MASK; * only be modified with pm_mutex held, unless the suspend/hibernate code is * guaranteed not to run in parallel with that modification). */ -void set_gfp_allowed_mask(gfp_t mask) + +static gfp_t saved_gfp_mask; + +void pm_restore_gfp_mask(void) { WARN_ON(!mutex_is_locked(&pm_mutex)); - gfp_allowed_mask = mask; + if (saved_gfp_mask) { + gfp_allowed_mask = saved_gfp_mask; + saved_gfp_mask = 0; + } } -gfp_t clear_gfp_allowed_mask(gfp_t mask) +void pm_restrict_gfp_mask(void) { - gfp_t ret = gfp_allowed_mask; - WARN_ON(!mutex_is_locked(&pm_mutex)); - gfp_allowed_mask &= ~mask; - return ret; + WARN_ON(saved_gfp_mask); + saved_gfp_mask = gfp_allowed_mask; + gfp_allowed_mask &= ~GFP_IOFS; } #endif /* CONFIG_PM_SLEEP */ -- cgit v1.2.3-59-g8ed1b From 88f5acf88ae6a9778f6d25d0d5d7ec2d57764a97 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 13 Jan 2011 15:45:41 -0800 Subject: mm: page allocator: adjust the per-cpu counter threshold when memory is low Commit aa45484 ("calculate a better estimate of NR_FREE_PAGES when memory is low") noted that watermarks were based on the vmstat NR_FREE_PAGES. To avoid synchronization overhead, these counters are maintained on a per-cpu basis and drained both periodically and when a threshold is above a threshold. On large CPU systems, the difference between the estimate and real value of NR_FREE_PAGES can be very high. The system can get into a case where pages are allocated far below the min watermark potentially causing livelock issues. The commit solved the problem by taking a better reading of NR_FREE_PAGES when memory was low. Unfortately, as reported by Shaohua Li this accurate reading can consume a large amount of CPU time on systems with many sockets due to cache line bouncing. This patch takes a different approach. For large machines where counter drift might be unsafe and while kswapd is awake, the per-cpu thresholds for the target pgdat are reduced to limit the level of drift to what should be a safe level. This incurs a performance penalty in heavy memory pressure by a factor that depends on the workload and the machine but the machine should function correctly without accidentally exhausting all memory on a node. There is an additional cost when kswapd wakes and sleeps but the event is not expected to be frequent - in Shaohua's test case, there was one recorded sleep and wake event at least. To ensure that kswapd wakes up, a safe version of zone_watermark_ok() is introduced that takes a more accurate reading of NR_FREE_PAGES when called from wakeup_kswapd, when deciding whether it is really safe to go back to sleep in sleeping_prematurely() and when deciding if a zone is really balanced or not in balance_pgdat(). We are still using an expensive function but limiting how often it is called. When the test case is reproduced, the time spent in the watermark functions is reduced. The following report is on the percentage of time spent cumulatively spent in the functions zone_nr_free_pages(), zone_watermark_ok(), __zone_watermark_ok(), zone_watermark_ok_safe(), zone_page_state_snapshot(), zone_page_state(). vanilla 11.6615% disable-threshold 0.2584% David said: : We had to pull aa454840 "mm: page allocator: calculate a better estimate : of NR_FREE_PAGES when memory is low and kswapd is awake" from 2.6.36 : internally because tests showed that it would cause the machine to stall : as the result of heavy kswapd activity. I merged it back with this fix as : it is pending in the -mm tree and it solves the issue we were seeing, so I : definitely think this should be pushed to -stable (and I would seriously : consider it for 2.6.37 inclusion even at this late date). Signed-off-by: Mel Gorman Reported-by: Shaohua Li Reviewed-by: Christoph Lameter Tested-by: Nicolas Bareil Cc: David Rientjes Cc: Kyle McMartin Cc: [2.6.37.1, 2.6.36.x] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 10 +++----- include/linux/vmstat.h | 5 ++++ mm/mmzone.c | 21 ---------------- mm/page_alloc.c | 35 ++++++++++++++++++++------ mm/vmscan.c | 23 +++++++++-------- mm/vmstat.c | 68 +++++++++++++++++++++++++++++++++++++++++++++++++- 6 files changed, 115 insertions(+), 47 deletions(-) (limited to 'mm/page_alloc.c') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 39c24ebe9cfd..48906629335c 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -458,12 +458,6 @@ static inline int zone_is_oom_locked(const struct zone *zone) return test_bit(ZONE_OOM_LOCKED, &zone->flags); } -#ifdef CONFIG_SMP -unsigned long zone_nr_free_pages(struct zone *zone); -#else -#define zone_nr_free_pages(zone) zone_page_state(zone, NR_FREE_PAGES) -#endif /* CONFIG_SMP */ - /* * The "priority" of VM scanning is how much of the queues we will scan in one * go. A value of 12 for DEF_PRIORITY implies that we will scan 1/4096th of the @@ -661,7 +655,9 @@ typedef struct pglist_data { extern struct mutex zonelists_mutex; void build_all_zonelists(void *data); void wakeup_kswapd(struct zone *zone, int order); -int zone_watermark_ok(struct zone *z, int order, unsigned long mark, +bool zone_watermark_ok(struct zone *z, int order, unsigned long mark, + int classzone_idx, int alloc_flags); +bool zone_watermark_ok_safe(struct zone *z, int order, unsigned long mark, int classzone_idx, int alloc_flags); enum memmap_context { MEMMAP_EARLY, diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index eaaea37b3b75..e4cc21cf5870 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -254,6 +254,8 @@ extern void dec_zone_state(struct zone *, enum zone_stat_item); extern void __dec_zone_state(struct zone *, enum zone_stat_item); void refresh_cpu_vm_stats(int); +void reduce_pgdat_percpu_threshold(pg_data_t *pgdat); +void restore_pgdat_percpu_threshold(pg_data_t *pgdat); #else /* CONFIG_SMP */ /* @@ -298,6 +300,9 @@ static inline void __dec_zone_page_state(struct page *page, #define dec_zone_page_state __dec_zone_page_state #define mod_zone_page_state __mod_zone_page_state +static inline void reduce_pgdat_percpu_threshold(pg_data_t *pgdat) { } +static inline void restore_pgdat_percpu_threshold(pg_data_t *pgdat) { } + static inline void refresh_cpu_vm_stats(int cpu) { } #endif diff --git a/mm/mmzone.c b/mm/mmzone.c index e35bfb82c855..f5b7d1760213 100644 --- a/mm/mmzone.c +++ b/mm/mmzone.c @@ -87,24 +87,3 @@ int memmap_valid_within(unsigned long pfn, return 1; } #endif /* CONFIG_ARCH_HAS_HOLES_MEMORYMODEL */ - -#ifdef CONFIG_SMP -/* Called when a more accurate view of NR_FREE_PAGES is needed */ -unsigned long zone_nr_free_pages(struct zone *zone) -{ - unsigned long nr_free_pages = zone_page_state(zone, NR_FREE_PAGES); - - /* - * While kswapd is awake, it is considered the zone is under some - * memory pressure. Under pressure, there is a risk that - * per-cpu-counter-drift will allow the min watermark to be breached - * potentially causing a live-lock. While kswapd is awake and - * free pages are low, get a better estimate for free pages - */ - if (nr_free_pages < zone->percpu_drift_mark && - !waitqueue_active(&zone->zone_pgdat->kswapd_wait)) - return zone_page_state_snapshot(zone, NR_FREE_PAGES); - - return nr_free_pages; -} -#endif /* CONFIG_SMP */ diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 826ba6922e84..22a1bb7723e4 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1460,24 +1460,24 @@ static inline int should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) #endif /* CONFIG_FAIL_PAGE_ALLOC */ /* - * Return 1 if free pages are above 'mark'. This takes into account the order + * Return true if free pages are above 'mark'. This takes into account the order * of the allocation. */ -int zone_watermark_ok(struct zone *z, int order, unsigned long mark, - int classzone_idx, int alloc_flags) +static bool __zone_watermark_ok(struct zone *z, int order, unsigned long mark, + int classzone_idx, int alloc_flags, long free_pages) { /* free_pages my go negative - that's OK */ long min = mark; - long free_pages = zone_nr_free_pages(z) - (1 << order) + 1; int o; + free_pages -= (1 << order) + 1; if (alloc_flags & ALLOC_HIGH) min -= min / 2; if (alloc_flags & ALLOC_HARDER) min -= min / 4; if (free_pages <= min + z->lowmem_reserve[classzone_idx]) - return 0; + return false; for (o = 0; o < order; o++) { /* At the next order, this order's pages become unavailable */ free_pages -= z->free_area[o].nr_free << o; @@ -1486,9 +1486,28 @@ int zone_watermark_ok(struct zone *z, int order, unsigned long mark, min >>= 1; if (free_pages <= min) - return 0; + return false; } - return 1; + return true; +} + +bool zone_watermark_ok(struct zone *z, int order, unsigned long mark, + int classzone_idx, int alloc_flags) +{ + return __zone_watermark_ok(z, order, mark, classzone_idx, alloc_flags, + zone_page_state(z, NR_FREE_PAGES)); +} + +bool zone_watermark_ok_safe(struct zone *z, int order, unsigned long mark, + int classzone_idx, int alloc_flags) +{ + long free_pages = zone_page_state(z, NR_FREE_PAGES); + + if (z->percpu_drift_mark && free_pages < z->percpu_drift_mark) + free_pages = zone_page_state_snapshot(z, NR_FREE_PAGES); + + return __zone_watermark_ok(z, order, mark, classzone_idx, alloc_flags, + free_pages); } #ifdef CONFIG_NUMA @@ -2442,7 +2461,7 @@ void show_free_areas(void) " all_unreclaimable? %s" "\n", zone->name, - K(zone_nr_free_pages(zone)), + K(zone_page_state(zone, NR_FREE_PAGES)), K(min_wmark_pages(zone)), K(low_wmark_pages(zone)), K(high_wmark_pages(zone)), diff --git a/mm/vmscan.c b/mm/vmscan.c index 9ca587c69274..5da4295e7d67 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2143,7 +2143,7 @@ static int sleeping_prematurely(pg_data_t *pgdat, int order, long remaining) if (zone->all_unreclaimable) continue; - if (!zone_watermark_ok(zone, order, high_wmark_pages(zone), + if (!zone_watermark_ok_safe(zone, order, high_wmark_pages(zone), 0, 0)) return 1; } @@ -2230,7 +2230,7 @@ loop_again: shrink_active_list(SWAP_CLUSTER_MAX, zone, &sc, priority, 0); - if (!zone_watermark_ok(zone, order, + if (!zone_watermark_ok_safe(zone, order, high_wmark_pages(zone), 0, 0)) { end_zone = i; break; @@ -2276,7 +2276,7 @@ loop_again: * We put equal pressure on every zone, unless one * zone has way too many pages free already. */ - if (!zone_watermark_ok(zone, order, + if (!zone_watermark_ok_safe(zone, order, 8*high_wmark_pages(zone), end_zone, 0)) shrink_zone(priority, zone, &sc); reclaim_state->reclaimed_slab = 0; @@ -2297,7 +2297,7 @@ loop_again: total_scanned > sc.nr_reclaimed + sc.nr_reclaimed / 2) sc.may_writepage = 1; - if (!zone_watermark_ok(zone, order, + if (!zone_watermark_ok_safe(zone, order, high_wmark_pages(zone), end_zone, 0)) { all_zones_ok = 0; /* @@ -2305,7 +2305,7 @@ loop_again: * means that we have a GFP_ATOMIC allocation * failure risk. Hurry up! */ - if (!zone_watermark_ok(zone, order, + if (!zone_watermark_ok_safe(zone, order, min_wmark_pages(zone), end_zone, 