Linux 3.0.39

index 97f8bf6..adda036 100644
@@ -60,6 +60,8 @@ struct thread_info {
 register struct thread_info *__current_thread_info __asm__("$28");
 #define current_thread_info()  __current_thread_info
 
+#endif /* !__ASSEMBLY__ */
+
 /* thread information allocation */
 #if defined(CONFIG_PAGE_SIZE_4KB) && defined(CONFIG_32BIT)
 #define THREAD_SIZE_ORDER (1)

@@ -97,8 +99,6 @@ register struct thread_info *__current_thread_info __asm__("$28");
 
 #define free_thread_info(info) kfree(info)
 
-#endif /* !__ASSEMBLY__ */
-
 #define PREEMPT_ACTIVE		0x10000000
 
 /*

79 lines not on this page · raw message

index 9bfd057..42ef54f 100644
@@ -1210,7 +1210,7 @@ static int mirror_end_io(struct dm_target *ti, struct bio *bio,
 	 * We need to dec pending if this was a write.
 	 */
 	if (rw == WRITE) {
-		if (!(bio->bi_rw & REQ_FLUSH))
+		if (!(bio->bi_rw & (REQ_FLUSH | REQ_DISCARD)))
 			dm_rh_dec(ms->rh, map_context->ll);
 		return error;
 	}

index 7771ed2..69732e0 100644
@@ -404,6 +404,9 @@ void dm_rh_mark_nosync(struct dm_region_hash *rh, struct bio *bio)
 		return;
 	}
 
+	if (bio->bi_rw & REQ_DISCARD)
+		return;
+
 	/* We must inform the log that the sync count has changed. */
 	log->type->set_region_sync(log, region, 0);
 

@@ -524,7 +527,7 @@ void dm_rh_inc_pending(struct dm_region_hash *rh, struct bio_list *bios)
 	struct bio *bio;
 
 	for (bio = bios->head; bio; bio = bio->bi_next) {
-		if (bio->bi_rw & REQ_FLUSH)
+		if (bio->bi_rw & (REQ_FLUSH | REQ_DISCARD))
 			continue;
 		rh_inc(rh, dm_rh_bio_to_region(rh, bio));
 	}

index 1ac8db5d..57106a9 100644
@@ -801,7 +801,8 @@ static int btree_submit_bio_hook(struct inode *inode, int rw, struct bio *bio,
 
 #ifdef CONFIG_MIGRATION
 static int btree_migratepage(struct address_space *mapping,
-			struct page *newpage, struct page *page)
+			struct page *newpage, struct page *page,
+			enum migrate_mode mode)
 {
 	/*
 	 * we can't safely write a btree page from here,

@@ -816,7 +817,7 @@ static int btree_migratepage(struct address_space *mapping,
 	if (page_has_private(page) &&
 	    !try_to_release_page(page, GFP_KERNEL))
 		return -EAGAIN;
-	return migrate_page(mapping, newpage, page);
+	return migrate_page(mapping, newpage, page, mode);
 }
 #endif
 

index 6751e74..c71032b 100644
@@ -85,9 +85,12 @@ cifs_readdir_lookup(struct dentry *parent, struct qstr *name,
 
 	dentry = d_lookup(parent, name);
 	if (dentry) {
-		/* FIXME: check for inode number changes? */
-		if (dentry->d_inode != NULL)
+		inode = dentry->d_inode;
+		/* update inode in place if i_ino didn't change */
+		if (inode && CIFS_I(inode)->uniqueid == fattr->cf_uniqueid) {
+			cifs_fattr_to_inode(inode, fattr);
 			return dentry;
+		}
 		d_drop(dentry);
 		dput(dentry);
 	}

index 8b0c875..6327a06 100644
@@ -568,7 +568,8 @@ static int hugetlbfs_set_page_dirty(struct page *page)
 }
 
 static int hugetlbfs_migrate_page(struct address_space *mapping,
-				struct page *newpage, struct page *page)
+				struct page *newpage, struct page *page,
+				enum migrate_mode mode)
 {
 	int rc;
 

index 2a55347..4f10d81 100644
@@ -315,7 +315,7 @@ void nfs_commit_release_pages(struct nfs_write_data *data);
 
