- v3 version of the patch (split into two chunks)

[packages/kernel.git] / kernel-small_fixes.patch

--- linux-2.6.33/scripts/mod/modpost.c~	2010-02-24 19:52:17.000000000 +0100
+++ linux-2.6.33/scripts/mod/modpost.c	2010-03-07 14:26:47.242168558 +0100
@@ -15,7 +15,8 @@
 #include <stdio.h>
 #include <ctype.h>
 #include "modpost.h"
-#include "../../include/generated/autoconf.h"
+// PLD architectures don't use CONFIG_SYMBOL_PREFIX
+//#include "../../include/generated/autoconf.h"
 #include "../../include/linux/license.h"
 
 /* Some toolchains use a `_' prefix for all user symbols. */

--- linux-3.0/scripts/kconfig/lxdialog/check-lxdialog.sh~	2011-07-22 04:17:23.000000000 +0200
+++ linux-3.0/scripts/kconfig/lxdialog/check-lxdialog.sh	2011-08-25 21:26:04.799150642 +0200
@@ -9,6 +9,12 @@
 			$cc -print-file-name=lib${lib}.${ext} | grep -q /
 			if [ $? -eq 0 ]; then
 				echo "-l${lib}"
+				for libt in tinfow tinfo ; do
+					$cc -print-file-name=lib${libt}.${ext} | grep -q /
+					if [ $? -eq 0 ]; then
+						echo "-l${libt}"
+					fi
+				done
 				exit
 			fi
 		done

From 7a29ac474a47eb8cf212b45917683ae89d6fa13b Mon Sep 17 00:00:00 2001
From: Chris Mason <clm@fb.com>
Date: Tue, 10 Nov 2015 10:10:34 +1100
Subject: xfs: give all workqueues rescuer threads

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.

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 <clm@fb.com>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Dave Chinner <david@fromorbit.com>
---
 fs/xfs/xfs_super.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 29531ec..65fbfb7 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 <akpm@linux-foundation.org>
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 <akpm@linux-foundation.org>
    Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

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 <mgorman@techsingularity.net>
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 <mgorman@techsingularity.net>
    Acked-by: Vlastimil Babka <vbabka@suse.cz>
    Cc: Christoph Lameter <cl@linux.com>
    Cc: David Rientjes <rientjes@google.com>
    Cc: Johannes Weiner <hannes@cmpxchg.org>
    Cc: Michal Hocko <mhocko@suse.com>
    Cc: Vitaly Wool <vitalywool@gmail.com>
    Cc: Rik van Riel <riel@redhat.com>
    Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
    Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

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 <mgorman@techsingularity.net>
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 <mgorman@techsingularity.net>
    Acked-by: Vlastimil Babka <vbabka@suse.cz>
    Cc: Christoph Lameter <cl@linux.com>
    Cc: David Rientjes <rientjes@google.com>
    Cc: Johannes Weiner <hannes@cmpxchg.org>
    Cc: Michal Hocko <mhocko@suse.com>
    Cc: Vitaly Wool <vitalywool@gmail.com>
    Cc: Rik van Riel <riel@redhat.com>
    Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
    Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

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

From 09ccfd238e5a0e670d8178cf50180ea81ae09ae1 Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Mon, 14 Dec 2015 13:48:36 -0800
Subject: pptp: verify sockaddr_len in pptp_bind() and pptp_connect()

Reported-by: Dmitry Vyukov <dvyukov@gmail.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ppp/pptp.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/ppp/pptp.c b/drivers/net/ppp/pptp.c
index fc69e41..597c53e 100644
--- a/drivers/net/ppp/pptp.c
+++ b/drivers/net/ppp/pptp.c
@@ -419,6 +419,9 @@ static int pptp_bind(struct socket *sock, struct sockaddr *uservaddr,
 	struct pptp_opt *opt = &po->proto.pptp;
 	int error = 0;
 
+	if (sockaddr_len < sizeof(struct sockaddr_pppox))
+		return -EINVAL;
+
 	lock_sock(sk);
 
 	opt->src_addr = sp->sa_addr.pptp;
@@ -440,6 +443,9 @@ static int pptp_connect(struct socket *sock, struct sockaddr *uservaddr,
 	struct flowi4 fl4;
 	int error = 0;
 
