summaryrefslogtreecommitdiff
path: root/mm
diff options
context:
space:
mode:
Diffstat (limited to 'mm')
-rw-r--r--mm/Kconfig17
-rw-r--r--mm/Makefile4
-rw-r--r--mm/backing-dev.c6
-rw-r--r--mm/bootmem.c6
-rw-r--r--mm/bounce.c8
-rw-r--r--mm/compaction.c147
-rw-r--r--mm/frontswap.c344
-rw-r--r--mm/internal.h9
-rw-r--r--mm/madvise.c18
-rw-r--r--mm/memblock.c115
-rw-r--r--mm/memcontrol.c6
-rw-r--r--mm/memory-failure.c20
-rw-r--r--mm/memory.c21
-rw-r--r--mm/memory_hotplug.c2
-rw-r--r--mm/mempolicy.c10
-rw-r--r--mm/migrate.c5
-rw-r--r--mm/nobootmem.c40
-rw-r--r--mm/nommu.c2
-rw-r--r--mm/oom_kill.c21
-rw-r--r--mm/page-writeback.c107
-rw-r--r--mm/page_alloc.c15
-rw-r--r--mm/page_cgroup.c4
-rw-r--r--mm/page_io.c12
-rw-r--r--mm/pagewalk.c1
-rw-r--r--mm/percpu-vm.c1
-rw-r--r--mm/shmem.c253
-rw-r--r--mm/slab.c406
-rw-r--r--mm/slab.h33
-rw-r--r--mm/slab_common.c120
-rw-r--r--mm/slob.c152
-rw-r--r--mm/slub.c436
-rw-r--r--mm/sparse.c20
-rw-r--r--mm/swapfile.c66
-rw-r--r--mm/vmalloc.c36
-rw-r--r--mm/vmscan.c17
35 files changed, 1407 insertions, 1073 deletions
diff --git a/mm/Kconfig b/mm/Kconfig
index b2176374b98e..82fed4eb2b6f 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -389,3 +389,20 @@ config CLEANCACHE
in a negligible performance hit.
If unsure, say Y to enable cleancache
+
+config FRONTSWAP
+ bool "Enable frontswap to cache swap pages if tmem is present"
+ depends on SWAP
+ default n
+ help
+ Frontswap is so named because it can be thought of as the opposite
+ of a "backing" store for a swap device. The data is stored into
+ "transcendent memory", memory that is not directly accessible or
+ addressable by the kernel and is of unknown and possibly
+ time-varying size. When space in transcendent memory is available,
+ a significant swap I/O reduction may be achieved. When none is
+ available, all frontswap calls are reduced to a single pointer-
+ compare-against-NULL resulting in a negligible performance hit
+ and swap data is stored as normal on the matching swap device.
+
+ If unsure, say Y to enable frontswap.
diff --git a/mm/Makefile b/mm/Makefile
index a156285ce88d..8e81fe263c94 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -16,7 +16,8 @@ obj-y := filemap.o mempool.o oom_kill.o fadvise.o \
readahead.o swap.o truncate.o vmscan.o shmem.o \
prio_tree.o util.o mmzone.o vmstat.o backing-dev.o \
page_isolation.o mm_init.o mmu_context.o percpu.o \
- compaction.o $(mmu-y)
+ compaction.o slab_common.o $(mmu-y)
+
obj-y += init-mm.o
ifdef CONFIG_NO_BOOTMEM
@@ -29,6 +30,7 @@ obj-$(CONFIG_HAVE_MEMBLOCK) += memblock.o
obj-$(CONFIG_BOUNCE) += bounce.o
obj-$(CONFIG_SWAP) += page_io.o swap_state.o swapfile.o
+obj-$(CONFIG_FRONTSWAP) += frontswap.o
obj-$(CONFIG_HAS_DMA) += dmapool.o
obj-$(CONFIG_HUGETLBFS) += hugetlb.o
obj-$(CONFIG_NUMA) += mempolicy.o
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index dd8e2aafb07e..3387aea11209 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -677,7 +677,7 @@ int bdi_init(struct backing_dev_info *bdi)
bdi->min_ratio = 0;
bdi->max_ratio = 100;
- bdi->max_prop_frac = PROP_FRAC_BASE;
+ bdi->max_prop_frac = FPROP_FRAC_BASE;
spin_lock_init(&bdi->wb_lock);
INIT_LIST_HEAD(&bdi->bdi_list);
INIT_LIST_HEAD(&bdi->work_list);
@@ -700,7 +700,7 @@ int bdi_init(struct backing_dev_info *bdi)
bdi->write_bandwidth = INIT_BW;
bdi->avg_write_bandwidth = INIT_BW;
- err = prop_local_init_percpu(&bdi->completions);
+ err = fprop_local_init_percpu(&bdi->completions);
if (err) {
err:
@@ -744,7 +744,7 @@ void bdi_destroy(struct backing_dev_info *bdi)
for (i = 0; i < NR_BDI_STAT_ITEMS; i++)
percpu_counter_destroy(&bdi->bdi_stat[i]);
- prop_local_destroy_percpu(&bdi->completions);
+ fprop_local_destroy_percpu(&bdi->completions);
}
EXPORT_SYMBOL(bdi_destroy);
diff --git a/mm/bootmem.c b/mm/bootmem.c
index ec4fcb7a56c8..bcb63ac48cc5 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -698,7 +698,7 @@ void * __init __alloc_bootmem(unsigned long size, unsigned long align,
return ___alloc_bootmem(size, align, goal, limit);
}
-static void * __init ___alloc_bootmem_node_nopanic(pg_data_t *pgdat,
+void * __init ___alloc_bootmem_node_nopanic(pg_data_t *pgdat,
unsigned long size, unsigned long align,
unsigned long goal, unsigned long limit)
{
@@ -710,6 +710,10 @@ again:
if (ptr)
return ptr;
+ /* do not panic in alloc_bootmem_bdata() */
+ if (limit && goal + size > limit)
+ limit = 0;
+
ptr = alloc_bootmem_bdata(pgdat->bdata, size, align, goal, limit);
if (ptr)
return ptr;
diff --git a/mm/bounce.c b/mm/bounce.c
index d1be02ca1889..042086775561 100644
--- a/mm/bounce.c
+++ b/mm/bounce.c
@@ -24,23 +24,25 @@
static mempool_t *page_pool, *isa_page_pool;
-#ifdef CONFIG_HIGHMEM
+#if defined(CONFIG_HIGHMEM) || defined(CONFIG_NEED_BOUNCE_POOL)
static __init int init_emergency_pool(void)
{
-#ifndef CONFIG_MEMORY_HOTPLUG
+#if defined(CONFIG_HIGHMEM) && !defined(CONFIG_MEMORY_HOTPLUG)
if (max_pfn <= max_low_pfn)
return 0;
#endif
page_pool = mempool_create_page_pool(POOL_SIZE, 0);
BUG_ON(!page_pool);
- printk("highmem bounce pool size: %d pages\n", POOL_SIZE);
+ printk("bounce pool size: %d pages\n", POOL_SIZE);
return 0;
}
__initcall(init_emergency_pool);
+#endif
+#ifdef CONFIG_HIGHMEM
/*
* highmem version, map in to vec
*/
diff --git a/mm/compaction.c b/mm/compaction.c
index 4ac338af5120..2f42d9528539 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -236,7 +236,7 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
*/
while (unlikely(too_many_isolated(zone))) {
/* async migration should just abort */
- if (cc->mode != COMPACT_SYNC)
+ if (!cc->sync)
return 0;
congestion_wait(BLK_RW_ASYNC, HZ/10);
@@ -304,8 +304,7 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
* satisfies the allocation
*/
pageblock_nr = low_pfn >> pageblock_order;
- if (cc->mode != COMPACT_SYNC &&
- last_pageblock_nr != pageblock_nr &&
+ if (!cc->sync && last_pageblock_nr != pageblock_nr &&
!migrate_async_suitable(get_pageblock_migratetype(page))) {
low_pfn += pageblock_nr_pages;
low_pfn = ALIGN(low_pfn, pageblock_nr_pages) - 1;
@@ -326,7 +325,7 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
continue;
}
- if (cc->mode != COMPACT_SYNC)
+ if (!cc->sync)
mode |= ISOLATE_ASYNC_MIGRATE;
lruvec = mem_cgroup_page_lruvec(page, zone);
@@ -361,90 +360,27 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
#endif /* CONFIG_COMPACTION || CONFIG_CMA */
#ifdef CONFIG_COMPACTION
-/*
- * Returns true if MIGRATE_UNMOVABLE pageblock was successfully
- * converted to MIGRATE_MOVABLE type, false otherwise.
- */
-static bool rescue_unmovable_pageblock(struct page *page)
-{
- unsigned long pfn, start_pfn, end_pfn;
- struct page *start_page, *end_page;
-
- pfn = page_to_pfn(page);
- start_pfn = pfn & ~(pageblock_nr_pages - 1);
- end_pfn = start_pfn + pageblock_nr_pages;
-
- start_page = pfn_to_page(start_pfn);
- end_page = pfn_to_page(end_pfn);
-
- /* Do not deal with pageblocks that overlap zones */
- if (page_zone(start_page) != page_zone(end_page))
- return false;
-
- for (page = start_page, pfn = start_pfn; page < end_page; pfn++,
- page++) {
- if (!pfn_valid_within(pfn))
- continue;
-
- if (PageBuddy(page)) {
- int order = page_order(page);
-
- pfn += (1 << order) - 1;
- page += (1 << order) - 1;
-
- continue;
- } else if (page_count(page) == 0 || PageLRU(page))
- continue;
-
- return false;
- }
-
- set_pageblock_migratetype(page, MIGRATE_MOVABLE);
- move_freepages_block(page_zone(page), page, MIGRATE_MOVABLE);
- return true;
-}
-
-enum smt_result {
- GOOD_AS_MIGRATION_TARGET,
- FAIL_UNMOVABLE_TARGET,
- FAIL_BAD_TARGET,
-};
-/*
- * Returns GOOD_AS_MIGRATION_TARGET if the page is within a block
- * suitable for migration to, FAIL_UNMOVABLE_TARGET if the page
- * is within a MIGRATE_UNMOVABLE block, FAIL_BAD_TARGET otherwise.
- */
-static enum smt_result suitable_migration_target(struct page *page,
- struct compact_control *cc)
+/* Returns true if the page is within a block suitable for migration to */
+static bool suitable_migration_target(struct page *page)
{
int migratetype = get_pageblock_migratetype(page);
/* Don't interfere with memory hot-remove or the min_free_kbytes blocks */
if (migratetype == MIGRATE_ISOLATE || migratetype == MIGRATE_RESERVE)
- return FAIL_BAD_TARGET;
+ return false;
/* If the page is a large free page, then allow migration */
if (PageBuddy(page) && page_order(page) >= pageblock_order)
- return GOOD_AS_MIGRATION_TARGET;
+ return true;
/* If the block is MIGRATE_MOVABLE or MIGRATE_CMA, allow migration */
- if (cc->mode != COMPACT_ASYNC_UNMOVABLE &&
- migrate_async_suitable(migratetype))
- return GOOD_AS_MIGRATION_TARGET;
-
- if (cc->mode == COMPACT_ASYNC_MOVABLE &&
- migratetype == MIGRATE_UNMOVABLE)
- return FAIL_UNMOVABLE_TARGET;
-
- if (cc->mode != COMPACT_ASYNC_MOVABLE &&
- migratetype == MIGRATE_UNMOVABLE &&
- rescue_unmovable_pageblock(page))
- return GOOD_AS_MIGRATION_TARGET;
+ if (migrate_async_suitable(migratetype))
+ return true;
/* Otherwise skip the block */
- return FAIL_BAD_TARGET;
+ return false;
}
/*
@@ -478,13 +414,6 @@ static void isolate_freepages(struct zone *zone,
zone_end_pfn = zone->zone_start_pfn + zone->spanned_pages;
/*
- * isolate_freepages() may be called more than once during
- * compact_zone_order() run and we want only the most recent
- * count.
- */
- cc->nr_pageblocks_skipped = 0;
-
- /*
* Isolate free pages until enough are available to migrate the
* pages on cc->migratepages. We stop searching if the migrate
* and free page scanners meet or enough free pages are isolated.
@@ -492,7 +421,6 @@ static void isolate_freepages(struct zone *zone,
for (; pfn > low_pfn && cc->nr_migratepages > nr_freepages;
pfn -= pageblock_nr_pages) {
unsigned long isolated;
- enum smt_result ret;
if (!pfn_valid(pfn))
continue;
@@ -509,12 +437,9 @@ static void isolate_freepages(struct zone *zone,
continue;
/* Check the block is suitable for migration */
- ret = suitable_migration_target(page, cc);
- if (ret != GOOD_AS_MIGRATION_TARGET) {
- if (ret == FAIL_UNMOVABLE_TARGET)
- cc->nr_pageblocks_skipped++;
+ if (!suitable_migration_target(page))
continue;
- }
+
/*
* Found a block suitable for isolating free pages from. Now
* we disabled interrupts, double check things are ok and
@@ -523,14 +448,12 @@ static void isolate_freepages(struct zone *zone,
*/
isolated = 0;
spin_lock_irqsave(&zone->lock, flags);
- ret = suitable_migration_target(page, cc);
- if (ret == GOOD_AS_MIGRATION_TARGET) {
+ if (suitable_migration_target(page)) {
end_pfn = min(pfn + pageblock_nr_pages, zone_end_pfn);
isolated = isolate_freepages_block(pfn, end_pfn,
freelist, false);
nr_freepages += isolated;
- } else if (ret == FAIL_UNMOVABLE_TARGET)
- cc->nr_pageblocks_skipped++;
+ }
spin_unlock_irqrestore(&zone->lock, flags);
/*
@@ -762,9 +685,8 @@ 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->freepages, false,
- (cc->mode == COMPACT_SYNC) ? MIGRATE_SYNC_LIGHT
- : MIGRATE_ASYNC);
+ (unsigned long)cc, false,
+ cc->sync ? MIGRATE_SYNC_LIGHT : MIGRATE_ASYNC);
update_nr_listpages(cc);
nr_remaining = cc->nr_migratepages;
@@ -779,8 +701,11 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
if (err) {
putback_lru_pages(&cc->migratepages);
cc->nr_migratepages = 0;
+ if (err == -ENOMEM) {
+ ret = COMPACT_PARTIAL;
+ goto out;
+ }
}
-
}
out:
@@ -793,8 +718,7 @@ out:
static unsigned long compact_zone_order(struct zone *zone,
int order, gfp_t gfp_mask,
- enum compact_mode mode,
- unsigned long *nr_pageblocks_skipped)
+ bool sync)
{
struct compact_control cc = {
.nr_freepages = 0,
@@ -802,17 +726,12 @@ static unsigned long compact_zone_order(struct zone *zone,
.order = order,
.migratetype = allocflags_to_migratetype(gfp_mask),
.zone = zone,
- .mode = mode,
+ .sync = sync,
};
- unsigned long rc;
-
INIT_LIST_HEAD(&cc.freepages);
INIT_LIST_HEAD(&cc.migratepages);
- rc = compact_zone(zone, &cc);
- *nr_pageblocks_skipped = cc.nr_pageblocks_skipped;
-
- return rc;
+ return compact_zone(zone, &cc);
}
int sysctl_extfrag_threshold = 500;
@@ -837,8 +756,6 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist,
struct zoneref *z;
struct zone *zone;
int rc = COMPACT_SKIPPED;
- unsigned long nr_pageblocks_skipped;
- enum compact_mode mode;
/*
* Check whether it is worth even starting compaction. The order check is
@@ -855,22 +772,12 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist,
nodemask) {
int status;
- mode = sync ? COMPACT_SYNC : COMPACT_ASYNC_MOVABLE;
-retry:
- status = compact_zone_order(zone, order, gfp_mask, mode,
- &nr_pageblocks_skipped);
+ status = compact_zone_order(zone, order, gfp_mask, sync);
rc = max(status, rc);
/* If a normal allocation would succeed, stop compacting */
if (zone_watermark_ok(zone, order, low_wmark_pages(zone), 0, 0))
break;
-
- if (rc == COMPACT_COMPLETE && mode == COMPACT_ASYNC_MOVABLE) {
- if (nr_pageblocks_skipped) {
- mode = COMPACT_ASYNC_UNMOVABLE;
- goto retry;
- }
- }
}
return rc;
@@ -904,7 +811,7 @@ static int __compact_pgdat(pg_data_t *pgdat, struct compact_control *cc)
if (ok && cc->order > zone->compact_order_failed)
zone->compact_order_failed = cc->order + 1;
/* Currently async compaction is never deferred. */
- else if (!ok && cc->mode == COMPACT_SYNC)
+ else if (!ok && cc->sync)
defer_compaction(zone, cc->order);
}
@@ -919,7 +826,7 @@ int compact_pgdat(pg_data_t *pgdat, int order)
{
struct compact_control cc = {
.order = order,
- .mode = COMPACT_ASYNC_MOVABLE,
+ .sync = false,
};
return __compact_pgdat(pgdat, &cc);
@@ -929,7 +836,7 @@ static int compact_node(int nid)
{
struct compact_control cc = {
.order = -1,
- .mode = COMPACT_SYNC,
+ .sync = true,
};
return __compact_pgdat(NODE_DATA(nid), &cc);
diff --git a/mm/frontswap.c b/mm/frontswap.c
new file mode 100644
index 000000000000..6b3e71a2cd48
--- /dev/null
+++ b/mm/frontswap.c
@@ -0,0 +1,344 @@
+/*
+ * Frontswap frontend
+ *
+ * This code provides the generic "frontend" layer to call a matching
+ * "backend" driver implementation of frontswap. See
+ * Documentation/vm/frontswap.txt for more information.
+ *
+ * Copyright (C) 2009-2012 Oracle Corp. All rights reserved.
+ * Author: Dan Magenheimer
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ */
+
+#include <linux/mman.h>
+#include <linux/swap.h>
+#include <linux/swapops.h>
+#include <linux/security.h>
+#include <linux/module.h>
+#include <linux/debugfs.h>
+#include <linux/frontswap.h>
+#include <linux/swapfile.h>
+
+/*
+ * frontswap_ops is set by frontswap_register_ops to contain the pointers
+ * to the frontswap "backend" implementation functions.
+ */
+static struct frontswap_ops frontswap_ops __read_mostly;
+
+/*
+ * This global enablement flag reduces overhead on systems where frontswap_ops
+ * has not been registered, so is preferred to the slower alternative: a
+ * function call that checks a non-global.
+ */
+bool frontswap_enabled __read_mostly;
+EXPORT_SYMBOL(frontswap_enabled);
+
+/*
+ * If enabled, frontswap_store will return failure even on success. As
+ * a result, the swap subsystem will always write the page to swap, in
+ * effect converting frontswap into a writethrough cache. In this mode,
+ * there is no direct reduction in swap writes, but a frontswap backend
+ * can unilaterally "reclaim" any pages in use with no data loss, thus
+ * providing increases control over maximum memory usage due to frontswap.
+ */
+static bool frontswap_writethrough_enabled __read_mostly;
+
+#ifdef CONFIG_DEBUG_FS
+/*
+ * Counters available via /sys/kernel/debug/frontswap (if debugfs is
+ * properly configured). These are for information only so are not protected
+ * against increment races.
+ */
+static u64 frontswap_loads;
+static u64 frontswap_succ_stores;
+static u64 frontswap_failed_stores;
+static u64 frontswap_invalidates;
+
+static inline void inc_frontswap_loads(void) {
+ frontswap_loads++;
+}
+static inline void inc_frontswap_succ_stores(void) {
+ frontswap_succ_stores++;
+}
+static inline void inc_frontswap_failed_stores(void) {
+ frontswap_failed_stores++;
+}
+static inline void inc_frontswap_invalidates(void) {
+ frontswap_invalidates++;
+}
+#else
+static inline void inc_frontswap_loads(void) { }
+static inline void inc_frontswap_succ_stores(void) { }
+static inline void inc_frontswap_failed_stores(void) { }
+static inline void inc_frontswap_invalidates(void) { }
+#endif
+/*
+ * Register operations for frontswap, returning previous thus allowing
+ * detection of multiple backends and possible nesting.
+ */
+struct frontswap_ops frontswap_register_ops(struct frontswap_ops *ops)
+{
+ struct frontswap_ops old = frontswap_ops;
+
+ frontswap_ops = *ops;
+ frontswap_enabled = true;
+ return old;
+}
+EXPORT_SYMBOL(frontswap_register_ops);
+
+/*
+ * Enable/disable frontswap writethrough (see above).
+ */
+void frontswap_writethrough(bool enable)
+{
+ frontswap_writethrough_enabled = enable;
+}
+EXPORT_SYMBOL(frontswap_writethrough);
+
+/*
+ * Called when a swap device is swapon'd.
