X-Git-Url: http://git.pld-linux.org/?a=blobdiff_plain;f=kernel-small_fixes.patch;h=12130347edfedd51684642703b98acab57e2463f;hb=4e1a4c84e6398a77c78048ea1fa3fe653dce7712;hp=a0928ee62871ca10c67827acbc6519ca0355b3af;hpb=b95c51470294fc508076f9bb98e28c31db8eabaa;p=packages%2Fkernel.git diff --git a/kernel-small_fixes.patch b/kernel-small_fixes.patch index a0928ee6..12130347 100644 --- a/kernel-small_fixes.patch +++ b/kernel-small_fixes.patch @@ -27,646 +27,45 @@ fi done -From 7a29ac474a47eb8cf212b45917683ae89d6fa13b Mon Sep 17 00:00:00 2001 -From: Chris Mason -Date: Tue, 10 Nov 2015 10:10:34 +1100 -Subject: xfs: give all workqueues rescuer threads +From: Shaohua Li -We're consistently hitting deadlocks here with XFS on recent kernels. -After some digging through the crash files, it looks like everyone in -the system is waiting for XFS to reclaim memory. +Basically this is a copy of commit 001e4a8775f6(ext4: implement cgroup +writeback support). Tested with a fio test, verified writeback is +throttled against cgroup io.max write bandwidth, also verified moving +the fio test to another cgroup and the writeback is throttled against +new cgroup setting. -Something like this: - -PID: 2733434 TASK: ffff8808cd242800 CPU: 19 COMMAND: "java" - #0 [ffff880019c53588] __schedule at ffffffff818c4df2 - #1 [ffff880019c535d8] schedule at ffffffff818c5517 - #2 [ffff880019c535f8] _xfs_log_force_lsn at ffffffff81316348 - #3 [ffff880019c53688] xfs_log_force_lsn at ffffffff813164fb - #4 [ffff880019c536b8] xfs_iunpin_wait at ffffffff8130835e - #5 [ffff880019c53728] xfs_reclaim_inode at ffffffff812fd453 - #6 [ffff880019c53778] xfs_reclaim_inodes_ag at ffffffff812fd8c7 - #7 [ffff880019c53928] xfs_reclaim_inodes_nr at ffffffff812fe433 - #8 [ffff880019c53958] xfs_fs_free_cached_objects at ffffffff8130d3b9 - #9 [ffff880019c53968] super_cache_scan at ffffffff811a6f73 -#10 [ffff880019c539c8] shrink_slab at ffffffff811460e6 -#11 [ffff880019c53aa8] shrink_zone at ffffffff8114a53f -#12 [ffff880019c53b48] do_try_to_free_pages at ffffffff8114a8ba -#13 [ffff880019c53be8] try_to_free_pages at ffffffff8114ad5a -#14 [ffff880019c53c78] __alloc_pages_nodemask at ffffffff8113e1b8 -#15 [ffff880019c53d88] alloc_kmem_pages_node at ffffffff8113e671 -#16 [ffff880019c53dd8] copy_process at ffffffff8104f781 -#17 [ffff880019c53ec8] do_fork at ffffffff8105129c -#18 [ffff880019c53f38] sys_clone at ffffffff810515b6 -#19 [ffff880019c53f48] stub_clone at ffffffff818c8e4d - -xfs_log_force_lsn is waiting for logs to get cleaned, which is waiting -for IO, which is waiting for workers to complete the IO which is waiting -for worker threads that don't exist yet: - -PID: 2752451 TASK: ffff880bd6bdda00 CPU: 37 COMMAND: "kworker/37:1" - #0 [ffff8808d20abbb0] __schedule at ffffffff818c4df2 - #1 [ffff8808d20abc00] schedule at ffffffff818c5517 - #2 [ffff8808d20abc20] schedule_timeout at ffffffff818c7c6c - #3 [ffff8808d20abcc0] wait_for_completion_killable at ffffffff818c6495 - #4 [ffff8808d20abd30] kthread_create_on_node