+	if (sockaddr_len < sizeof(struct sockaddr_pppox))
+		return -EINVAL;
+
 	if (sp->sa_protocol != PX_PROTO_PPTP)
 		return -EINVAL;
 
-- 
cgit v0.11.2

commit cc57858831e3e9678291de730c4b4d2e52a19f59
Author: Artur Paszkiewicz <artur.paszkiewicz@intel.com>
Date:   Fri Dec 18 15:19:16 2015 +1100

    md/raid10: fix data corruption and crash during resync
    
    The commit c31df25f20e3 ("md/raid10: make sync_request_write() call
    bio_copy_data()") replaced manual data copying with bio_copy_data() but
    it doesn't work as intended. The source bio (fbio) is already processed,
    so its bvec_iter has bi_size == 0 and bi_idx == bi_vcnt.  Because of
    this, bio_copy_data() either does not copy anything, or worse, copies
    data from the ->bi_next bio if it is set.  This causes wrong data to be
    written to drives during resync and sometimes lockups/crashes in
    bio_copy_data():
    
    [  517.338478] NMI watchdog: BUG: soft lockup - CPU#0 stuck for 22s! [md126_raid10:3319]
    [  517.347324] Modules linked in: raid10 xt_CHECKSUM ipt_MASQUERADE nf_nat_masquerade_ipv4 tun ip6t_rpfilter ip6t_REJECT nf_reject_ipv6 ipt_REJECT nf_reject_ipv4 xt_conntrack ebtable_nat ebtable_broute bridge stp llc ebtable_filter ebtables ip6table_nat nf_conntrack_ipv6 nf_defrag_ipv6 nf_nat_ipv6 ip6table_mangle ip6table_security ip6table_raw ip6table_filter ip6_tables iptable_nat nf_conntrack_ipv4 nf_defrag_ipv4 nf_nat_ipv4 nf_nat nf_conntrack iptable_mangle iptable_security iptable_raw iptable_filter ip_tables x86_pkg_temp_thermal coretemp kvm_intel kvm crct10dif_pclmul crc32_pclmul cryptd shpchp pcspkr ipmi_si ipmi_msghandler tpm_crb acpi_power_meter acpi_cpufreq ext4 mbcache jbd2 sr_mod cdrom sd_mod e1000e ax88179_178a usbnet mii ahci ata_generic crc32c_intel libahci ptp pata_acpi libata pps_core wmi sunrpc dm_mirror dm_region_hash dm_log dm_mod
    [  517.440555] CPU: 0 PID: 3319 Comm: md126_raid10 Not tainted 4.3.0-rc6+ #1
    [  517.448384] Hardware name: Intel Corporation PURLEY/PURLEY, BIOS PLYDCRB1.86B.0055.D14.1509221924 09/22/2015
    [  517.459768] task: ffff880153773980 ti: ffff880150df8000 task.ti: ffff880150df8000
    [  517.468529] RIP: 0010:[<ffffffff812e1888>]  [<ffffffff812e1888>] bio_copy_data+0xc8/0x3c0
    [  517.478164] RSP: 0018:ffff880150dfbc98  EFLAGS: 00000246
    [  517.484341] RAX: ffff880169356688 RBX: 0000000000001000 RCX: 0000000000000000
    [  517.492558] RDX: 0000000000000000 RSI: ffffea0001ac2980 RDI: ffffea0000d835c0
    [  517.500773] RBP: ffff880150dfbd08 R08: 0000000000000001 R09: ffff880153773980
    [  517.508987] R10: ffff880169356600 R11: 0000000000001000 R12: 0000000000010000
    [  517.517199] R13: 000000000000e000 R14: 0000000000000000 R15: 0000000000001000
    [  517.525412] FS:  0000000000000000(0000) GS:ffff880174a00000(0000) knlGS:0000000000000000
    [  517.534844] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
    [  517.541507] CR2: 00007f8a044d5fed CR3: 0000000169504000 CR4: 00000000001406f0
    [  517.549722] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
    [  517.557929] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
    [  517.566144] Stack:
    [  517.568626]  ffff880174a16bc0 ffff880153773980 ffff880169356600 0000000000000000
    [  517.577659]  0000000000000001 0000000000000001 ffff880153773980 ffff88016a61a800
    [  517.586715]  ffff880150dfbcf8 0000000000000001 ffff88016dd209e0 0000000000001000
    [  517.595773] Call Trace:
    [  517.598747]  [<ffffffffa043ef95>] raid10d+0xfc5/0x1690 [raid10]
    [  517.605610]  [<ffffffff816697ae>] ? __schedule+0x29e/0x8e2
    [  517.611987]  [<ffffffff814ff206>] md_thread+0x106/0x140
    [  517.618072]  [<ffffffff810c1d80>] ? wait_woken+0x80/0x80
    [  517.624252]  [<ffffffff814ff100>] ? super_1_load+0x520/0x520
    [  517.630817]  [<ffffffff8109ef89>] kthread+0xc9/0xe0
    [  517.636506]  [<ffffffff8109eec0>] ? flush_kthread_worker+0x70/0x70
    [  517.643653]  [<ffffffff8166d99f>] ret_from_fork+0x3f/0x70
    [  517.649929]  [<ffffffff8109eec0>] ? flush_kthread_worker+0x70/0x70
    