 #ifdef CONFIG_MIGRATION
 extern int nfs_migrate_page(struct address_space *,
-		struct page *, struct page *);
+		struct page *, struct page *, enum migrate_mode);
 #else
 #define nfs_migrate_page NULL
 #endif

index f2f80c0..58bb999 100644
@@ -1662,7 +1662,7 @@ out_error:
 
 #ifdef CONFIG_MIGRATION
 int nfs_migrate_page(struct address_space *mapping, struct page *newpage,
-		struct page *page)
+		struct page *page, enum migrate_mode mode)
 {
 	/*
 	 * If PagePrivate is set, then the page is currently associated with

@@ -1677,7 +1677,7 @@ int nfs_migrate_page(struct address_space *mapping, struct page *newpage,
 
 	nfs_fscache_release_page(page, GFP_KERNEL);
 
-	return migrate_page(mapping, newpage, page);
+	return migrate_page(mapping, newpage, page, mode);
 }
 #endif
 

index c606f01..1250016 100644
@@ -715,8 +715,12 @@ static int fixup_free_space(struct ubifs_info *c)
 		lnum = ubifs_next_log_lnum(c, lnum);
 	}
 
-	/* Fixup the current log head */
-	err = fixup_leb(c, c->lhead_lnum, c->lhead_offs);
+	/*
+	 * Fixup the log head which contains the only a CS node at the
+	 * beginning.
+	 */
+	err = fixup_leb(c, c->lhead_lnum,
+			ALIGN(UBIFS_CS_NODE_SZ, c->min_io_size));
 	if (err)
 		goto out;
 

74 lines not on this page · raw message

index 96b1035..212ea7b 100644
@@ -523,6 +523,7 @@ enum positive_aop_returns {
 struct page;
 struct address_space;
 struct writeback_control;
+enum migrate_mode;
 
 struct iov_iter {
 	const struct iovec *iov;

@@ -607,9 +608,12 @@ struct address_space_operations {
 			loff_t offset, unsigned long nr_segs);
 	int (*get_xip_mem)(struct address_space *, pgoff_t, int,
 						void **, unsigned long *);
-	/* migrate the contents of a page to the specified target */
+	/*
+	 * migrate the contents of a page to the specified target. If sync
+	 * is false, it must not block.
+	 */
 	int (*migratepage) (struct address_space *,
-			struct page *, struct page *);
+			struct page *, struct page *, enum migrate_mode);
 	int (*launder_page) (struct page *);
 	int (*is_partially_uptodate) (struct page *, read_descriptor_t *,
 					unsigned long);

@@ -2478,7 +2482,8 @@ extern int generic_check_addressable(unsigned, u64);
 
 #ifdef CONFIG_MIGRATION
 extern int buffer_migrate_page(struct address_space *,
-				struct page *, struct page *);
+				struct page *, struct page *,
+				enum migrate_mode);
 #else
 #define buffer_migrate_page NULL
 #endif

index 580f70c..5e41a8e 100644
@@ -30,6 +30,13 @@ extern struct fs_struct init_fs;
 #define INIT_THREADGROUP_FORK_LOCK(sig)
 #endif
 
+#ifdef CONFIG_CPUSETS
+#define INIT_CPUSET_SEQ							\
+	.mems_allowed_seq = SEQCNT_ZERO,
+#else
+#define INIT_CPUSET_SEQ
+#endif
+
 #define INIT_SIGNALS(sig) {						\
 	.nr_threads	= 1,						\
 	.wait_chldexit	= __WAIT_QUEUE_HEAD_INITIALIZER(sig.wait_chldexit),\

@@ -193,6 +200,7 @@ extern struct cred init_cred;
 	INIT_FTRACE_GRAPH						\
 	INIT_TRACE_RECURSION						\
 	INIT_TASK_RCU_PREEMPT(tsk)					\
+	INIT_CPUSET_SEQ							\
 }
 