+ */
+void __frontswap_init(unsigned type)
+{
+ struct swap_info_struct *sis = swap_info[type];
+
+ BUG_ON(sis == NULL);
+ if (sis->frontswap_map == NULL)
+ return;
+ frontswap_ops.init(type);
+}
+EXPORT_SYMBOL(__frontswap_init);
+
+static inline void __frontswap_clear(struct swap_info_struct *sis, pgoff_t offset)
+{
+ frontswap_clear(sis, offset);
+ atomic_dec(&sis->frontswap_pages);
+}
+
+/*
+ * "Store" data from a page to frontswap and associate it with the page's
+ * swaptype and offset. Page must be locked and in the swap cache.
+ * If frontswap already contains a page with matching swaptype and
+ * offset, the frontswap implementation may either overwrite the data and
+ * return success or invalidate the page from frontswap and return failure.
+ */
+int __frontswap_store(struct page *page)
+{
+ int ret = -1, dup = 0;
+ swp_entry_t entry = { .val = page_private(page), };
+ int type = swp_type(entry);
+ struct swap_info_struct *sis = swap_info[type];
+ pgoff_t offset = swp_offset(entry);
+
+ BUG_ON(!PageLocked(page));
+ BUG_ON(sis == NULL);
+ if (frontswap_test(sis, offset))
+ dup = 1;
+ ret = frontswap_ops.store(type, offset, page);
+ if (ret == 0) {
+ frontswap_set(sis, offset);
+ inc_frontswap_succ_stores();
+ if (!dup)
+ atomic_inc(&sis->frontswap_pages);
+ } else {
+ /*
+ failed dup always results in automatic invalidate of
+ the (older) page from frontswap
+ */
+ inc_frontswap_failed_stores();
+ if (dup)
+ __frontswap_clear(sis, offset);
+ }
+ if (frontswap_writethrough_enabled)
+ /* report failure so swap also writes to swap device */
+ ret = -1;
+ return ret;
+}
+EXPORT_SYMBOL(__frontswap_store);
+
+/*
+ * "Get" data from frontswap associated with swaptype and offset that were
+ * specified when the data was put to frontswap and use it to fill the
+ * specified page with data. Page must be locked and in the swap cache.
+ */
+int __frontswap_load(struct page *page)
+{
+ int ret = -1;
+ swp_entry_t entry = { .val = page_private(page), };
+ int type = swp_type(entry);
+ struct swap_info_struct *sis = swap_info[type];
+ pgoff_t offset = swp_offset(entry);
+
+ BUG_ON(!PageLocked(page));
+ BUG_ON(sis == NULL);
+ if (frontswap_test(sis, offset))
+ ret = frontswap_ops.load(type, offset, page);
+ if (ret == 0)
+ inc_frontswap_loads();
+ return ret;
+}
+EXPORT_SYMBOL(__frontswap_load);
+
+/*
+ * Invalidate any data from frontswap associated with the specified swaptype
+ * and offset so that a subsequent "get" will fail.
+ */
+void __frontswap_invalidate_page(unsigned type, pgoff_t offset)
+{
+ struct swap_info_struct *sis = swap_info[type];
+
+ BUG_ON(sis == NULL);
+ if (frontswap_test(sis, offset)) {
+ frontswap_ops.invalidate_page(type, offset);
+ __frontswap_clear(sis, offset);
+ inc_frontswap_invalidates();
+ }
+}
+EXPORT_SYMBOL(__frontswap_invalidate_page);
+
+/*
+ * Invalidate all data from frontswap associated with all offsets for the
+ * specified swaptype.
+ */
+void __frontswap_invalidate_area(unsigned type)
+{
+ struct swap_info_struct *sis = swap_info[type];
+
+ BUG_ON(sis == NULL);
+ if (sis->frontswap_map == NULL)
+ return;
+ frontswap_ops.invalidate_area(type);
+ atomic_set(&sis->frontswap_pages, 0);
+ memset(sis->frontswap_map, 0, sis->max / sizeof(long));
+}
+EXPORT_SYMBOL(__frontswap_invalidate_area);
+
+static unsigned long __frontswap_curr_pages(void)
+{
+ int type;
+ unsigned long totalpages = 0;
+ struct swap_info_struct *si = NULL;
+
+ assert_spin_locked(&swap_lock);
+ for (type = swap_list.head; type >= 0; type = si->next) {
+ si = swap_info[type];
+ totalpages += atomic_read(&si->frontswap_pages);
+ }
+ return totalpages;
+}
+
+static int __frontswap_unuse_pages(unsigned long total, unsigned long *unused,
+ int *swapid)
+{
+ int ret = -EINVAL;
+ struct swap_info_struct *si = NULL;
+ int si_frontswap_pages;
+ unsigned long total_pages_to_unuse = total;
+ unsigned long pages = 0, pages_to_unuse = 0;
+ int type;
+
+ assert_spin_locked(&swap_lock);
+ for (type = swap_list.head; type >= 0; type = si->next) {
+ si = swap_info[type];
+ si_frontswap_pages = atomic_read(&si->frontswap_pages);
+ if (total_pages_to_unuse < si_frontswap_pages) {
+ pages = pages_to_unuse = total_pages_to_unuse;
+ } else {
+ pages = si_frontswap_pages;
+ pages_to_unuse = 0; /* unuse all */
+ }
+ /* ensure there is enough RAM to fetch pages from frontswap */
+ if (security_vm_enough_memory_mm(current->mm, pages)) {
+ ret = -ENOMEM;
+ continue;
+ }
+ vm_unacct_memory(pages);
+ *unused = pages_to_unuse;
+ *swapid = type;
+ ret = 0;
+ break;
+ }
+
+ return ret;
+}
+
+static int __frontswap_shrink(unsigned long target_pages,
+ unsigned long *pages_to_unuse,
+ int *type)
+{
+ unsigned long total_pages = 0, total_pages_to_unuse;
+
+ assert_spin_locked(&swap_lock);
+
+ total_pages = __frontswap_curr_pages();
+ if (total_pages <= target_pages) {
+ /* Nothing to do */
+ *pages_to_unuse = 0;
+ return 0;
+ }
+ total_pages_to_unuse = total_pages - target_pages;
+ return __frontswap_unuse_pages(total_pages_to_unuse, pages_to_unuse, type);
+}
+
+/*
+ * Frontswap, like a true swap device, may unnecessarily retain pages
+ * under certain circumstances; "shrink" frontswap is essentially a
+ * "partial swapoff" and works by calling try_to_unuse to attempt to
+ * unuse enough frontswap pages to attempt to -- subject to memory
+ * constraints -- reduce the number of pages in frontswap to the
+ * number given in the parameter target_pages.
+ */
+void frontswap_shrink(unsigned long target_pages)
+{
+ unsigned long pages_to_unuse = 0;
+ int type, ret;
+
+ /*
+ * we don't want to hold swap_lock while doing a very
+ * lengthy try_to_unuse, but swap_list may change
+ * so restart scan from swap_list.head each time
+ */
+ spin_lock(&swap_lock);
+ ret = __frontswap_shrink(target_pages, &pages_to_unuse, &type);
+ spin_unlock(&swap_lock);
+ if (ret == 0 && pages_to_unuse)
+ try_to_unuse(type, true, pages_to_unuse);
+ return;
+}
+EXPORT_SYMBOL(frontswap_shrink);
+
+/*
+ * Count and return the number of frontswap pages across all
+ * swap devices. This is exported so that backend drivers can
+ * determine current usage without reading debugfs.
+ */
+unsigned long frontswap_curr_pages(void)
+{
+ unsigned long totalpages = 0;
+
+ spin_lock(&swap_lock);
+ totalpages = __frontswap_curr_pages();
+ spin_unlock(&swap_lock);
+
+ return totalpages;
+}
+EXPORT_SYMBOL(frontswap_curr_pages);
+
+static int __init init_frontswap(void)
+{
+#ifdef CONFIG_DEBUG_FS
+ struct dentry *root = debugfs_create_dir("frontswap", NULL);
+ if (root == NULL)
+ return -ENXIO;
+ debugfs_create_u64("loads", S_IRUGO, root, &frontswap_loads);
+ debugfs_create_u64("succ_stores", S_IRUGO, root, &frontswap_succ_stores);
+ debugfs_create_u64("failed_stores", S_IRUGO, root,
+ &frontswap_failed_stores);
+ debugfs_create_u64("invalidates", S_IRUGO,
+ root, &frontswap_invalidates);
+#endif
+ return 0;
+}
+
+module_init(init_frontswap);
diff --git a/mm/internal.h b/mm/internal.h
index 5cbb78190041..2ba87fbfb75b 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -94,9 +94,6 @@ extern void putback_lru_page(struct page *page);
/*
* in mm/page_alloc.c
*/
-extern void set_pageblock_migratetype(struct page *page, int migratetype);
-extern int move_freepages_block(struct zone *zone, struct page *page,
- int migratetype);
extern void __free_pages_bootmem(struct page *page, unsigned int order);
extern void prep_compound_page(struct page *page, unsigned long order);
#ifdef CONFIG_MEMORY_FAILURE
@@ -104,7 +101,6 @@ extern bool is_free_buddy_page(struct page *page);
#endif
#if defined CONFIG_COMPACTION || defined CONFIG_CMA
-#include <linux/compaction.h>
/*
* in mm/compaction.c
@@ -123,14 +119,11 @@ 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 */
- enum compact_mode mode; /* Compaction mode */
+ bool sync; /* Synchronous migration */
int order; /* order a direct compactor needs */
int migratetype; /* MOVABLE, RECLAIMABLE etc */
struct zone *zone;
-
- /* Number of UNMOVABLE destination pageblocks skipped during scan */
- unsigned long nr_pageblocks_skipped;
};
unsigned long
diff --git a/mm/madvise.c b/mm/madvise.c
index deff1b64a08c..14d260fa0d17 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -15,6 +15,7 @@
#include <linux/sched.h>
#include <linux/ksm.h>
#include <linux/fs.h>
+#include <linux/file.h>
/*
* Any behaviour which results in changes to the vma->vm_flags needs to
@@ -204,14 +205,16 @@ static long madvise_remove(struct vm_area_struct *vma,
{
loff_t offset;
int error;
+ struct file *f;
*prev = NULL; /* tell sys_madvise we drop mmap_sem */
if (vma->vm_flags & (VM_LOCKED|VM_NONLINEAR|VM_HUGETLB))
return -EINVAL;
- if (!vma->vm_file || !vma->vm_file->f_mapping
- || !vma->vm_file->f_mapping->host) {
+ f = vma->vm_file;
+
+ if (!f || !f->f_mapping || !f->f_mapping->host) {
return -EINVAL;
}
@@ -221,11 +224,18 @@ static long madvise_remove(struct vm_area_struct *vma,
offset = (loff_t)(start - vma->vm_start)
+ ((loff_t)vma->vm_pgoff << PAGE_SHIFT);
- /* filesystem's fallocate may need to take i_mutex */
+ /*
+ * Filesystem's fallocate may need to take i_mutex. We need to
+ * explicitly grab a reference because the vma (and hence the
+ * vma's reference to the file) can go away as soon as we drop
+ * mmap_sem.
+ */
+ get_file(f);
up_read(&current->mm->mmap_sem);
- error = do_fallocate(vma->vm_file,
+ error = do_fallocate(f,
FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
offset, end - start);
+ fput(f);
down_read(&current->mm->mmap_sem);
return error;
}
diff --git a/mm/memblock.c b/mm/memblock.c
index 952123eba433..5cc6731b00cc 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -143,30 +143,6 @@ phys_addr_t __init_memblock memblock_find_in_range(phys_addr_t start,
MAX_NUMNODES);
}
-/*
- * Free memblock.reserved.regions
- */
-int __init_memblock memblock_free_reserved_regions(void)
-{
- if (memblock.reserved.regions == memblock_reserved_init_regions)
- return 0;
-
- return memblock_free(__pa(memblock.reserved.regions),
- sizeof(struct memblock_region) * memblock.reserved.max);
-}
-
-/*
- * Reserve memblock.reserved.regions
- */
-int __init_memblock memblock_reserve_reserved_regions(void)
-{
- if (memblock.reserved.regions == memblock_reserved_init_regions)
- return 0;
-
- return memblock_reserve(__pa(memblock.reserved.regions),
- sizeof(struct memblock_region) * memblock.reserved.max);
-}
-
static void __init_memblock memblock_remove_region(struct memblock_type *type, unsigned long r)
{
type->total_size -= type->regions[r].size;
@@ -184,9 +160,39 @@ static void __init_memblock memblock_remove_region(struct memblock_type *type, u
}
}
-static int __init_memblock memblock_double_array(struct memblock_type *type)
+phys_addr_t __init_memblock get_allocated_memblock_reserved_regions_info(
+ phys_addr_t *addr)
+{
+ if (memblock.reserved.regions == memblock_reserved_init_regions)
+ return 0;
+
+ *addr = __pa(memblock.reserved.regions);
+
+ return PAGE_ALIGN(sizeof(struct memblock_region) *
+ memblock.reserved.max);
+}
+
+/**
+ * memblock_double_array - double the size of the memblock regions array
+ * @type: memblock type of the regions array being doubled
+ * @new_area_start: starting address of memory range to avoid overlap with
+ * @new_area_size: size of memory range to avoid overlap with
+ *
+ * Double the size of the @type regions array. If memblock is being used to
+ * allocate memory for a new reserved regions array and there is a previously
+ * allocated memory range [@new_area_start,@new_area_start+@new_area_size]
+ * waiting to be reserved, ensure the memory used by the new array does
+ * not overlap.
+ *
+ * RETURNS:
+ * 0 on success, -1 on failure.
+ */
+static int __init_memblock memblock_double_array(struct memblock_type *type,
+ phys_addr_t new_area_start,
+ phys_addr_t new_area_size)
{
struct memblock_region *new_array, *old_array;
+ phys_addr_t old_alloc_size, new_alloc_size;
phys_addr_t old_size, new_size, addr;
int use_slab = slab_is_available();
int *in_slab;
@@ -200,6 +206,12 @@ static int __init_memblock memblock_double_array(struct memblock_type *type)
/* Calculate new doubled size */
old_size = type->max * sizeof(struct memblock_region);
new_size = old_size << 1;
+ /*
+ * We need to allocated new one align to PAGE_SIZE,
+ * so we can free them completely later.
+ */
+ old_alloc_size = PAGE_ALIGN(old_size);
+ new_alloc_size = PAGE_ALIGN(new_size);
/* Retrieve the slab flag */
if (type == &memblock.memory)
@@ -222,7 +234,18 @@ static int __init_memblock memblock_double_array(struct memblock_type *type)
new_array = kmalloc(new_size, GFP_KERNEL);
addr = new_array ? __pa(new_array) : 0;
} else {
- addr = memblock_find_in_range(0, MEMBLOCK_ALLOC_ACCESSIBLE, new_size, sizeof(phys_addr_t));
+ /* only exclude range when trying to double reserved.regions */
+ if (type != &memblock.reserved)
+ new_area_start = new_area_size = 0;
+
+ addr = memblock_find_in_range(new_area_start + new_area_size,
+ memblock.current_limit,
+ new_alloc_size, PAGE_SIZE);
+ if (!addr && new_area_size)
+ addr = memblock_find_in_range(0,
+ min(new_area_start, memblock.current_limit),
+ new_alloc_size, PAGE_SIZE);
+
new_array = addr ? __va(addr) : 0;
}
if (!addr) {
@@ -251,13 +274,13 @@ static int __init_memblock memblock_double_array(struct memblock_type *type)
kfree(old_array);
else if (old_array != memblock_memory_init_regions &&
old_array != memblock_reserved_init_regions)
- memblock_free(__pa(old_array), old_size);
+ memblock_free(__pa(old_array), old_alloc_size);
/* Reserve the new array if that comes from the memblock.
* Otherwise, we needn't do it
*/
if (!use_slab)
- BUG_ON(memblock_reserve(addr, new_size));
+ BUG_ON(memblock_reserve(addr, new_alloc_size));
/* Update slab flag */
*in_slab = use_slab;
@@ -399,7 +422,7 @@ repeat:
*/
if (!insert) {
while (type->cnt + nr_new > type->max)
- if (memblock_double_array(type) < 0)
+ if (memblock_double_array(type, obase, size) < 0)
return -ENOMEM;
insert = true;
goto repeat;
@@ -450,7 +473,7 @@ static int __init_memblock memblock_isolate_range(struct memblock_type *type,
/* we'll create at most two more regions */
while (type->cnt + 2 > type->max)
- if (memblock_double_array(type) < 0)
+ if (memblock_double_array(type, base, size) < 0)
return -ENOMEM;
for (i = 0; i < type->cnt; i++) {
@@ -540,9 +563,9 @@ int __init_memblock memblock_reserve(phys_addr_t base, phys_addr_t size)
* __next_free_mem_range - next function for for_each_free_mem_range()
* @idx: pointer to u64 loop variable
* @nid: nid: node selector, %MAX_NUMNODES for all nodes
- * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL
- * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL
- * @p_nid: ptr to int for nid of the range, can be %NULL
+ * @out_start: ptr to phys_addr_t for start address of the range, can be %NULL
+ * @out_end: ptr to phys_addr_t for end address of the range, can be %NULL
+ * @out_nid: ptr to int for nid of the range, can be %NULL
*
* Find the first free area from *@idx which matches @nid, fill the out
* parameters, and update *@idx for the next iteration. The lower 32bit of
@@ -616,9 +639,9 @@ void __init_memblock __next_free_mem_range(u64 *idx, int nid,
* __next_free_mem_range_rev - next function for for_each_free_mem_range_reverse()
* @idx: pointer to u64 loop variable
* @nid: nid: node selector, %MAX_NUMNODES for all nodes
- * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL
- * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL
- * @p_nid: ptr to int for nid of the range, can be %NULL
+ * @out_start: ptr to phys_addr_t for start address of the range, can be %NULL
+ * @out_end: ptr to phys_addr_t for end address of the range, can be %NULL
+ * @out_nid: ptr to int for nid of the range, can be %NULL
*
* Reverse of __next_free_mem_range().
*/
@@ -867,6 +890,16 @@ int __init_memblock memblock_is_memory(phys_addr_t addr)
return memblock_search(&memblock.memory, addr) != -1;
}
+/**
+ * memblock_is_region_memory - check if a region is a subset of memory
+ * @base: base of region to check
+ * @size: size of region to check
+ *
+ * Check if the region [@base, @base+@size) is a subset of a memory block.
+ *
+ * RETURNS:
+ * 0 if false, non-zero if true
+ */
int __init_memblock memblock_is_region_memory(phys_addr_t base, phys_addr_t size)
{
int idx = memblock_search(&memblock.memory, base);
@@ -879,6 +912,16 @@ int __init_memblock memblock_is_region_memory(phys_addr_t base, phys_addr_t size
memblock.memory.regions[idx].size) >= end;
}
+/**
+ * memblock_is_region_reserved - check if a region intersects reserved memory
+ * @base: base of region to check
+ * @size: size of region to check
+ *
+ * Check if the region [@base, @base+@size) intersects a reserved memory block.
+ *
+ * RETURNS:
+ * 0 if false, non-zero if true
+ */
int __init_memblock memblock_is_region_reserved(phys_addr_t base, phys_addr_t size)
{
memblock_cap_size(base, &size);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index ac35bccadb7b..f72b5e52451a 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1148,7 +1148,7 @@ bool __mem_cgroup_same_or_subtree(const struct mem_cgroup *root_memcg,
{
if (root_memcg == memcg)
return true;
- if (!root_memcg->use_hierarchy)
+ if (!root_memcg->use_hierarchy || !memcg)
return false;
return css_is_ancestor(&memcg->css, &root_memcg->css);
}
@@ -1234,7 +1234,7 @@ int mem_cgroup_inactive_file_is_low(struct lruvec *lruvec)
/**
* mem_cgroup_margin - calculate chargeable space of a memory cgroup
- * @mem: the memory cgroup
+ * @memcg: the memory cgroup
*
* Returns the maximum amount of memory @mem can be charged with, in
* pages.
@@ -1508,7 +1508,7 @@ static unsigned long mem_cgroup_reclaim(struct mem_cgroup *memcg,
/**
* test_mem_cgroup_node_reclaimable
- * @mem: the target memcg
+ * @memcg: the target memcg
* @nid: the node ID to be checked.
* @noswap : specify true here if the user wants flle only information.
*
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index ab1e7145e290..6de0d613bbe6 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -345,14 +345,14 @@ static void add_to_kill(struct task_struct *tsk, struct page *p,
* Also when FAIL is set do a force kill because something went
* wrong earlier.