    Signed-off-by: Artur Paszkiewicz <artur.paszkiewicz@intel.com>
    Reviewed-by: Shaohua Li <shli@kernel.org>
    Cc: stable@vger.kernel.org (v4.2+)
    Fixes: c31df25f20e3 ("md/raid10: make sync_request_write() call bio_copy_data()")
    Signed-off-by: NeilBrown <neilb@suse.com>

diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 41d70bc..84e597e 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -1946,6 +1946,8 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio)
 
 	first = i;
 	fbio = r10_bio->devs[i].bio;
+	fbio->bi_iter.bi_size = r10_bio->sectors << 9;
+	fbio->bi_iter.bi_idx = 0;
 
 	vcnt = (r10_bio->sectors + (PAGE_SIZE >> 9) - 1) >> (PAGE_SHIFT - 9);
 	/* now find blocks with errors */
@@ -1989,7 +1991,7 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio)
 		bio_reset(tbio);
 
 		tbio->bi_vcnt = vcnt;
-		tbio->bi_iter.bi_size = r10_bio->sectors << 9;
+		tbio->bi_iter.bi_size = fbio->bi_iter.bi_size;
 		tbio->bi_rw = WRITE;
 		tbio->bi_private = r10_bio;
 		tbio->bi_iter.bi_sector = r10_bio->devs[i].addr;
From: Michal Hocko <mhocko@suse.com>

kernel test robot has reported the following crash:
[    3.870718] BUG: unable to handle kernel NULL pointer dereferenceNULL pointer dereference at 00000100
 at 00000100
[    3.872615] IP: [<c1074df6>] __queue_work+0x26/0x390 [<c1074df6>] __queue_work+0x26/0x390
[    3.873758] *pdpt = 0000000000000000 *pde = f000ff53f000ff53 *pde = f000ff53f000ff53
[    3.875096] Oops: 0000 [#1] PREEMPT PREEMPT SMP SMP
[    3.876130] CPU: 0 PID: 24 Comm: kworker/0:1 Not tainted 4.4.0-rc4-00139-g373ccbe #1
[    3.878135] Workqueue: events vmstat_shepherd
[    3.879207] task: cb684600 ti: cb7ba000 task.ti: cb7ba000
[    3.880445] EIP: 0060:[<c1074df6>] EFLAGS: 00010046 CPU: 0
[    3.881704] EIP is at __queue_work+0x26/0x390
[    3.882823] EAX: 00000046 EBX: cbb37800 ECX: cbb37800 EDX: 00000000
[    3.884457] ESI: 00000000 EDI: 00000000 EBP: cb7bbe68 ESP: cb7bbe38
[    3.886005]  DS: 007b ES: 007b FS: 00d8 GS: 00e0 SS: 0068
[    3.887229] CR0: 8005003b CR2: 00000100 CR3: 01fd5000 CR4: 000006b0
[    3.888663] Stack:
[    3.895204] Call Trace:
[    3.895854]  [<c1a381dd>] ? mutex_unlock+0xd/0x10
[    3.897120]  [<c1075221>] __queue_delayed_work+0xa1/0x160
[    3.898530]  [<c10764c6>] queue_delayed_work_on+0x36/0x60
[    3.899790]  [<c11494bd>] vmstat_shepherd+0xad/0xf0
[    3.900899]  [<c1075a7a>] process_one_work+0x1aa/0x4c0
[    3.902093]  [<c10759e2>] ? process_one_work+0x112/0x4c0
[    3.903520]  [<c10ac31e>] ? do_raw_spin_lock+0xe/0x150
[    3.904853]  [<c1075dd1>] worker_thread+0x41/0x440
[    3.906023]  [<c1075d90>] ? process_one_work+0x4c0/0x4c0
[    3.907242]  [<c107b7c0>] kthread+0xb0/0xd0
[    3.908188]  [<c1a3c651>] ret_from_kernel_thread+0x21/0x40
[    3.909601]  [<c107b710>] ? __kthread_parkme+0x80/0x80