at ffffffff8106ec82 - #5 [ffff8808d20abdf0] create_worker at ffffffff8106752f - #6 [ffff8808d20abe40] worker_thread at ffffffff810699be - #7 [ffff8808d20abec0] kthread at ffffffff8106ef59 - #8 [ffff8808d20abf50] ret_from_fork at ffffffff818c8ac8 - -I think we should be using WQ_MEM_RECLAIM to make sure this thread -pool makes progress when we're not able to allocate new workers. - -[dchinner: make all workqueues WQ_MEM_RECLAIM] - -Signed-off-by: Chris Mason -Reviewed-by: Dave Chinner -Signed-off-by: Dave Chinner +Cc: Tejun Heo +Signed-off-by: Shaohua Li --- - fs/xfs/xfs_super.c | 7 ++++--- - 1 file changed, 4 insertions(+), 3 deletions(-) - + fs/xfs/xfs_aops.c | 2 ++ + fs/xfs/xfs_super.c | 1 + + 2 files changed, 3 insertions(+) + +diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c +index f18e593..6535054 100644 +--- a/fs/xfs/xfs_aops.c ++++ b/fs/xfs/xfs_aops.c +@@ -630,8 +630,10 @@ xfs_add_to_ioend( + if (wpc->ioend) + list_add(&wpc->ioend->io_list, iolist); + wpc->ioend = xfs_alloc_ioend(inode, wpc->io_type, offset, bh); ++ wbc_init_bio(wbc, wpc->ioend->io_bio); + } + ++ wbc_account_io(wbc, bh->b_page, bh->b_size); + /* + * If the buffer doesn't fit into the bio we need to allocate a new + * one. This shouldn't happen more than once for a given buffer. diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c -index 29531ec..65fbfb7 100644 +index 584cf2d..aea3bc2 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c -@@ -838,17 +838,18 @@ xfs_init_mount_workqueues( - goto out_destroy_unwritten; - - mp->m_reclaim_workqueue = alloc_workqueue("xfs-reclaim/%s", -- WQ_FREEZABLE, 0, mp->m_fsname); -+ WQ_MEM_RECLAIM|WQ_FREEZABLE, 0, mp->m_fsname); - if (!mp->m_reclaim_workqueue) - goto out_destroy_cil; - - mp->m_log_workqueue = alloc_workqueue("xfs-log/%s", -- WQ_FREEZABLE|WQ_HIGHPRI, 0, mp->m_fsname); -+ WQ_MEM_RECLAIM|WQ_FREEZABLE|WQ_HIGHPRI, 0, -+ mp->m_fsname); - if (!mp->m_log_workqueue) - goto out_destroy_reclaim; - - mp->m_eofblocks_workqueue = alloc_workqueue("xfs-eofblocks/%s", -- WQ_FREEZABLE, 0, mp->m_fsname); -+ WQ_MEM_RECLAIM|WQ_FREEZABLE, 0, mp->m_fsname); - if (!mp->m_eofblocks_workqueue) - goto out_destroy_log; - --- -cgit v0.11.2 - -commit c2d42c16ad83006a706d83e51a7268db04af733a -Author: Andrew Morton -Date: Thu Nov 5 18:48:43 2015 -0800 - - mm/vmstat.c: uninline node_page_state() - - With x86_64 (config http://ozlabs.org/~akpm/config-akpm2.txt) and old gcc - (4.4.4), drivers/base/node.c:node_read_meminfo() is using 2344 bytes of - stack. Uninlining node_page_state() reduces this to 440 bytes. - - The stack consumption issue is fixed by newer gcc (4.8.4) however with - that compiler this patch reduces the node.o text size from 7314 bytes to - 4578. - - Signed-off-by: Andrew Morton - Signed-off-by: Linus Torvalds - -diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h -index 82e7db7..49dfe40 100644 ---- a/include/linux/vmstat.h -+++ b/include/linux/vmstat.h -@@ -161,30 +161,8 @@ static inline unsigned long