*/
-static void kill_procs(struct list_head *to_kill, int doit, int trapno,
+static void kill_procs(struct list_head *to_kill, int forcekill, int trapno,
int fail, struct page *page, unsigned long pfn,
int flags)
{
struct to_kill *tk, *next;
list_for_each_entry_safe (tk, next, to_kill, nd) {
- if (doit) {
+ if (forcekill) {
/*
* In case something went wrong with munmapping
* make sure the process doesn't catch the
@@ -858,7 +858,7 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn,
struct address_space *mapping;
LIST_HEAD(tokill);
int ret;
- int kill = 1;
+ int kill = 1, forcekill;
struct page *hpage = compound_head(p);
struct page *ppage;
@@ -888,7 +888,7 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn,
* be called inside page lock (it's recommended but not enforced).
*/
mapping = page_mapping(hpage);
- if (!PageDirty(hpage) && mapping &&
+ if (!(flags & MF_MUST_KILL) && !PageDirty(hpage) && mapping &&
mapping_cap_writeback_dirty(mapping)) {
if (page_mkclean(hpage)) {
SetPageDirty(hpage);
@@ -965,12 +965,14 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn,
* Now that the dirty bit has been propagated to the
* struct page and all unmaps done we can decide if
* killing is needed or not. Only kill when the page
- * was dirty, otherwise the tokill list is merely
+ * was dirty or the process is not restartable,
+ * otherwise the tokill list is merely
* freed. When there was a problem unmapping earlier
* use a more force-full uncatchable kill to prevent
* any accesses to the poisoned memory.
*/
- kill_procs(&tokill, !!PageDirty(ppage), trapno,
+ forcekill = PageDirty(ppage) || (flags & MF_MUST_KILL);
+ kill_procs(&tokill, forcekill, trapno,
ret != SWAP_SUCCESS, p, pfn, flags);
return ret;
@@ -1431,8 +1433,8 @@ 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,
- true);
+ ret = migrate_huge_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL, false,
+ MIGRATE_SYNC);
if (ret) {
struct page *page1, *page2;
list_for_each_entry_safe(page1, page2, &pagelist, lru)
@@ -1561,7 +1563,7 @@ 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, MIGRATE_SYNC);
+ false, MIGRATE_SYNC);
if (ret) {
putback_lru_pages(&pagelist);
pr_info("soft offline: %#lx: migration failed %d, type %lx\n",
diff --git a/mm/memory.c b/mm/memory.c
index 1b7dc662bf9f..91f69459d3e8 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -206,6 +206,8 @@ void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, bool fullmm)
tlb->mm = mm;
tlb->fullmm = fullmm;
+ tlb->start = -1UL;
+ tlb->end = 0;
tlb->need_flush = 0;
tlb->fast_mode = (num_possible_cpus() == 1);
tlb->local.next = NULL;
@@ -248,6 +250,8 @@ void tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long e
{
struct mmu_gather_batch *batch, *next;
+ tlb->start = start;
+ tlb->end = end;
tlb_flush_mmu(tlb);
/* keep the page table cache within bounds */
@@ -1204,6 +1208,11 @@ again:
*/
if (force_flush) {
force_flush = 0;
+
+#ifdef HAVE_GENERIC_MMU_GATHER
+ tlb->start = addr;
+ tlb->end = end;
+#endif
tlb_flush_mmu(tlb);
if (addr != end)
goto again;
@@ -1225,7 +1234,15 @@ static inline unsigned long zap_pmd_range(struct mmu_gather *tlb,
next = pmd_addr_end(addr, end);
if (pmd_trans_huge(*pmd)) {
if (next - addr != HPAGE_PMD_SIZE) {
- VM_BUG_ON(!rwsem_is_locked(&tlb->mm->mmap_sem));
+#ifdef CONFIG_DEBUG_VM
+ if (!rwsem_is_locked(&tlb->mm->mmap_sem)) {
+ pr_err("%s: mmap_sem is unlocked! addr=0x%lx end=0x%lx vma->vm_start=0x%lx vma->vm_end=0x%lx\n",
+ __func__, addr, end,
+ vma->vm_start,
+ vma->vm_end);
+ BUG();
+ }
+#endif
split_huge_page_pmd(vma->vm_mm, pmd);
} else if (zap_huge_pmd(tlb, vma, pmd, addr))
goto next;
@@ -1366,7 +1383,7 @@ void unmap_vmas(struct mmu_gather *tlb,
/**
* zap_page_range - remove user pages in a given range
* @vma: vm_area_struct holding the applicable pages
- * @address: starting address of pages to zap
+ * @start: starting address of pages to zap
* @size: number of bytes to zap
* @details: details of nonlinear truncation or shared cache invalidation
*
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 0d7e3ec8e0f3..427bb291dd0f 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -618,7 +618,7 @@ int __ref add_memory(int nid, u64 start, u64 size)
pgdat = hotadd_new_pgdat(nid, start);
ret = -ENOMEM;
if (!pgdat)
- goto out;
+ goto error;
new_pgdat = 1;
}
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index f15c1b24ca18..bd92431d4c49 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1177,7 +1177,7 @@ 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,
- false, true);
+ false, MIGRATE_SYNC);
if (nr_failed)
putback_lru_pages(&pagelist);
}
@@ -1602,8 +1602,14 @@ static unsigned interleave_nodes(struct mempolicy *policy)
* task can change it's policy. The system default policy requires no
* such protection.
*/
-unsigned slab_node(struct mempolicy *policy)
+unsigned slab_node(void)
{
+ struct mempolicy *policy;
+
+ if (in_interrupt())
+ return numa_node_id();
+
+ policy = current->mempolicy;
if (!policy || policy->flags & MPOL_F_LOCAL)
return numa_node_id();
diff --git a/mm/migrate.c b/mm/migrate.c
index ab81d482ae6f..be26d5cbe56b 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -436,7 +436,10 @@ void migrate_page_copy(struct page *newpage, struct page *page)
* is actually a signal that all of the page has become dirty.
* Whereas only part of our page may be dirty.
*/
- __set_page_dirty_nobuffers(newpage);
+ if (PageSwapBacked(page))
+ SetPageDirty(newpage);
+ else
+ __set_page_dirty_nobuffers(newpage);
}
mlock_migrate_page(newpage, page);
diff --git a/mm/nobootmem.c b/mm/nobootmem.c
index d23415c001bc..405573010f99 100644
--- a/mm/nobootmem.c
+++ b/mm/nobootmem.c
@@ -105,27 +105,35 @@ static void __init __free_pages_memory(unsigned long start, unsigned long end)
__free_pages_bootmem(pfn_to_page(i), 0);
}
+static unsigned long __init __free_memory_core(phys_addr_t start,
+ phys_addr_t end)
+{
+ unsigned long start_pfn = PFN_UP(start);
+ unsigned long end_pfn = min_t(unsigned long,
+ PFN_DOWN(end), max_low_pfn);
+
+ if (start_pfn > end_pfn)
+ return 0;
+
+ __free_pages_memory(start_pfn, end_pfn);
+
+ return end_pfn - start_pfn;
+}
+
unsigned long __init free_low_memory_core_early(int nodeid)
{
unsigned long count = 0;
- phys_addr_t start, end;
+ phys_addr_t start, end, size;
u64 i;
- /* free reserved array temporarily so that it's treated as free area */
- memblock_free_reserved_regions();
-
- for_each_free_mem_range(i, MAX_NUMNODES, &start, &end, NULL) {
- unsigned long start_pfn = PFN_UP(start);
- unsigned long end_pfn = min_t(unsigned long,
- PFN_DOWN(end), max_low_pfn);
- if (start_pfn < end_pfn) {
- __free_pages_memory(start_pfn, end_pfn);
- count += end_pfn - start_pfn;
- }
- }
+ for_each_free_mem_range(i, MAX_NUMNODES, &start, &end, NULL)
+ count += __free_memory_core(start, end);
+
+ /* free range that is used for reserved array if we allocate it */
+ size = get_allocated_memblock_reserved_regions_info(&start);
+ if (size)
+ count += __free_memory_core(start, start + size);
- /* put region array back? */
- memblock_reserve_reserved_regions();
return count;
}
@@ -274,7 +282,7 @@ void * __init __alloc_bootmem(unsigned long size, unsigned long align,
return ___alloc_bootmem(size, align, goal, limit);
}
-static void * __init ___alloc_bootmem_node_nopanic(pg_data_t *pgdat,
+void * __init ___alloc_bootmem_node_nopanic(pg_data_t *pgdat,
unsigned long size,
unsigned long align,
unsigned long goal,
diff --git a/mm/nommu.c b/mm/nommu.c
index c4acfbc09972..d4b0c10872de 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -1486,7 +1486,7 @@ SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len,
flags &= ~(MAP_EXECUTABLE | MAP_DENYWRITE);
- ret = vm_mmap_pgoff(file, addr, len, prot, flags, pgoff);
+ retval = vm_mmap_pgoff(file, addr, len, prot, flags, pgoff);
if (file)
fput(file);
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index ed0e19677360..ac300c99baf6 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -183,7 +183,8 @@ static bool oom_unkillable_task(struct task_struct *p,
unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg,
const nodemask_t *nodemask, unsigned long totalpages)
{
- unsigned long points;
+ long points;
+ long adj;
if (oom_unkillable_task(p, memcg, nodemask))
return 0;
@@ -192,7 +193,8 @@ unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg,
if (!p)
return 0;
- if (p->signal->oom_score_adj == OOM_SCORE_ADJ_MIN) {
+ adj = p->signal->oom_score_adj;
+ if (adj == OOM_SCORE_ADJ_MIN) {
task_unlock(p);
return 0;
}
@@ -210,20 +212,17 @@ unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg,
* implementation used by LSMs.
*/
if (has_capability_noaudit(p, CAP_SYS_ADMIN))
- points -= 30 * totalpages / 1000;
+ adj -= 30;
- /*
- * /proc/pid/oom_score_adj ranges from -1000 to +1000 such that it may
- * either completely disable oom killing or always prefer a certain
- * task.
- */
- points += p->signal->oom_score_adj * totalpages / 1000;
+ /* Normalize to oom_score_adj units */
+ adj *= totalpages / 1000;
+ points += adj;
/*
* Never return 0 for an eligible task regardless of the root bonus and
* oom_score_adj (oom_score_adj can't be OOM_SCORE_ADJ_MIN here).
*/
- return points ? points : 1;
+ return points > 0 ? points : 1;
}
/*
@@ -366,7 +365,7 @@ static struct task_struct *select_bad_process(unsigned int *ppoints,
/**
* dump_tasks - dump current memory state of all system tasks
- * @mem: current's memory controller, if constrained
+ * @memcg: current's memory controller, if constrained
* @nodemask: nodemask passed to page allocator for mempolicy ooms
*
* Dumps the current memory state of all eligible tasks. Tasks not in the same
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 93d8d2f7108c..e5363f34e025 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -34,6 +34,7 @@
#include <linux/syscalls.h>
#include <linux/buffer_head.h> /* __set_page_dirty_buffers */
#include <linux/pagevec.h>
+#include <linux/timer.h>
#include <trace/events/writeback.h>
/*
@@ -135,7 +136,20 @@ unsigned long global_dirty_limit;
* measured in page writeback completions.
*
*/
-static struct prop_descriptor vm_completions;
+static struct fprop_global writeout_completions;
+
+static void writeout_period(unsigned long t);
+/* Timer for aging of writeout_completions */
+static struct timer_list writeout_period_timer =
+ TIMER_DEFERRED_INITIALIZER(writeout_period, 0, 0);
+static unsigned long writeout_period_time = 0;
+
+/*
+ * Length of period for aging writeout fractions of bdis. This is an
+ * arbitrarily chosen number. The longer the period, the slower fractions will
+ * reflect changes in current writeout rate.
+ */
+#define VM_COMPLETIONS_PERIOD_LEN (3*HZ)
/*
* Work out the current dirty-memory clamping and background writeout
@@ -322,34 +336,6 @@ bool zone_dirty_ok(struct zone *zone)
zone_page_state(zone, NR_WRITEBACK) <= limit;
}
-/*
- * couple the period to the dirty_ratio:
- *
- * period/2 ~ roundup_pow_of_two(dirty limit)
- */
-static int calc_period_shift(void)
-{
- unsigned long dirty_total;
-
- if (vm_dirty_bytes)
- dirty_total = vm_dirty_bytes / PAGE_SIZE;
- else
- dirty_total = (vm_dirty_ratio * global_dirtyable_memory()) /
- 100;
- return 2 + ilog2(dirty_total - 1);
-}
-
-/*
- * update the period when the dirty threshold changes.
- */
-static void update_completion_period(void)
-{
- int shift = calc_period_shift();
- prop_change_shift(&vm_completions, shift);
-
- writeback_set_ratelimit();
-}
-
int dirty_background_ratio_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos)
@@ -383,7 +369,7 @@ int dirty_ratio_handler(struct ctl_table *table, int write,
ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
if (ret == 0 && write && vm_dirty_ratio != old_ratio) {
- update_completion_period();
+ writeback_set_ratelimit();
vm_dirty_bytes = 0;
}
return ret;
@@ -398,12 +384,21 @@ int dirty_bytes_handler(struct ctl_table *table, int write,
ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
if (ret == 0 && write && vm_dirty_bytes != old_bytes) {
- update_completion_period();
+ writeback_set_ratelimit();
vm_dirty_ratio = 0;
}
return ret;
}
+static unsigned long wp_next_time(unsigned long cur_time)
+{
+ cur_time += VM_COMPLETIONS_PERIOD_LEN;
+ /* 0 has a special meaning... */
+ if (!cur_time)
+ return 1;
+ return cur_time;
+}
+
/*
* Increment the BDI's writeout completion count and the global writeout
* completion count. Called from test_clear_page_writeback().
@@ -411,8 +406,19 @@ int dirty_bytes_handler(struct ctl_table *table, int write,
static inline void __bdi_writeout_inc(struct backing_dev_info *bdi)
{
__inc_bdi_stat(bdi, BDI_WRITTEN);
- __prop_inc_percpu_max(&vm_completions, &bdi->completions,
- bdi->max_prop_frac);
+ __fprop_inc_percpu_max(&writeout_completions, &bdi->completions,
+ bdi->max_prop_frac);
+ /* First event after period switching was turned off? */
+ if (!unlikely(writeout_period_time)) {
+ /*
+ * We can race with other __bdi_writeout_inc calls here but
+ * it does not cause any harm since the resulting time when
+ * timer will fire and what is in writeout_period_time will be
+ * roughly the same.
+ */
+ writeout_period_time = wp_next_time(jiffies);
+ mod_timer(&writeout_period_timer, writeout_period_time);
+ }
}
void bdi_writeout_inc(struct backing_dev_info *bdi)
@@ -431,11 +437,33 @@ EXPORT_SYMBOL_GPL(bdi_writeout_inc);
static void bdi_writeout_fraction(struct backing_dev_info *bdi,
long *numerator, long *denominator)
{
- prop_fraction_percpu(&vm_completions, &bdi->completions,
+ fprop_fraction_percpu(&writeout_completions, &bdi->completions,
numerator, denominator);
}
/*
+ * On idle system, we can be called long after we scheduled because we use
+ * deferred timers so count with missed periods.
+ */
+static void writeout_period(unsigned long t)
+{
+ int miss_periods = (jiffies - writeout_period_time) /
+ VM_COMPLETIONS_PERIOD_LEN;
+
+ if (fprop_new_period(&writeout_completions, miss_periods + 1)) {
+ writeout_period_time = wp_next_time(writeout_period_time +
+ miss_periods * VM_COMPLETIONS_PERIOD_LEN);
+ mod_timer(&writeout_period_timer, writeout_period_time);
+ } else {
+ /*
+ * Aging has zeroed all fractions. Stop wasting CPU on period
+ * updates.
+ */
+ writeout_period_time = 0;
+ }
+}
+
+/*
* bdi_min_ratio keeps the sum of the minimum dirty shares of all
* registered backing devices, which, for obvious reasons, can not
* exceed 100%.
@@ -475,7 +503,7 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned max_ratio)
ret = -EINVAL;
} else {
bdi->max_ratio = max_ratio;
- bdi->max_prop_frac = (PROP_FRAC_BASE * max_ratio) / 100;
+ bdi->max_prop_frac = (FPROP_FRAC_BASE * max_ratio) / 100;
}
spin_unlock_bh(&bdi_lock);
@@ -918,7 +946,7 @@ static void bdi_update_dirty_ratelimit(struct backing_dev_info *bdi,
* bdi->dirty_ratelimit = balanced_dirty_ratelimit;
*
* However to get a more stable dirty_ratelimit, the below elaborated
- * code makes use of task_ratelimit to filter out sigular points and
+ * code makes use of task_ratelimit to filter out singular points and
* limit the step size.
*
* The below code essentially only uses the relative value of
@@ -941,7 +969,7 @@ static void bdi_update_dirty_ratelimit(struct backing_dev_info *bdi,
* feel and care are stable dirty rate and small position error.
*
* |task_ratelimit - dirty_ratelimit| is used to limit the step size
- * and filter out the sigular points of balanced_dirty_ratelimit. Which
+ * and filter out the singular points of balanced_dirty_ratelimit. Which
* keeps jumping around randomly and can even leap far away at times
* due to the small 200ms estimation period of dirty_rate (we want to
* keep that period small to reduce time lags).
@@ -1606,13 +1634,10 @@ static struct notifier_block __cpuinitdata ratelimit_nb = {
*/
void __init page_writeback_init(void)
{
- int shift;
-
writeback_set_ratelimit();
register_cpu_notifier(&ratelimit_nb);
- shift = calc_period_shift();
- prop_descriptor_init(&vm_completions, shift);
+ fprop_global_init(&writeout_completions);
}
/**
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 6092f331b32e..4a4f9219683f 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -219,7 +219,7 @@ EXPORT_SYMBOL(nr_online_nodes);
int page_group_by_mobility_disabled __read_mostly;
-void set_pageblock_migratetype(struct page *page, int migratetype)
+static void set_pageblock_migratetype(struct page *page, int migratetype)
{
if (unlikely(page_group_by_mobility_disabled))
@@ -954,8 +954,8 @@ static int move_freepages(struct zone *zone,
return pages_moved;
}
-int move_freepages_block(struct zone *zone, struct page *page,
- int migratetype)
+static int move_freepages_block(struct zone *zone, struct page *page,
+ int migratetype)
{
unsigned long start_pfn, end_pfn;
struct page *start_page, *end_page;
@@ -5635,7 +5635,12 @@ static struct page *
__alloc_contig_migrate_alloc(struct page *page, unsigned long private,
int **resultp)
{
- return alloc_page(GFP_HIGHUSER_MOVABLE);
+ gfp_t gfp_mask = GFP_USER | __GFP_MOVABLE;
+
+ if (PageHighMem(page))
+ gfp_mask |= __GFP_HIGHMEM;
+
+ return alloc_page(gfp_mask);
}
/* [start, end) must belong to a single zone. */
@@ -5651,7 +5656,7 @@ static int __alloc_contig_migrate_range(unsigned long start, unsigned long end)
.nr_migratepages = 0,
.order = -1,
.zone = page_zone(pfn_to_page(start)),
- .mode = COMPACT_SYNC,
+ .sync = true,
};
INIT_LIST_HEAD(&cc.migratepages);
diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c
index 1ccbd714059c..eb750f851395 100644
--- a/mm/page_cgroup.c
+++ b/mm/page_cgroup.c
@@ -392,7 +392,7 @@ static struct swap_cgroup *lookup_swap_cgroup(swp_entry_t ent,
/**
* swap_cgroup_cmpxchg - cmpxchg mem_cgroup's id for this swp_entry.
- * @end: swap entry to be cmpxchged
+ * @ent: swap entry to be cmpxchged
* @old: old id
* @new: new id
*
@@ -422,7 +422,7 @@ unsigned short swap_cgroup_cmpxchg(swp_entry_t ent,
/**
* swap_cgroup_record - record mem_cgroup for this swp_entry.
* @ent: swap entry to be recorded into
- * @mem: mem_cgroup to be recorded
+ * @id: mem_cgroup to be recorded
*
* Returns old value at success, 0 at failure.