0)) has_under_min_watermark_zone = 1; } else { @@ -2448,7 +2448,9 @@ static int kswapd(void *p) */ if (!sleeping_prematurely(pgdat, order, remaining)) { trace_mm_vmscan_kswapd_sleep(pgdat->node_id); + restore_pgdat_percpu_threshold(pgdat); schedule(); + reduce_pgdat_percpu_threshold(pgdat); } else { if (remaining) count_vm_event(KSWAPD_LOW_WMARK_HIT_QUICKLY); @@ -2487,16 +2489,17 @@ void wakeup_kswapd(struct zone *zone, int order) if (!populated_zone(zone)) return; - pgdat = zone->zone_pgdat; - if (zone_watermark_ok(zone, order, low_wmark_pages(zone), 0, 0)) + if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL)) return; + pgdat = zone->zone_pgdat; if (pgdat->kswapd_max_order < order) pgdat->kswapd_max_order = order; - trace_mm_vmscan_wakeup_kswapd(pgdat->node_id, zone_idx(zone), order); - if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL)) - return; if (!waitqueue_active(&pgdat->kswapd_wait)) return; + if (zone_watermark_ok_safe(zone, order, low_wmark_pages(zone), 0, 0)) + return; + + trace_mm_vmscan_wakeup_kswapd(pgdat->node_id, zone_idx(zone), order); wake_up_interruptible(&pgdat->kswapd_wait); } diff --git a/mm/vmstat.c b/mm/vmstat.c index 312d728976f1..bc0f095791b4 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -83,6 +83,30 @@ EXPORT_SYMBOL(vm_stat); #ifdef CONFIG_SMP +static int calculate_pressure_threshold(struct zone *zone) +{ + int threshold; + int watermark_distance; + + /* + * As vmstats are not up to date, there is drift between the estimated + * and real values. For high thresholds and a high number of CPUs, it + * is possible for the min watermark to be breached while the estimated + * value looks fine. The pressure threshold is a reduced value such + * that even the maximum amount of drift will not accidentally breach + * the min watermark + */ + watermark_distance = low_wmark_pages(zone) - min_wmark_pages(zone); + threshold = max(1, (int)(watermark_distance / num_online_cpus())); + + /* + * Maximum threshold is 125 + */ + threshold = min(125, threshold); + + return threshold; +} + static int calculate_threshold(struct zone *zone) { int threshold; @@ -161,6 +185,48 @@ static void refresh_zone_stat_thresholds(void) } } +void reduce_pgdat_percpu_threshold(pg_data_t *pgdat) +{ + struct zone *zone; + int cpu; + int threshold; + int i; + + get_online_cpus(); + for (i = 0; i < pgdat->nr_zones; i++) { + zone = &pgdat->node_zones[i]; + if (!zone->percpu_drift_mark) + continue; + + threshold = calculate_pressure_threshold(zone); + for_each_online_cpu(cpu) + per_cpu_ptr(zone->pageset, cpu)->stat_threshold + = threshold; + } + put_online_cpus(); +} + +void restore_pgdat_percpu_threshold(pg_data_t *pgdat) +{ + struct zone *zone; + int cpu; + int threshold; + int i; + + get_online_cpus(); + for (i = 0; i < pgdat->nr_zones; i++) { + zone = &pgdat->node_zones[i]; + if (!zone->percpu_drift_mark) + continue; + + threshold = calculate_threshold(zone); + for_each_online_cpu(cpu) + per_cpu_ptr(zone->pageset, cpu)->stat_threshold + = threshold; + } + put_online_cpus(); +} + /* * For use when we know that interrupts are disabled. */ @@ -911,7 +977,7 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat, "\n scanned %lu" "\n spanned %lu" "\n present %lu", - zone_nr_free_pages(zone), + zone_page_state(zone, NR_FREE_PAGES), min_wmark_pages(zone), low_wmark_pages(zone), high_wmark_pages(zone), -- cgit v1.2.3-59-g8ed1b From 3e7d344970673c5334cf7b5bb27c8c0942b06126 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 13 Jan 2011 15:45:56 -0800 Subject: mm: vmscan: reclaim order-0 and use compaction instead of lumpy reclaim Lumpy reclaim is disruptive. It reclaims a large number of pages and ignores the age of the pages it reclaims. This can incur significant stalls and potentially increase the number of major faults. Compaction has reached the point where it is considered reasonably stable (meaning it has passed a lot of testing) and is a potential candidate for displacing lumpy reclaim. This patch introduces an alternative to lumpy reclaim whe compaction is available called reclaim/compaction. The basic operation is very simple - instead of selecting a contiguous range of pages to reclaim, a number of order-0 pages are reclaimed and then compaction is later by either kswapd (compact_zone_order()) or direct compaction (__alloc_pages_direct_compact()). [akpm@linux-foundation.org: fix build] [akpm@linux-foundation.org: use conventional task_struct naming] Signed-off-by: Mel Gorman Cc: Andrea Arcangeli Cc: KOSAKI Motohiro Cc: Rik van Riel Acked-by: Johannes Weiner Cc: Andy Whitcroft Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compaction.h | 14 +++++++ include/linux/kernel.h | 7 ++++ mm/compaction.c | 89 ++++++++++++++++++++++++--------------- mm/migrate.c | 17 ++++++++ mm/page_alloc.c | 16 +++++++ mm/vmscan.c | 102 ++++++++++++++++++++++++++++++++++++++------- 6 files changed, 196 insertions(+), 49 deletions(-) (limited to 'mm/page_alloc.c') diff --git a/include/linux/compaction.h b/include/linux/compaction.h index 5ac51552d908..2592883d862d 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -22,6 +22,9 @@ extern int sysctl_extfrag_handler(struct ctl_table *table, int write, extern int fragmentation_index(struct zone *zone, unsigned int order); extern unsigned long try_to_compact_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *mask); +extern unsigned long compaction_suitable(struct zone *zone, int order); +extern unsigned long compact_zone_order(struct zone *zone, int order, + gfp_t gfp_mask); /* Do not skip compaction more than 64 times */ #define COMPACT_MAX_DEFER_SHIFT 6 @@ -59,6 +62,17 @@ static inline unsigned long try_to_compact_pages(struct zonelist *zonelist, return COMPACT_CONTINUE; } +static inline unsigned long compaction_suitable(struct zone *zone, int order) +{ + return COMPACT_SKIPPED; +} + +static inline unsigned long compact_zone_order(struct zone *zone, int order, + gfp_t gfp_mask) +{ + return 0; +} + static inline void defer_compaction(struct zone *zone) { } diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 57dac7022b63..5a9d9059520b 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -600,6 +600,13 @@ struct sysinfo { #define NUMA_BUILD 0 #endif +/* This helps us avoid #ifdef CONFIG_COMPACTION */ +#ifdef CONFIG_COMPACTION +#define COMPACTION_BUILD 1 +#else +#define COMPACTION_BUILD 0 +#endif + /* Rebuild everything on CONFIG_FTRACE_MCOUNT_RECORD */ #ifdef CONFIG_FTRACE_MCOUNT_RECORD # define REBUILD_DUE_TO_FTRACE_MCOUNT_RECORD diff --git a/mm/compaction.c b/mm/compaction.c index 20011a850fef..8fe917ec7c11 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -384,10 +384,62 @@ static int compact_finished(struct zone *zone, return COMPACT_CONTINUE; } +/* + * compaction_suitable: Is this suitable to run compaction on this zone now? + * Returns + * COMPACT_SKIPPED - If there are too few free pages for compaction + * COMPACT_PARTIAL - If the allocation would succeed without compaction + * COMPACT_CONTINUE - If compaction should run now + */ +unsigned long compaction_suitable(struct zone *zone, int order) +{ + int fragindex; + unsigned long watermark; + + /* + * Watermarks for order-0 must be met for compaction. Note the 2UL. + * This is because during migration, copies of pages need to be + * allocated and for a short time, the footprint is higher + */ + watermark = low_wmark_pages(zone) + (2UL << order); + if (!zone_watermark_ok(zone, 0, watermark, 0, 0)) + return COMPACT_SKIPPED; + + /* + * fragmentation index determines if allocation failures are due to + * low memory or external fragmentation + * + * index of -1 implies allocations might succeed dependingon watermarks + * index towards 0 implies failure is due to lack of memory + * index towards 1000 implies failure is due to fragmentation + * + * Only compact if a failure would be due to fragmentation. + */ + fragindex = fragmentation_index(zone, order); + if (fragindex >= 0 && fragindex <= sysctl_extfrag_threshold) + return COMPACT_SKIPPED; + + if (fragindex == -1 && zone_watermark_ok(zone, order, watermark, 0, 0)) + return COMPACT_PARTIAL; + + return COMPACT_CONTINUE; +} + static int compact_zone(struct zone *zone, struct compact_control *cc) { int ret; + ret = compaction_suitable(zone, cc->order); + switch (ret) { + case COMPACT_PARTIAL: + case COMPACT_SKIPPED: + /* Compaction is likely to fail */ + return ret; + case COMPACT_CONTINUE: + /* Fall through to compaction */ + ; + } + /* Setup to move all movable pages to the end of the zone */ cc->migrate_pfn = zone->zone_start_pfn; cc->free_pfn = cc->migrate_pfn + zone->spanned_pages; @@ -429,7 +481,7 @@ static int compact_zone(struct zone *zone, struct compact_control *cc) return ret; } -static unsigned long compact_zone_order(struct zone *zone, +unsigned long compact_zone_order(struct zone *zone, int order, gfp_t gfp_mask) { struct compact_control cc = { @@ -462,7 +514,6 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist, enum zone_type high_zoneidx = gfp_zone(gfp_mask); int may_enter_fs = gfp_mask & __GFP_FS; int may_perform_io = gfp_mask & __GFP_IO; - unsigned long watermark; struct zoneref *z; struct zone *zone; int rc = COMPACT_SKIPPED; @@ -480,43 +531,13 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist, /* Compact each zone in the list */ for_each_zone_zonelist_nodemask(zone, z, zonelist, high_zoneidx, nodemask) { - int fragindex; int status; - /* - * Watermarks for order-0 must be met for compaction. Note - * the 2UL. This is because during migration, copies of - * pages need to be allocated and for a short time, the - * footprint is higher - */ - watermark = low_wmark_pages(zone) + (2UL << order); - if (!zone_watermark_ok(zone, 0, watermark, 0, 0)) - continue; - - /* - * fragmentation index determines if allocation failures are - * due to low memory or external fragmentation - * - * index of -1 implies allocations might succeed depending - * on watermarks - * index towards 0 implies failure is due to lack of memory - * index towards 1000 implies failure is due to fragmentation - * - * Only compact if a failure would be due to fragmentation. - */ - fragindex = fragmentation_index(zone, order); - if (fragindex >= 0 && fragindex <= sysctl_extfrag_threshold) - continue; - - if (fragindex == -1 && zone_watermark_ok(zone, order, watermark, 0, 0)) { - rc = COMPACT_PARTIAL; - break; - } - status = compact_zone_order(zone, order, gfp_mask); rc = max(status, rc); - if (zone_watermark_ok(zone, order, watermark, 0, 0)) + /* If a normal allocation would succeed, stop compacting */ + if (zone_watermark_ok(zone, order, low_wmark_pages(zone), 0, 0)) break; } diff --git a/mm/migrate.c b/mm/migrate.c index 6ae8a66a7045..94875b265928 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -639,6 +639,23 @@ static int unmap_and_move(new_page_t get_new_page, unsigned long private, if (!trylock_page(page)) { if (!force) goto move_newpage; + + /* + * It's not safe for direct compaction to call lock_page. + * For example, during page readahead pages are added locked + * to the LRU. Later, when the IO completes the pages are + * marked uptodate and unlocked. However, the queueing + * could be merging multiple pages for one bio (e.g. + * mpage_readpages). If an allocation happens for the + * second or third page, the process can end up locking + * the same page twice and deadlocking. Rather than + * trying to be clever about what pages can be locked, + * avoid the use of lock_page for direct compaction + * altogether. + */ + if (current->flags & PF_MEMALLOC) + goto move_newpage; + lock_page(page); } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 22a1bb7723e4..03a66a31bfcd 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1815,12 +1815,15 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, int migratetype, unsigned long *did_some_progress) { struct page *page; + struct task_struct *tsk = current; if (!order || compaction_deferred(preferred_zone)) return NULL; + tsk->flags |= PF_MEMALLOC; *did_some_progress = try_to_compact_pages(zonelist, order, gfp_mask, nodemask); + tsk->flags &= ~PF_MEMALLOC; if (*did_some_progress != COMPACT_SKIPPED) { /* Page migration frees to the PCP lists but we want merging */ @@ -2121,6 +2124,19 @@ rebalance: /* Wait for some write requests to complete then retry */ wait_iff_congested(preferred_zone, BLK_RW_ASYNC, HZ/50); goto rebalance; + } else { + /* + * High-order allocations do not necessarily loop after + * direct reclaim and reclaim/compaction depends on compaction + * being called after reclaim so call directly if necessary + */ + page = __alloc_pages_direct_compact(gfp_mask, order, + zonelist, high_zoneidx, + nodemask, + alloc_flags, preferred_zone, + migratetype, &did_some_progress); + if (page) + goto got_pg; } nopage: diff --git a/mm/vmscan.c b/mm/vmscan.c index 3464312bde07..10ebd74a423c 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -32,6 +32,7 @@ #include #include #include +#include #include #include #include @@ -59,12 +60,15 @@ * LUMPY_MODE_CONTIGRECLAIM: For high-order allocations, take a reference * page from the LRU and reclaim all pages within a * naturally aligned range + * LUMPY_MODE_COMPACTION: For high-order allocations, reclaim a number of + * order-0 pages and then compact the zone */ typedef unsigned __bitwise__ lumpy_mode; #define LUMPY_MODE_SINGLE ((__force lumpy_mode)0x01u) #define LUMPY_MODE_ASYNC ((__force lumpy_mode)0x02u) #define LUMPY_MODE_SYNC ((__force lumpy_mode)0x04u) #define LUMPY_MODE_CONTIGRECLAIM ((__force lumpy_mode)0x08u) +#define LUMPY_MODE_COMPACTION ((__force lumpy_mode)0x10u) struct scan_control { /* Incremented by the number of inactive pages that were scanned */ @@ -286,18 +290,20 @@ static void set_lumpy_reclaim_mode(int priority, struct scan_control *sc, lumpy_mode syncmode = sync ? LUMPY_MODE_SYNC : LUMPY_MODE_ASYNC; /* - * Some reclaim have alredy been failed. No worth to try synchronous - * lumpy reclaim. + * Initially assume we are entering either lumpy reclaim or + * reclaim/compaction.Depending on the order, we will either set the + * sync mode or just reclaim order-0 pages later. */ - if (sync && sc->lumpy_reclaim_mode & LUMPY_MODE_SINGLE) - return; + if (COMPACTION_BUILD) + sc->lumpy_reclaim_mode = LUMPY_MODE_COMPACTION; + else + sc->lumpy_reclaim_mode = LUMPY_MODE_CONTIGRECLAIM; /* - * If we need a large contiguous chunk of memory, or have - * trouble getting a small set of contiguous pages, we - * will reclaim both active and inactive pages. + * Avoid using lumpy reclaim or reclaim/compaction if possible by + * restricting when its set to either costly allocations or when + * under memory pressure */ - sc->lumpy_reclaim_mode = LUMPY_MODE_CONTIGRECLAIM; if (sc->order > PAGE_ALLOC_COSTLY_ORDER) sc->lumpy_reclaim_mode |= syncmode; else if (sc->order && priority < DEF_PRIORITY - 2) @@ -1385,8 +1391,8 @@ shrink_inactive_list(unsigned long nr_to_scan, struct zone *zone, if (scanning_global_lru(sc)) { nr_taken = isolate_pages_global(nr_to_scan, &page_list, &nr_scanned, sc->order, - sc->lumpy_reclaim_mode & LUMPY_MODE_SINGLE ? - ISOLATE_INACTIVE : ISOLATE_BOTH, + sc->lumpy_reclaim_mode & LUMPY_MODE_CONTIGRECLAIM ? + ISOLATE_BOTH : ISOLATE_INACTIVE, zone, 0, file); zone->pages_scanned += nr_scanned; if (current_is_kswapd()) @@ -1398,8 +1404,8 @@ shrink_inactive_list(unsigned long nr_to_scan, struct zone *zone, } else { nr_taken = mem_cgroup_isolate_pages(nr_to_scan, &page_list, &nr_scanned, sc->order, - sc->lumpy_reclaim_mode & LUMPY_MODE_SINGLE ? - ISOLATE_INACTIVE : ISOLATE_BOTH, + sc->lumpy_reclaim_mode & LUMPY_MODE_CONTIGRECLAIM ? + ISOLATE_BOTH : ISOLATE_INACTIVE, zone, sc->mem_cgroup, 0, file); /* @@ -1814,6 +1820,57 @@ out: } } +/* + * Reclaim/compaction depends on a number of pages being freed. To avoid + * disruption to the system, a small number of order-0 pages continue to be + * rotated and reclaimed in the normal fashion. However, by the time we get + * back to the allocator and call try_to_compact_zone(), we ensure that + * there are enough free pages for it to be likely successful + */ +static inline bool should_continue_reclaim(struct zone *zone, + unsigned long nr_reclaimed, + unsigned long nr_scanned, + struct scan_control *sc) +{ + unsigned long pages_for_compaction; + unsigned long inactive_lru_pages; + + /* If not in reclaim/compaction mode, stop */ + if (!(sc->lumpy_reclaim_mode & LUMPY_MODE_COMPACTION)) + return false; + + /* + * If we failed to reclaim and have scanned the full list, stop. + * NOTE: Checking just nr_reclaimed would exit reclaim/compaction far + * faster but obviously would be less likely to succeed + * allocation. If this is desirable, use GFP_REPEAT to decide + * if both reclaimed and scanned should be checked or just + * reclaimed + */ + if (!nr_reclaimed && !nr_scanned) + return false; + + /* + * If we have not reclaimed enough pages for compaction and the + * inactive lists are large enough, continue reclaiming + */ + pages_for_compaction = (2UL << sc->order); + inactive_lru_pages = zone_nr_lru_pages(zone, sc, LRU_INACTIVE_ANON) + + zone_nr_lru_pages(zone, sc, LRU_INACTIVE_FILE); + if (sc->nr_reclaimed < pages_for_compaction && + inactive_lru_pages > pages_for_compaction) + return true; + + /* If compaction would go ahead or the allocation would succeed, stop */ + switch (compaction_suitable(zone, sc->order)) { + case COMPACT_PARTIAL: + case COMPACT_CONTINUE: + return false; + default: + return true; + } +} + /* * This is a basic per-zone page freer. Used by both kswapd and direct reclaim. */ @@ -1823,9 +1880,12 @@ static void shrink_zone(int priority, struct zone *zone, unsigned long nr[NR_LRU_LISTS]; unsigned long nr_to_scan; enum lru_list l; - unsigned long nr_reclaimed = sc->nr_reclaimed; + unsigned long nr_reclaimed; unsigned long nr_to_reclaim = sc->nr_to_reclaim; + unsigned long nr_scanned = sc->nr_scanned; +restart: + nr_reclaimed = 0; get_scan_count(zone, sc, nr, priority); while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] || @@ -1851,8 +1911,7 @@ static void shrink_zone(int priority, struct zone *zone, if (nr_reclaimed >= nr_to_reclaim && priority < DEF_PRIORITY) break; } - - sc->nr_reclaimed = nr_reclaimed; + sc->nr_reclaimed += nr_reclaimed; /* * Even if we did not try to evict anon pages at all, we want to @@ -1861,6 +1920,11 @@ static void shrink_zone(int priority, struct zone *zone, if (inactive_anon_is_low(zone, sc)) shrink_active_list(SWAP_CLUSTER_MAX, zone, sc, priority, 0); + /* reclaim/compaction might need reclaim to continue */ + if (should_continue_reclaim(zone, nr_reclaimed, + sc->nr_scanned - nr_scanned, sc)) + goto restart; + throttle_vm_writeout(sc->gfp_mask); } @@ -2307,6 +2371,14 @@ loop_again: total_scanned > sc.nr_reclaimed + sc.nr_reclaimed / 2) sc.may_writepage = 1; + /* + * Compact the zone for higher orders to reduce + * latencies for higher-order allocations that + * would ordinarily call try_to_compact_pages() + */ + if (sc.order > PAGE_ALLOC_COSTLY_ORDER) + compact_zone_order(zone, sc.order, sc.gfp_mask); + if (!zone_watermark_ok_safe(zone, order, high_wmark_pages(zone), end_zone, 0)) { all_zones_ok = 0; -- cgit v1.2.3-59-g8ed1b From 77f1fe6b08b13a87391549c8a820ddc817b6f50e Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 13 Jan 2011 15:45:57 -0800 Subject: mm: migration: allow migration to operate asynchronously and avoid synchronous compaction in the faster path Migration synchronously waits for writeback if the initial passes fails. Callers of memory compaction do not necessarily want this behaviour if the caller is latency sensitive or expects that synchronous migration is not going to have a significantly better success rate. This patch adds a sync parameter to migrate_pages() allowing the caller to indicate if wait_on_page_writeback() is allowed within migration or not. For reclaim/compaction, try_to_compact_pages() is first called asynchronously, direct reclaim runs and then try_to_compact_pages() is called synchronously as there is a greater expectation that it'll succeed. [akpm@linux-foundation.org: build/merge fix] Signed-off-by: Mel Gorman Cc: Andrea Arcangeli Cc: KOSAKI Motohiro Cc: Rik van Riel Acked-by: Johannes Weiner Cc: Andy Whitcroft Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compaction.h | 10 ++++++---- include/linux/migrate.h | 12 ++++++++---- mm/compaction.c | 14 ++++++++++---- mm/memory-failure.c | 8 +++++--- mm/memory_hotplug.c | 3 ++- mm/mempolicy.c | 4 ++-- mm/migrate.c | 22 +++++++++++++--------- mm/page_alloc.c | 21 +++++++++++++++------ mm/vmscan.c | 3 ++- 9 files changed, 63 insertions(+), 34 deletions(-) (limited to 'mm/page_alloc.c') diff --git a/include/linux/compaction.h b/include/linux/compaction.h index 2592883d862d..72cba4034785 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -21,10 +21,11 @@ extern int sysctl_extfrag_handler(struct ctl_table *table, int write, extern int fragmentation_index(struct zone *zone, unsigned int order); extern unsigned long try_to_compact_pages(struct zonelist *zonelist, - int order, gfp_t gfp_mask, nodemask_t *mask); + int order, gfp_t gfp_mask, nodemask_t *mask, + bool sync); extern unsigned long compaction_suitable(struct zone *zone, int order); extern unsigned long compact_zone_order(struct zone *zone, int order, - gfp_t gfp_mask); + gfp_t gfp_mask, bool sync); /* Do not skip compaction more than 64 times */ #define COMPACT_MAX_DEFER_SHIFT 6 @@ -57,7 +58,8 @@ static inline bool compaction_deferred(struct zone *zone) #else static inline unsigned long try_to_compact_pages(struct zonelist *zonelist, - int order, gfp_t gfp_mask, nodemask_t *nodemask) + int order, gfp_t gfp_mask, nodemask_t *nodemask, + bool sync) { return COMPACT_CONTINUE; } @@ -68,7 +70,7 @@ static inline unsigned long compaction_suitable(struct zone *zone, int order) } static inline unsigned long compact_zone_order(struct zone *zone, int order, - gfp_t gfp_mask) + gfp_t gfp_mask, bool sync) { return 0; } diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 085527fb8261..fa31902803fd 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -13,9 +13,11 @@ extern void putback_lru_pages(struct list_head *l); extern int migrate_page(struct address_space *, struct page *, struct page *); extern int migrate_pages(struct list_head *l, new_page_t x, - unsigned long private, int offlining); + unsigned long private, int offlining, + bool sync); extern int migrate_huge_pages(struct list_head *l, new_page_t x, - unsigned long private, int offlining); + unsigned long private, int offlining, + bool sync); extern int fail_migrate_page(struct address_space *, struct page *, struct page *); @@ -33,9 +35,11 @@ extern int migrate_huge_page_move_mapping(struct address_space *mapping, static inline void putback_lru_pages(struct list_head *l) {} static inline int migrate_pages(struct list_head *l, new_page_t x, - unsigned long private, int offlining) { return -ENOSYS; } + unsigned long private, int offlining, + bool sync) { return -ENOSYS; } static inline int migrate_huge_pages(struct list_head *l, new_page_t x, - unsigned long private, int offlining) { return -ENOSYS; } + unsigned long private, int offlining, + bool sync) { return -ENOSYS; } static inline int migrate_prep(void) { return -ENOSYS; } static inline int migrate_prep_local(void) { return -ENOSYS; } diff --git a/mm/compaction.c b/mm/compaction.c index 8fe917ec7c11..47fca1069343 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -33,6 +33,7 @@ struct compact_control { unsigned long nr_migratepages; /* Number of pages to migrate */ unsigned long free_pfn; /* isolate_freepages search base */ unsigned long migrate_pfn; /* isolate_migratepages search base */ + bool sync; /* Synchronous migration */ /* Account for isolated anon and file pages */ unsigned long nr_anon; @@ -455,7 +456,8 @@ static int compact_zone(struct zone *zone, struct compact_control *cc) nr_migrate = cc->nr_migratepages; migrate_pages(&cc->migratepages, compaction_alloc, - (unsigned long)cc, 0); + (unsigned long)cc, 0, + cc->sync); update_nr_listpages(cc); nr_remaining = cc->nr_migratepages; @@ -482,7 +484,8 @@ static int compact_zone(struct zone *zone, struct compact_control *cc) } unsigned long compact_zone_order(struct zone *zone, - int order, gfp_t gfp_mask) + int order, gfp_t gfp_mask, + bool sync) { struct compact_control cc = { .nr_freepages = 0, @@ -490,6 +493,7 @@ unsigned long compact_zone_order(struct zone *zone, .order = order, .migratetype = allocflags_to_migratetype(gfp_mask), .zone = zone, + .sync = sync, }; INIT_LIST_HEAD(&cc.freepages); INIT_LIST_HEAD(&cc.migratepages); @@ -505,11 +509,13 @@ int sysctl_extfrag_threshold = 500; * @order: The order of the current allocation * @gfp_mask: The GFP mask of the current allocation * @nodemask: The allowed nodes to allocate from + * @sync: Whether migration is synchronous or not * * This is the main entry point for direct page compaction. */ unsigned long try_to_compact_pages(struct zonelist *zonelist, - int order, gfp_t gfp_mask, nodemask_t *nodemask) + int order, gfp_t gfp_mask, nodemask_t *nodemask, + bool sync) { enum zone_type high_zoneidx = gfp_zone(gfp_mask); int may_enter_fs = gfp_mask & __GFP_FS; @@ -533,7 +539,7 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist, nodemask) { int status; - status = compact_zone_order(zone, order, gfp_mask); + status = compact_zone_order(zone, order, gfp_mask, sync); rc = max(status, rc); /* If a normal allocation would succeed, stop compacting */ diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 46ab2c044b0e..2323a8039a98 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1290,9 +1290,10 @@ static int soft_offline_huge_page(struct page *page, int flags) /* Keep page count to indicate a given hugepage is isolated. */ list_add(&hpage->lru, &pagelist); - ret = migrate_huge_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL, 0); + ret = migrate_huge_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL, 0, + true); if (ret) { - putback_lru_pages(&pagelist); + putback_lru_pages(&pagelist); pr_debug("soft offline: %#lx: migration failed %d, type %lx\n", pfn, ret, page->flags); if (ret > 0) @@ -1413,7 +1414,8 @@ int soft_offline_page(struct page *page, int flags) LIST_HEAD(pagelist); list_add(&page->lru, &pagelist); - ret = migrate_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL, 0); + ret = migrate_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL, + 0, true); if (ret) { pr_info("soft offline: %#lx: migration failed %d, type %lx\n", pfn, ret, page->flags); diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 2c6523af5473..584fc5588fdd 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -733,7 +733,8 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) goto out; } /* this function returns # of failed pages */ - ret = migrate_pages(&source, hotremove_migrate_alloc, 0, 1); + ret = migrate_pages(&source, hotremove_migrate_alloc, 0, + 1, true); if (ret) putback_lru_pages(&source); } diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 11ff260fb282..9db274593086 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -935,7 +935,7 @@ static int migrate_to_node(struct mm_struct *mm, int source, int dest, return PTR_ERR(vma); if (!list_empty(&pagelist)) { - err = migrate_pages(&pagelist, new_node_page, dest, 0); + err = migrate_pages(&pagelist, new_node_page, dest, 0, true); if (err) putback_lru_pages(&pagelist); } @@ -1155,7 +1155,7 @@ static long do_mbind(unsigned long start, unsigned long len, if (!list_empty(&pagelist)) { nr_failed = migrate_pages(&pagelist, new_vma_page, - (unsigned long)vma, 0); + (unsigned long)vma, 0, true); if (nr_failed) putback_lru_pages(&pagelist); } diff --git a/mm/migrate.c b/mm/migrate.c index 94875b265928..dc47f6c40353 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -614,7 +614,7 @@ static int move_to_new_page(struct page *newpage, struct page *page, * to the newly allocated page in newpage. */ static int unmap_and_move(new_page_t get_new_page, unsigned long private, - struct page *page, int force, int offlining) + struct page *page, int force, int offlining, bool sync) { int rc = 0; int *result = NULL; @@ -682,7 +682,7 @@ static int unmap_and_move(new_page_t get_new_page, unsigned long private, BUG_ON(charge); if (PageWriteback(page)) { - if (!force) + if (!force || !sync) goto uncharge; wait_on_page_writeback(page); } @@ -827,7 +827,7 @@ move_newpage: */ static int unmap_and_move_huge_page(new_page_t get_new_page, unsigned long private, struct page *hpage, - int force, int offlining) + int force, int offlining, bool sync) { int rc = 0; int *result = NULL; @@ -841,7 +841,7 @@ static int unmap_and_move_huge_page(new_page_t get_new_page, rc = -EAGAIN; if (!trylock_page(hpage)) { - if (!force) + if (!force || !sync) goto out; lock_page(hpage); } @@ -909,7 +909,8 @@ out: * Return: Number of pages not migrated or error code. */ int migrate_pages(struct list_head *from, - new_page_t get_new_page, unsigned long private, int offlining) + new_page_t get_new_page, unsigned long private, int offlining, + bool sync) { int retry = 1; int nr_failed = 0; @@ -929,7 +930,8 @@ int migrate_pages(struct list_head *from, cond_resched(); rc = unmap_and_move(get_new_page, private, - page, pass > 2, offlining); + page, pass > 2, offlining, + sync); switch(rc) { case -ENOMEM: @@ -958,7 +960,8 @@ out: } int migrate_huge_pages(struct list_head *from, - new_page_t get_new_page, unsigned long private, int offlining) + new_page_t get_new_page, unsigned long private, int offlining, + bool sync) { int retry = 1; int nr_failed = 0; @@ -974,7 +977,8 @@ int migrate_huge_pages(struct list_head *from, cond_resched(); rc = unmap_and_move_huge_page(get_new_page, - private, page, pass > 2, offlining); + private, page, pass > 2, offlining, + sync); switch(rc) { case -ENOMEM: @@ -1107,7 +1111,7 @@ set_status: err = 0; if (!list_empty(&pagelist)) { err = migrate_pages(&pagelist, new_page_node, - (unsigned long)pm, 0); + (unsigned long)pm, 0, true); if (err) putback_lru_pages(&pagelist); } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 03a66a31bfcd..0fd486467b4b 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1812,7 +1812,8 @@ static struct page * __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, struct zonelist *zonelist, enum zone_type high_zoneidx, nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone, - int migratetype, unsigned long *did_some_progress) + int migratetype, unsigned long *did_some_progress, + bool sync_migration) { struct page *page; struct task_struct *tsk = current; @@ -1822,7 +1823,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, tsk->flags |= PF_MEMALLOC; *did_some_progress = try_to_compact_pages(zonelist, order, gfp_mask, - nodemask); + nodemask, sync_migration); tsk->flags &= ~PF_MEMALLOC; if (*did_some_progress != COMPACT_SKIPPED) { @@ -1859,7 +1860,8 @@ static inline struct page * __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, struct zonelist *zonelist, enum zone_type high_zoneidx, nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone, - int migratetype, unsigned long *did_some_progress) + int migratetype, unsigned long *did_some_progress, + bool sync_migration) { return NULL; } @@ -2001,6 +2003,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, unsigned long pages_reclaimed = 0; unsigned long did_some_progress; struct task_struct *p = current; + bool sync_migration = false; /* * In the slowpath, we sanity check order to avoid ever trying to @@ -2063,14 +2066,19 @@ rebalance: if (test_thread_flag(TIF_MEMDIE) && !