The reason is that start_shepherd_timer schedules the shepherd work item
which uses vmstat_wq (vmstat_shepherd) before setup_vmstat allocates
that workqueue so if the further initialization takes more than HZ
we might end up scheduling on a NULL vmstat_wq. This is really unlikely
but not impossible.

Fixes: 373ccbe59270 ("mm, vmstat: allow WQ concurrency to discover memory reclaim doesn't make any progress")
Reported-by: kernel test robot <ying.huang@linux.intel.com>
Signed-off-by: Michal Hocko <mhocko@suse.com>
---
Hi Linus,
I am not marking this for stable because I hope we can sneak it into 4.4.
The patch is trivial and obvious. I am sorry about the breakage. If you prefer 
to postpone it to 4.5-rc1 because this is not really that critical and shouldn't
happen most of the time then I will repost with stable tag added.

Thanks!

 mm/vmstat.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/mm/vmstat.c b/mm/vmstat.c
index 4ebc17d948cb..c54fd2924f25 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1483,6 +1483,7 @@ static void __init start_shepherd_timer(void)
 		BUG();
 	cpumask_copy(cpu_stat_off, cpu_online_mask);
 
+	vmstat_wq = alloc_workqueue("vmstat", WQ_FREEZABLE|WQ_MEM_RECLAIM, 0);
 	schedule_delayed_work(&shepherd,
 		round_jiffies_relative(sysctl_stat_interval));
 }
@@ -1550,7 +1551,6 @@ 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);
-- 
2.6.4

From: Dave Chinner <dchinner@redhat.com>

When we do inode readahead in log recovery, we do can do the
readahead before we've replayed the icreate transaction that stamps
the buffer with inode cores. The inode readahead verifier catches
this and marks the buffer as !done to indicate that it doesn't yet
contain valid inodes.

In adding buffer error notification  (i.e. setting b_error = -EIO at
the same time as as we clear the done flag) to such a readahead
verifier failure, we can then get subsequent inode recovery failing
with this error:

XFS (dm-0): metadata I/O error: block 0xa00060 ("xlog_recover_do..(read#2)") error 5 numblks 32

This occurs when readahead completion races with icreate item replay
such as:

	inode readahead
		find buffer
		lock buffer
		submit RA io
	....
	icreate recovery
	    xfs_trans_get_buffer
		find buffer
		lock buffer
		<blocks on RA completion>
	.....
	<ra completion>
		fails verifier
		clear XBF_DONE
		set bp->b_error = -EIO
		release and unlock buffer
	<icreate gains lock>
	icreate initialises buffer
	marks buffer as done
	adds buffer to delayed write queue
	releases buffer

At this point, we have an initialised inode buffer that is up to
date but has an -EIO state registered against it. When we finally
get to recovering an inode in that buffer:

	inode item recovery
	    xfs_trans_read_buffer
		find buffer
		lock buffer
		sees XBF_DONE is set, returns buffer
	    sees bp->b_error is set
		fail log recovery!

Essentially, we need xfs_trans_get_buf_map() to clear the error status of
the buffer when doing a lookup. This function returns uninitialised
buffers, so the buffer returned can not be in an error state and
none of the code that uses this function expects b_error to be set
on return. Indeed, there is an ASSERT(!bp->b_error); in the
transaction case in xfs_trans_get_buf_map() that would have caught
this if log recovery used transactions....