* (Of course, old value can be 0.)
diff --git a/mm/page_io.c b/mm/page_io.c
index dc76b4d0611e..34f02923744c 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -18,6 +18,7 @@
#include <linux/bio.h>
#include <linux/swapops.h>
#include <linux/writeback.h>
+#include <linux/frontswap.h>
#include <asm/pgtable.h>
static struct bio *get_swap_bio(gfp_t gfp_flags,
@@ -98,6 +99,12 @@ int swap_writepage(struct page *page, struct writeback_control *wbc)
unlock_page(page);
goto out;
}
+ if (frontswap_store(page) == 0) {
+ set_page_writeback(page);
+ unlock_page(page);
+ end_page_writeback(page);
+ goto out;
+ }
bio = get_swap_bio(GFP_NOIO, page, end_swap_bio_write);
if (bio == NULL) {
set_page_dirty(page);
@@ -122,6 +129,11 @@ int swap_readpage(struct page *page)
VM_BUG_ON(!PageLocked(page));
VM_BUG_ON(PageUptodate(page));
+ if (frontswap_load(page) == 0) {
+ SetPageUptodate(page);
+ unlock_page(page);
+ goto out;
+ }
bio = get_swap_bio(GFP_KERNEL, page, end_swap_bio_read);
if (bio == NULL) {
unlock_page(page);
diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index aa9701e12714..6c118d012bb5 100644
--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -162,7 +162,6 @@ static int walk_hugetlb_range(struct vm_area_struct *vma,
/**
* walk_page_range - walk a memory map's page tables with a callback
- * @mm: memory map to walk
* @addr: starting address
* @end: ending address
* @walk: set of callbacks to invoke for each level of the tree
diff --git a/mm/percpu-vm.c b/mm/percpu-vm.c
index 405d331804c3..3707c71ae4cd 100644
--- a/mm/percpu-vm.c
+++ b/mm/percpu-vm.c
@@ -360,7 +360,6 @@ err_free:
* @chunk: chunk to depopulate
* @off: offset to the area to depopulate
* @size: size of the area to depopulate in bytes
- * @flush: whether to flush cache and tlb or not
*
* For each cpu, depopulate and unmap pages [@page_start,@page_end)
* from @chunk. If @flush is true, vcache is flushed before unmapping
diff --git a/mm/shmem.c b/mm/shmem.c
index 585bd220a21e..c15b998e5a86 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -264,46 +264,55 @@ static int shmem_radix_tree_replace(struct address_space *mapping,
}
/*
+ * Sometimes, before we decide whether to proceed or to fail, we must check
+ * that an entry was not already brought back from swap by a racing thread.
+ *
+ * Checking page is not enough: by the time a SwapCache page is locked, it
+ * might be reused, and again be SwapCache, using the same swap as before.
+ */
+static bool shmem_confirm_swap(struct address_space *mapping,
+ pgoff_t index, swp_entry_t swap)
+{
+ void *item;
+
+ rcu_read_lock();
+ item = radix_tree_lookup(&mapping->page_tree, index);
+ rcu_read_unlock();
+ return item == swp_to_radix_entry(swap);
+}
+
+/*
* Like add_to_page_cache_locked, but error if expected item has gone.
*/
static int shmem_add_to_page_cache(struct page *page,
struct address_space *mapping,
pgoff_t index, gfp_t gfp, void *expected)
{
- int error = 0;
+ int error;
VM_BUG_ON(!PageLocked(page));
VM_BUG_ON(!PageSwapBacked(page));
+ page_cache_get(page);
+ page->mapping = mapping;
+ page->index = index;
+
+ spin_lock_irq(&mapping->tree_lock);
if (!expected)
- error = radix_tree_preload(gfp & GFP_RECLAIM_MASK);
+ error = radix_tree_insert(&mapping->page_tree, index, page);
+ else
+ error = shmem_radix_tree_replace(mapping, index, expected,
+ page);
if (!error) {
- page_cache_get(page);
- page->mapping = mapping;
- page->index = index;
-
- spin_lock_irq(&mapping->tree_lock);
- if (!expected)
- error = radix_tree_insert(&mapping->page_tree,
- index, page);
- else
- error = shmem_radix_tree_replace(mapping, index,
- expected, page);
- if (!error) {
- mapping->nrpages++;
- __inc_zone_page_state(page, NR_FILE_PAGES);
- __inc_zone_page_state(page, NR_SHMEM);
- spin_unlock_irq(&mapping->tree_lock);
- } else {
- page->mapping = NULL;
- spin_unlock_irq(&mapping->tree_lock);
- page_cache_release(page);
- }
- if (!expected)
- radix_tree_preload_end();
+ mapping->nrpages++;
+ __inc_zone_page_state(page, NR_FILE_PAGES);
+ __inc_zone_page_state(page, NR_SHMEM);
+ spin_unlock_irq(&mapping->tree_lock);
+ } else {
+ page->mapping = NULL;
+ spin_unlock_irq(&mapping->tree_lock);
+ page_cache_release(page);
}
- if (error)
- mem_cgroup_uncharge_cache_page(page);
return error;
}
@@ -683,10 +692,21 @@ static int shmem_unuse_inode(struct shmem_inode_info *info,
mutex_lock(&shmem_swaplist_mutex);
/*
* We needed to drop mutex to make that restrictive page
- * allocation; but the inode might already be freed by now,
- * and we cannot refer to inode or mapping or info to check.
- * However, we do hold page lock on the PageSwapCache page,
- * so can check if that still has our reference remaining.
+ * allocation, but the inode might have been freed while we
+ * dropped it: although a racing shmem_evict_inode() cannot
+ * complete without emptying the radix_tree, our page lock
+ * on this swapcache page is not enough to prevent that -
+ * free_swap_and_cache() of our swap entry will only
+ * trylock_page(), removing swap from radix_tree whatever.
+ *
+ * We must not proceed to shmem_add_to_page_cache() if the
+ * inode has been freed, but of course we cannot rely on
+ * inode or mapping or info to check that. However, we can
+ * safely check if our swap entry is still in use (and here
+ * it can't have got reused for another page): if it's still
+ * in use, then the inode cannot have been freed yet, and we
+ * can safely proceed (if it's no longer in use, that tells
+ * nothing about the inode, but we don't need to unuse swap).
*/
if (!page_swapcount(*pagep))
error = -ENOENT;
@@ -730,9 +750,9 @@ int shmem_unuse(swp_entry_t swap, struct page *page)
/*
* There's a faint possibility that swap page was replaced before
- * caller locked it: it will come back later with the right page.
+ * caller locked it: caller will come back later with the right page.
*/
- if (unlikely(!PageSwapCache(page)))
+ if (unlikely(!PageSwapCache(page) || page_private(page) != swap.val))
goto out;
/*
@@ -995,21 +1015,15 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp,
newpage = shmem_alloc_page(gfp, info, index);
if (!newpage)
return -ENOMEM;
- VM_BUG_ON(shmem_should_replace_page(newpage, gfp));
- *pagep = newpage;
page_cache_get(newpage);
copy_highpage(newpage, oldpage);
+ flush_dcache_page(newpage);
- VM_BUG_ON(!PageLocked(oldpage));
__set_page_locked(newpage);
- VM_BUG_ON(!PageUptodate(oldpage));
SetPageUptodate(newpage);
- VM_BUG_ON(!PageSwapBacked(oldpage));
SetPageSwapBacked(newpage);
- VM_BUG_ON(!swap_index);
set_page_private(newpage, swap_index);
- VM_BUG_ON(!PageSwapCache(oldpage));
SetPageSwapCache(newpage);
/*
@@ -1019,13 +1033,24 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp,
spin_lock_irq(&swap_mapping->tree_lock);
error = shmem_radix_tree_replace(swap_mapping, swap_index, oldpage,
newpage);
- __inc_zone_page_state(newpage, NR_FILE_PAGES);
- __dec_zone_page_state(oldpage, NR_FILE_PAGES);
+ if (!error) {
+ __inc_zone_page_state(newpage, NR_FILE_PAGES);
+ __dec_zone_page_state(oldpage, NR_FILE_PAGES);
+ }
spin_unlock_irq(&swap_mapping->tree_lock);
- BUG_ON(error);
- mem_cgroup_replace_page_cache(oldpage, newpage);
- lru_cache_add_anon(newpage);
+ if (unlikely(error)) {
+ /*
+ * Is this possible? I think not, now that our callers check
+ * both PageSwapCache and page_private after getting page lock;
+ * but be defensive. Reverse old to newpage for clear and free.
+ */
+ oldpage = newpage;
+ } else {
+ mem_cgroup_replace_page_cache(oldpage, newpage);
+ lru_cache_add_anon(newpage);
+ *pagep = newpage;
+ }
ClearPageSwapCache(oldpage);
set_page_private(oldpage, 0);
@@ -1033,7 +1058,7 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp,
unlock_page(oldpage);
page_cache_release(oldpage);
page_cache_release(oldpage);
- return 0;
+ return error;
}
/*
@@ -1107,9 +1132,10 @@ repeat:
/* We have to do this with page locked to prevent races */
lock_page(page);
- if (!PageSwapCache(page) || page->mapping) {
+ if (!PageSwapCache(page) || page_private(page) != swap.val ||
+ !shmem_confirm_swap(mapping, index, swap)) {
error = -EEXIST; /* try again */
- goto failed;
+ goto unlock;
}
if (!PageUptodate(page)) {
error = -EIO;
@@ -1125,9 +1151,12 @@ repeat:
error = mem_cgroup_cache_charge(page, current->mm,
gfp & GFP_RECLAIM_MASK);
- if (!error)
+ if (!error) {
error = shmem_add_to_page_cache(page, mapping, index,
gfp, swp_to_radix_entry(swap));
+ /* We already confirmed swap, and make no allocation */
+ VM_BUG_ON(error);
+ }
if (error)
goto failed;
@@ -1164,11 +1193,18 @@ repeat:
__set_page_locked(page);
error = mem_cgroup_cache_charge(page, current->mm,
gfp & GFP_RECLAIM_MASK);
- if (!error)
- error = shmem_add_to_page_cache(page, mapping, index,
- gfp, NULL);
if (error)
goto decused;
+ error = radix_tree_preload(gfp & GFP_RECLAIM_MASK);
+ if (!error) {
+ error = shmem_add_to_page_cache(page, mapping, index,
+ gfp, NULL);
+ radix_tree_preload_end();
+ }
+ if (error) {
+ mem_cgroup_uncharge_cache_page(page);
+ goto decused;
+ }
lru_cache_add_anon(page);
spin_lock(&info->lock);
@@ -1228,14 +1264,10 @@ decused:
unacct:
shmem_unacct_blocks(info->flags, 1);
failed:
- if (swap.val && error != -EINVAL) {
- struct page *test = find_get_page(mapping, index);
- if (test && !radix_tree_exceptional_entry(test))
- page_cache_release(test);
- /* Have another try if the entry has changed */
- if (test != swp_to_radix_entry(swap))
- error = -EEXIST;
- }
+ if (swap.val && error != -EINVAL &&
+ !shmem_confirm_swap(mapping, index, swap))
+ error = -EEXIST;
+unlock:
if (page) {
unlock_page(page);
page_cache_release(page);
@@ -1247,7 +1279,7 @@ failed:
spin_unlock(&info->lock);
goto repeat;
}
- if (error == -EEXIST)
+ if (error == -EEXIST) /* from above or from radix_tree_insert */
goto repeat;
return error;
}
@@ -1577,6 +1609,7 @@ static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos,
struct splice_pipe_desc spd = {
.pages = pages,
.partial = partial,
+ .nr_pages_max = PIPE_DEF_BUFFERS,
.flags = flags,
.ops = &page_cache_pipe_buf_ops,
.spd_release = spd_release_page,
@@ -1665,7 +1698,7 @@ static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos,
if (spd.nr_pages)
error = splice_to_pipe(pipe, &spd);
- splice_shrink_spd(pipe, &spd);
+ splice_shrink_spd(&spd);
if (error > 0) {
*ppos += error;
@@ -1674,98 +1707,6 @@ static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos,
return error;
}
-/*
- * llseek SEEK_DATA or SEEK_HOLE through the radix_tree.
- */
-static pgoff_t shmem_seek_hole_data(struct address_space *mapping,
- pgoff_t index, pgoff_t end, int origin)
-{
- struct page *page;
- struct pagevec pvec;
- pgoff_t indices[PAGEVEC_SIZE];
- bool done = false;
- int i;
-
- pagevec_init(&pvec, 0);
- pvec.nr = 1; /* start small: we may be there already */
- while (!done) {
- pvec.nr = shmem_find_get_pages_and_swap(mapping, index,
- pvec.nr, pvec.pages, indices);
- if (!pvec.nr) {
- if (origin == SEEK_DATA)
- index = end;
- break;
- }
- for (i = 0; i < pvec.nr; i++, index++) {
- if (index < indices[i]) {
- if (origin == SEEK_HOLE) {
- done = true;
- break;
- }
- index = indices[i];
- }
- page = pvec.pages[i];
- if (page && !radix_tree_exceptional_entry(page)) {
- if (!PageUptodate(page))
- page = NULL;
- }
- if (index >= end ||
- (page && origin == SEEK_DATA) ||
- (!page && origin == SEEK_HOLE)) {
- done = true;
- break;
- }
- }
- shmem_deswap_pagevec(&pvec);
- pagevec_release(&pvec);
- pvec.nr = PAGEVEC_SIZE;
- cond_resched();
- }
- return index;
-}
-
-static loff_t shmem_file_llseek(struct file *file, loff_t offset, int origin)
-{
- struct address_space *mapping;
- struct inode *inode;
- pgoff_t start, end;
- loff_t new_offset;
-
- if (origin != SEEK_DATA && origin != SEEK_HOLE)
- return generic_file_llseek_size(file, offset, origin,
- MAX_LFS_FILESIZE);
- mapping = file->f_mapping;
- inode = mapping->host;
- mutex_lock(&inode->i_mutex);
- /* We're holding i_mutex so we can access i_size directly */
-
- if (offset < 0)
- offset = -EINVAL;
- else if (offset >= inode->i_size)
- offset = -ENXIO;
- else {
- start = offset >> PAGE_CACHE_SHIFT;
- end = (inode->i_size + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
- new_offset = shmem_seek_hole_data(mapping, start, end, origin);
- new_offset <<= PAGE_CACHE_SHIFT;
- if (new_offset > offset) {
- if (new_offset < inode->i_size)
- offset = new_offset;
- else if (origin == SEEK_DATA)
- offset = -ENXIO;
- else
- offset = inode->i_size;
- }
- }
-
- if (offset >= 0 && offset != file->f_pos) {
- file->f_pos = offset;
- file->f_version = 0;
- }
- mutex_unlock(&inode->i_mutex);
- return offset;
-}
-
static long shmem_fallocate(struct file *file, int mode, loff_t offset,
loff_t len)
{
@@ -1936,7 +1877,7 @@ static int shmem_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
}
static int shmem_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- struct nameidata *nd)
+ bool excl)
{
return shmem_mknod(dir, dentry, mode | S_IFREG, 0);
}
@@ -2769,7 +2710,7 @@ static const struct address_space_operations shmem_aops = {
static const struct file_operations shmem_file_operations = {
.mmap = shmem_mmap,
#ifdef CONFIG_TMPFS
- .llseek = shmem_file_llseek,
+ .llseek = generic_file_llseek,
.read = do_sync_read,
.write = do_sync_write,
.aio_read = shmem_file_aio_read,
diff --git a/mm/slab.c b/mm/slab.c
index e901a36e2520..1fcf3ac94b6c 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -68,7 +68,7 @@
* Further notes from the original documentation:
*
* 11 April '97. Started multi-threading - markhe
- * The global cache-chain is protected by the mutex 'cache_chain_mutex'.
+ * The global cache-chain is protected by the mutex 'slab_mutex'.
* The sem is only needed when accessing/extending the cache-chain, which
* can never happen inside an interrupt (kmem_cache_create(),
* kmem_cache_shrink() and kmem_cache_reap()).
@@ -87,6 +87,7 @@
*/
#include <linux/slab.h>
+#include "slab.h"
#include <linux/mm.h>
#include <linux/poison.h>
#include <linux/swap.h>
@@ -424,8 +425,8 @@ static void kmem_list3_init(struct kmem_list3 *parent)
* cachep->obj_offset - BYTES_PER_WORD .. cachep->obj_offset - 1:
* redzone word.
* cachep->obj_offset: The real object.
- * cachep->buffer_size - 2* BYTES_PER_WORD: redzone word [BYTES_PER_WORD long]
- * cachep->buffer_size - 1* BYTES_PER_WORD: last caller address
+ * cachep->size - 2* BYTES_PER_WORD: redzone word [BYTES_PER_WORD long]
+ * cachep->size - 1* BYTES_PER_WORD: last caller address
* [BYTES_PER_WORD long]
*/
static int obj_offset(struct kmem_cache *cachep)
@@ -433,11 +434,6 @@ static int obj_offset(struct kmem_cache *cachep)
return cachep->obj_offset;
}
-static int obj_size(struct kmem_cache *cachep)
-{
- return cachep->obj_size;
-}
-
static unsigned long long *dbg_redzone1(struct kmem_cache *cachep, void *objp)
{
BUG_ON(!(cachep->flags & SLAB_RED_ZONE));
@@ -449,23 +445,22 @@ static unsigned long long *dbg_redzone2(struct kmem_cache *cachep, void *objp)
{
BUG_ON(!(cachep->flags & SLAB_RED_ZONE));
if (cachep->flags & SLAB_STORE_USER)
- return (unsigned long long *)(objp + cachep->buffer_size -
+ return (unsigned long long *)(objp + cachep->size -
sizeof(unsigned long long) -
REDZONE_ALIGN);
- return (unsigned long long *) (objp + cachep->buffer_size -
+ return (unsigned long long *) (objp + cachep->size -
sizeof(unsigned long long));
}
static void **dbg_userword(struct kmem_cache *cachep, void *objp)
{
BUG_ON(!(cachep->flags & SLAB_STORE_USER));
- return (void **)(objp + cachep->buffer_size - BYTES_PER_WORD);
+ return (void **)(objp + cachep->size - BYTES_PER_WORD);
}
#else
#define obj_offset(x) 0
-#define obj_size(cachep) (cachep->buffer_size)
#define dbg_redzone1(cachep, objp) ({BUG(); (unsigned long long *)NULL;})
#define dbg_redzone2(cachep, objp) ({BUG(); (unsigned long long *)NULL;})
#define dbg_userword(cachep, objp) ({BUG(); (void **)NULL;})
@@ -475,7 +470,7 @@ static void **dbg_userword(struct kmem_cache *cachep, void *objp)
#ifdef CONFIG_TRACING
size_t slab_buffer_size(struct kmem_cache *cachep)
{
- return cachep->buffer_size;
+ return cachep->size;
}
EXPORT_SYMBOL(slab_buffer_size);
#endif
@@ -489,56 +484,37 @@ EXPORT_SYMBOL(slab_buffer_size);
static int slab_max_order = SLAB_MAX_ORDER_LO;
static bool slab_max_order_set __initdata;
-/*
- * Functions for storing/retrieving the cachep and or slab from the page
- * allocator. These are used to find the slab an obj belongs to. With kfree(),
- * these are used to find the cache which an obj belongs to.
- */
-static inline void page_set_cache(struct page *page, struct kmem_cache *cache)
-{
- page->lru.next = (struct list_head *)cache;
-}
-
static inline struct kmem_cache *page_get_cache(struct page *page)
{
page = compound_head(page);
BUG_ON(!PageSlab(page));
- return (struct kmem_cache *)page->lru.next;
-}
-
-static inline void page_set_slab(struct page *page, struct slab *slab)
-{
- page->lru.prev = (struct list_head *)slab;
-}
-
-static inline struct slab *page_get_slab(struct page *page)
-{
- BUG_ON(!PageSlab(page));
- return (struct slab *)page->lru.prev;
+ return page->slab_cache;
}
static inline struct kmem_cache *virt_to_cache(const void *obj)
{
struct page *page = virt_to_head_page(obj);
- return page_get_cache(page);
+ return page->slab_cache;
}
static inline struct slab *virt_to_slab(const void *obj)
{
struct page *page = virt_to_head_page(obj);
- return page_get_slab(page);
+
+ VM_BUG_ON(!PageSlab(page));
+ return page->slab_page;
}
static inline void *index_to_obj(struct kmem_cache *cache, struct slab *slab,
unsigned int idx)
{
- return slab->s_mem + cache->buffer_size * idx;
+ return slab->s_mem + cache->size * idx;
}
/*
- * We want to avoid an expensive divide : (offset / cache->buffer_size)
- * Using the fact that buffer_size is a constant for a particular cache,
- * we can replace (offset / cache->buffer_size) by
+ * We want to avoid an expensive divide : (offset / cache->size)
+ * Using the fact that size is a constant for a particular cache,
+ * we can replace (offset / cache->size) by
* reciprocal_divide(offset, cache->reciprocal_buffer_size)
*/
static inline unsigned int obj_to_index(const struct kmem_cache *cache,
@@ -584,33 +560,12 @@ static struct kmem_cache cache_cache = {
.batchcount = 1,
.limit = BOOT_CPUCACHE_ENTRIES,
.shared = 1,
- .buffer_size = sizeof(struct kmem_cache),
+ .size = sizeof(struct kmem_cache),
.name = "kmem_cache",
};
#define BAD_ALIEN_MAGIC 0x01020304ul
-/*
- * chicken and egg problem: delay the per-cpu array allocation
- * until the general caches are up.