 

index 313a00e..4a8da84 100644
@@ -35,7 +35,8 @@ enum mem_cgroup_page_stat_item {
 extern unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
 					struct list_head *dst,
 					unsigned long *scanned, int order,
-					int mode, struct zone *z,
+					isolate_mode_t mode,
+					struct zone *z,
 					struct mem_cgroup *mem_cont,
 					int active, int file);
 

index e39aeec..eaf8674 100644
@@ -6,18 +6,31 @@
 
 typedef struct page *new_page_t(struct page *, unsigned long private, int **);
 
+/*
+ * MIGRATE_ASYNC means never block
+ * MIGRATE_SYNC_LIGHT in the current implementation means to allow blocking
+ *	on most operations but not ->writepage as the potential stall time
+ *	is too significant
+ * MIGRATE_SYNC will block when migrating pages
+ */
+enum migrate_mode {
+	MIGRATE_ASYNC,
+	MIGRATE_SYNC_LIGHT,
+	MIGRATE_SYNC,
+};
+
 #ifdef CONFIG_MIGRATION
 #define PAGE_MIGRATION 1
 
 extern void putback_lru_pages(struct list_head *l);
 extern int migrate_page(struct address_space *,
-			struct page *, struct page *);
+			struct page *, struct page *, enum migrate_mode);
 extern int migrate_pages(struct list_head *l, new_page_t x,
 			unsigned long private, bool offlining,
-			bool sync);
+			enum migrate_mode mode);
 extern int migrate_huge_pages(struct list_head *l, new_page_t x,
 			unsigned long private, bool offlining,
-			bool sync);
+			enum migrate_mode mode);
 
 extern int fail_migrate_page(struct address_space *,
 			struct page *, struct page *);

@@ -36,10 +49,10 @@ 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, bool offlining,
-		bool sync) { return -ENOSYS; }
+		enum migrate_mode mode) { return -ENOSYS; }
 static inline int migrate_huge_pages(struct list_head *l, new_page_t x,
 		unsigned long private, bool offlining,
-		bool sync) { return -ENOSYS; }
+		enum migrate_mode mode) { return -ENOSYS; }
 
 static inline int migrate_prep(void) { return -ENOSYS; }
 static inline int migrate_prep_local(void) { return -ENOSYS; }

index aa2d80b..b32f3f9 100644
@@ -158,6 +158,20 @@ static inline int is_unevictable_lru(enum lru_list l)
 	return (l == LRU_UNEVICTABLE);
 }
 
+/* Isolate inactive pages */
+#define ISOLATE_INACTIVE	((__force isolate_mode_t)0x1)
+/* Isolate active pages */
+#define ISOLATE_ACTIVE		((__force isolate_mode_t)0x2)
+/* Isolate clean file */
+#define ISOLATE_CLEAN		((__force isolate_mode_t)0x4)
+/* Isolate unmapped file */
+#define ISOLATE_UNMAPPED	((__force isolate_mode_t)0x8)
+/* Isolate for asynchronous migration */
+#define ISOLATE_ASYNC_MIGRATE	((__force isolate_mode_t)0x10)
+
+/* LRU Isolation modes. */
+typedef unsigned __bitwise__ isolate_mode_t;
+
 enum zone_watermarks {
 	WMARK_MIN,
 	WMARK_LOW,

index 4ef452b..443ec43 100644
@@ -1484,7 +1484,7 @@ struct task_struct {
 #endif
 #ifdef CONFIG_CPUSETS
 	nodemask_t mems_allowed;	/* Protected by alloc_lock */
-	int mems_allowed_change_disable;
+	seqcount_t mems_allowed_seq;	/* Seqence no to catch updates */
 	int cpuset_mem_spread_rotor;
 	int cpuset_slab_spread_rotor;
 #endif

index a273468..e73799d 100644
@@ -243,11 +243,6 @@ static inline void lru_cache_add_file(struct page *page)
 	__lru_cache_add(page, LRU_INACTIVE_FILE);
 }
 