(gfp_mask & __GFP_NOFAIL)) goto nopage; - /* Try direct compaction */ + /* + * Try direct compaction. The first pass is asynchronous. Subsequent + * attempts after direct reclaim are synchronous + */ page = __alloc_pages_direct_compact(gfp_mask, order, zonelist, high_zoneidx, nodemask, alloc_flags, preferred_zone, - migratetype, &did_some_progress); + migratetype, &did_some_progress, + sync_migration); if (page) goto got_pg; + sync_migration = true; /* Try direct reclaim and then allocating */ page = __alloc_pages_direct_reclaim(gfp_mask, order, @@ -2134,7 +2142,8 @@ rebalance: zonelist, high_zoneidx, nodemask, alloc_flags, preferred_zone, - migratetype, &did_some_progress); + migratetype, &did_some_progress, + sync_migration); if (page) goto got_pg; } diff --git a/mm/vmscan.c b/mm/vmscan.c index 10ebd74a423c..8320d115c85d 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2377,7 +2377,8 @@ loop_again: * would ordinarily call try_to_compact_pages() */ if (sc.order > PAGE_ALLOC_COSTLY_ORDER) - compact_zone_order(zone, sc.order, sc.gfp_mask); + compact_zone_order(zone, sc.order, sc.gfp_mask, + false); if (!zone_watermark_ok_safe(zone, order, high_wmark_pages(zone), end_zone, 0)) { -- cgit v1.2.3-59-g8ed1b From 9950474883e027e6e728cbcff25f7f2bf0c96530 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 13 Jan 2011 15:46:20 -0800 Subject: mm: kswapd: stop high-order balancing when any suitable zone is balanced Simon Kirby reported the following problem We're seeing cases on a number of servers where cache never fully grows to use all available memory. Sometimes we see servers with 4 GB of memory that never seem to have less than 1.5 GB free, even with a constantly-active VM. In some cases, these servers also swap out while this happens, even though they are constantly reading the working set into memory. We have been seeing this happening for a long time; I don't think it's anything recent, and it still happens on 2.6.36. After some debugging work by Simon, Dave Hansen and others, the prevaling theory became that kswapd is reclaiming order-3 pages requested by SLUB too aggressive about it. There are two apparent problems here. On the target machine, there is a small Normal zone in comparison to DMA32. As kswapd tries to balance all zones, it would continually try reclaiming for Normal even though DMA32 was balanced enough for callers. The second problem is that sleeping_prematurely() does not use the same logic as balance_pgdat() when deciding whether to sleep or not. This keeps kswapd artifically awake. A number of tests were run and the figures from previous postings will look very different for a few reasons. One, the old figures were forcing my network card to use GFP_ATOMIC in attempt to replicate Simon's problem. Second, I previous specified slub_min_order=3 again in an attempt to reproduce Simon's problem. In this posting, I'm depending on Simon to say whether his problem is fixed or not and these figures are to show the impact to the ordinary cases. Finally, the "vmscan" figures are taken from /proc/vmstat instead of the tracepoints. There is less information but recording is less disruptive. The first test of relevance was postmark with a process running in the background reading a large amount of anonymous memory in blocks. The objective was to vaguely simulate what was happening on Simon's machine and it's memory intensive enough to have kswapd awake. POSTMARK traceonly kanyzone Transactions per second: 156.00 ( 0.00%) 153.00 (-1.96%) Data megabytes read per second: 21.51 ( 0.00%) 21.52 ( 0.05%) Data megabytes written per second: 29.28 ( 0.00%) 29.11 (-0.58%) Files created alone per second: 250.00 ( 0.00%) 416.00 (39.90%) Files create/transact per second: 79.00 ( 0.00%) 76.00 (-3.95%) Files deleted alone per second: 520.00 ( 0.00%) 420.00 (-23.81%) Files delete/transact per second: 79.00 ( 0.00%) 76.00 (-3.95%) MMTests Statistics: duration User/Sys Time Running Test (seconds) 16.58 17.4 Total Elapsed Time (seconds) 218.48 222.47 VMstat Reclaim Statistics: vmscan Direct reclaims 0 4 Direct reclaim pages scanned 0 203 Direct reclaim pages reclaimed 0 184 Kswapd pages scanned 326631 322018 Kswapd pages reclaimed 312632 309784 Kswapd low wmark quickly 1 4 Kswapd high wmark quickly 122 475 Kswapd skip congestion_wait 1 0 Pages activated 700040 705317 Pages deactivated 212113 203922 Pages written 9875 6363 Total pages scanned 326631 322221 Total pages reclaimed 312632 309968 %age total pages scanned/reclaimed 95.71% 96.20% %age total pages scanned/written 3.02% 1.97% proc vmstat: Faults Major Faults 300 254 Minor Faults 645183 660284 Page ins 493588 486704 Page outs 4960088 4986704 Swap ins 1230 661 Swap outs 9869 6355 Performance is mildly affected because kswapd is no longer doing as much work and the background memory consumer process is getting in the way. Note that kswapd scanned and reclaimed fewer pages as it's less aggressive and overall fewer pages were scanned and reclaimed. Swap in/out is particularly reduced again reflecting kswapd throwing out fewer pages. The slight performance impact is unfortunate here but it looks like a direct result of kswapd being less aggressive. As the bug report is about too many pages being freed by kswapd, it may have to be accepted for now. The second test is a streaming IO benchmark that was previously used by Johannes to show regressions in page reclaim. MICRO traceonly kanyzone User/Sys Time Running Test (seconds) 29.29 28.87 Total Elapsed Time (seconds) 492.18 488.79 VMstat Reclaim Statistics: vmscan Direct reclaims 2128 1460 Direct reclaim pages scanned 2284822 1496067 Direct reclaim pages reclaimed 148919 110937 Kswapd pages scanned 15450014 16202876 Kswapd pages reclaimed 8503697 8537897 Kswapd low wmark quickly 3100 3397 Kswapd high wmark quickly 1860 7243 Kswapd skip congestion_wait 708 801 Pages activated 9635 9573 Pages deactivated 1432 1271 Pages written 223 1130 Total pages scanned 17734836 17698943 Total pages reclaimed 8652616 8648834 %age total pages scanned/reclaimed 48.79% 48.87% %age total pages scanned/written 0.00% 0.01% proc vmstat: Faults Major Faults 165 221 Minor Faults 9655785 9656506 Page ins 3880 7228 Page outs 37692940 37480076 Swap ins 0 69 Swap outs 19 15 Again fewer pages are scanned and reclaimed as expected and this time the test completed faster. Note that kswapd is hitting its watermarks faster (low and high wmark quickly) which I expect is due to kswapd reclaiming fewer pages. I also ran fs-mark, iozone and sysbench but there is nothing interesting to report in the figures. Performance is not significantly changed and the reclaim statistics look reasonable. Tgis patch: When the allocator enters its slow path, kswapd is woken up to balance the node. It continues working until all zones within the node are balanced. For order-0 allocations, this makes perfect sense but for higher orders it can have unintended side-effects. If the zone sizes are imbalanced, kswapd may reclaim heavily within a smaller zone discarding an excessive number of pages. The user-visible behaviour is that kswapd is awake and reclaiming even though plenty of pages are free from a suitable zone. This patch alters the "balance" logic for high-order reclaim allowing kswapd to stop if any suitable zone becomes balanced to reduce the number of pages it reclaims from other zones. kswapd still tries to ensure that order-0 watermarks for all zones are met before sleeping. Signed-off-by: Mel Gorman Reviewed-by: Minchan Kim Reviewed-by: KAMEZAWA Hiroyuki Reviewed-by: Eric B Munson Cc: Simon Kirby Cc: KOSAKI Motohiro Cc: Shaohua Li Cc: Dave Hansen Cc: Johannes Weiner Cc: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 3 ++- mm/page_alloc.c | 8 +++--- mm/vmscan.c | 68 +++++++++++++++++++++++++++++++++++++++++++------- 3 files changed, 66 insertions(+), 13 deletions(-) (limited to 'mm/page_alloc.c') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 48906629335c..dad3612a7e39 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -639,6 +639,7 @@ typedef struct pglist_data { wait_queue_head_t kswapd_wait; struct task_struct *kswapd; int kswapd_max_order; + enum zone_type classzone_idx; } pg_data_t; #define node_present_pages(nid) (NODE_DATA(nid)->node_present_pages) @@ -654,7 +655,7 @@ typedef struct pglist_data { extern struct mutex zonelists_mutex; void build_all_zonelists(void *data); -void wakeup_kswapd(struct zone *zone, int order); +void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx); bool zone_watermark_ok(struct zone *z, int order, unsigned long mark, int classzone_idx, int alloc_flags); bool zone_watermark_ok_safe(struct zone *z, int order, unsigned long mark, diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 0fd486467b4b..c31460918506 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1944,13 +1944,14 @@ __alloc_pages_high_priority(gfp_t gfp_mask, unsigned int order, static inline void wake_all_kswapd(unsigned int order, struct zonelist *zonelist, - enum zone_type high_zoneidx) + enum zone_type high_zoneidx, + enum zone_type classzone_idx) { struct zoneref *z; struct zone *zone; for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) - wakeup_kswapd(zone, order); + wakeup_kswapd(zone, order, classzone_idx); } static inline int @@ -2028,7 +2029,8 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, goto nopage; restart: - wake_all_kswapd(order, zonelist, high_zoneidx); + wake_all_kswapd(order, zonelist, high_zoneidx, + zone_idx(preferred_zone)); /* * OK, we're below the kswapd watermark and have kicked background diff --git a/mm/vmscan.c b/mm/vmscan.c index 7037cc8c60b6..3584067800e1 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2246,11 +2246,14 @@ static int sleeping_prematurely(pg_data_t *pgdat, int order, long remaining) * interoperates with the page allocator fallback scheme to ensure that aging * of pages is balanced across the zones. */ -static unsigned long balance_pgdat(pg_data_t *pgdat, int order) +static unsigned long balance_pgdat(pg_data_t *pgdat, int order, + int classzone_idx) { int all_zones_ok; + int any_zone_ok; int priority; int i; + int end_zone = 0; /* Inclusive. 0 = ZONE_DMA */ unsigned long total_scanned; struct reclaim_state *reclaim_state = current->reclaim_state; struct scan_control sc = { @@ -2273,7 +2276,6 @@ loop_again: count_vm_event(PAGEOUTRUN); for (priority = DEF_PRIORITY; priority >= 0; priority--) { - int end_zone = 0; /* Inclusive. 0 = ZONE_DMA */ unsigned long lru_pages = 0; int has_under_min_watermark_zone = 0; @@ -2282,6 +2284,7 @@ loop_again: disable_swap_token(); all_zones_ok = 1; + any_zone_ok = 0; /* * Scan in the highmem->dma direction for the highest @@ -2400,10 +2403,12 @@ loop_again: * spectulatively avoid congestion waits */ zone_clear_flag(zone, ZONE_CONGESTED); + if (i <= classzone_idx) + any_zone_ok = 1; } } - if (all_zones_ok) + if (all_zones_ok || (order && any_zone_ok)) break; /* kswapd: all done */ /* * OK, kswapd is getting into trouble. Take a nap, then take @@ -2426,7 +2431,13 @@ loop_again: break; } out: - if (!all_zones_ok) { + + /* + * order-0: All zones must meet high watermark for a balanced node + * high-order: Any zone below pgdats classzone_idx must meet the high + * watermark for a balanced node + */ + if (!