- */
-static enum {
- NONE,
- PARTIAL_AC,
- PARTIAL_L3,
- EARLY,
- LATE,
- FULL
-} g_cpucache_up;
-
-/*
- * used by boot code to determine if it can use slab based allocator
- */
-int slab_is_available(void)
-{
- return g_cpucache_up >= EARLY;
-}
-
#ifdef CONFIG_LOCKDEP
/*
@@ -676,7 +631,7 @@ static void init_node_lock_keys(int q)
{
struct cache_sizes *s = malloc_sizes;
- if (g_cpucache_up < LATE)
+ if (slab_state < UP)
return;
for (s = malloc_sizes; s->cs_size != ULONG_MAX; s++) {
@@ -716,12 +671,6 @@ static void slab_set_debugobj_lock_classes(struct kmem_cache *cachep)
}
#endif
-/*
- * Guard access to the cache-chain.
- */
-static DEFINE_MUTEX(cache_chain_mutex);
-static struct list_head cache_chain;
-
static DEFINE_PER_CPU(struct delayed_work, slab_reap_work);
static inline struct array_cache *cpu_cache_get(struct kmem_cache *cachep)
@@ -1145,7 +1094,7 @@ static inline int cache_free_alien(struct kmem_cache *cachep, void *objp)
* When hotplugging memory or a cpu, existing nodelists are not replaced if
* already in use.
*
- * Must hold cache_chain_mutex.
+ * Must hold slab_mutex.
*/
static int init_cache_nodelists_node(int node)
{
@@ -1153,7 +1102,7 @@ static int init_cache_nodelists_node(int node)
struct kmem_list3 *l3;
const int memsize = sizeof(struct kmem_list3);
- list_for_each_entry(cachep, &cache_chain, next) {
+ list_for_each_entry(cachep, &slab_caches, list) {
/*
* Set up the size64 kmemlist for cpu before we can
* begin anything. Make sure some other cpu on this
@@ -1169,7 +1118,7 @@ static int init_cache_nodelists_node(int node)
/*
* The l3s don't come and go as CPUs come and
- * go. cache_chain_mutex is sufficient
+ * go. slab_mutex is sufficient
* protection here.
*/
cachep->nodelists[node] = l3;
@@ -1191,7 +1140,7 @@ static void __cpuinit cpuup_canceled(long cpu)
int node = cpu_to_mem(cpu);
const struct cpumask *mask = cpumask_of_node(node);
- list_for_each_entry(cachep, &cache_chain, next) {
+ list_for_each_entry(cachep, &slab_caches, list) {
struct array_cache *nc;
struct array_cache *shared;
struct array_cache **alien;
@@ -1241,7 +1190,7 @@ free_array_cache:
* the respective cache's slabs, now we can go ahead and
* shrink each nodelist to its limit.
*/
- list_for_each_entry(cachep, &cache_chain, next) {
+ list_for_each_entry(cachep, &slab_caches, list) {
l3 = cachep->nodelists[node];
if (!l3)
continue;
@@ -1270,7 +1219,7 @@ static int __cpuinit cpuup_prepare(long cpu)
* Now we can go ahead with allocating the shared arrays and
* array caches
*/
- list_for_each_entry(cachep, &cache_chain, next) {
+ list_for_each_entry(cachep, &slab_caches, list) {
struct array_cache *nc;
struct array_cache *shared = NULL;
struct array_cache **alien = NULL;
@@ -1338,9 +1287,9 @@ static int __cpuinit cpuup_callback(struct notifier_block *nfb,
switch (action) {
case CPU_UP_PREPARE:
case CPU_UP_PREPARE_FROZEN:
- mutex_lock(&cache_chain_mutex);
+ mutex_lock(&slab_mutex);
err = cpuup_prepare(cpu);
- mutex_unlock(&cache_chain_mutex);
+ mutex_unlock(&slab_mutex);
break;
case CPU_ONLINE:
case CPU_ONLINE_FROZEN:
@@ -1350,7 +1299,7 @@ static int __cpuinit cpuup_callback(struct notifier_block *nfb,
case CPU_DOWN_PREPARE:
case CPU_DOWN_PREPARE_FROZEN:
/*
- * Shutdown cache reaper. Note that the cache_chain_mutex is
+ * Shutdown cache reaper. Note that the slab_mutex is
* held so that if cache_reap() is invoked it cannot do
* anything expensive but will only modify reap_work
* and reschedule the timer.
@@ -1377,9 +1326,9 @@ static int __cpuinit cpuup_callback(struct notifier_block *nfb,
#endif
case CPU_UP_CANCELED:
case CPU_UP_CANCELED_FROZEN:
- mutex_lock(&cache_chain_mutex);
+ mutex_lock(&slab_mutex);
cpuup_canceled(cpu);
- mutex_unlock(&cache_chain_mutex);
+ mutex_unlock(&slab_mutex);
break;
}
return notifier_from_errno(err);
@@ -1395,14 +1344,14 @@ static struct notifier_block __cpuinitdata cpucache_notifier = {
* Returns -EBUSY if all objects cannot be drained so that the node is not
* removed.
*
- * Must hold cache_chain_mutex.
+ * Must hold slab_mutex.
*/
static int __meminit drain_cache_nodelists_node(int node)
{
struct kmem_cache *cachep;
int ret = 0;
- list_for_each_entry(cachep, &cache_chain, next) {
+ list_for_each_entry(cachep, &slab_caches, list) {
struct kmem_list3 *l3;
l3 = cachep->nodelists[node];
@@ -1433,14 +1382,14 @@ static int __meminit slab_memory_callback(struct notifier_block *self,
switch (action) {
case MEM_GOING_ONLINE:
- mutex_lock(&cache_chain_mutex);
+ mutex_lock(&slab_mutex);
ret = init_cache_nodelists_node(nid);
- mutex_unlock(&cache_chain_mutex);
+ mutex_unlock(&slab_mutex);
break;
case MEM_GOING_OFFLINE:
- mutex_lock(&cache_chain_mutex);
+ mutex_lock(&slab_mutex);
ret = drain_cache_nodelists_node(nid);
- mutex_unlock(&cache_chain_mutex);
+ mutex_unlock(&slab_mutex);
break;
case MEM_ONLINE:
case MEM_OFFLINE:
@@ -1544,8 +1493,8 @@ void __init kmem_cache_init(void)
node = numa_mem_id();
/* 1) create the cache_cache */
- INIT_LIST_HEAD(&cache_chain);
- list_add(&cache_cache.next, &cache_chain);
+ INIT_LIST_HEAD(&slab_caches);
+ list_add(&cache_cache.list, &slab_caches);
cache_cache.colour_off = cache_line_size();
cache_cache.array[smp_processor_id()] = &initarray_cache.cache;
cache_cache.nodelists[node] = &initkmem_list3[CACHE_CACHE + node];
@@ -1553,18 +1502,16 @@ void __init kmem_cache_init(void)
/*
* struct kmem_cache size depends on nr_node_ids & nr_cpu_ids
*/
- cache_cache.buffer_size = offsetof(struct kmem_cache, array[nr_cpu_ids]) +
+ cache_cache.size = offsetof(struct kmem_cache, array[nr_cpu_ids]) +
nr_node_ids * sizeof(struct kmem_list3 *);
-#if DEBUG
- cache_cache.obj_size = cache_cache.buffer_size;
-#endif
- cache_cache.buffer_size = ALIGN(cache_cache.buffer_size,
+ cache_cache.object_size = cache_cache.size;
+ cache_cache.size = ALIGN(cache_cache.size,
cache_line_size());
cache_cache.reciprocal_buffer_size =
- reciprocal_value(cache_cache.buffer_size);
+ reciprocal_value(cache_cache.size);
for (order = 0; order < MAX_ORDER; order++) {
- cache_estimate(order, cache_cache.buffer_size,
+ cache_estimate(order, cache_cache.size,
cache_line_size(), 0, &left_over, &cache_cache.num);
if (cache_cache.num)
break;
@@ -1585,7 +1532,7 @@ void __init kmem_cache_init(void)
* bug.
*/
- sizes[INDEX_AC].cs_cachep = kmem_cache_create(names[INDEX_AC].name,
+ sizes[INDEX_AC].cs_cachep = __kmem_cache_create(names[INDEX_AC].name,
sizes[INDEX_AC].cs_size,
ARCH_KMALLOC_MINALIGN,
ARCH_KMALLOC_FLAGS|SLAB_PANIC,
@@ -1593,7 +1540,7 @@ void __init kmem_cache_init(void)
if (INDEX_AC != INDEX_L3) {
sizes[INDEX_L3].cs_cachep =
- kmem_cache_create(names[INDEX_L3].name,
+ __kmem_cache_create(names[INDEX_L3].name,
sizes[INDEX_L3].cs_size,
ARCH_KMALLOC_MINALIGN,
ARCH_KMALLOC_FLAGS|SLAB_PANIC,
@@ -1611,14 +1558,14 @@ void __init kmem_cache_init(void)
* allow tighter packing of the smaller caches.
*/
if (!sizes->cs_cachep) {
- sizes->cs_cachep = kmem_cache_create(names->name,
+ sizes->cs_cachep = __kmem_cache_create(names->name,
sizes->cs_size,
ARCH_KMALLOC_MINALIGN,
ARCH_KMALLOC_FLAGS|SLAB_PANIC,
NULL);
}
#ifdef CONFIG_ZONE_DMA
- sizes->cs_dmacachep = kmem_cache_create(
+ sizes->cs_dmacachep = __kmem_cache_create(
names->name_dma,
sizes->cs_size,
ARCH_KMALLOC_MINALIGN,
@@ -1676,27 +1623,27 @@ void __init kmem_cache_init(void)
}
}
- g_cpucache_up = EARLY;
+ slab_state = UP;
}
void __init kmem_cache_init_late(void)
{
struct kmem_cache *cachep;
- g_cpucache_up = LATE;
+ slab_state = UP;
/* Annotate slab for lockdep -- annotate the malloc caches */
init_lock_keys();
/* 6) resize the head arrays to their final sizes */
- mutex_lock(&cache_chain_mutex);
- list_for_each_entry(cachep, &cache_chain, next)
+ mutex_lock(&slab_mutex);
+ list_for_each_entry(cachep, &slab_caches, list)
if (enable_cpucache(cachep, GFP_NOWAIT))
BUG();
- mutex_unlock(&cache_chain_mutex);
+ mutex_unlock(&slab_mutex);
/* Done! */
- g_cpucache_up = FULL;
+ slab_state = FULL;
/*
* Register a cpu startup notifier callback that initializes
@@ -1727,6 +1674,9 @@ static int __init cpucache_init(void)
*/
for_each_online_cpu(cpu)
start_cpu_timer(cpu);
+
+ /* Done! */
+ slab_state = FULL;
return 0;
}
__initcall(cpucache_init);
@@ -1743,7 +1693,7 @@ slab_out_of_memory(struct kmem_cache *cachep, gfp_t gfpflags, int nodeid)
"SLAB: Unable to allocate memory on node %d (gfp=0x%x)\n",
nodeid, gfpflags);
printk(KERN_WARNING " cache: %s, object size: %d, order: %d\n",
- cachep->name, cachep->buffer_size, cachep->gfporder);
+ cachep->name, cachep->size, cachep->gfporder);
for_each_online_node(node) {
unsigned long active_objs = 0, num_objs = 0, free_objects = 0;
@@ -1798,7 +1748,7 @@ static void *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, int nodeid)
flags |= __GFP_COMP;
#endif
- flags |= cachep->gfpflags;
+ flags |= cachep->allocflags;
if (cachep->flags & SLAB_RECLAIM_ACCOUNT)
flags |= __GFP_RECLAIMABLE;
@@ -1874,7 +1824,7 @@ static void kmem_rcu_free(struct rcu_head *head)
static void store_stackinfo(struct kmem_cache *cachep, unsigned long *addr,
unsigned long caller)
{
- int size = obj_size(cachep);
+ int size = cachep->object_size;
addr = (unsigned long *)&((char *)addr)[obj_offset(cachep)];
@@ -1906,7 +1856,7 @@ static void store_stackinfo(struct kmem_cache *cachep, unsigned long *addr,
static void poison_obj(struct kmem_cache *cachep, void *addr, unsigned char val)
{
- int size = obj_size(cachep);
+ int size = cachep->object_size;
addr = &((char *)addr)[obj_offset(cachep)];
memset(addr, val, size);
@@ -1966,7 +1916,7 @@ static void print_objinfo(struct kmem_cache *cachep, void *objp, int lines)
printk("\n");
}
realobj = (char *)objp + obj_offset(cachep);
- size = obj_size(cachep);
+ size = cachep->object_size;
for (i = 0; i < size && lines; i += 16, lines--) {
int limit;
limit = 16;
@@ -1983,7 +1933,7 @@ static void check_poison_obj(struct kmem_cache *cachep, void *objp)
int lines = 0;
realobj = (char *)objp + obj_offset(cachep);
- size = obj_size(cachep);
+ size = cachep->object_size;
for (i = 0; i < size; i++) {
char exp = POISON_FREE;
@@ -2047,10 +1997,10 @@ static void slab_destroy_debugcheck(struct kmem_cache *cachep, struct slab *slab
if (cachep->flags & SLAB_POISON) {
#ifdef CONFIG_DEBUG_PAGEALLOC
- if (cachep->buffer_size % PAGE_SIZE == 0 &&
+ if (cachep->size % PAGE_SIZE == 0 &&
OFF_SLAB(cachep))
kernel_map_pages(virt_to_page(objp),
- cachep->buffer_size / PAGE_SIZE, 1);
+ cachep->size / PAGE_SIZE, 1);
else
check_poison_obj(cachep, objp);
#else
@@ -2194,10 +2144,10 @@ static size_t calculate_slab_order(struct kmem_cache *cachep,
static int __init_refok setup_cpu_cache(struct kmem_cache *cachep, gfp_t gfp)
{
- if (g_cpucache_up == FULL)
+ if (slab_state >= FULL)
return enable_cpucache(cachep, gfp);
- if (g_cpucache_up == NONE) {
+ if (slab_state == DOWN) {
/*
* Note: the first kmem_cache_create must create the cache
* that's used by kmalloc(24), otherwise the creation of
@@ -2212,16 +2162,16 @@ static int __init_refok setup_cpu_cache(struct kmem_cache *cachep, gfp_t gfp)
*/
set_up_list3s(cachep, SIZE_AC);
if (INDEX_AC == INDEX_L3)
- g_cpucache_up = PARTIAL_L3;
+ slab_state = PARTIAL_L3;
else
- g_cpucache_up = PARTIAL_AC;
+ slab_state = PARTIAL_ARRAYCACHE;
} else {
cachep->array[smp_processor_id()] =
kmalloc(sizeof(struct arraycache_init), gfp);
- if (g_cpucache_up == PARTIAL_AC) {
+ if (slab_state == PARTIAL_ARRAYCACHE) {
set_up_list3s(cachep, SIZE_L3);
- g_cpucache_up = PARTIAL_L3;
+ slab_state = PARTIAL_L3;
} else {
int node;
for_each_online_node(node) {
@@ -2247,7 +2197,7 @@ static int __init_refok setup_cpu_cache(struct kmem_cache *cachep, gfp_t gfp)
}
/**
- * kmem_cache_create - Create a cache.
+ * __kmem_cache_create - Create a cache.
* @name: A string which is used in /proc/slabinfo to identify this cache.
* @size: The size of objects to be created in this cache.
* @align: The required alignment for the objects.
@@ -2274,59 +2224,14 @@ static int __init_refok setup_cpu_cache(struct kmem_cache *cachep, gfp_t gfp)
* as davem.
*/
struct kmem_cache *
-kmem_cache_create (const char *name, size_t size, size_t align,
+__kmem_cache_create (const char *name, size_t size, size_t align,
unsigned long flags, void (*ctor)(void *))
{
size_t left_over, slab_size, ralign;
- struct kmem_cache *cachep = NULL, *pc;
+ struct kmem_cache *cachep = NULL;
gfp_t gfp;
- /*
- * Sanity checks... these are all serious usage bugs.
- */
- if (!name || in_interrupt() || (size < BYTES_PER_WORD) ||
- size > KMALLOC_MAX_SIZE) {
- printk(KERN_ERR "%s: Early error in slab %s\n", __func__,
- name);
- BUG();
- }
-
- /*
- * We use cache_chain_mutex to ensure a consistent view of
- * cpu_online_mask as well. Please see cpuup_callback
- */
- if (slab_is_available()) {
- get_online_cpus();
- mutex_lock(&cache_chain_mutex);
- }
-
- list_for_each_entry(pc, &cache_chain, next) {
- char tmp;
- int res;
-
- /*
- * This happens when the module gets unloaded and doesn't
- * destroy its slab cache and no-one else reuses the vmalloc
- * area of the module. Print a warning.