zone_page_state_snapshot(struct zone *zone, - } - - #ifdef CONFIG_NUMA --/* -- * Determine the per node value of a stat item. This function -- * is called frequently in a NUMA machine, so try to be as -- * frugal as possible. -- */ --static inline unsigned long node_page_state(int node, -- enum zone_stat_item item) --{ -- struct zone *zones = NODE_DATA(node)->node_zones; -- -- return --#ifdef CONFIG_ZONE_DMA -- zone_page_state(&zones[ZONE_DMA], item) + --#endif --#ifdef CONFIG_ZONE_DMA32 -- zone_page_state(&zones[ZONE_DMA32], item) + --#endif --#ifdef CONFIG_HIGHMEM -- zone_page_state(&zones[ZONE_HIGHMEM], item) + --#endif -- zone_page_state(&zones[ZONE_NORMAL], item) + -- zone_page_state(&zones[ZONE_MOVABLE], item); --} - -+extern unsigned long node_page_state(int node, enum zone_stat_item item); - extern void zone_statistics(struct zone *, struct zone *, gfp_t gfp); - - #else -diff --git a/mm/vmstat.c b/mm/vmstat.c -index fbf1448..ffcb4f5 100644 ---- a/mm/vmstat.c -+++ b/mm/vmstat.c -@@ -591,6 +591,28 @@ void zone_statistics(struct zone *preferred_zone, struct zone *z, gfp_t flags) - else - __inc_zone_state(z, NUMA_OTHER); - } -+ -+/* -+ * Determine the per node value of a stat item. -+ */ -+unsigned long node_page_state(int node, enum zone_stat_item item) -+{ -+ struct zone *zones = NODE_DATA(node)->node_zones; -+ -+ return -+#ifdef CONFIG_ZONE_DMA -+ zone_page_state(&zones[ZONE_DMA], item) + -+#endif -+#ifdef CONFIG_ZONE_DMA32 -+ zone_page_state(&zones[ZONE_DMA32], item) + -+#endif -+#ifdef CONFIG_HIGHMEM -+ zone_page_state(&zones[ZONE_HIGHMEM], item) + -+#endif -+ zone_page_state(&zones[ZONE_NORMAL], item) + -+ zone_page_state(&zones[ZONE_MOVABLE], item); -+} -+ - #endif - - #ifdef CONFIG_COMPACTION -commit 016c13daa5c9e4827eca703e2f0621c131f2cca3 -Author: Mel Gorman -Date: Fri Nov 6 16:28:18 2015 -0800 - - mm, page_alloc: use masks and shifts when converting GFP flags to migrate types - - This patch redefines which GFP bits are used for specifying mobility and - the order of the migrate types. Once redefined it's possible to convert - GFP flags to a migrate type with a simple mask and shift. The only - downside is that readers of OOM kill messages and allocation failures may - have been used to the existing values but scripts/gfp-translate will help. - - Signed-off-by: Mel Gorman - Acked-by: Vlastimil Babka - Cc: Christoph Lameter - Cc: David Rientjes - Cc: Johannes Weiner - Cc: Michal Hocko - Cc: Vitaly Wool - Cc: Rik van Riel - Signed-off-by: Andrew Morton - Signed-off-by: Linus Torvalds - -diff --git a/include/linux/gfp.h b/include/linux/gfp.h -index f92cbd2..440fca3 100644 ---- a/include/linux/gfp.h -+++ b/include/linux/gfp.h -@@ -14,7 +14,7 @@ struct vm_area_struct; - #define ___GFP_HIGHMEM 0x02u - #define ___GFP_DMA32 0x04u - #define ___GFP_MOVABLE 0x08u --#define ___GFP_WAIT 0x10u -+#define ___GFP_RECLAIMABLE 0x10u - #define ___GFP_HIGH 0x20u - #define ___GFP_IO 0x40u - #define ___GFP_FS 0x80u -@@ -29,7 +29,7 @@ struct vm_area_struct; - #define ___GFP_NOMEMALLOC 0x10000u - #define ___GFP_HARDWALL 0x20000u - #define ___GFP_THISNODE 0x40000u --#define ___GFP_RECLAIMABLE 0x80000u -+#define ___GFP_WAIT 0x80000u - #define ___GFP_NOACCOUNT 0x100000u - #define ___GFP_NOTRACK 0x200000u - #define ___GFP_NO_KSWAPD 0x400000u -@@ -126,6 +126,7 @@ struct vm_area_struct; - - /* This mask makes up all the page movable related flags */ - #define GFP_MOVABLE_MASK (__GFP_RECLAIMABLE|__GFP_MOVABLE) -+#define GFP_MOVABLE_SHIFT 3 - - /* Control page allocator reclaim behavior */ - #define GFP_RECLAIM_MASK (__GFP_WAIT|__GFP_HIGH|__GFP_IO|__GFP_FS|\ -@@ -152,14 +153,15 @@ struct vm_area_struct; - /* Convert GFP flags to their corresponding migrate type */ - static inline int gfpflags_to_migratetype(const gfp_t gfp_flags) - { -- WARN_ON((gfp_flags & GFP_MOVABLE_MASK) == GFP_MOVABLE_MASK); -+ VM_WARN_ON((gfp_flags & GFP_MOVABLE_MASK) == GFP_MOVABLE_MASK); -+ BUILD_BUG_ON((1UL << GFP_MOVABLE_SHIFT) != ___GFP_MOVABLE); -+ BUILD_BUG_ON((___GFP_MOVABLE >> GFP_MOVABLE_SHIFT) != MIGRATE_MOVABLE); - - if (unlikely(page_group_by_mobility_disabled)) - return MIGRATE_UNMOVABLE; - - /* Group based on mobility */ -- return (((gfp_flags & __GFP_MOVABLE) != 0) << 1) | -- ((gfp_flags & __GFP_RECLAIMABLE) != 0); -+ return (gfp_flags & GFP_MOVABLE_MASK) >> GFP_MOVABLE_SHIFT; - } - - #ifdef CONFIG_HIGHMEM -diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h -index e326843..38bed71 100644 ---- a/include/linux/mmzone.h -+++ b/include/linux/mmzone.h -@@ -37,8 +37,8 @@ - - enum { - MIGRATE_UNMOVABLE, -- MIGRATE_RECLAIMABLE, - MIGRATE_MOVABLE, -+ MIGRATE_RECLAIMABLE, - MIGRATE_PCPTYPES, /* the number of types on the pcp lists */ - MIGRATE_RESERVE = MIGRATE_PCPTYPES, - #ifdef CONFIG_CMA -commit 974a786e63c96a2401a78ddba926f34c128474f1 -Author: Mel Gorman -Date: Fri Nov 6 16:28:34 2015 -0800 - - mm, page_alloc: remove MIGRATE_RESERVE - - MIGRATE_RESERVE preserves an old property of the buddy allocator that - existed prior to fragmentation avoidance -- min_free_kbytes worth of pages - tended to remain contiguous until the only alternative was to fail the - allocation. At the time it was discovered that high-order atomic - allocations relied on this property so MIGRATE_RESERVE was introduced. A - later patch will introduce an alternative MIGRATE_HIGHATOMIC so this patch - deletes MIGRATE_RESERVE and supporting code so it'll be easier to review. - Note that this patch in isolation may look like a false regression if - someone was bisecting high-order atomic allocation failures. - - Signed-off-by: Mel Gorman - Acked-by: Vlastimil Babka - Cc: Christoph Lameter - Cc: David Rientjes - Cc: Johannes Weiner - Cc: Michal Hocko - Cc: Vitaly Wool - Cc: Rik van Riel - Signed-off-by: Andrew Morton - Signed-off-by: Linus Torvalds - -diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h -index 1e88aae..b86cfa3 100644 ---- a/include/linux/mmzone.h -+++ b/include/linux/mmzone.h -@@ -39,8 +39,6 @@ enum { - MIGRATE_UNMOVABLE, - MIGRATE_MOVABLE, - MIGRATE_RECLAIMABLE, -- MIGRATE_PCPTYPES, /* the number of types on the pcp lists */ -- MIGRATE_RESERVE = MIGRATE_PCPTYPES, - #ifdef CONFIG_CMA - /* - * MIGRATE_CMA migration type is designed to mimic the way -@@ -63,6 +61,8 @@ enum { - MIGRATE_TYPES - }; - -+#define MIGRATE_PCPTYPES (MIGRATE_RECLAIMABLE+1) -+ - #ifdef CONFIG_CMA - # define is_migrate_cma(migratetype) unlikely((migratetype) == MIGRATE_CMA) - #else -@@ -429,12 +429,6 @@ struct zone { - - const char *name; - -- /* -- * Number of MIGRATE_RESERVE page block. To maintain for just -- * optimization. Protected by zone->lock. -- */ -- int nr_migrate_reserve_block; -- - #ifdef CONFIG_MEMORY_ISOLATION - /* - * Number of isolated pageblock. It is used to solve incorrect -diff --git a/mm/huge_memory.c b/mm/huge_memory.c -index 9812d46..dabd247 100644 ---- a/mm/huge_memory.c -+++ b/mm/huge_memory.c -@@ -116,7 +116,7 @@ static void set_recommended_min_free_kbytes(void) - for_each_populated_zone(zone) - nr_zones++; - -- /* Make sure at least 2 hugepages are free for MIGRATE_RESERVE */ -+ /* Ensure 2 pageblocks are free to assist fragmentation avoidance */ - recommended_min = pageblock_nr_pages * nr_zones * 2; - - /* -diff --git a/mm/page_alloc.c b/mm/page_alloc.c -index 8dc6e3c..5888126 100644 ---- a/mm/page_alloc.c -+++ b/mm/page_alloc.c -@@ -817,7 +817,6 @@ static void free_pcppages_bulk(struct zone *zone, int count, - if (unlikely(has_isolate_pageblock(zone))) - mt = get_pageblock_migratetype(page); - -- /* MIGRATE_MOVABLE list may include MIGRATE_RESERVEs */ - __free_one_page(page, page_to_pfn(page), zone, 0, mt); - trace_mm_page_pcpu_drain(page, 0, mt); - } while (--to_free && --batch_free && !list_empty(list)); -@@ -1417,15 +1416,14 @@ struct page *__rmqueue_smallest(struct zone *zone, unsigned int order, - * the free lists for the desirable migrate type are depleted - */ - static int fallbacks[MIGRATE_TYPES][4] = { -- [MIGRATE_UNMOVABLE] = { MIGRATE_RECLAIMABLE, MIGRATE_MOVABLE, MIGRATE_RESERVE }, -- [MIGRATE_RECLAIMABLE] = { MIGRATE_UNMOVABLE, MIGRATE_MOVABLE, MIGRATE_RESERVE }, -- [MIGRATE_MOVABLE] = { MIGRATE_RECLAIMABLE, MIGRATE_UNMOVABLE, MIGRATE_RESERVE }, -+ [MIGRATE_UNMOVABLE] = { MIGRATE_RECLAIMABLE, MIGRATE_MOVABLE, MIGRATE_TYPES }, -+ [MIGRATE_RECLAIMABLE] = { MIGRATE_UNMOVABLE, MIGRATE_MOVABLE, MIGRATE_TYPES }, -+ [MIGRATE_MOVABLE] = { MIGRATE_RECLAIMABLE, MIGRATE_UNMOVABLE, MIGRATE_TYPES }, - #ifdef CONFIG_CMA -- [MIGRATE_CMA] = { MIGRATE_RESERVE }, /* Never used */ -+ [MIGRATE_CMA] = { MIGRATE_TYPES }, /* Never used */ - #endif -- [MIGRATE_RESERVE] = { MIGRATE_RESERVE }, /* Never used */ - #ifdef CONFIG_MEMORY_ISOLATION -- [MIGRATE_ISOLATE] = { MIGRATE_RESERVE }, /* Never used */ -+ [MIGRATE_ISOLATE] = { MIGRATE_TYPES }, /* Never used */ - #endif - }; - -@@ -1598,7 +1596,7 @@ int find_suitable_fallback(struct free_area *area, unsigned int order, - *can_steal = false; - for (i = 0;; i++) { - fallback_mt = fallbacks[migratetype][i]; -- if (fallback_mt == MIGRATE_RESERVE) -+ if (fallback_mt == MIGRATE_TYPES) - break; - - if (list_empty(&area->free_list[fallback_mt])) -@@ -1676,25 +1674,13 @@ static struct page *__rmqueue(struct zone *zone, unsigned int order, - { - struct page *page; - --retry_reserve: - page = __rmqueue_smallest(zone, order, migratetype); -- -- if (unlikely(!page) && migratetype != MIGRATE_RESERVE) { -+ if (unlikely(!page)) { - if (migratetype == MIGRATE_MOVABLE) - page = __rmqueue_cma_fallback(zone, order); - - if (!page) - page = __rmqueue_fallback(zone, order, migratetype); -- -- /* -- * Use MIGRATE_RESERVE rather than fail an allocation. goto -- * is used because __rmqueue_smallest is an inline function -- * and we want just one call site -- */ -- if (!page) { -- migratetype = MIGRATE_RESERVE; -- goto retry_reserve; -- } - } - - trace_mm_page_alloc_zone_locked(page, order, migratetype); -@@ -3492,7 +3478,6 @@ static void show_migration_types(unsigned char type) - [MIGRATE_UNMOVABLE] = 'U', - [MIGRATE_RECLAIMABLE] = 'E', - [MIGRATE_MOVABLE] = 'M', -- [MIGRATE_RESERVE] = 'R', - #ifdef CONFIG_CMA - [MIGRATE_CMA] = 'C', - #endif -@@ -4303,120 +4288,6 @@ static inline unsigned long wait_table_bits(unsigned long size) - } - - /* -- * Check if a pageblock contains reserved pages -- */ --static int pageblock_is_reserved(unsigned long start_pfn, unsigned long end_pfn) --{ -- unsigned long pfn; -- -- for (pfn = start_pfn; pfn < end_pfn; pfn++) { -- if (!pfn_valid_within(pfn) || PageReserved(pfn_to_page(pfn))) -- return 1; -- } -- return 0; --} -- --/* -- * Mark a number of pageblocks as MIGRATE_RESERVE. The number -- * of blocks reserved is based on min_wmark_pages(zone). The memory within -- * the reserve will tend to store contiguous free pages. Setting min_free_kbytes -- * higher will lead to a bigger reserve which will get freed as contiguous -- * blocks as reclaim kicks in -- */ --static void setup_zone_migrate_reserve(struct zone *zone) --{ -- unsigned long start_pfn, pfn, end_pfn, block_end_pfn; -- struct page *page; -- unsigned long block_migratetype; -- int reserve; -- int old_reserve; -- -- /* -- * Get the start pfn, end pfn and the number of blocks to reserve -- * We have to be careful to be aligned to pageblock_nr_pages to -- * make sure that we always check pfn_valid for the first page in -- * the block. -- */ -- start_pfn = zone->zone_start_pfn; -- end_pfn = zone_end_pfn(zone); -- start_pfn = roundup(start_pfn, pageblock_nr_pages); -- reserve = roundup(min_wmark_pages(zone), pageblock_nr_pages) >> -- pageblock_order; -- -- /* -- * Reserve blocks are generally in place to help high-order atomic -- * allocations that are short-lived. A min_free_kbytes value that -- * would result in more than 2 reserve blocks for atomic allocations -- * is assumed to be in place to help anti-fragmentation for the -- * future allocation of hugepages at runtime. -- */ -- reserve = min(2, reserve); -- old_reserve = zone->nr_migrate_reserve_block; -- -- /* When memory hot-add, we almost always need to do