-/* LRU Isolation modes. */
-#define ISOLATE_INACTIVE 0	/* Isolate inactive pages. */
-#define ISOLATE_ACTIVE 1	/* Isolate active pages. */
-#define ISOLATE_BOTH 2		/* Isolate both active and inactive pages. */
-
 /* linux/mm/vmscan.c */
 extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 					gfp_t gfp_mask, nodemask_t *mask);

@@ -259,7 +254,7 @@ extern unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem,
 						unsigned int swappiness,
 						struct zone *zone,
 						unsigned long *nr_scanned);
-extern int __isolate_lru_page(struct page *page, int mode, int file);
+extern int __isolate_lru_page(struct page *page, isolate_mode_t mode, int file);
 extern unsigned long shrink_all_memory(unsigned long nr_pages);
 extern int vm_swappiness;
 extern int remove_mapping(struct address_space *mapping, struct page *page);

115 lines not on this page · raw message

88 lines not on this page · raw message

index 4712e3e..3d42aa3 100644
@@ -985,6 +985,9 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 #ifdef CONFIG_CGROUPS
 	init_rwsem(&sig->threadgroup_fork_lock);
 #endif
+#ifdef CONFIG_CPUSETS
+	seqcount_init(&tsk->mems_allowed_seq);
+#endif
 
 	sig->oom_adj = current->signal->oom_adj;
 	sig->oom_score_adj = current->signal->oom_score_adj;

index f1eb182..61fc450 100644
@@ -375,7 +375,9 @@ int second_overflow(unsigned long secs)
 			time_state = TIME_DEL;
 		break;
 	case TIME_INS:
-		if (secs % 86400 == 0) {
+		if (!(time_status & STA_INS))
+			time_state = TIME_OK;
+		else if (secs % 86400 == 0) {
 			leap = -1;
 			time_state = TIME_OOP;
 			time_tai++;

@@ -384,7 +386,9 @@ int second_overflow(unsigned long secs)
 		}
 		break;
 	case TIME_DEL:
-		if ((secs + 1) % 86400 == 0) {
+		if (!(time_status & STA_DEL))
+			time_state = TIME_OK;
+		else if ((secs + 1) % 86400 == 0) {
 			leap = 1;
 			time_tai--;
 			time_state = TIME_WAIT;

index adc5336..8ea7308 100644
@@ -35,10 +35,6 @@ struct compact_control {
 	unsigned long migrate_pfn;	/* isolate_migratepages search base */
 	bool sync;			/* Synchronous migration */
 
-	/* Account for isolated anon and file pages */
-	unsigned long nr_anon;
-	unsigned long nr_file;
-
 	unsigned int order;		/* order a direct compactor needs */
 	int migratetype;		/* MOVABLE, RECLAIMABLE etc */
 	struct zone *zone;

@@ -223,17 +219,13 @@ static void isolate_freepages(struct zone *zone,
 static void acct_isolated(struct zone *zone, struct compact_control *cc)
 {
 	struct page *page;
-	unsigned int count[NR_LRU_LISTS] = { 0, };
+	unsigned int count[2] = { 0, };
 
-	list_for_each_entry(page, &cc->migratepages, lru) {
-		int lru = page_lru_base_type(page);
-		count[lru]++;
-	}
+	list_for_each_entry(page, &cc->migratepages, lru)
+		count[!!page_is_file_cache(page)]++;
 
-	cc->nr_anon = count[LRU_ACTIVE_ANON] + count[LRU_INACTIVE_ANON];
-	cc->nr_file = count[LRU_ACTIVE_FILE] + count[LRU_INACTIVE_FILE];
-	__mod_zone_page_state(zone, NR_ISOLATED_ANON, cc->nr_anon);
-	__mod_zone_page_state(zone, NR_ISOLATED_FILE, cc->nr_file);
+	__mod_zone_page_state(zone, NR_ISOLATED_ANON, count[0]);
+	__mod_zone_page_state(zone, NR_ISOLATED_FILE, count[1]);
 }
 