(all_zones_ok || (order && any_zone_ok))) { cond_resched(); try_to_freeze(); @@ -2451,6 +2462,36 @@ out: goto loop_again; } + /* + * If kswapd was reclaiming at a higher order, it has the option of + * sleeping without all zones being balanced. Before it does, it must + * ensure that the watermarks for order-0 on *all* zones are met and + * that the congestion flags are cleared. The congestion flag must + * be cleared as kswapd is the only mechanism that clears the flag + * and it is potentially going to sleep here. + */ + if (order) { + for (i = 0; i <= end_zone; i++) { + struct zone *zone = pgdat->node_zones + i; + + if (!populated_zone(zone)) + continue; + + if (zone->all_unreclaimable && priority != DEF_PRIORITY) + continue; + + /* Confirm the zone is balanced for order-0 */ + if (!zone_watermark_ok(zone, 0, + high_wmark_pages(zone), 0, 0)) { + order = sc.order = 0; + goto loop_again; + } + + /* If balanced, clear the congested flag */ + zone_clear_flag(zone, ZONE_CONGESTED); + } + } + return sc.nr_reclaimed; } @@ -2514,6 +2555,7 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order) static int kswapd(void *p) { unsigned long order; + int classzone_idx; pg_data_t *pgdat = (pg_data_t*)p; struct task_struct *tsk = current; @@ -2544,21 +2586,27 @@ static int kswapd(void *p) set_freezable(); order = 0; + classzone_idx = MAX_NR_ZONES - 1; for ( ; ; ) { unsigned long new_order; + int new_classzone_idx; int ret; new_order = pgdat->kswapd_max_order; + new_classzone_idx = pgdat->classzone_idx; pgdat->kswapd_max_order = 0; - if (order < new_order) { + pgdat->classzone_idx = MAX_NR_ZONES - 1; + if (order < new_order || classzone_idx > new_classzone_idx) { /* * Don't sleep if someone wants a larger 'order' - * allocation + * allocation or has tigher zone constraints */ order = new_order; + classzone_idx = new_classzone_idx; } else { kswapd_try_to_sleep(pgdat, order); order = pgdat->kswapd_max_order; + classzone_idx = pgdat->classzone_idx; } ret = try_to_freeze(); @@ -2571,7 +2619,7 @@ static int kswapd(void *p) */ if (!ret) { trace_mm_vmscan_kswapd_wake(pgdat->node_id, order); - balance_pgdat(pgdat, order); + balance_pgdat(pgdat, order, classzone_idx); } } return 0; @@ -2580,7 +2628,7 @@ static int kswapd(void *p) /* * A zone is low on free memory, so wake its kswapd task to service it. */ -void wakeup_kswapd(struct zone *zone, int order) +void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx) { pg_data_t *pgdat; @@ -2590,8 +2638,10 @@ void wakeup_kswapd(struct zone *zone, int order) if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL)) return; pgdat = zone->zone_pgdat; - if (pgdat->kswapd_max_order < order) + if (pgdat->kswapd_max_order < order) { pgdat->kswapd_max_order = order; + pgdat->classzone_idx = min(pgdat->classzone_idx, classzone_idx); + } if (!waitqueue_active(&pgdat->kswapd_wait)) return; if (zone_watermark_ok_safe(zone, order, low_wmark_pages(zone), 0, 0)) -- cgit v1.2.3-59-g8ed1b From ecb256f815232b35ae8382cff36ca8ce0bbd077e Mon Sep 17 00:00:00 2001 From: "Volodymyr G. Lukiianyk" Date: Thu, 13 Jan 2011 15:46:26 -0800 Subject: mm: set correct numa_zonelist_order string when configured on the kernel command line When numa_zonelist_order parameter is set to "node" or "zone" on the command line it's still showing as "default" in sysctl. That's because early_param parsing function changes only user_zonelist_order variable. Fix this by copying user-provided string to numa_zonelist_order if it was successfully parsed. Signed-off-by: Volodymyr G Lukiianyk Acked-by: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) (limited to 'mm/page_alloc.c') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index c31460918506..c18d1f7cff84 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2631,9 +2631,16 @@ static int __parse_numa_zonelist_order(char *s) static __init int setup_numa_zonelist_order(char *s) { - if (s) - return __parse_numa_zonelist_order(s); - return 0; + int ret; + + if (!s) + return 0; + + ret = __parse_numa_zonelist_order(s); + if (ret == 0) + strlcpy(numa_zonelist_order, s, NUMA_ZONELIST_ORDER_LEN); + + return ret; } early_param("numa_zonelist_order", setup_numa_zonelist_order); -- cgit v1.2.3-59-g8ed1b From 4e9f64c42d0ba5eb0c78569435ada4c224332ce4 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Thu, 13 Jan 2011 15:46:29 -0800 Subject: thp: fix bad_page to show the real reason the page is bad page_count shows the count of the head page, but the actual check is done on the tail page, so show what is really being checked. Signed-off-by: Andrea Arcangeli Acked-by: Rik van Riel Acked-by: Mel Gorman Reviewed-by: KOSAKI Motohiro 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/page_alloc.c') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index c18d1f7cff84..2a67c3bd403a 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5618,7 +5618,7 @@ void dump_page(struct page *page) { printk(KERN_ALERT "page:%p count:%d mapcount:%d mapping:%p index:%#lx\n", - page, page_count(page), page_mapcount(page), + page, atomic_read(&page->_count), page_mapcount(page), page->mapping, page->index); dump_page_flags(page->flags); } -- cgit v1.2.3-59-g8ed1b From 8dd60a3a65c1b057bf0031d28436d3447a3c545b Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Thu, 13 Jan 2011 15:46:34 -0800 Subject: thp: clear compound mapping Clear compound mapping for anonymous compound pages like it already happens for regular anonymous pages. But crash if mapping is set for any tail page, also the PageAnon check is meaningless for tail pages. This check only makes sense for the head page, for tail page it can only hide bugs and we definitely don't want to hide bugs. Signed-off-by: Andrea Arcangeli Acked-by: Rik van Riel Acked-by: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-) (limited to 'mm/page_alloc.c') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 2a67c3bd403a..8be81422d4bd 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -651,13 +651,10 @@ static bool free_pages_prepare(struct page *page, unsigned int order) trace_mm_page_free_direct(page, order); kmemcheck_free_shadow(page, order); - for (i = 0; i < (1 << order); i++) { - struct page *pg = page + i; - - if (PageAnon(pg)) - pg->mapping = NULL; - bad += free_pages_check(pg); - } + if (PageAnon(page)) + page->mapping = NULL; + for (i = 0; i < (1 << order); i++) + bad += free_pages_check(page + i); if (bad) return false; -- cgit v1.2.3-59-g8ed1b From 59ff421631295cd54dbf75dcc53d27e84af6d9c0 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Thu, 13 Jan 2011 15:46:38 -0800 Subject: thp: comment reminder in destroy_compound_page Warn destroy_compound_page that __split_huge_page_refcount is heavily dependent on its internal behavior. Signed-off-by: Andrea Arcangeli Acked-by: Rik van Riel Acked-by: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 1 + 1 file changed, 1 insertion(+) (limited to 'mm/page_alloc.c') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 8be81422d4bd..6e62d5f9d40b 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -357,6 +357,7 @@ void prep_compound_page(struct page *page, unsigned long order) } } +/* update __split_huge_page_refcount if you change this function */ static int destroy_compound_page(struct page *page, unsigned long order) { int i; -- cgit v1.2.3-59-g8ed1b From 32dba98e085f8b2b4345887df9abf5e0e93bfc12 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Thu, 13 Jan 2011 15:46:49 -0800 Subject: thp: _GFP_NO_KSWAPD Transparent hugepage allocations must be allowed not to invoke kswapd or any other kind of indirect reclaim (especially when the defrag sysfs is control disabled). It's unacceptable to swap out anonymous pages (potentially anonymous transparent hugepages) in order to create new transparent hugepages. This is true for the MADV_HUGEPAGE areas too (swapping out a kvm virtual machine and so having it suffer an unbearable slowdown, so another one with guest physical memory marked MADV_HUGEPAGE can run 30% faster if it is running memory intensive workloads, makes no sense). If a transparent hugepage allocation fails the slowdown is minor and there is total fallback, so kswapd should never be asked to swapout memory to allow the high order allocation to succeed. Signed-off-by: Andrea Arcangeli Acked-by: Rik van Riel Acked-by: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 5 ++++- mm/page_alloc.c | 3 ++- 2 files changed, 6 insertions(+), 2 deletions(-) (limited to 'mm/page_alloc.c') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index f54adfcbec9c..49d2356bb82d 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -34,6 +34,7 @@ struct vm_area_struct; #else #define ___GFP_NOTRACK 0 #endif +#define ___GFP_NO_KSWAPD 0x400000u /* * GFP bitmasks.. @@ -81,13 +82,15 @@ struct vm_area_struct; #define __GFP_RECLAIMABLE ((__force gfp_t)___GFP_RECLAIMABLE) /* Page is reclaimable */ #define __GFP_NOTRACK ((__force gfp_t)___GFP_NOTRACK) /* Don't track with kmemcheck */ +#define __GFP_NO_KSWAPD ((__force gfp_t)___GFP_NO_KSWAPD) + /* * This may seem redundant, but it's a way of annotating false positives vs. * allocations that simply cannot be supported (e.g. page tables). */ #define __GFP_NOTRACK_FALSE_POSITIVE (__GFP_NOTRACK) -#define __GFP_BITS_SHIFT 22 /* Room for 22 __GFP_FOO bits */ +#define __GFP_BITS_SHIFT 23 /* Room for 23 __GFP_FOO bits */ #define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1)) /* This equals 0, but use constants in case they ever change */ diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 6e62d5f9d40b..bbd0423f2820 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2027,7 +2027,8 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, goto nopage; restart: - wake_all_kswapd(order, zonelist, high_zoneidx, + if (!(gfp_mask & __GFP_NO_KSWAPD)) + wake_all_kswapd(order, zonelist, high_zoneidx, zone_idx(preferred_zone)); /* -- cgit v1.2.3-59-g8ed1b From 5c3240d92e29ae7bfb9cb58a9b37e80ab40894ff Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Thu, 13 Jan 2011 15:46:49 -0800 Subject: thp: don't alloc harder for gfp nomemalloc even if nowait Not worth throwing away the precious reserved free memory pool for allocations that can fail gracefully (either through mempool or because they're transhuge allocations later falling back to 4k allocations). Signed-off-by: Andrea Arcangeli Acked-by: Rik van Riel Reviewed-by: KOSAKI Motohiro Acked-by: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'mm/page_alloc.c') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index bbd0423f2820..e7664b9f706c 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1971,7 +1971,12 @@ gfp_to_alloc_flags(gfp_t gfp_mask) alloc_flags |= (__force int) (gfp_mask & __GFP_HIGH); if (!wait) { - alloc_flags |= ALLOC_HARDER; + /* + * Not worth trying to allocate harder for + * __GFP_NOMEMALLOC even if it can't schedule. + */ + if (!