- */
- res = probe_kernel_address(pc->name, tmp);
- if (res) {
- printk(KERN_ERR
- "SLAB: cache with size %d has lost its name\n",
- pc->buffer_size);
- continue;
- }
-
- if (!strcmp(pc->name, name)) {
- printk(KERN_ERR
- "kmem_cache_create: duplicate cache %s\n", name);
- dump_stack();
- goto oops;
- }
- }
-
#if DEBUG
- WARN_ON(strchr(name, ' ')); /* It confuses parsers */
#if FORCED_DEBUG
/*
* Enable redzoning and last user accounting, except for caches with
@@ -2415,11 +2320,12 @@ kmem_cache_create (const char *name, size_t size, size_t align,
/* Get cache's description obj. */
cachep = kmem_cache_zalloc(&cache_cache, gfp);
if (!cachep)
- goto oops;
+ return NULL;
cachep->nodelists = (struct kmem_list3 **)&cachep->array[nr_cpu_ids];
+ cachep->object_size = size;
+ cachep->align = align;
#if DEBUG
- cachep->obj_size = size;
/*
* Both debugging options require word-alignment which is calculated
@@ -2442,7 +2348,7 @@ kmem_cache_create (const char *name, size_t size, size_t align,
}
#if FORCED_DEBUG && defined(CONFIG_DEBUG_PAGEALLOC)
if (size >= malloc_sizes[INDEX_L3 + 1].cs_size
- && cachep->obj_size > cache_line_size() && ALIGN(size, align) < PAGE_SIZE) {
+ && cachep->object_size > cache_line_size() && ALIGN(size, align) < PAGE_SIZE) {
cachep->obj_offset += PAGE_SIZE - ALIGN(size, align);
size = PAGE_SIZE;
}
@@ -2471,8 +2377,7 @@ kmem_cache_create (const char *name, size_t size, size_t align,
printk(KERN_ERR
"kmem_cache_create: couldn't create cache %s.\n", name);
kmem_cache_free(&cache_cache, cachep);
- cachep = NULL;
- goto oops;
+ return NULL;
}
slab_size = ALIGN(cachep->num * sizeof(kmem_bufctl_t)
+ sizeof(struct slab), align);
@@ -2508,10 +2413,10 @@ kmem_cache_create (const char *name, size_t size, size_t align,
cachep->colour = left_over / cachep->colour_off;
cachep->slab_size = slab_size;
cachep->flags = flags;
- cachep->gfpflags = 0;
+ cachep->allocflags = 0;
if (CONFIG_ZONE_DMA_FLAG && (flags & SLAB_CACHE_DMA))
- cachep->gfpflags |= GFP_DMA;
- cachep->buffer_size = size;
+ cachep->allocflags |= GFP_DMA;
+ cachep->size = size;
cachep->reciprocal_buffer_size = reciprocal_value(size);
if (flags & CFLGS_OFF_SLAB) {
@@ -2530,8 +2435,7 @@ kmem_cache_create (const char *name, size_t size, size_t align,
if (setup_cpu_cache(cachep, gfp)) {
__kmem_cache_destroy(cachep);
- cachep = NULL;
- goto oops;
+ return NULL;
}
if (flags & SLAB_DEBUG_OBJECTS) {
@@ -2545,18 +2449,9 @@ kmem_cache_create (const char *name, size_t size, size_t align,
}
/* cache setup completed, link it into the list */
- list_add(&cachep->next, &cache_chain);
-oops:
- if (!cachep && (flags & SLAB_PANIC))
- panic("kmem_cache_create(): failed to create slab `%s'\n",
- name);
- if (slab_is_available()) {
- mutex_unlock(&cache_chain_mutex);
- put_online_cpus();
- }
+ list_add(&cachep->list, &slab_caches);
return cachep;
}
-EXPORT_SYMBOL(kmem_cache_create);
#if DEBUG
static void check_irq_off(void)
@@ -2671,7 +2566,7 @@ out:
return nr_freed;
}
-/* Called with cache_chain_mutex held to protect against cpu hotplug */
+/* Called with slab_mutex held to protect against cpu hotplug */
static int __cache_shrink(struct kmem_cache *cachep)
{
int ret = 0, i = 0;
@@ -2706,9 +2601,9 @@ int kmem_cache_shrink(struct kmem_cache *cachep)
BUG_ON(!cachep || in_interrupt());
get_online_cpus();
- mutex_lock(&cache_chain_mutex);
+ mutex_lock(&slab_mutex);
ret = __cache_shrink(cachep);
- mutex_unlock(&cache_chain_mutex);
+ mutex_unlock(&slab_mutex);
put_online_cpus();
return ret;
}
@@ -2736,15 +2631,15 @@ void kmem_cache_destroy(struct kmem_cache *cachep)
/* Find the cache in the chain of caches. */
get_online_cpus();
- mutex_lock(&cache_chain_mutex);
+ mutex_lock(&slab_mutex);
/*
* the chain is never empty, cache_cache is never destroyed
*/
- list_del(&cachep->next);
+ list_del(&cachep->list);
if (__cache_shrink(cachep)) {
slab_error(cachep, "Can't free all objects");
- list_add(&cachep->next, &cache_chain);
- mutex_unlock(&cache_chain_mutex);
+ list_add(&cachep->list, &slab_caches);
+ mutex_unlock(&slab_mutex);
put_online_cpus();
return;
}
@@ -2753,7 +2648,7 @@ void kmem_cache_destroy(struct kmem_cache *cachep)
rcu_barrier();
__kmem_cache_destroy(cachep);
- mutex_unlock(&cache_chain_mutex);
+ mutex_unlock(&slab_mutex);
put_online_cpus();
}
EXPORT_SYMBOL(kmem_cache_destroy);
@@ -2840,10 +2735,10 @@ static void cache_init_objs(struct kmem_cache *cachep,
slab_error(cachep, "constructor overwrote the"
" start of an object");
}
- if ((cachep->buffer_size % PAGE_SIZE) == 0 &&
+ if ((cachep->size % PAGE_SIZE) == 0 &&
OFF_SLAB(cachep) && cachep->flags & SLAB_POISON)
kernel_map_pages(virt_to_page(objp),
- cachep->buffer_size / PAGE_SIZE, 0);
+ cachep->size / PAGE_SIZE, 0);
#else
if (cachep->ctor)
cachep->ctor(objp);
@@ -2857,9 +2752,9 @@ static void kmem_flagcheck(struct kmem_cache *cachep, gfp_t flags)
{
if (CONFIG_ZONE_DMA_FLAG) {
if (flags & GFP_DMA)
- BUG_ON(!(cachep->gfpflags & GFP_DMA));
+ BUG_ON(!(cachep->allocflags & GFP_DMA));
else
- BUG_ON(cachep->gfpflags & GFP_DMA);
+ BUG_ON(cachep->allocflags & GFP_DMA);
}
}
@@ -2918,8 +2813,8 @@ static void slab_map_pages(struct kmem_cache *cache, struct slab *slab,
nr_pages <<= cache->gfporder;
do {
- page_set_cache(page, cache);
- page_set_slab(page, slab);
+ page->slab_cache = cache;
+ page->slab_page = slab;
page++;
} while (--nr_pages);
}
@@ -3057,7 +2952,7 @@ static void *cache_free_debugcheck(struct kmem_cache *cachep, void *objp,
kfree_debugcheck(objp);
page = virt_to_head_page(objp);
- slabp = page_get_slab(page);
+ slabp = page->slab_page;
if (cachep->flags & SLAB_RED_ZONE) {
verify_redzone_free(cachep, objp);
@@ -3077,10 +2972,10 @@ static void *cache_free_debugcheck(struct kmem_cache *cachep, void *objp,
#endif
if (cachep->flags & SLAB_POISON) {
#ifdef CONFIG_DEBUG_PAGEALLOC
- if ((cachep->buffer_size % PAGE_SIZE)==0 && OFF_SLAB(cachep)) {
+ if ((cachep->size % PAGE_SIZE)==0 && OFF_SLAB(cachep)) {
store_stackinfo(cachep, objp, (unsigned long)caller);
kernel_map_pages(virt_to_page(objp),
- cachep->buffer_size / PAGE_SIZE, 0);
+ cachep->size / PAGE_SIZE, 0);
} else {
poison_obj(cachep, objp, POISON_FREE);
}
@@ -3230,9 +3125,9 @@ static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep,
return objp;
if (cachep->flags & SLAB_POISON) {
#ifdef CONFIG_DEBUG_PAGEALLOC
- if ((cachep->buffer_size % PAGE_SIZE) == 0 && OFF_SLAB(cachep))
+ if ((cachep->size % PAGE_SIZE) == 0 && OFF_SLAB(cachep))
kernel_map_pages(virt_to_page(objp),
- cachep->buffer_size / PAGE_SIZE, 1);
+ cachep->size / PAGE_SIZE, 1);
else
check_poison_obj(cachep, objp);
#else
@@ -3261,8 +3156,8 @@ static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep,
struct slab *slabp;
unsigned objnr;
- slabp = page_get_slab(virt_to_head_page(objp));
- objnr = (unsigned)(objp - slabp->s_mem) / cachep->buffer_size;
+ slabp = virt_to_head_page(objp)->slab_page;
+ objnr = (unsigned)(objp - slabp->s_mem) / cachep->size;
slab_bufctl(slabp)[objnr] = BUFCTL_ACTIVE;
}
#endif
@@ -3285,7 +3180,7 @@ static bool slab_should_failslab(struct kmem_cache *cachep, gfp_t flags)
if (cachep == &cache_cache)
return false;
- return should_failslab(obj_size(cachep), flags, cachep->flags);
+ return should_failslab(cachep->object_size, flags, cachep->flags);
}
static inline void *____cache_alloc(struct kmem_cache *cachep, gfp_t flags)
@@ -3336,7 +3231,7 @@ static void *alternate_node_alloc(struct kmem_cache *cachep, gfp_t flags)
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);
+ nid_alloc = slab_node();
if (nid_alloc != nid_here)
return ____cache_alloc_node(cachep, flags, nid_alloc);
return NULL;
@@ -3368,7 +3263,7 @@ static void *fallback_alloc(struct kmem_cache *cache, gfp_t flags)
retry_cpuset:
cpuset_mems_cookie = get_mems_allowed();
- zonelist = node_zonelist(slab_node(current->mempolicy), flags);
+ zonelist = node_zonelist(slab_node(), flags);
retry:
/*
@@ -3545,14 +3440,14 @@ __cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid,
out:
local_irq_restore(save_flags);
ptr = cache_alloc_debugcheck_after(cachep, flags, ptr, caller);
- kmemleak_alloc_recursive(ptr, obj_size(cachep), 1, cachep->flags,
+ kmemleak_alloc_recursive(ptr, cachep->object_size, 1, cachep->flags,
flags);
if (likely(ptr))
- kmemcheck_slab_alloc(cachep, flags, ptr, obj_size(cachep));
+ kmemcheck_slab_alloc(cachep, flags, ptr, cachep->object_size);
if (unlikely((flags & __GFP_ZERO) && ptr))
- memset(ptr, 0, obj_size(cachep));
+ memset(ptr, 0, cachep->object_size);
return ptr;
}
@@ -3607,15 +3502,15 @@ __cache_alloc(struct kmem_cache *cachep, gfp_t flags, void *caller)
objp = __do_cache_alloc(cachep, flags);
local_irq_restore(save_flags);
objp = cache_alloc_debugcheck_after(cachep, flags, objp, caller);
- kmemleak_alloc_recursive(objp, obj_size(cachep), 1, cachep->flags,
+ kmemleak_alloc_recursive(objp, cachep->object_size, 1, cachep->flags,
flags);
prefetchw(objp);
if (likely(objp))
- kmemcheck_slab_alloc(cachep, flags, objp, obj_size(cachep));
+ kmemcheck_slab_alloc(cachep, flags, objp, cachep->object_size);
if (unlikely((flags & __GFP_ZERO) && objp))
- memset(objp, 0, obj_size(cachep));
+ memset(objp, 0, cachep->object_size);
return objp;
}
@@ -3731,7 +3626,7 @@ static inline void __cache_free(struct kmem_cache *cachep, void *objp,
kmemleak_free_recursive(objp, cachep->flags);
objp = cache_free_debugcheck(cachep, objp, caller);
- kmemcheck_slab_free(cachep, objp, obj_size(cachep));
+ kmemcheck_slab_free(cachep, objp, cachep->object_size);
/*
* Skip calling cache_free_alien() when the platform is not numa.
@@ -3766,7 +3661,7 @@ void *kmem_cache_alloc(struct kmem_cache *cachep, gfp_t flags)
void *ret = __cache_alloc(cachep, flags, __builtin_return_address(0));
trace_kmem_cache_alloc(_RET_IP_, ret,
- obj_size(cachep), cachep->buffer_size, flags);
+ cachep->object_size, cachep->size, flags);
return ret;
}
@@ -3794,7 +3689,7 @@ void *kmem_cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid)
__builtin_return_address(0));
trace_kmem_cache_alloc_node(_RET_IP_, ret,
- obj_size(cachep), cachep->buffer_size,
+ cachep->object_size, cachep->size,
flags, nodeid);
return ret;
@@ -3876,7 +3771,7 @@ static __always_inline void *__do_kmalloc(size_t size, gfp_t flags,
ret = __cache_alloc(cachep, flags, caller);
trace_kmalloc((unsigned long) caller, ret,
- size, cachep->buffer_size, flags);
+ size, cachep->size, flags);
return ret;
}
@@ -3916,9 +3811,9 @@ void kmem_cache_free(struct kmem_cache *cachep, void *objp)
unsigned long flags;
local_irq_save(flags);
- debug_check_no_locks_freed(objp, obj_size(cachep));
+ debug_check_no_locks_freed(objp, cachep->object_size);
if (!(cachep->flags & SLAB_DEBUG_OBJECTS))
- debug_check_no_obj_freed(objp, obj_size(cachep));
+ debug_check_no_obj_freed(objp, cachep->object_size);
__cache_free(cachep, objp, __builtin_return_address(0));
local_irq_restore(flags);
@@ -3947,8 +3842,9 @@ void kfree(const void *objp)
local_irq_save(flags);
kfree_debugcheck(objp);
c = virt_to_cache(objp);
- debug_check_no_locks_freed(objp, obj_size(c));
- debug_check_no_obj_freed(objp, obj_size(c));
+ debug_check_no_locks_freed(objp, c->object_size);
+
+ debug_check_no_obj_freed(objp, c->object_size);
__cache_free(c, (void *)objp, __builtin_return_address(0));
local_irq_restore(flags);
}
@@ -3956,7 +3852,7 @@ EXPORT_SYMBOL(kfree);
unsigned int kmem_cache_size(struct kmem_cache *cachep)
{
- return obj_size(cachep);
+ return cachep->object_size;
}
EXPORT_SYMBOL(kmem_cache_size);
@@ -4030,7 +3926,7 @@ static int alloc_kmemlist(struct kmem_cache *cachep, gfp_t gfp)
return 0;
fail:
- if (!cachep->next.next) {
+ if (!cachep->list.next) {
/* Cache is not active yet. Roll back what we did */
node--;
while (node >= 0) {
@@ -4065,7 +3961,7 @@ static void do_ccupdate_local(void *info)
new->new[smp_processor_id()] = old;
}
-/* Always called with the cache_chain_mutex held */
+/* Always called with the slab_mutex held */
static int do_tune_cpucache(struct kmem_cache *cachep, int limit,
int batchcount, int shared, gfp_t gfp)
{
@@ -4109,7 +4005,7 @@ static int do_tune_cpucache(struct kmem_cache *cachep, int limit,
return alloc_kmemlist(cachep, gfp);
}
-/* Called with cache_chain_mutex held always */
+/* Called with slab_mutex held always */
static int enable_cpucache(struct kmem_cache *cachep, gfp_t gfp)
{
int err;
@@ -4124,13 +4020,13 @@ static int enable_cpucache(struct kmem_cache *cachep, gfp_t gfp)
* The numbers are guessed, we should auto-tune as described by
* Bonwick.
*/
- if (cachep->buffer_size > 131072)
+ if (cachep->size > 131072)
limit = 1;
- else if (cachep->buffer_size > PAGE_SIZE)
+ else if (cachep->size > PAGE_SIZE)
limit = 8;
- else if (cachep->buffer_size > 1024)
+ else if (cachep->size > 1024)
limit = 24;
- else if (cachep->buffer_size > 256)
+ else if (cachep->size > 256)
limit = 54;
else
limit = 120;
@@ -4145,7 +4041,7 @@ static int enable_cpucache(struct kmem_cache *cachep, gfp_t gfp)
* to a larger limit. Thus disabled by default.
*/
shared = 0;
- if (cachep->buffer_size <= PAGE_SIZE && num_possible_cpus() > 1)
+ if (cachep->size <= PAGE_SIZE && num_possible_cpus() > 1)
shared = 8;
#if DEBUG
@@ -4211,11 +4107,11 @@ static void cache_reap(struct work_struct *w)
int node = numa_mem_id();
struct delayed_work *work = to_delayed_work(w);
- if (!mutex_trylock(&cache_chain_mutex))
+ if (!mutex_trylock(&slab_mutex))
/* Give up. Setup the next iteration. */
goto out;
- list_for_each_entry(searchp, &cache_chain, next) {
+ list_for_each_entry(searchp, &slab_caches, list) {
check_irq_on();
/*
@@ -4253,7 +4149,7 @@ next:
cond_resched();
}
check_irq_on();
- mutex_unlock(&cache_chain_mutex);
+ mutex_unlock(&slab_mutex);
next_reap_node();
out:
/* Set up the next iteration */
@@ -4289,26 +4185,26 @@ static void *s_start(struct seq_file *m, loff_t *pos)
{
loff_t n = *pos;
- mutex_lock(&cache_chain_mutex);
+ mutex_lock(&slab_mutex);
if (!n)
print_slabinfo_header(m);
- return seq_list_start(&cache_chain, *pos);
+ return seq_list_start(&slab_caches, *pos);
}
static void *s_next(struct seq_file *m, void *p, loff_t *pos)
{
- return seq_list_next(p, &cache_chain, pos);
+ return seq_list_next(p, &slab_caches, pos);
}
static void s_stop(struct seq_file *m, void *p)
{
- mutex_unlock(&cache_chain_mutex);
+ mutex_unlock(&slab_mutex);
}
static int s_show(struct seq_file *m, void *p)
{
- struct kmem_cache *cachep = list_entry(p, struct kmem_cache, next);
+ struct kmem_cache *cachep = list_entry(p, struct kmem_cache, list);
struct slab *slabp;
unsigned long active_objs;
unsigned long num_objs;
@@ -4364,7 +4260,7 @@ static int s_show(struct seq_file *m, void *p)
printk(KERN_ERR "slab: cache %s error: %s\n", name, error);
seq_printf(m, "%-17s %6lu %6lu %6u %4u %4d",
- name, active_objs, num_objs, cachep->buffer_size,
+ name, active_objs, num_objs, cachep->size,
cachep->num, (1 << cachep->gfporder));
seq_printf(m, " : tunables %4u %4u %4u",
cachep->limit, cachep->batchcount, cachep->shared);
@@ -4454,9 +4350,9 @@ static ssize_t slabinfo_write(struct file *file, const char __user *buffer,
return -EINVAL;
/* Find the cache in the chain of caches. */
- mutex_lock(&cache_chain_mutex);
+ mutex_lock(&slab_mutex);
res = -EINVAL;
- list_for_each_entry(cachep, &cache_chain, next) {
+ list_for_each_entry(cachep, &slab_caches, list) {
if (!strcmp(cachep->name, kbuf)) {
if (limit < 1 || batchcount < 1 ||
batchcount > limit || shared < 0) {
@@ -4469,7 +4365,7 @@ static ssize_t slabinfo_write(struct file *file, const char __user *buffer,
break;
}
}
- mutex_unlock(&cache_chain_mutex);
+ mutex_unlock(&slab_mutex);
if (res >= 0)
res = count;
return res;
@@ -4492,8 +4388,8 @@ static const struct file_operations proc_slabinfo_operations = {
static void *leaks_start(struct seq_file *m, loff_t *pos)
{
- mutex_lock(&cache_chain_mutex);
- return seq_list_start(&cache_chain, *pos);
+ mutex_lock(&slab_mutex);
+ return seq_list_start(&slab_caches, *pos);
}
static inline int add_caller(unsigned long *n, unsigned long v)
@@ -4532,7 +4428,7 @@ static void handle_slab(unsigned long *n, struct kmem_cache *c, struct slab *s)
int i;
if (n[0] == n[1])
return;
- for (i = 0, p = s->s_mem; i < c->num; i++, p += c->buffer_size) {
+ for (i = 0, p = s->s_mem; i < c->num; i++, p += c->size) {
if (slab_bufctl(s)[i] != BUFCTL_ACTIVE)
continue;
if (!add_caller(n, (unsigned long)*dbg_userword(c, p)))
@@ -4558,7 +4454,7 @@ static void show_symbol(struct seq_file *m, unsigned long address)
static int leaks_show(struct seq_file *m, void *p)
{
- struct kmem_cache *cachep = list_entry(p, struct kmem_cache, next);
+ struct kmem_cache *cachep = list_entry(p, struct kmem_cache, list);
struct slab *slabp;
struct kmem_list3 *l3;
const char *name;
@@ -4592,17 +4488,17 @@ static int leaks_show(struct seq_file *m, void *p)
name = cachep->name;
if (n[0] == n[1]) {
/* Increase the buffer size */
- mutex_unlock(&cache_chain_mutex);
+ mutex_unlock(&slab_mutex);
m->private = kzalloc(n[0] * 4 * sizeof(unsigned long), GFP_KERNEL);
if (!m->private) {
/* Too bad, we are really out */
m->private = n;
- mutex_lock(&cache_chain_mutex);
+ mutex_lock(&slab_mutex);
return -ENOMEM;
}
*(unsigned long *)m->private = n[0] * 2;
kfree(n);
- mutex_lock(&cache_chain_mutex);
+ mutex_lock(&slab_mutex);
/* Now make sure this entry will be retried */
m->count = m->size;
return 0;
@@ -4677,6 +4573,6 @@ size_t ksize(const void *objp)
if (unlikely(objp == ZERO_SIZE_PTR))
return 0;
- return obj_size(virt_to_cache(objp));
+ return virt_to_cache(objp)->object_size;
}
EXPORT_SYMBOL(ksize);
diff --git a/mm/slab.h b/mm/slab.h
new file mode 100644
index 000000000000..db7848caaa25
--- /dev/null
+++ b/mm/slab.h
@@ -0,0 +1,33 @@
+#ifndef MM_SLAB_H
+#define MM_SLAB_H
+/*
+ * Internal slab definitions
+ */
+
+/*
+ * State of the slab allocator.
+ *
+ * This is used to describe the states of the allocator during bootup.
+ * Allocators use this to gradually bootstrap themselves. Most allocators
+ * have the problem that the structures used for managing slab caches are
+ * allocated from slab caches themselves.
+ */
+enum slab_state {
+ DOWN, /* No slab functionality yet */
+ PARTIAL, /* SLUB: kmem_cache_node available */
+ PARTIAL_ARRAYCACHE, /* SLAB: kmalloc size for arraycache available */
+ PARTIAL_L3, /* SLAB: kmalloc size for l3 struct available */
+ UP, /* Slab caches usable but not all extras yet */
+ FULL /* Everything is working */
+};
+
+extern enum slab_state slab_state;
+
+/* The slab cache mutex protects the management structures during changes */
+extern struct mutex slab_mutex;
+extern struct list_head slab_caches;
+
+struct kmem_cache *__kmem_cache_create(const char *name, size_t size,
+ size_t align, unsigned long flags, void (*ctor)(void *));
+
+#endif
diff --git a/mm/slab_common.c b/mm/slab_common.c
new file mode 100644
index 000000000000..aa3ca5bb01b5
--- /dev/null
+++ b/mm/slab_common.c
@@ -0,0 +1,120 @@
+/*
+ * Slab allocator functions that are independent of the allocator strategy
+ *
+ * (C) 2012 Christoph Lameter <cl@linux.com>
+ */
+#include <linux/slab.h>
+
+#include <linux/mm.h>
+#include <linux/poison.h>
+#include <linux/interrupt.h>
+#include <linux/memory.h>
+#include <linux/compiler.h>
+#include <linux/module.h>
+#include <linux/cpu.h>
+#include <linux/uaccess.h>
+#include <asm/cacheflush.h>
+#include <asm/tlbflush.h>
+#include <asm/page.h>
+
+#include "slab.h"
+
+enum slab_state slab_state;
+LIST_HEAD(slab_caches);
+DEFINE_MUTEX(slab_mutex);
+
+/*
+ * kmem_cache_create - Create a cache.