nothing */ -- if (reserve == old_reserve) -- return; -- zone->nr_migrate_reserve_block = reserve; -- -- for (pfn = start_pfn; pfn < end_pfn; pfn += pageblock_nr_pages) { -- if (!early_page_nid_uninitialised(pfn, zone_to_nid(zone))) -- return; -- -- if (!pfn_valid(pfn)) -- continue; -- page = pfn_to_page(pfn); -- -- /* Watch out for overlapping nodes */ -- if (page_to_nid(page) != zone_to_nid(zone)) -- continue; -- -- block_migratetype = get_pageblock_migratetype(page); -- -- /* Only test what is necessary when the reserves are not met */ -- if (reserve > 0) { -- /* -- * Blocks with reserved pages will never free, skip -- * them. -- */ -- block_end_pfn = min(pfn + pageblock_nr_pages, end_pfn); -- if (pageblock_is_reserved(pfn, block_end_pfn)) -- continue; -- -- /* If this block is reserved, account for it */ -- if (block_migratetype == MIGRATE_RESERVE) { -- reserve--; -- continue; -- } -- -- /* Suitable for reserving if this block is movable */ -- if (block_migratetype == MIGRATE_MOVABLE) { -- set_pageblock_migratetype(page, -- MIGRATE_RESERVE); -- move_freepages_block(zone, page, -- MIGRATE_RESERVE); -- reserve--; -- continue; -- } -- } else if (!old_reserve) { -- /* -- * At boot time we don't need to scan the whole zone -- * for turning off MIGRATE_RESERVE. -- */ -- break; -- } -- -- /* -- * If the reserve is met and this is a previous reserved block, -- * take it back -- */ -- if (block_migratetype == MIGRATE_RESERVE) { -- set_pageblock_migratetype(page, MIGRATE_MOVABLE); -- move_freepages_block(zone, page, MIGRATE_MOVABLE); -- } -- } --} -- --/* - * Initially all pages are reserved - free ones are freed - * up by free_all_bootmem() once the early boot process is - * done. Non-atomic initialization, single-pass. -@@ -4455,9 +4326,7 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, - * movable at startup. This will force kernel allocations - * to reserve their blocks rather than leaking throughout - * the address space during boot when many long-lived -- * kernel allocations are made. Later some blocks near -- * the start are marked MIGRATE_RESERVE by -- * setup_zone_migrate_reserve() -+ * kernel allocations are made. - * - * bitmap is created for zone's valid pfn range. but memmap - * can be created for invalid pages (for alignment) -@@ -6018,7 +5887,6 @@ static void __setup_per_zone_wmarks(void) - high_wmark_pages(zone) - low_wmark_pages(zone) - - atomic_long_read(&zone->vm_stat[NR_ALLOC_BATCH])); - -- setup_zone_migrate_reserve(zone); - spin_unlock_irqrestore(&zone->lock, flags); - } - -diff --git a/mm/vmstat.c b/mm/vmstat.c -index ffcb4f5..5b289dc 100644 ---- a/mm/vmstat.c -+++ b/mm/vmstat.c -@@ -923,7 +923,6 @@ static char * const migratetype_names[MIGRATE_TYPES] = { - "Unmovable", - "Reclaimable", - "Movable", -- "Reserve", - #ifdef CONFIG_CMA - "CMA", - #endif -diff --git a/mm/backing-dev.c b/mm/backing-dev.c -index 8ed2ffd963c5..7340353f8aea 100644 ---- a/mm/backing-dev.c -+++ b/mm/backing-dev.c -@@ -957,8 +957,9 @@ EXPORT_SYMBOL(congestion_wait); - * jiffies for either a BDI to exit congestion of the given @sync queue - * or a write to complete. - * -- * In the absence of zone congestion, cond_resched() is called to yield -- * the processor if necessary but otherwise does not sleep. -+ * In the absence of zone congestion, a short sleep or a cond_resched is -+ * performed to yield the processor and to allow other subsystems to make -+ * a forward progress. - * - * The return value is 0 if the sleep is for the full timeout. Otherwise, - * it is the number of jiffies that were still remaining when the function -@@ -978,7 +979,19 @@ long wait_iff_congested(struct zone *zone, int sync, long timeout) - */ - if (atomic_read(&nr_wb_congested[sync]) == 0 || - !test_bit(ZONE_CONGESTED, &zone->flags)) { -- cond_resched(); -+ -+ /* -+ * Memory allocation/reclaim might be called from a WQ -+ * context and the current implementation of the WQ -+ * concurrency control doesn't recognize that a particular -+ * WQ is congested if the worker thread is looping without -+ * ever sleeping. Therefore we have to do a short sleep -+ * here rather than calling cond_resched(). -+ */ -+ if (current->flags & PF_WQ_WORKER) -+ schedule_timeout(1); -+ else -+ cond_resched(); - - /* In case we scheduled, work out time remaining */ - ret = timeout - (jiffies - start); -diff --git a/mm/vmstat.c b/mm/vmstat.c -index 45dcbcb5c594..0975da8e3432 100644 ---- a/mm/vmstat.c -+++ b/mm/vmstat.c -@@ -1381,6 +1381,7 @@ static const struct file_operations proc_vmstat_file_operations = { - #endif /* CONFIG_PROC_FS */ - - #ifdef CONFIG_SMP -+static struct workqueue_struct *vmstat_wq; - static DEFINE_PER_CPU(struct delayed_work, vmstat_work); - int sysctl_stat_interval __read_mostly = HZ; - static cpumask_var_t cpu_stat_off; -@@ -1393,7 +1394,7 @@ static void vmstat_update(struct work_struct *w) - * to occur in the future. Keep on running the - * update worker thread. - */ -- schedule_delayed_work_on(smp_processor_id(), -+ queue_delayed_work_on(smp_processor_id(), vmstat_wq, - this_cpu_ptr(&vmstat_work), - round_jiffies_relative(sysctl_stat_interval)); - } else { -@@ -1462,7 +1463,7 @@ static void vmstat_shepherd(struct work_struct *w) - if (need_update(cpu) && - cpumask_test_and_clear_cpu(cpu, cpu_stat_off)) - -- schedule_delayed_work_on(cpu, -+ queue_delayed_work_on(cpu, vmstat_wq, - &per_cpu(vmstat_work, cpu), 0); - - put_online_cpus(); -@@ -1551,6 +1552,7 @@ static int __init setup_vmstat(void) - - start_shepherd_timer(); - cpu_notifier_register_done(); -+ vmstat_wq = alloc_workqueue("vmstat", WQ_FREEZABLE|WQ_MEM_RECLAIM, 0); - #endif - #ifdef CONFIG_PROC_FS - proc_create("buddyinfo", S_IRUGO, NULL, &fragmentation_file_operations); --- -2.6.2 - +@@ -1634,6 +1634,7 @@ xfs_fs_fill_super( + sb->s_max_links = XFS_MAXLINK; + sb->s_time_gran = 1; + set_posix_acl_flag(sb); ++ sb->s_iflags |= SB_I_CGROUPWB; + + /* version 5 superblocks support inode version counters. */ + if (XFS_SB_VERSION_NUM(&mp->m_sb) == XFS_SB_VERSION_5)