This patch firstly changes the inode readahead failure to set -EIO
on the buffer, and secondly changes xfs_buf_get_map() to never
return a buffer with an error state set so this first change doesn't
cause unexpected log recovery failures.

Signed-off-by: Dave Chinner <dchinner@redhat.com>
---
 fs/xfs/libxfs/xfs_inode_buf.c | 12 +++++++-----
 fs/xfs/xfs_buf.c              |  7 +++++++
 2 files changed, 14 insertions(+), 5 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c
index 1b8d98a..ff17c48 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.c
+++ b/fs/xfs/libxfs/xfs_inode_buf.c
@@ -62,11 +62,12 @@ xfs_inobp_check(
  * has not had the inode cores stamped into it. Hence for readahead, the buffer
  * may be potentially invalid.
  *
- * If the readahead buffer is invalid, we don't want to mark it with an error,
- * but we do want to clear the DONE status of the buffer so that a followup read
- * will re-read it from disk. This will ensure that we don't get an unnecessary
- * warnings during log recovery and we don't get unnecssary panics on debug
- * kernels.
+ * If the readahead buffer is invalid, we need to mark it with an error and
+ * clear the DONE status of the buffer so that a followup read will re-read it
+ * from disk. We don't report the error otherwise to avoid warnings during log
+ * recovery and we don't get unnecssary panics on debug kernels. We use EIO here
+ * because all we want to do is say readahead failed; there is no-one to report
+ * the error to, so this will distinguish it from a non-ra verifier failure.
  */
 static void
 xfs_inode_buf_verify(
@@ -93,6 +94,7 @@ xfs_inode_buf_verify(
 						XFS_RANDOM_ITOBP_INOTOBP))) {
 			if (readahead) {
 				bp->b_flags &= ~XBF_DONE;
+				xfs_buf_ioerror(bp, -EIO);
 				return;
 			}
 
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 45a8ea7..ae86b16 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -604,6 +604,13 @@ found:
 		}
 	}
 
+	/*
+	 * Clear b_error if this is a lookup from a caller that doesn't expect
+	 * valid data to be found in the buffer.
+	 */
+	if (!(flags & XBF_READ))
+		xfs_buf_ioerror(bp, 0);
+
 	XFS_STATS_INC(xb_get);
 	trace_xfs_buf_get(bp, flags, _RET_IP_);
 	return bp;
-- 
2.5.0

_______________________________________________
xfs mailing list
xfs@oss.sgi.com
http://oss.sgi.com/mailman/listinfo/xfs
From: Dave Chinner <dchinner@redhat.com>

When we do dquot readahead in log recovery, we do not use a verifier
as the underlying buffer may not have dquots in it. e.g. the
allocation operation hasn't yet been replayed. Hence we do not want
to fail recovery because we detect an operation to be replayed has
not been run yet. This problem was addressed for inodes in commit
d891400 ("xfs: inode buffers may not be valid during recovery
readahead") but the problem was not recognised to exist for dquots
and their buffers as the dquot readahead did not have a verifier.

The result of not using a verifier is that when the buffer is then
next read to replay a dquot modification, the dquot buffer verifier
will only be attached to the buffer if *readahead is not complete*.
Hence we can read the buffer, replay the dquot changes and then add
it to the delwri submission list without it having a verifier
attached to it. This then generates warnings in xfs_buf_ioapply(),
which catches and warns about this case.

Fix this and make it handle the same readahead verifier error cases
as for inode buffers by adding a new readahead verifier that has a
write operation as well as a read operation that marks the buffer as
not done if any corruption is detected.  Also make sure we don't run
readahead if the dquot buffer has been marked as cancelled by
recovery.

This will result in readahead either succeeding and the buffer
having a valid write verifier, or readahead failing and the buffer
state requiring the subsequent read to resubmit the IO with the new
verifier.  In either case, this will result in the buffer always
ending up with a valid write verifier on it.