+ * @name: A string which is used in /proc/slabinfo to identify this cache.
+ * @size: The size of objects to be created in this cache.
+ * @align: The required alignment for the objects.
+ * @flags: SLAB flags
+ * @ctor: A constructor for the objects.
+ *
+ * Returns a ptr to the cache on success, NULL on failure.
+ * Cannot be called within a interrupt, but can be interrupted.
+ * The @ctor is run when new pages are allocated by the cache.
+ *
+ * The flags are
+ *
+ * %SLAB_POISON - Poison the slab with a known test pattern (a5a5a5a5)
+ * to catch references to uninitialised memory.
+ *
+ * %SLAB_RED_ZONE - Insert `Red' zones around the allocated memory to check
+ * for buffer overruns.
+ *
+ * %SLAB_HWCACHE_ALIGN - Align the objects in this cache to a hardware
+ * cacheline. This can be beneficial if you're counting cycles as closely
+ * as davem.
+ */
+
+struct kmem_cache *kmem_cache_create(const char *name, size_t size, size_t align,
+ unsigned long flags, void (*ctor)(void *))
+{
+ struct kmem_cache *s = NULL;
+
+#ifdef CONFIG_DEBUG_VM
+ if (!name || in_interrupt() || size < sizeof(void *) ||
+ size > KMALLOC_MAX_SIZE) {
+ printk(KERN_ERR "kmem_cache_create(%s) integrity check"
+ " failed\n", name);
+ goto out;
+ }
+#endif
+
+ get_online_cpus();
+ mutex_lock(&slab_mutex);
+
+#ifdef CONFIG_DEBUG_VM
+ list_for_each_entry(s, &slab_caches, list) {
+ char tmp;
+ int res;
+
+ /*
+ * This happens when the module gets unloaded and doesn't
+ * destroy its slab cache and no-one else reuses the vmalloc
+ * area of the module. Print a warning.
+ */
+ res = probe_kernel_address(s->name, tmp);
+ if (res) {
+ printk(KERN_ERR
+ "Slab cache with size %d has lost its name\n",
+ s->object_size);
+ continue;
+ }
+
+ if (!strcmp(s->name, name)) {
+ printk(KERN_ERR "kmem_cache_create(%s): Cache name"
+ " already exists.\n",
+ name);
+ dump_stack();
+ s = NULL;
+ goto oops;
+ }
+ }
+
+ WARN_ON(strchr(name, ' ')); /* It confuses parsers */
+#endif
+
+ s = __kmem_cache_create(name, size, align, flags, ctor);
+
+#ifdef CONFIG_DEBUG_VM
+oops:
+#endif
+ mutex_unlock(&slab_mutex);
+ put_online_cpus();
+
+#ifdef CONFIG_DEBUG_VM
+out:
+#endif
+ if (!s && (flags & SLAB_PANIC))
+ panic("kmem_cache_create: Failed to create slab '%s'\n", name);
+
+ return s;
+}
+EXPORT_SYMBOL(kmem_cache_create);
+
+int slab_is_available(void)
+{
+ return slab_state >= UP;
+}
diff --git a/mm/slob.c b/mm/slob.c
index 8105be42cad1..45d4ca79933a 100644
--- a/mm/slob.c
+++ b/mm/slob.c
@@ -59,6 +59,8 @@
#include <linux/kernel.h>
#include <linux/slab.h>
+#include "slab.h"
+
#include <linux/mm.h>
#include <linux/swap.h> /* struct reclaim_state */
#include <linux/cache.h>
@@ -92,36 +94,6 @@ struct slob_block {
typedef struct slob_block slob_t;
/*
- * We use struct page fields to manage some slob allocation aspects,
- * however to avoid the horrible mess in include/linux/mm_types.h, we'll
- * just define our own struct page type variant here.
- */
-struct slob_page {
- union {
- struct {
- unsigned long flags; /* mandatory */
- atomic_t _count; /* mandatory */
- slobidx_t units; /* free units left in page */
- unsigned long pad[2];
- slob_t *free; /* first free slob_t in page */
- struct list_head list; /* linked list of free pages */
- };
- struct page page;
- };
-};
-static inline void struct_slob_page_wrong_size(void)
-{ BUILD_BUG_ON(sizeof(struct slob_page) != sizeof(struct page)); }
-
-/*
- * free_slob_page: call before a slob_page is returned to the page allocator.
- */
-static inline void free_slob_page(struct slob_page *sp)
-{
- reset_page_mapcount(&sp->page);
- sp->page.mapping = NULL;
-}
-
-/*
* All partially free slob pages go on these lists.
*/
#define SLOB_BREAK1 256
@@ -131,46 +103,23 @@ static LIST_HEAD(free_slob_medium);
static LIST_HEAD(free_slob_large);
/*
- * is_slob_page: True for all slob pages (false for bigblock pages)
- */
-static inline int is_slob_page(struct slob_page *sp)
-{
- return PageSlab((struct page *)sp);
-}
-
-static inline void set_slob_page(struct slob_page *sp)
-{
- __SetPageSlab((struct page *)sp);
-}
-
-static inline void clear_slob_page(struct slob_page *sp)
-{
- __ClearPageSlab((struct page *)sp);
-}
-
-static inline struct slob_page *slob_page(const void *addr)
-{
- return (struct slob_page *)virt_to_page(addr);
-}
-
-/*
* slob_page_free: true for pages on free_slob_pages list.
*/
-static inline int slob_page_free(struct slob_page *sp)
+static inline int slob_page_free(struct page *sp)
{
- return PageSlobFree((struct page *)sp);
+ return PageSlobFree(sp);
}
-static void set_slob_page_free(struct slob_page *sp, struct list_head *list)
+static void set_slob_page_free(struct page *sp, struct list_head *list)
{
list_add(&sp->list, list);
- __SetPageSlobFree((struct page *)sp);
+ __SetPageSlobFree(sp);
}
-static inline void clear_slob_page_free(struct slob_page *sp)
+static inline void clear_slob_page_free(struct page *sp)
{
list_del(&sp->list);
- __ClearPageSlobFree((struct page *)sp);
+ __ClearPageSlobFree(sp);
}
#define SLOB_UNIT sizeof(slob_t)
@@ -267,12 +216,12 @@ static void slob_free_pages(void *b, int order)
/*
* Allocate a slob block within a given slob_page sp.
*/
-static void *slob_page_alloc(struct slob_page *sp, size_t size, int align)
+static void *slob_page_alloc(struct page *sp, size_t size, int align)
{
slob_t *prev, *cur, *aligned = NULL;
int delta = 0, units = SLOB_UNITS(size);
- for (prev = NULL, cur = sp->free; ; prev = cur, cur = slob_next(cur)) {
+ for (prev = NULL, cur = sp->freelist; ; prev = cur, cur = slob_next(cur)) {
slobidx_t avail = slob_units(cur);
if (align) {
@@ -296,12 +245,12 @@ static void *slob_page_alloc(struct slob_page *sp, size_t size, int align)
if (prev)
set_slob(prev, slob_units(prev), next);
else
- sp->free = next;
+ sp->freelist = next;
} else { /* fragment */
if (prev)
set_slob(prev, slob_units(prev), cur + units);
else
- sp->free = cur + units;
+ sp->freelist = cur + units;
set_slob(cur + units, avail - units, next);
}
@@ -320,7 +269,7 @@ static void *slob_page_alloc(struct slob_page *sp, size_t size, int align)
*/
static void *slob_alloc(size_t size, gfp_t gfp, int align, int node)
{
- struct slob_page *sp;
+ struct page *sp;
struct list_head *prev;
struct list_head *slob_list;
slob_t *b = NULL;
@@ -341,7 +290,7 @@ static void *slob_alloc(size_t size, gfp_t gfp, int align, int node)
* If there's a node specification, search for a partial
* page with a matching node id in the freelist.
*/
- if (node != -1 && page_to_nid(&sp->page) != node)
+ if (node != -1 && page_to_nid(sp) != node)
continue;
#endif
/* Enough room on this page? */
@@ -369,12 +318,12 @@ static void *slob_alloc(size_t size, gfp_t gfp, int align, int node)
b = slob_new_pages(gfp & ~__GFP_ZERO, 0, node);
if (!b)
return NULL;
- sp = slob_page(b);
- set_slob_page(sp);
+ sp = virt_to_page(b);
+ __SetPageSlab(sp);
spin_lock_irqsave(&slob_lock, flags);
sp->units = SLOB_UNITS(PAGE_SIZE);
- sp->free = b;
+ sp->freelist = b;
INIT_LIST_HEAD(&sp->list);
set_slob(b, SLOB_UNITS(PAGE_SIZE), b + SLOB_UNITS(PAGE_SIZE));
set_slob_page_free(sp, slob_list);
@@ -392,7 +341,7 @@ static void *slob_alloc(size_t size, gfp_t gfp, int align, int node)
*/
static void slob_free(void *block, int size)
{
- struct slob_page *sp;
+ struct page *sp;
slob_t *prev, *next, *b = (slob_t *)block;
slobidx_t units;
unsigned long flags;
@@ -402,7 +351,7 @@ static void slob_free(void *block, int size)
return;
BUG_ON(!size);
- sp = slob_page(block);
+ sp = virt_to_page(block);
units = SLOB_UNITS(size);
spin_lock_irqsave(&slob_lock, flags);
@@ -412,8 +361,8 @@ static void slob_free(void *block, int size)
if (slob_page_free(sp))
clear_slob_page_free(sp);
spin_unlock_irqrestore(&slob_lock, flags);
- clear_slob_page(sp);
- free_slob_page(sp);
+ __ClearPageSlab(sp);
+ reset_page_mapcount(sp);
slob_free_pages(b, 0);
return;
}
@@ -421,7 +370,7 @@ static void slob_free(void *block, int size)
if (!slob_page_free(sp)) {
/* This slob page is about to become partially free. Easy! */
sp->units = units;
- sp->free = b;
+ sp->freelist = b;
set_slob(b, units,
(void *)((unsigned long)(b +
SLOB_UNITS(PAGE_SIZE)) & PAGE_MASK));
@@ -441,15 +390,15 @@ static void slob_free(void *block, int size)
*/
sp->units += units;
- if (b < sp->free) {
- if (b + units == sp->free) {
- units += slob_units(sp->free);
- sp->free = slob_next(sp->free);
+ if (b < (slob_t *)sp->freelist) {
+ if (b + units == sp->freelist) {
+ units += slob_units(sp->freelist);
+ sp->freelist = slob_next(sp->freelist);
}
- set_slob(b, units, sp->free);
- sp->free = b;
+ set_slob(b, units, sp->freelist);
+ sp->freelist = b;
} else {
- prev = sp->free;
+ prev = sp->freelist;
next = slob_next(prev);
while (b > next) {
prev = next;
@@ -522,7 +471,7 @@ EXPORT_SYMBOL(__kmalloc_node);
void kfree(const void *block)
{
- struct slob_page *sp;
+ struct page *sp;
trace_kfree(_RET_IP_, block);
@@ -530,43 +479,36 @@ void kfree(const void *block)
return;
kmemleak_free(block);
- sp = slob_page(block);
- if (is_slob_page(sp)) {
+ sp = virt_to_page(block);
+ if (PageSlab(sp)) {
int align = max(ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN);
unsigned int *m = (unsigned int *)(block - align);
slob_free(m, *m + align);
} else
- put_page(&sp->page);
+ put_page(sp);
}
EXPORT_SYMBOL(kfree);
/* can't use ksize for kmem_cache_alloc memory, only kmalloc */
size_t ksize(const void *block)
{
- struct slob_page *sp;
+ struct page *sp;
BUG_ON(!block);
if (unlikely(block == ZERO_SIZE_PTR))
return 0;
- sp = slob_page(block);
- if (is_slob_page(sp)) {
+ sp = virt_to_page(block);
+ if (PageSlab(sp)) {
int align = max(ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN);
unsigned int *m = (unsigned int *)(block - align);
return SLOB_UNITS(*m) * SLOB_UNIT;
} else
- return sp->page.private;
+ return sp->private;
}
EXPORT_SYMBOL(ksize);
-struct kmem_cache {
- unsigned int size, align;
- unsigned long flags;
- const char *name;
- void (*ctor)(void *);
-};
-
-struct kmem_cache *kmem_cache_create(const char *name, size_t size,
+struct kmem_cache *__kmem_cache_create(const char *name, size_t size,
size_t align, unsigned long flags, void (*ctor)(void *))
{
struct kmem_cache *c;
@@ -589,13 +531,12 @@ struct kmem_cache *kmem_cache_create(const char *name, size_t size,
c->align = ARCH_SLAB_MINALIGN;
if (c->align < align)
c->align = align;
- } else if (flags & SLAB_PANIC)
- panic("Cannot create slab cache %s\n", name);
- kmemleak_alloc(c, sizeof(struct kmem_cache), 1, GFP_KERNEL);
+ kmemleak_alloc(c, sizeof(struct kmem_cache), 1, GFP_KERNEL);
+ c->refcount = 1;
+ }
return c;
}
-EXPORT_SYMBOL(kmem_cache_create);
void kmem_cache_destroy(struct kmem_cache *c)
{
@@ -678,19 +619,12 @@ int kmem_cache_shrink(struct kmem_cache *d)
}
EXPORT_SYMBOL(kmem_cache_shrink);
-static unsigned int slob_ready __read_mostly;
-
-int slab_is_available(void)
-{
- return slob_ready;
-}
-
void __init kmem_cache_init(void)
{
- slob_ready = 1;
+ slab_state = UP;
}
void __init kmem_cache_init_late(void)
{
- /* Nothing to do */
+ slab_state = FULL;
}
diff --git a/mm/slub.c b/mm/slub.c
index 8c691fa1cf3c..e517d435e5dc 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -16,6 +16,7 @@
#include <linux/interrupt.h>
#include <linux/bitops.h>
#include <linux/slab.h>
+#include "slab.h"
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/kmemcheck.h>
@@ -35,13 +36,13 @@
/*
* Lock order:
- * 1. slub_lock (Global Semaphore)
+ * 1. slab_mutex (Global Mutex)
* 2. node->list_lock
* 3. slab_lock(page) (Only on some arches and for debugging)
*
- * slub_lock
+ * slab_mutex
*
- * The role of the slub_lock is to protect the list of all the slabs
+ * The role of the slab_mutex is to protect the list of all the slabs
* and to synchronize major metadata changes to slab cache structures.
*
* The slab_lock is only used for debugging and on arches that do not
@@ -182,17 +183,6 @@ static int kmem_size = sizeof(struct kmem_cache);
static struct notifier_block slab_notifier;
#endif
-static enum {
- DOWN, /* No slab functionality available */
- PARTIAL, /* Kmem_cache_node works */
- UP, /* Everything works but does not show up in sysfs */
- SYSFS /* Sysfs up */
-} slab_state = DOWN;
-
-/* A list of all slab caches on the system */
-static DECLARE_RWSEM(slub_lock);
-static LIST_HEAD(slab_caches);
-
/*
* Tracking user of a slab.
*/
@@ -237,11 +227,6 @@ static inline void stat(const struct kmem_cache *s, enum stat_item si)
* Core slab cache functions
*******************************************************************/
-int slab_is_available(void)
-{
- return slab_state >= UP;
-}
-
static inline struct kmem_cache_node *get_node(struct kmem_cache *s, int node)
{
return s->node[node];
@@ -311,7 +296,7 @@ static inline size_t slab_ksize(const struct kmem_cache *s)
* and whatever may come after it.
*/
if (s->flags & (SLAB_RED_ZONE | SLAB_POISON))
- return s->objsize;
+ return s->object_size;
#endif
/*
@@ -609,11 +594,11 @@ static void print_trailer(struct kmem_cache *s, struct page *page, u8 *p)
if (p > addr + 16)
print_section("Bytes b4 ", p - 16, 16);
- print_section("Object ", p, min_t(unsigned long, s->objsize,
+ print_section("Object ", p, min_t(unsigned long, s->object_size,
PAGE_SIZE));
if (s->flags & SLAB_RED_ZONE)
- print_section("Redzone ", p + s->objsize,
- s->inuse - s->objsize);
+ print_section("Redzone ", p + s->object_size,
+ s->inuse - s->object_size);
if (s->offset)
off = s->offset + sizeof(void *);
@@ -655,12 +640,12 @@ static void init_object(struct kmem_cache *s, void *object, u8 val)
u8 *p = object;
if (s->flags & __OBJECT_POISON) {
- memset(p, POISON_FREE, s->objsize - 1);
- p[s->objsize - 1] = POISON_END;
+ memset(p, POISON_FREE, s->object_size - 1);
+ p[s->object_size - 1] = POISON_END;
}
if (s->flags & SLAB_RED_ZONE)
- memset(p + s->objsize, val, s->inuse - s->objsize);
+ memset(p + s->object_size, val, s->inuse - s->object_size);
}
static void restore_bytes(struct kmem_cache *s, char *message, u8 data,
@@ -705,10 +690,10 @@ static int check_bytes_and_report(struct kmem_cache *s, struct page *page,
* Poisoning uses 0x6b (POISON_FREE) and the last byte is
* 0xa5 (POISON_END)
*
- * object + s->objsize
+ * object + s->object_size
* Padding to reach word boundary. This is also used for Redzoning.
* Padding is extended by another word if Redzoning is enabled and
- * objsize == inuse.
+ * object_size == inuse.
*
* We fill with 0xbb (RED_INACTIVE) for inactive objects and with
* 0xcc (RED_ACTIVE) for objects in use.
@@ -727,7 +712,7 @@ static int check_bytes_and_report(struct kmem_cache *s, struct page *page,
* object + s->size
* Nothing is used beyond s->size.
*
- * If slabcaches are merged then the objsize and inuse boundaries are mostly
+ * If slabcaches are merged then the object_size and inuse boundaries are mostly
* ignored. And therefore no slab options that rely on these boundaries
* may be used with merged slabcaches.
*/
@@ -787,25 +772,25 @@ static int check_object(struct kmem_cache *s, struct page *page,
void *object, u8 val)
{
u8 *p = object;
- u8 *endobject = object + s->objsize;
+ u8 *endobject = object + s->object_size;
if (s->flags & SLAB_RED_ZONE) {
if (!check_bytes_and_report(s, page, object, "Redzone",
- endobject, val, s->inuse - s->objsize))
+ endobject, val, s->inuse - s->object_size))
return 0;
} else {
- if ((s->flags & SLAB_POISON) && s->objsize < s->inuse) {
+ if ((s->flags & SLAB_POISON) && s->object_size < s->inuse) {
check_bytes_and_report(s, page, p, "Alignment padding",
- endobject, POISON_INUSE, s->inuse - s->objsize);
+ endobject, POISON_INUSE, s->inuse - s->object_size);
}
}
if (s->flags & SLAB_POISON) {
if (val != SLUB_RED_ACTIVE && (s->flags & __OBJECT_POISON) &&
(!check_bytes_and_report(s, page, p, "Poison", p,
- POISON_FREE, s->objsize - 1) ||
+ POISON_FREE, s->object_size - 1) ||
!check_bytes_and_report(s, page, p, "Poison",
- p + s->objsize - 1, POISON_END, 1)))
+ p + s->object_size - 1, POISON_END, 1)))
return 0;
/*
* check_pad_bytes cleans up on its own.