 /* Similar to reclaim, but different enough that they don't share logic */

@@ -269,6 +261,7 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone,
 	unsigned long last_pageblock_nr = 0, pageblock_nr;
 	unsigned long nr_scanned = 0, nr_isolated = 0;
 	struct list_head *migratelist = &cc->migratepages;
+	isolate_mode_t mode = ISOLATE_ACTIVE|ISOLATE_INACTIVE;
 
 	/* Do not scan outside zone boundaries */
 	low_pfn = max(cc->migrate_pfn, zone->zone_start_pfn);

@@ -378,8 +371,11 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone,
 			continue;
 		}
 
+		if (!cc->sync)
+			mode |= ISOLATE_ASYNC_MIGRATE;
+
 		/* Try isolate the page */
-		if (__isolate_lru_page(page, ISOLATE_BOTH, 0) != 0)
+		if (__isolate_lru_page(page, mode, 0) != 0)
 			continue;
 
 		VM_BUG_ON(PageTransCompound(page));

@@ -581,7 +577,7 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 		nr_migrate = cc->nr_migratepages;
 		err = migrate_pages(&cc->migratepages, compaction_alloc,
 				(unsigned long)cc, false,
-				cc->sync);
+				cc->sync ? MIGRATE_SYNC_LIGHT : MIGRATE_ASYNC);
 		update_nr_listpages(cc);
 		nr_remaining = cc->nr_migratepages;
 

index b7d8603..10481eb 100644
@@ -516,10 +516,13 @@ struct page *__page_cache_alloc(gfp_t gfp)
 	struct page *page;
 
 	if (cpuset_do_page_mem_spread()) {
-		get_mems_allowed();
-		n = cpuset_mem_spread_node();
-		page = alloc_pages_exact_node(n, gfp, 0);
-		put_mems_allowed();
+		unsigned int cpuset_mems_cookie;
+		do {
+			cpuset_mems_cookie = get_mems_allowed();
+			n = cpuset_mem_spread_node();
+			page = alloc_pages_exact_node(n, gfp, 0);
+		} while (!put_mems_allowed(cpuset_mems_cookie) && !page);
+
 		return page;
 	}
 	return alloc_pages(gfp, 0);

index 05f8fd4..ae60a53 100644
@@ -460,8 +460,10 @@ static struct page *dequeue_huge_page_vma(struct hstate *h,
 	struct zonelist *zonelist;
 	struct zone *zone;
 	struct zoneref *z;
+	unsigned int cpuset_mems_cookie;
 
-	get_mems_allowed();
+retry_cpuset:
+	cpuset_mems_cookie = get_mems_allowed();
 	zonelist = huge_zonelist(vma, address,
 					htlb_alloc_mask, &mpol, &nodemask);
 	/*

@@ -488,10 +490,15 @@ static struct page *dequeue_huge_page_vma(struct hstate *h,
 			}
 		}
 	}
-err:
+
 	mpol_cond_put(mpol);
-	put_mems_allowed();
+	if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page))
+		goto retry_cpuset;
 	return page;
+
+err:
+	mpol_cond_put(mpol);
+	return NULL;
 }
 
 static void update_and_free_page(struct hstate *h, struct page *page)

index ffb99b4..57cdf5a 100644
@@ -1251,7 +1251,8 @@ mem_cgroup_get_reclaim_stat_from_page(struct page *page)
 unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
 					struct list_head *dst,
 					unsigned long *scanned, int order,
-					int mode, struct zone *z,
+					isolate_mode_t mode,
+					struct zone *z,
 					struct mem_cgroup *mem_cont,
 					int active, int file)
 {