Note: we also need to fix the inode buffer readahead error handling
to mark the buffer with EIO. Brian noticed the code I copied from
there wrong during review, so fix it at the same time. Add comments
linking the two functions that handle readahead verifier errors
together so we don't forget this behavioural link in future.

cc: <stable@vger.kernel.org> # 3.12 - current
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
Signed-off-by: Dave Chinner <david@fromorbit.com>
---
 fs/xfs/libxfs/xfs_dquot_buf.c  | 36 ++++++++++++++++++++++++++++++------
 fs/xfs/libxfs/xfs_inode_buf.c  |  2 ++
 fs/xfs/libxfs/xfs_quota_defs.h |  2 +-
 fs/xfs/libxfs/xfs_shared.h     |  1 +
 fs/xfs/xfs_log_recover.c       |  9 +++++++--
 5 files changed, 41 insertions(+), 9 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_dquot_buf.c b/fs/xfs/libxfs/xfs_dquot_buf.c
index 11cefb2..3cc3cf7 100644
--- a/fs/xfs/libxfs/xfs_dquot_buf.c
+++ b/fs/xfs/libxfs/xfs_dquot_buf.c
@@ -54,7 +54,7 @@ xfs_dqcheck(
 	xfs_dqid_t	 id,
 	uint		 type,	  /* used only when IO_dorepair is true */
 	uint		 flags,
-	char		 *str)
+	const char	 *str)
 {
 	xfs_dqblk_t	 *d = (xfs_dqblk_t *)ddq;
 	int		errs = 0;
@@ -207,7 +207,8 @@ xfs_dquot_buf_verify_crc(
 STATIC bool
 xfs_dquot_buf_verify(
 	struct xfs_mount	*mp,
-	struct xfs_buf		*bp)
+	struct xfs_buf		*bp,
+	int			warn)
 {
 	struct xfs_dqblk	*d = (struct xfs_dqblk *)bp->b_addr;
 	xfs_dqid_t		id = 0;
@@ -240,8 +241,7 @@ xfs_dquot_buf_verify(
 		if (i == 0)
 			id = be32_to_cpu(ddq->d_id);
 
-		error = xfs_dqcheck(mp, ddq, id + i, 0, XFS_QMOPT_DOWARN,
-				       "xfs_dquot_buf_verify");
+		error = xfs_dqcheck(mp, ddq, id + i, 0, warn, __func__);
 		if (error)
 			return false;
 	}
@@ -256,7 +256,7 @@ xfs_dquot_buf_read_verify(
 
 	if (!xfs_dquot_buf_verify_crc(mp, bp))
 		xfs_buf_ioerror(bp, -EFSBADCRC);
-	else if (!xfs_dquot_buf_verify(mp, bp))
+	else if (!xfs_dquot_buf_verify(mp, bp, XFS_QMOPT_DOWARN))
 		xfs_buf_ioerror(bp, -EFSCORRUPTED);
 
 	if (bp->b_error)
@@ -264,6 +264,25 @@ xfs_dquot_buf_read_verify(
 }
 
 /*
+ * readahead errors are silent and simply leave the buffer as !done so a real
+ * read will then be run with the xfs_dquot_buf_ops verifier. See
+ * xfs_inode_buf_verify() for why we use EIO and ~XBF_DONE here rather than
+ * reporting the failure.
+ */
+static void
+xfs_dquot_buf_readahead_verify(
+	struct xfs_buf	*bp)
+{
+	struct xfs_mount	*mp = bp->b_target->bt_mount;
+
+	if (!xfs_dquot_buf_verify_crc(mp, bp) ||
+	    !xfs_dquot_buf_verify(mp, bp, 0)) {
+		xfs_buf_ioerror(bp, -EIO);
+		bp->b_flags &= ~XBF_DONE;
+	}
+}
+
+/*
  * we don't calculate the CRC here as that is done when the dquot is flushed to
  * the buffer after the update is done. This ensures that the dquot in the
  * buffer always has an up-to-date CRC value.
@@ -274,7 +293,7 @@ xfs_dquot_buf_write_verify(
 {
 	struct xfs_mount	*mp = bp->b_target->bt_mount;
 
-	if (!xfs_dquot_buf_verify(mp, bp)) {
+	if (!xfs_dquot_buf_verify(mp, bp, XFS_QMOPT_DOWARN)) {
 		xfs_buf_ioerror(bp, -EFSCORRUPTED);
 		xfs_verifier_error(bp);
 		return;
@@ -287,3 +306,8 @@ const struct xfs_buf_ops xfs_dquot_buf_ops = {
 	.verify_write = xfs_dquot_buf_write_verify,
 };
 