(gfp_mask & __GFP_NOMEMALLOC)) + alloc_flags |= ALLOC_HARDER; /* * Ignore cpuset if GFP_ATOMIC (!wait) rather than fail alloc. * See also cpuset_zone_allowed() comment in kernel/cpuset.c. -- cgit v1.2.3-59-g8ed1b From 5f24ce5fd34c3ca1b3d10d30da754732da64d5c0 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Thu, 13 Jan 2011 15:47:00 -0800 Subject: thp: remove PG_buddy PG_buddy can be converted to _mapcount == -2. So the PG_compound_lock can be added to page->flags without overflowing (because of the sparse section bits increasing) with CONFIG_X86_PAE=y and CONFIG_X86_PAT=y. This also has to move the memory hotplug code from _mapcount to lru.next to avoid any risk of clashes. We can't use lru.next for PG_buddy removal, but memory hotplug can use lru.next even more easily than the mapcount instead. Signed-off-by: Andrea Arcangeli Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/page.c | 14 ++++++++------ include/linux/memory_hotplug.h | 14 +++++++++----- include/linux/mm.h | 21 +++++++++++++++++++++ include/linux/page-flags.h | 7 +------ mm/memory_hotplug.c | 14 ++++++++------ mm/page_alloc.c | 7 +++---- mm/sparse.c | 4 ++-- 7 files changed, 52 insertions(+), 29 deletions(-) (limited to 'mm/page_alloc.c') diff --git a/fs/proc/page.c b/fs/proc/page.c index b06c674624e6..6d8e6a9e93ab 100644 --- a/fs/proc/page.c +++ b/fs/proc/page.c @@ -116,15 +116,17 @@ u64 stable_page_flags(struct page *page) if (PageHuge(page)) u |= 1 << KPF_HUGE; - u |= kpf_copy_bit(k, KPF_LOCKED, PG_locked); - /* - * Caveats on high order pages: - * PG_buddy will only be set on the head page; SLUB/SLQB do the same - * for PG_slab; SLOB won't set PG_slab at all on compound pages. + * Caveats on high order pages: page->_count will only be set + * -1 on the head page; SLUB/SLQB do the same for PG_slab; + * SLOB won't set PG_slab at all on compound pages. */ + if (PageBuddy(page)) + u |= 1 << KPF_BUDDY; + + u |= kpf_copy_bit(k, KPF_LOCKED, PG_locked); + u |= kpf_copy_bit(k, KPF_SLAB, PG_slab); - u |= kpf_copy_bit(k, KPF_BUDDY, PG_buddy); u |= kpf_copy_bit(k, KPF_ERROR, PG_error); u |= kpf_copy_bit(k, KPF_DIRTY, PG_dirty); diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 31c237a00c48..24376fe7ee68 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -13,12 +13,16 @@ struct mem_section; #ifdef CONFIG_MEMORY_HOTPLUG /* - * Types for free bootmem. - * The normal smallest mapcount is -1. Here is smaller value than it. + * Types for free bootmem stored in page->lru.next. These have to be in + * some random range in unsigned long space for debugging purposes. */ -#define SECTION_INFO (-1 - 1) -#define MIX_SECTION_INFO (-1 - 2) -#define NODE_INFO (-1 - 3) +enum { + MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE = 12, + SECTION_INFO = MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE, + MIX_SECTION_INFO, + NODE_INFO, + MEMORY_HOTPLUG_MAX_BOOTMEM_TYPE = NODE_INFO, +}; /* * pgdat resizing functions diff --git a/include/linux/mm.h b/include/linux/mm.h index 2ec5138badab..7ab7d2b60041 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -397,6 +397,27 @@ static inline void init_page_count(struct page *page) atomic_set(&page->_count, 1); } +/* + * PageBuddy() indicate that the page is free and in the buddy system + * (see mm/page_alloc.c). + */ +static inline int PageBuddy(struct page *page) +{ + return atomic_read(&page->_mapcount) == -2; +} + +static inline void __SetPageBuddy(struct page *page) +{ + VM_BUG_ON(atomic_read(&page->_mapcount) != -1); + atomic_set(&page->_mapcount, -2); +} + +static inline void __ClearPageBuddy(struct page *page) +{ + VM_BUG_ON(!PageBuddy(page)); + atomic_set(&page->_mapcount, -1); +} + void put_page(struct page *page); void put_pages_list(struct list_head *pages); diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 4ca1241ef94e..0db8037e2725 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -48,9 +48,6 @@ * struct page (these bits with information) are always mapped into kernel * address space... * - * PG_buddy is set to indicate that the page is free and in the buddy system - * (see mm/page_alloc.c). - * * PG_hwpoison indicates that a page got corrupted in hardware and contains * data with incorrect ECC bits that triggered a machine check. Accessing is * not safe since it may cause another machine check. Don't touch! @@ -96,7 +93,6 @@ enum pageflags { PG_swapcache, /* Swap page: swp_entry_t in private */ PG_mappedtodisk, /* Has blocks allocated on-disk */ PG_reclaim, /* To be reclaimed asap */ - PG_buddy, /* Page is free, on buddy lists */ PG_swapbacked, /* Page is backed by RAM/swap */ PG_unevictable, /* Page is "unevictable" */ #ifdef CONFIG_MMU @@ -233,7 +229,6 @@ PAGEFLAG(OwnerPriv1, owner_priv_1) TESTCLEARFLAG(OwnerPriv1, owner_priv_1) * risky: they bypass page accounting. */ TESTPAGEFLAG(Writeback, writeback) TESTSCFLAG(Writeback, writeback) -__PAGEFLAG(Buddy, buddy) PAGEFLAG(MappedToDisk, mappedtodisk) /* PG_readahead is only used for file reads; PG_reclaim is only for writes */ @@ -461,7 +456,7 @@ static inline int PageTransCompound(struct page *page) #define PAGE_FLAGS_CHECK_AT_FREE \ (1 << PG_lru | 1 << PG_locked | \ 1 << PG_private | 1 << PG_private_2 | \ - 1 << PG_buddy | 1 << PG_writeback | 1 << PG_reserved | \ + 1 << PG_writeback | 1 << PG_reserved | \ 1 << PG_slab | 1 << PG_swapcache | 1 << PG_active | \ 1 << PG_unevictable | __PG_MLOCKED | __PG_HWPOISON | \ __PG_COMPOUND_LOCK) diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index a2832c092509..e92f04749fcb 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -82,9 +82,10 @@ static void release_memory_resource(struct resource *res) #ifdef CONFIG_MEMORY_HOTPLUG_SPARSE #ifndef CONFIG_SPARSEMEM_VMEMMAP -static void get_page_bootmem(unsigned long info, struct page *page, int type) +static void get_page_bootmem(unsigned long info, struct page *page, + unsigned long type) { - atomic_set(&page->_mapcount, type); + page->lru.next = (struct list_head *) type; SetPagePrivate(page); set_page_private(page, info); atomic_inc(&page->_count); @@ -94,15 +95,16 @@ static void get_page_bootmem(unsigned long info, struct page *page, int type) * so use __ref to tell modpost not to generate a warning */ void __ref put_page_bootmem(struct page *page) { - int type; + unsigned long type; - type = atomic_read(&page->_mapcount); - BUG_ON(type >= -1); + type = (unsigned long) page->lru.next; + BUG_ON(type < MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE || + type > MEMORY_HOTPLUG_MAX_BOOTMEM_TYPE); if (atomic_dec_return(&page->_count) == 1) { ClearPagePrivate(page); set_page_private(page, 0); - reset_page_mapcount(page); + INIT_LIST_HEAD(&page->lru); __free_pages_bootmem(page, 0); } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index e7664b9f706c..9dfe49bceff4 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -449,8 +449,8 @@ __find_combined_index(unsigned long page_idx, unsigned int order) * (c) a page and its buddy have the same order && * (d) a page and its buddy are in the same zone. * - * For recording whether a page is in the buddy system, we use PG_buddy. - * Setting, clearing, and testing PG_buddy is serialized by zone->lock. + * For recording whether a page is in the buddy system, we set ->_mapcount -2. + * Setting, clearing, and testing _mapcount -2 is serialized by zone->lock. * * For recording page's order, we use page_private(page). */ @@ -483,7 +483,7 @@ static inline int page_is_buddy(struct page *page, struct page *buddy, * as necessary, plus some accounting needed to play nicely with other * parts of the VM system. * At each level, we keep a list of pages, which are heads of continuous - * free pages of length of (1 << order) and marked with PG_buddy. Page's + * free pages of length of (1 << order) and marked with _mapcount -2. Page's * order is recorded in page_private(page) field. * So when we are allocating or freeing one, we can derive the state of the * other. That is, if we allocate a small block, and both were @@ -5574,7 +5574,6 @@ static struct trace_print_flags pageflag_names[] = { {1UL << PG_swapcache, "swapcache" }, {1UL << PG_mappedtodisk, "mappedtodisk" }, {1UL << PG_reclaim, "reclaim" }, - {1UL << PG_buddy, "buddy" }, {1UL << PG_swapbacked, "swapbacked" }, {1UL << PG_unevictable, "unevictable" }, #ifdef CONFIG_MMU diff --git a/mm/sparse.c b/mm/sparse.c index 95ac219af379..93250207c5cf 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -671,10 +671,10 @@ static void __kfree_section_memmap(struct page *memmap, unsigned long nr_pages) static void free_map_bootmem(struct page *page, unsigned long nr_pages) { unsigned long maps_section_nr, removing_section_nr, i; - int magic; + unsigned long magic; for (i = 0; i < nr_pages; i++, page++) { - magic = atomic_read(&page->_mapcount); + magic = (unsigned long) page->lru.next; BUG_ON(magic == NODE_INFO); -- cgit v1.2.3-59-g8ed1b From 43506fad21ca3d8dc59e768ff458f7c5e5c01086 Mon Sep 17 00:00:00 2001 From: KyongHo Cho Date: Thu, 13 Jan 2011 15:47:24 -0800 Subject: mm/page_alloc.c: simplify calculation of combined index of adjacent buddy lists The previous approach of calucation of combined index was page_idx & ~(1 << order)) but we have same result with page_idx & buddy_idx This reduces instructions slightly as well as enhances readability. [akpm@linux-foundation.org: coding-style fixes] [akpm@linux-foundation.org: fix used-unintialised warning] Signed-off-by: KyongHo Cho Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 25 ++++++++++--------------- 1 file changed, 10 insertions(+), 15 deletions(-) (limited to 'mm/page_alloc.c') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 9dfe49bceff4..bda1db301d44 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -427,18 +427,10 @@ static inline void rmv_page_order(struct page *page) * * Assumption: *_mem_map is contiguous at least up to MAX_ORDER */ -static inline struct page * -__page_find_buddy(struct page *page, unsigned long page_idx, unsigned int order) -{ - unsigned long buddy_idx = page_idx ^ (1 << order); - - return page + (buddy_idx - page_idx); -} - static inline unsigned long -__find_combined_index(unsigned long page_idx, unsigned int order) +__find_buddy_index(unsigned long page_idx, unsigned int order) { - return (page_idx & ~(1 << order)); + return page_idx ^ (1 << order); } /* @@ -500,6 +492,7 @@ static inline void __free_one_page(struct page *page, { unsigned long page_idx; unsigned long combined_idx; + unsigned long uninitialized_var(buddy_idx); struct page *buddy; if (unlikely(PageCompound(page))) @@ -514,7 +507,8 @@ static inline void __free_one_page(struct page *page, VM_BUG_ON(bad_range(zone, page)); while (order < MAX_ORDER-1) { - buddy = __page_find_buddy(page, page_idx, order); + buddy_idx = __find_buddy_index(page_idx, order); + buddy = page + (buddy_idx - page_idx); if (!page_is_buddy(page, buddy, order)) break; @@ -522,7 +516,7 @@ static inline void __free_one_page(struct page *page, list_del(&buddy->lru); zone->free_area[order].nr_free--; rmv_page_order(buddy); - combined_idx = __find_combined_index(page_idx, order); + combined_idx = buddy_idx & page_idx; page = page + (combined_idx - page_idx); page_idx = combined_idx; order++; @@ -539,9 +533,10 @@ static inline void __free_one_page(struct page *page, */ if ((order < MAX_ORDER-2) && pfn_valid_within(page_to_pfn(buddy))) { struct page *higher_page, *higher_buddy; - combined_idx = __find_combined_index(page_idx, order); - higher_page = page + combined_idx - page_idx; - higher_buddy = __page_find_buddy(higher_page, combined_idx, order + 1); + combined_idx = buddy_idx & page_idx; + higher_page = page + (combined_idx - page_idx); + buddy_idx = __find_buddy_index(combined_idx, order + 1); + higher_buddy = page + (buddy_idx - combined_idx); if (page_is_buddy(higher_page, higher_buddy, order + 1)) { list_add_tail(&page->lru, &zone->free_area[order].free_list[migratetype]); -- cgit v1.2.3-59-g8ed1b From c06b1fca18c3ad868bfcaca230146e3038583422 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Thu, 13 Jan 2011 15:47:32 -0800 Subject: mm/page_alloc.c: don't cache `current' in a local It's old-fashioned and unneeded. akpm:/usr/src/25> size mm/page_alloc.o text data bss dec hex filename 39884 1241317 18808 1300009 13d629 mm/page_alloc.o (before) 39838 1241317 18808 1299963 13d5fb mm/page_alloc.o (after) Acked-by: David Rientjes Acked-by: Mel Gorman Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 24 ++++++++++-------------- 1 file changed, 10 insertions(+), 14 deletions(-) (limited to 'mm/page_alloc.c') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index bda1db301d44..90c1439549fd 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1809,15 +1809,14 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, bool sync_migration) { struct page *page; - struct task_struct *tsk = current; if (!order || compaction_deferred(preferred_zone)) return NULL; - tsk->flags |= PF_MEMALLOC; + current->flags |= PF_MEMALLOC; *did_some_progress = try_to_compact_pages(zonelist, order, gfp_mask, nodemask, sync_migration); - tsk->flags &= ~PF_MEMALLOC; + current->flags &= ~PF_MEMALLOC; if (*did_some_progress != COMPACT_SKIPPED) { /* Page migration frees to the PCP lists but we want merging */ @@ -1869,23 +1868,22 @@ __alloc_pages_direct_reclaim(gfp_t gfp_mask, unsigned int order, { struct page *page = NULL; struct reclaim_state reclaim_state; - struct task_struct *p = current; bool drained = false; cond_resched(); /* We now go into synchronous reclaim */ cpuset_memory_pressure_bump(); - p->flags |= PF_MEMALLOC; + current->flags |= PF_MEMALLOC; lockdep_set_current_reclaim_state(gfp_mask); reclaim_state.reclaimed_slab = 0; - p->reclaim_state = &reclaim_state; + current->reclaim_state = &reclaim_state; *did_some_progress = try_to_free_pages(zonelist, order, gfp_mask, nodemask); - p->reclaim_state = NULL; + current->reclaim_state = NULL; lockdep_clear_current_reclaim_state(); - p->flags &= ~PF_MEMALLOC; + current->flags &= ~PF_MEMALLOC; cond_resched(); @@ -1950,7 +1948,6 @@ void wake_all_kswapd(unsigned int order, struct zonelist *zonelist, static inline int gfp_to_alloc_flags(gfp_t gfp_mask) { - struct task_struct *p = current; int alloc_flags = ALLOC_WMARK_MIN | ALLOC_CPUSET; const gfp_t wait = gfp_mask & __GFP_WAIT; @@ -1977,12 +1974,12 @@ 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)) && !in_interrupt()) + } else if (unlikely(rt_task(current)) && !in_interrupt()) alloc_flags |= ALLOC_HARDER; if (likely(!(gfp_mask & __GFP_NOMEMALLOC))) { if (!in_interrupt() && - ((p->flags & PF_MEMALLOC) || + ((current->flags & PF_MEMALLOC) || unlikely(test_thread_flag(TIF_MEMDIE)))) alloc_flags |= ALLOC_NO_WATERMARKS; } @@ -2001,7 +1998,6 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, int alloc_flags; unsigned long pages_reclaimed = 0; unsigned long did_some_progress; - struct task_struct *p = current; bool sync_migration = false; /* @@ -2060,7 +2056,7 @@ rebalance: goto nopage; /* Avoid recursion of direct reclaim */ - if (p->flags & PF_MEMALLOC) + if (current->flags & PF_MEMALLOC) goto nopage; /* Avoid allocations with no watermarks from looping endlessly */ @@ -2153,7 +2149,7 @@ nopage: if (!(gfp_mask & __GFP_NOWARN) && printk_ratelimit()) { printk(KERN_WARNING "%s: page allocation failure." " order:%d, mode:0x%x\n", - p->comm, order, gfp_mask); + current->comm, order, gfp_mask); dump_stack(); show_mem(); } -- cgit v1.2.3-59-g8ed1b From f33261d75b88f55a08e6a9648cef73509979bfba Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Tue, 25 Jan 2011 15:07:20 -0800 Subject: mm: fix deferred congestion timeout if preferred zone is not allowed Before 0e093d99763e ("writeback: do not sleep on the congestion queue if there are no congested BDIs or if significant congestion is not being encountered in the current zone"), preferred_zone was only used for NUMA statistics, to determine the zoneidx from which to allocate from given the type requested, and whether to utilize memory compaction. wait_iff_congested(), though, uses preferred_zone to determine if the congestion wait should be deferred because its dirty pages are backed by a congested bdi. This incorrectly defers the timeout and busy loops in the page allocator with various cond_resched() calls if preferred_zone is not allowed in the current context, usually consuming 100% of a cpu. This patch ensures preferred_zone is an allowed zone in the fastpath depending on whether current is constrained by its cpuset or nodes in its mempolicy (when the nodemask passed is non-NULL). This is correct since the fastpath allocation always passes ALLOC_CPUSET when trying to allocate memory. In the slowpath, this patch resets preferred_zone to the first zone of the allowed type when the allocation is not constrained by current's cpuset, i.e. it does not pass ALLOC_CPUSET. This patch also ensures preferred_zone is from the set of allowed nodes when called from within direct reclaim since allocations are always constrained by cpusets in this context (it is blockable). Both of these uses of cpuset_current_mems_allowed are protected by get_mems_allowed(). Signed-off-by: David Rientjes Cc: Mel Gorman Cc: Johannes Weiner Cc: Minchan Kim Cc: Wu Fengguang Cc: KAMEZAWA Hiroyuki Cc: KOSAKI Motohiro Acked-by: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 12 +++++++++++- mm/vmscan.c | 3 ++- 2 files changed, 13 insertions(+), 2 deletions(-) (limited to 'mm/page_alloc.c') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 90c1439549fd..f4967910c967 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2034,6 +2034,14 @@ restart: */ alloc_flags = gfp_to_alloc_flags(gfp_mask); + /* + * Find the true preferred zone if the allocation is unconstrained by + * cpusets. + */ + if (!(alloc_flags & ALLOC_CPUSET) && !nodemask) + first_zones_zonelist(zonelist, high_zoneidx, NULL, + &preferred_zone); + /* This is the last chance, in general, before the goto nopage. */ page = get_page_from_freelist(gfp_mask, nodemask, order, zonelist, high_zoneidx, alloc_flags & ~ALLOC_NO_WATERMARKS, @@ -2192,7 +2200,9 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, get_mems_allowed(); /* The preferred zone is used for statistics later */ - first_zones_zonelist(zonelist, high_zoneidx, nodemask, &preferred_zone); + first_zones_zonelist(zonelist, high_zoneidx, + nodemask ? : &cpuset_current_mems_allowed, + &preferred_zone); if (!preferred_zone) { put_mems_allowed(); return NULL; diff --git a/mm/vmscan.c b/mm/vmscan.c index f5d90dedebba..148c6e630df2 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2083,7 +2083,8 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, struct zone *preferred_zone; first_zones_zonelist(zonelist, gfp_zone(sc->gfp_mask), - NULL, &preferred_zone); + &cpuset_current_mems_allowed, + &preferred_zone); wait_iff_congested(preferred_zone, BLK_RW_ASYNC, HZ/10); } } -- cgit v1.2.3-59-g8ed1b From 2ff754fa8f416e82327f2d8f1354a033b66286df Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Tue, 25 Jan 2011 15:07:23 -0800 Subject: mm: clear pages_scanned only if draining a pcp adds pages to the buddy allocator Commit 0e093d99763e ("writeback: do not sleep on the congestion queue if there are no congested BDIs or if significant congestion is not being encountered in the current zone") uncovered a livelock in the page allocator that resulted in tasks infinitely looping trying to find memory and kswapd running at 100% cpu. The issue occurs because drain_all_pages() is called immediately following direct reclaim when no memory is freed and try_to_free_pages() returns non-zero because all zones in the zonelist do not have their all_unreclaimable flag set. When draining the per-cpu pagesets back to the buddy allocator for each zone, the zone->pages_scanned counter is cleared to avoid erroneously setting zone->all_unreclaimable later. The problem is that no pages may actually be drained and, thus, the unreclaimable logic never fails direct reclaim so the oom killer may be invoked. This apparently only manifested after wait_iff_congested() was introduced and the zone was full of anonymous memory that would not congest the backing store. The page allocator would infinitely loop if there were no other tasks waiting to be scheduled and clear zone->pages_scanned because of drain_all_pages() as the result of this change before kswapd could scan enough pages to trigger the reclaim logic. Additionally, with every loop of the page allocator and in the reclaim path, kswapd would be kicked and would end up running at 100% cpu. In this scenario, current and kswapd are all running continuously with kswapd incrementing zone->pages_scanned and current clearing it. The problem is even more pronounced when current swaps some of its memory to swap cache and the reclaimable logic then considers all active anonymous memory in the all_unreclaimable logic, which requires a much higher zone->pages_scanned value for try_to_free_pages() to return zero that is never attainable in this scenario. Before wait_iff_congested(), the page allocator would incur an unconditional timeout and allow kswapd to elevate zone->pages_scanned to a level that the oom killer would be called the next time it loops. The fix is to only attempt to drain pcp pages if there is actually a quantity to be drained. The unconditional clearing of zone->pages_scanned in free_pcppages_bulk() need not be changed since other callers already ensure that draining will occur. This patch ensures that free_pcppages_bulk() will actually free memory before calling into it from drain_all_pages() so zone->pages_scanned is only cleared if appropriate. Signed-off-by: David Rientjes Cc: Mel Gorman Reviewed-by: Johannes Weiner Cc: Minchan Kim Cc: Wu Fengguang Cc: KAMEZAWA Hiroyuki Cc: KOSAKI Motohiro Reviewed-by: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'mm/page_alloc.c') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index f4967910c967..a873e61e312e 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1088,8 +1088,10 @@ static void drain_pages(unsigned int cpu) pset = per_cpu_ptr(zone->pageset, cpu); pcp = &pset->pcp; - free_pcppages_bulk(zone, pcp->count, pcp); - pcp->count = 0; + if (pcp->count) { + free_pcppages_bulk(zone, pcp->count, pcp); + pcp->count = 0; + } local_irq_restore(flags); } } -- cgit v1.2.3-59-g8ed1b