index 740c4f5..6496748 100644
@@ -1464,7 +1464,7 @@ int soft_offline_page(struct page *page, int flags)
 					    page_is_file_cache(page));
 		list_add(&page->lru, &pagelist);
 		ret = migrate_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL,
-								0, true);
+							0, MIGRATE_SYNC);
 		if (ret) {
 			putback_lru_pages(&pagelist);
 			pr_info("soft offline: %#lx: migration failed %d, type %lx\n",

index c46887b..ae5a3f2 100644
@@ -747,7 +747,7 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn)
 		}
 		/* this function returns # of failed pages */
 		ret = migrate_pages(&source, hotremove_migrate_alloc, 0,
-								true, true);
+							true, MIGRATE_SYNC);
 		if (ret)
 			putback_lru_pages(&source);
 	}

index 3dac2d1..cff919f 100644
@@ -926,7 +926,7 @@ static int migrate_to_node(struct mm_struct *mm, int source, int dest,
 
 	if (!list_empty(&pagelist)) {
 		err = migrate_pages(&pagelist, new_node_page, dest,
-								false, true);
+							false, MIGRATE_SYNC);
 		if (err)
 			putback_lru_pages(&pagelist);
 	}

@@ -1810,18 +1810,24 @@ struct page *
 alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
 		unsigned long addr, int node)
 {
-	struct mempolicy *pol = get_vma_policy(current, vma, addr);
+	struct mempolicy *pol;
 	struct zonelist *zl;
 	struct page *page;
+	unsigned int cpuset_mems_cookie;
+
+retry_cpuset:
+	pol = get_vma_policy(current, vma, addr);
+	cpuset_mems_cookie = get_mems_allowed();
 
-	get_mems_allowed();
 	if (unlikely(pol->mode == MPOL_INTERLEAVE)) {
 		unsigned nid;
 
 		nid = interleave_nid(pol, vma, addr, PAGE_SHIFT + order);
 		mpol_cond_put(pol);
 		page = alloc_page_interleave(gfp, order, nid);
-		put_mems_allowed();
+		if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page))
+			goto retry_cpuset;
+
 		return page;
 	}
 	zl = policy_zonelist(gfp, pol, node);

@@ -1832,7 +1838,8 @@ alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
 		struct page *page =  __alloc_pages_nodemask(gfp, order,
 						zl, policy_nodemask(gfp, pol));
 		__mpol_put(pol);
-		put_mems_allowed();
+		if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page))
+			goto retry_cpuset;
 		return page;
 	}
 	/*

@@ -1840,7 +1847,8 @@ alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
 	 */
 	page = __alloc_pages_nodemask(gfp, order, zl,
 				      policy_nodemask(gfp, pol));
-	put_mems_allowed();
+	if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page))
+		goto retry_cpuset;
 	return page;
 }
 

@@ -1867,11 +1875,14 @@ struct page *alloc_pages_current(gfp_t gfp, unsigned order)
 {
 	struct mempolicy *pol = current->mempolicy;
 	struct page *page;
+	unsigned int cpuset_mems_cookie;
 
 	if (!pol || in_interrupt() || (gfp & __GFP_THISNODE))
 		pol = &default_policy;
 
-	get_mems_allowed();
+retry_cpuset:
+	cpuset_mems_cookie = get_mems_allowed();
+
 	/*
 	 * No reference counting needed for current->mempolicy
 	 * nor system default_policy

@@ -1882,7 +1893,10 @@ struct page *alloc_pages_current(gfp_t gfp, unsigned order)
 		page = __alloc_pages_nodemask(gfp, order,
 				policy_zonelist(gfp, pol, numa_node_id()),
 				policy_nodemask(gfp, pol));
-	put_mems_allowed();
+
+	if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page))
+		goto retry_cpuset;
+
 	return page;
 }
 EXPORT_SYMBOL(alloc_pages_current);