+const struct xfs_buf_ops xfs_dquot_buf_ra_ops = {
+
+	.verify_read = xfs_dquot_buf_readahead_verify,
+	.verify_write = xfs_dquot_buf_write_verify,
+};
diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c
index ff17c48..1aabfda 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.c
+++ b/fs/xfs/libxfs/xfs_inode_buf.c
@@ -68,6 +68,8 @@ xfs_inobp_check(
  * recovery and we don't get unnecssary panics on debug kernels. We use EIO here
  * because all we want to do is say readahead failed; there is no-one to report
  * the error to, so this will distinguish it from a non-ra verifier failure.
+ * Changes to this readahead error behavour also need to be reflected in
+ * xfs_dquot_buf_readahead_verify().
  */
 static void
 xfs_inode_buf_verify(
diff --git a/fs/xfs/libxfs/xfs_quota_defs.h b/fs/xfs/libxfs/xfs_quota_defs.h
index 1b0a083..f51078f 100644
--- a/fs/xfs/libxfs/xfs_quota_defs.h
+++ b/fs/xfs/libxfs/xfs_quota_defs.h
@@ -153,7 +153,7 @@ typedef __uint16_t	xfs_qwarncnt_t;
 #define XFS_QMOPT_RESBLK_MASK	(XFS_QMOPT_RES_REGBLKS | XFS_QMOPT_RES_RTBLKS)
 
 extern int xfs_dqcheck(struct xfs_mount *mp, xfs_disk_dquot_t *ddq,
-		       xfs_dqid_t id, uint type, uint flags, char *str);
+		       xfs_dqid_t id, uint type, uint flags, const char *str);
 extern int xfs_calc_dquots_per_chunk(unsigned int nbblks);
 
 #endif	/* __XFS_QUOTA_H__ */
diff --git a/fs/xfs/libxfs/xfs_shared.h b/fs/xfs/libxfs/xfs_shared.h
index 5be5297..15c3ceb 100644
--- a/fs/xfs/libxfs/xfs_shared.h
+++ b/fs/xfs/libxfs/xfs_shared.h
@@ -49,6 +49,7 @@ extern const struct xfs_buf_ops xfs_inobt_buf_ops;
 extern const struct xfs_buf_ops xfs_inode_buf_ops;
 extern const struct xfs_buf_ops xfs_inode_buf_ra_ops;
 extern const struct xfs_buf_ops xfs_dquot_buf_ops;
+extern const struct xfs_buf_ops xfs_dquot_buf_ra_ops;
 extern const struct xfs_buf_ops xfs_sb_buf_ops;
 extern const struct xfs_buf_ops xfs_sb_quiet_buf_ops;
 extern const struct xfs_buf_ops xfs_symlink_buf_ops;
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index c5ecaac..5991cdc 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -3204,6 +3204,7 @@ xlog_recover_dquot_ra_pass2(
 	struct xfs_disk_dquot	*recddq;
 	struct xfs_dq_logformat	*dq_f;
 	uint			type;
+	int			len;
 
 
 	if (mp->m_qflags == 0)
@@ -3224,8 +3225,12 @@ xlog_recover_dquot_ra_pass2(
 	ASSERT(dq_f);
 	ASSERT(dq_f->qlf_len == 1);
 
-	xfs_buf_readahead(mp->m_ddev_targp, dq_f->qlf_blkno,
-			  XFS_FSB_TO_BB(mp, dq_f->qlf_len), NULL);
+	len = XFS_FSB_TO_BB(mp, dq_f->qlf_len);
+	if (xlog_peek_buffer_cancelled(log, dq_f->qlf_blkno, len, 0))
+		return;
+
+	xfs_buf_readahead(mp->m_ddev_targp, dq_f->qlf_blkno, len,
+			  &xfs_dquot_buf_ra_ops);
 }
 
 STATIC void
-- 
2.5.0

_______________________________________________
xfs mailing list
xfs@oss.sgi.com
http://oss.sgi.com/mailman/listinfo/xfs