412 lines not on this page · raw message

207 lines not on this page · raw message

index d96e223..a67f812 100644
@@ -3218,12 +3218,10 @@ static void *alternate_node_alloc(struct kmem_cache *cachep, gfp_t flags)
 	if (in_interrupt() || (flags & __GFP_THISNODE))
 		return NULL;
 	nid_alloc = nid_here = numa_mem_id();
-	get_mems_allowed();
 	if (cpuset_do_slab_mem_spread() && (cachep->flags & SLAB_MEM_SPREAD))
 		nid_alloc = cpuset_slab_spread_node();
 	else if (current->mempolicy)
 		nid_alloc = slab_node(current->mempolicy);
-	put_mems_allowed();
 	if (nid_alloc != nid_here)
 		return ____cache_alloc_node(cachep, flags, nid_alloc);
 	return NULL;

@@ -3246,14 +3244,17 @@ static void *fallback_alloc(struct kmem_cache *cache, gfp_t flags)
 	enum zone_type high_zoneidx = gfp_zone(flags);
 	void *obj = NULL;
 	int nid;
+	unsigned int cpuset_mems_cookie;
 
 	if (flags & __GFP_THISNODE)
 		return NULL;
 
-	get_mems_allowed();
-	zonelist = node_zonelist(slab_node(current->mempolicy), flags);
 	local_flags = flags & (GFP_CONSTRAINT_MASK|GFP_RECLAIM_MASK);
 
+retry_cpuset:
+	cpuset_mems_cookie = get_mems_allowed();
+	zonelist = node_zonelist(slab_node(current->mempolicy), flags);
+
 retry:
 	/*
 	 * Look through allowed nodes for objects available

@@ -3306,7 +3307,9 @@ retry:
 			}
 		}
 	}
-	put_mems_allowed();
+
+	if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !obj))
+		goto retry_cpuset;
 	return obj;
 }
 

index 10ab233..ae6e80e 100644
@@ -1457,6 +1457,7 @@ static struct page *get_any_partial(struct kmem_cache *s, gfp_t flags)
 	struct zone *zone;
 	enum zone_type high_zoneidx = gfp_zone(flags);
 	struct page *page;
+	unsigned int cpuset_mems_cookie;
 
 	/*
 	 * The defrag ratio allows a configuration of the tradeoffs between

@@ -1480,23 +1481,32 @@ static struct page *get_any_partial(struct kmem_cache *s, gfp_t flags)
 			get_cycles() % 1024 > s->remote_node_defrag_ratio)
 		return NULL;
 
-	get_mems_allowed();
-	zonelist = node_zonelist(slab_node(current->mempolicy), flags);
-	for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) {
-		struct kmem_cache_node *n;
-
-		n = get_node(s, zone_to_nid(zone));
-
-		if (n && cpuset_zone_allowed_hardwall(zone, flags) &&
-				n->nr_partial > s->min_partial) {
-			page = get_partial_node(n);
-			if (page) {
-				put_mems_allowed();
-				return page;
+	do {
+		cpuset_mems_cookie = get_mems_allowed();
+		zonelist = node_zonelist(slab_node(current->mempolicy), flags);
+		for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) {
+			struct kmem_cache_node *n;
+
+			n = get_node(s, zone_to_nid(zone));
+
+			if (n && cpuset_zone_allowed_hardwall(zone, flags) &&
+					n->nr_partial > s->min_partial) {
+				page = get_partial_node(n);
+				if (page) {
+					/*
+					 * Return the object even if
+					 * put_mems_allowed indicated that
+					 * the cpuset mems_allowed was
+					 * updated in parallel. It's a
+					 * harmless race between the alloc
+					 * and the cpuset update.
+					 */
+					put_mems_allowed(cpuset_mems_cookie);
+					return page;
+				}
 			}
 		}
-	}
-	put_mems_allowed();
+	} while (!put_mems_allowed(cpuset_mems_cookie));
 #endif
 	return NULL;
 }

537 lines not on this page · raw message

index 20c18b7..6559013 100644
@@ -78,7 +78,7 @@ void vm_events_fold_cpu(int cpu)
  *
  * vm_stat contains the global counters
  */
-atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS];
+atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS] __cacheline_aligned_in_smp;
 EXPORT_SYMBOL(vm_stat);
 
 #ifdef CONFIG_SMP