@@ -926,7 +911,7 @@ static void trace(struct kmem_cache *s, struct page *page, void *object,
page->freelist);
if (!alloc)
- print_section("Object ", (void *)object, s->objsize);
+ print_section("Object ", (void *)object, s->object_size);
dump_stack();
}
@@ -942,14 +927,14 @@ static inline int slab_pre_alloc_hook(struct kmem_cache *s, gfp_t flags)
lockdep_trace_alloc(flags);
might_sleep_if(flags & __GFP_WAIT);
- return should_failslab(s->objsize, flags, s->flags);
+ return should_failslab(s->object_size, flags, s->flags);
}
static inline void slab_post_alloc_hook(struct kmem_cache *s, gfp_t flags, void *object)
{
flags &= gfp_allowed_mask;
kmemcheck_slab_alloc(s, flags, object, slab_ksize(s));
- kmemleak_alloc_recursive(object, s->objsize, 1, s->flags, flags);
+ kmemleak_alloc_recursive(object, s->object_size, 1, s->flags, flags);
}
static inline void slab_free_hook(struct kmem_cache *s, void *x)
@@ -966,13 +951,13 @@ static inline void slab_free_hook(struct kmem_cache *s, void *x)
unsigned long flags;
local_irq_save(flags);
- kmemcheck_slab_free(s, x, s->objsize);
- debug_check_no_locks_freed(x, s->objsize);
+ kmemcheck_slab_free(s, x, s->object_size);
+ debug_check_no_locks_freed(x, s->object_size);
local_irq_restore(flags);
}
#endif
if (!(s->flags & SLAB_DEBUG_OBJECTS))
- debug_check_no_obj_freed(x, s->objsize);
+ debug_check_no_obj_freed(x, s->object_size);
}
/*
@@ -1207,7 +1192,7 @@ out:
__setup("slub_debug", setup_slub_debug);
-static unsigned long kmem_cache_flags(unsigned long objsize,
+static unsigned long kmem_cache_flags(unsigned long object_size,
unsigned long flags, const char *name,
void (*ctor)(void *))
{
@@ -1237,7 +1222,7 @@ static inline int check_object(struct kmem_cache *s, struct page *page,
static inline void add_full(struct kmem_cache *s, struct kmem_cache_node *n,
struct page *page) {}
static inline void remove_full(struct kmem_cache *s, struct page *page) {}
-static inline unsigned long kmem_cache_flags(unsigned long objsize,
+static inline unsigned long kmem_cache_flags(unsigned long object_size,
unsigned long flags, const char *name,
void (*ctor)(void *))
{
@@ -1314,13 +1299,7 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node)
stat(s, ORDER_FALLBACK);
}
- if (flags & __GFP_WAIT)
- local_irq_disable();
-
- if (!page)
- return NULL;
-
- if (kmemcheck_enabled
+ if (kmemcheck_enabled && page
&& !(s->flags & (SLAB_NOTRACK | DEBUG_DEFAULT_FLAGS))) {
int pages = 1 << oo_order(oo);
@@ -1336,6 +1315,11 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node)
kmemcheck_mark_unallocated_pages(page, pages);
}
+ if (flags & __GFP_WAIT)
+ local_irq_disable();
+ if (!page)
+ return NULL;
+
page->objects = oo_objects(oo);
mod_zone_page_state(page_zone(page),
(s->flags & SLAB_RECLAIM_ACCOUNT) ?
@@ -1490,12 +1474,12 @@ static inline void remove_partial(struct kmem_cache_node *n,
}
/*
- * Lock slab, remove from the partial list and put the object into the
- * per cpu freelist.
+ * Remove slab from the partial list, freeze it and
+ * return the pointer to the freelist.
*
* Returns a list of objects or NULL if it fails.
*
- * Must hold list_lock.
+ * Must hold list_lock since we modify the partial list.
*/
static inline void *acquire_slab(struct kmem_cache *s,
struct kmem_cache_node *n, struct page *page,
@@ -1510,26 +1494,27 @@ static inline void *acquire_slab(struct kmem_cache *s,
* The old freelist is the list of objects for the
* per cpu allocation list.
*/
- do {
- freelist = page->freelist;
- counters = page->counters;
- new.counters = counters;
- if (mode) {
- new.inuse = page->objects;
- new.freelist = NULL;
- } else {
- new.freelist = freelist;
- }
+ freelist = page->freelist;
+ counters = page->counters;
+ new.counters = counters;
+ if (mode) {
+ new.inuse = page->objects;
+ new.freelist = NULL;
+ } else {
+ new.freelist = freelist;
+ }
- VM_BUG_ON(new.frozen);
- new.frozen = 1;
+ VM_BUG_ON(new.frozen);
+ new.frozen = 1;
- } while (!__cmpxchg_double_slab(s, page,
+ if (!__cmpxchg_double_slab(s, page,
freelist, counters,
new.freelist, new.counters,
- "lock and freeze"));
+ "acquire_slab"))
+ return NULL;
remove_partial(n, page);
+ WARN_ON(!freelist);
return freelist;
}
@@ -1563,7 +1548,6 @@ static void *get_partial_node(struct kmem_cache *s,
if (!object) {
c->page = page;
- c->node = page_to_nid(page);
stat(s, ALLOC_FROM_PARTIAL);
object = t;
available = page->objects - page->inuse;
@@ -1617,7 +1601,7 @@ static void *get_any_partial(struct kmem_cache *s, gfp_t flags,
do {
cpuset_mems_cookie = get_mems_allowed();
- zonelist = node_zonelist(slab_node(current->mempolicy), flags);
+ zonelist = node_zonelist(slab_node(), flags);
for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) {
struct kmem_cache_node *n;
@@ -1731,14 +1715,12 @@ void init_kmem_cache_cpus(struct kmem_cache *s)
/*
* Remove the cpu slab
*/
-static void deactivate_slab(struct kmem_cache *s, struct kmem_cache_cpu *c)
+static void deactivate_slab(struct kmem_cache *s, struct page *page, void *freelist)
{
enum slab_modes { M_NONE, M_PARTIAL, M_FULL, M_FREE };
- struct page *page = c->page;
struct kmem_cache_node *n = get_node(s, page_to_nid(page));
int lock = 0;
enum slab_modes l = M_NONE, m = M_NONE;
- void *freelist;
void *nextfree;
int tail = DEACTIVATE_TO_HEAD;
struct page new;
@@ -1749,11 +1731,6 @@ static void deactivate_slab(struct kmem_cache *s, struct kmem_cache_cpu *c)
tail = DEACTIVATE_TO_TAIL;
}
- c->tid = next_tid(c->tid);
- c->page = NULL;
- freelist = c->freelist;
- c->freelist = NULL;
-
/*
* Stage one: Free all available per cpu objects back
* to the page freelist while it is still frozen. Leave the
@@ -1879,21 +1856,31 @@ redo:
}
}
-/* Unfreeze all the cpu partial slabs */
+/*
+ * Unfreeze all the cpu partial slabs.
+ *
+ * This function must be called with interrupt disabled.
+ */
static void unfreeze_partials(struct kmem_cache *s)
{
- struct kmem_cache_node *n = NULL;
+ struct kmem_cache_node *n = NULL, *n2 = NULL;
struct kmem_cache_cpu *c = this_cpu_ptr(s->cpu_slab);
struct page *page, *discard_page = NULL;
while ((page = c->partial)) {
- enum slab_modes { M_PARTIAL, M_FREE };
- enum slab_modes l, m;
struct page new;
struct page old;
c->partial = page->next;
- l = M_FREE;
+
+ n2 = get_node(s, page_to_nid(page));
+ if (n != n2) {
+ if (n)
+ spin_unlock(&n->list_lock);
+
+ n = n2;
+ spin_lock(&n->list_lock);
+ }
do {
@@ -1906,43 +1893,17 @@ static void unfreeze_partials(struct kmem_cache *s)
new.frozen = 0;
- if (!new.inuse && (!n || n->nr_partial > s->min_partial))
- m = M_FREE;
- else {
- struct kmem_cache_node *n2 = get_node(s,
- page_to_nid(page));
-
- m = M_PARTIAL;
- if (n != n2) {
- if (n)
- spin_unlock(&n->list_lock);
-
- n = n2;
- spin_lock(&n->list_lock);
- }
- }
-
- if (l != m) {
- if (l == M_PARTIAL) {
- remove_partial(n, page);
- stat(s, FREE_REMOVE_PARTIAL);
- } else {
- add_partial(n, page,
- DEACTIVATE_TO_TAIL);
- stat(s, FREE_ADD_PARTIAL);
- }
-
- l = m;
- }
-
- } while (!cmpxchg_double_slab(s, page,
+ } while (!__cmpxchg_double_slab(s, page,
old.freelist, old.counters,
new.freelist, new.counters,
"unfreezing slab"));
- if (m == M_FREE) {
+ if (unlikely(!new.inuse && n->nr_partial > s->min_partial)) {
page->next = discard_page;
discard_page = page;
+ } else {
+ add_partial(n, page, DEACTIVATE_TO_TAIL);
+ stat(s, FREE_ADD_PARTIAL);
}
}
@@ -2011,7 +1972,11 @@ int put_cpu_partial(struct kmem_cache *s, struct page *page, int drain)
static inline void flush_slab(struct kmem_cache *s, struct kmem_cache_cpu *c)
{
stat(s, CPUSLAB_FLUSH);
- deactivate_slab(s, c);
+ deactivate_slab(s, c->page, c->freelist);
+
+ c->tid = next_tid(c->tid);
+ c->page = NULL;
+ c->freelist = NULL;
}
/*
@@ -2055,10 +2020,10 @@ static void flush_all(struct kmem_cache *s)
* Check if the objects in a per cpu structure fit numa
* locality expectations.
*/
-static inline int node_match(struct kmem_cache_cpu *c, int node)
+static inline int node_match(struct page *page, int node)
{
#ifdef CONFIG_NUMA
- if (node != NUMA_NO_NODE && c->node != node)
+ if (node != NUMA_NO_NODE && page_to_nid(page) != node)
return 0;
#endif
return 1;
@@ -2101,10 +2066,10 @@ slab_out_of_memory(struct kmem_cache *s, gfp_t gfpflags, int nid)
"SLUB: Unable to allocate memory on node %d (gfp=0x%x)\n",
nid, gfpflags);
printk(KERN_WARNING " cache: %s, object size: %d, buffer size: %d, "
- "default order: %d, min order: %d\n", s->name, s->objsize,
+ "default order: %d, min order: %d\n", s->name, s->object_size,
s->size, oo_order(s->oo), oo_order(s->min));
- if (oo_order(s->min) > get_order(s->objsize))
+ if (oo_order(s->min) > get_order(s->object_size))
printk(KERN_WARNING " %s debugging increased min order, use "
"slub_debug=O to disable.\n", s->name);
@@ -2130,10 +2095,16 @@ slab_out_of_memory(struct kmem_cache *s, gfp_t gfpflags, int nid)
static inline void *new_slab_objects(struct kmem_cache *s, gfp_t flags,
int node, struct kmem_cache_cpu **pc)
{
- void *object;
- struct kmem_cache_cpu *c;
- struct page *page = new_slab(s, flags, node);
+ void *freelist;
+ struct kmem_cache_cpu *c = *pc;
+ struct page *page;
+
+ freelist = get_partial(s, flags, node, c);
+ if (freelist)
+ return freelist;
+
+ page = new_slab(s, flags, node);
if (page) {
c = __this_cpu_ptr(s->cpu_slab);
if (c->page)
@@ -2143,17 +2114,16 @@ static inline void *new_slab_objects(struct kmem_cache *s, gfp_t flags,
* No other reference to the page yet so we can
* muck around with it freely without cmpxchg
*/
- object = page->freelist;
+ freelist = page->freelist;
page->freelist = NULL;
stat(s, ALLOC_SLAB);
- c->node = page_to_nid(page);
c->page = page;
*pc = c;
} else
- object = NULL;
+ freelist = NULL;
- return object;
+ return freelist;
}
/*
@@ -2163,6 +2133,8 @@ static inline void *new_slab_objects(struct kmem_cache *s, gfp_t flags,
* The page is still frozen if the return value is not NULL.
*
* If this function returns NULL then the page has been unfrozen.
+ *
+ * This function must be called with interrupt disabled.
*/
static inline void *get_freelist(struct kmem_cache *s, struct page *page)
{
@@ -2173,13 +2145,14 @@ static inline void *get_freelist(struct kmem_cache *s, struct page *page)
do {
freelist = page->freelist;
counters = page->counters;
+
new.counters = counters;
VM_BUG_ON(!new.frozen);
new.inuse = page->objects;
new.frozen = freelist != NULL;
- } while (!cmpxchg_double_slab(s, page,
+ } while (!__cmpxchg_double_slab(s, page,
freelist, counters,
NULL, new.counters,
"get_freelist"));
@@ -2206,7 +2179,8 @@ static inline void *get_freelist(struct kmem_cache *s, struct page *page)
static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
unsigned long addr, struct kmem_cache_cpu *c)
{
- void **object;
+ void *freelist;
+ struct page *page;
unsigned long flags;
local_irq_save(flags);
@@ -2219,25 +2193,29 @@ static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
c = this_cpu_ptr(s->cpu_slab);
#endif
- if (!c->page)
+ page = c->page;
+ if (!page)
goto new_slab;
redo:
- if (unlikely(!node_match(c, node))) {
+
+ if (unlikely(!node_match(page, node))) {
stat(s, ALLOC_NODE_MISMATCH);
- deactivate_slab(s, c);
+ deactivate_slab(s, page, c->freelist);
+ c->page = NULL;
+ c->freelist = NULL;
goto new_slab;
}
/* must check again c->freelist in case of cpu migration or IRQ */
- object = c->freelist;
- if (object)
+ freelist = c->freelist;
+ if (freelist)
goto load_freelist;
stat(s, ALLOC_SLOWPATH);
- object = get_freelist(s, c->page);
+ freelist = get_freelist(s, page);
- if (!object) {
+ if (!freelist) {
c->page = NULL;
stat(s, DEACTIVATE_BYPASS);
goto new_slab;
@@ -2246,50 +2224,50 @@ redo:
stat(s, ALLOC_REFILL);
load_freelist:
- c->freelist = get_freepointer(s, object);
+ /*
+ * freelist is pointing to the list of objects to be used.
+ * page is pointing to the page from which the objects are obtained.
+ * That page must be frozen for per cpu allocations to work.
+ */
+ VM_BUG_ON(!c->page->frozen);
+ c->freelist = get_freepointer(s, freelist);
c->tid = next_tid(c->tid);
local_irq_restore(flags);
- return object;
+ return freelist;
new_slab:
if (c->partial) {
- c->page = c->partial;
- c->partial = c->page->next;
- c->node = page_to_nid(c->page);
+ page = c->page = c->partial;
+ c->partial = page->next;
stat(s, CPU_PARTIAL_ALLOC);
c->freelist = NULL;
goto redo;
}
- /* Then do expensive stuff like retrieving pages from the partial lists */
- object = get_partial(s, gfpflags, node, c);
+ freelist = new_slab_objects(s, gfpflags, node, &c);
- if (unlikely(!object)) {
+ if (unlikely(!freelist)) {
+ if (!(gfpflags & __GFP_NOWARN) && printk_ratelimit())
+ slab_out_of_memory(s, gfpflags, node);
- object = new_slab_objects(s, gfpflags, node, &c);
-
- if (unlikely(!object)) {
- if (!(gfpflags & __GFP_NOWARN) && printk_ratelimit())
- slab_out_of_memory(s, gfpflags, node);
-
- local_irq_restore(flags);
- return NULL;
- }
+ local_irq_restore(flags);
+ return NULL;
}
+ page = c->page;
if (likely(!kmem_cache_debug(s)))
goto load_freelist;
/* Only entered in the debug case */
- if (!alloc_debug_processing(s, c->page, object, addr))
+ if (!alloc_debug_processing(s, page, freelist, addr))
goto new_slab; /* Slab failed checks. Next slab needed */
- c->freelist = get_freepointer(s, object);
- deactivate_slab(s, c);
- c->node = NUMA_NO_NODE;
+ deactivate_slab(s, page, get_freepointer(s, freelist));
+ c->page = NULL;
+ c->freelist = NULL;
local_irq_restore(flags);
- return object;
+ return freelist;
}
/*
@@ -2307,6 +2285,7 @@ static __always_inline void *slab_alloc(struct kmem_cache *s,
{
void **object;
struct kmem_cache_cpu *c;
+ struct page *page;
unsigned long tid;
if (slab_pre_alloc_hook(s, gfpflags))
@@ -2332,7 +2311,8 @@ redo:
barrier();
object = c->freelist;
- if (unlikely(!object || !node_match(c, node)))
+ page = c->page;
+ if (unlikely(!object || !node_match(page, node)))
object = __slab_alloc(s, gfpflags, node, addr, c);
@@ -2364,7 +2344,7 @@ redo:
}
if (unlikely(gfpflags & __GFP_ZERO) && object)
- memset(object, 0, s->objsize);
+ memset(object, 0, s->object_size);
slab_post_alloc_hook(s, gfpflags, object);
@@ -2375,7 +2355,7 @@ void *kmem_cache_alloc(struct kmem_cache *s, gfp_t gfpflags)
{
void *ret = slab_alloc(s, gfpflags, NUMA_NO_NODE, _RET_IP_);
- trace_kmem_cache_alloc(_RET_IP_, ret, s->objsize, s->size, gfpflags);
+ trace_kmem_cache_alloc(_RET_IP_, ret, s->object_size, s->size, gfpflags);
return ret;
}
@@ -2405,7 +2385,7 @@ void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t gfpflags, int node)
void *ret = slab_alloc(s, gfpflags, node, _RET_IP_);
trace_kmem_cache_alloc_node(_RET_IP_, ret,
- s->objsize, s->size, gfpflags, node);
+ s->object_size, s->size, gfpflags, node);
return ret;
}
@@ -2900,7 +2880,7 @@ static void set_min_partial(struct kmem_cache *s, unsigned long min)
static int calculate_sizes(struct kmem_cache *s, int forced_order)
{
unsigned long flags = s->flags;
- unsigned long size = s->objsize;
+ unsigned long size = s->object_size;
unsigned long align = s->align;
int order;
@@ -2929,7 +2909,7 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order)
* end of the object and the free pointer. If not then add an
* additional word to have some bytes to store Redzone information.
*/
- if ((flags & SLAB_RED_ZONE) && size == s->objsize)
+ if ((flags & SLAB_RED_ZONE) && size == s->object_size)
size += sizeof(void *);
#endif
@@ -2977,7 +2957,7 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order)
* user specified and the dynamic determination of cache line size
* on bootup.
*/
- align = calculate_alignment(flags, align, s->objsize);
+ align = calculate_alignment(flags, align, s->object_size);
s->align = align;
/*
@@ -3025,7 +3005,7 @@ static int kmem_cache_open(struct kmem_cache *s,
memset(s, 0, kmem_size);
s->name = name;
s->ctor = ctor;
- s->objsize = size;
+ s->object_size = size;
s->align = align;
s->flags = kmem_cache_flags(size, flags, name, ctor);
s->reserved = 0;
@@ -3040,7 +3020,7 @@ static int kmem_cache_open(struct kmem_cache *s,
* Disable debugging flags that store metadata if the min slab
* order increased.
*/
- if (get_order(s->size) > get_order(s->objsize)) {
+ if (get_order(s->size) > get_order(s->object_size)) {
s->flags &= ~DEBUG_METADATA_FLAGS;
s->offset = 0;
if (!calculate_sizes(s, -1))
@@ -3114,7 +3094,7 @@ error:
*/
unsigned int kmem_cache_size(struct kmem_cache *s)
{
- return s->objsize;
+ return s->object_size;
}
EXPORT_SYMBOL(kmem_cache_size);
@@ -3192,11 +3172,11 @@ static inline int kmem_cache_close(struct kmem_cache *s)
*/
void kmem_cache_destroy(struct kmem_cache *s)
{
- down_write(&slub_lock);
+ mutex_lock(&slab_mutex);
s->refcount--;
if (!s->refcount) {
list_del(&s->list);
- up_write(&slub_lock);
+ mutex_unlock(&slab_mutex);
if (kmem_cache_close(s)) {
printk(KERN_ERR "SLUB %s: %s called for cache that "
"still has objects.\n", s->name, __func__);
@@ -3206,7 +3186,7 @@ void kmem_cache_destroy(struct kmem_cache *s)
rcu_barrier();
sysfs_slab_remove(s);
} else
- up_write(&slub_lock);
+ mutex_unlock(&slab_mutex);
}
EXPORT_SYMBOL(kmem_cache_destroy);
@@ -3268,7 +3248,7 @@ static struct kmem_cache *__init create_kmalloc_cache(const char *name,
/*
* This function is called with IRQs disabled during early-boot on
- * single CPU so there's no need to take slub_lock here.
+ * single CPU so there's no need to take slab_mutex here.
*/
if (!kmem_cache_open(s, name, size, ARCH_KMALLOC_MINALIGN,
flags, NULL))
@@ -3553,10 +3533,10 @@ static int slab_mem_going_offline_callback(void *arg)
{
struct kmem_cache *s;
- down_read(&slub_lock);
+ mutex_lock(&slab_mutex);
list_for_each_entry(s, &slab_caches, list)
kmem_cache_shrink(s);
- up_read(&slub_lock);
+ mutex_unlock(&slab_mutex);
return 0;
}
@@ -3577,7 +3557,7 @@ static void slab_mem_offline_callback(void *arg)
if (offline_node < 0)
return;
- down_read(&slub_lock);
+ mutex_lock(&slab_mutex);
list_for_each_entry(s, &slab_caches, list) {
n = get_node(s, offline_node);
if (n) {
@@ -3593,7 +3573,7 @@ static void slab_mem_offline_callback(void *arg)
kmem_cache_free(kmem_cache_node, n);
}
}
- up_read(&slub_lock);
+ mutex_unlock(&slab_mutex);
}
static int slab_mem_going_online_callback(void *arg)
@@ -3616,7 +3596,7 @@ static int slab_mem_going_online_callback(void *arg)
* allocate a kmem_cache_node structure in order to bring the node
* online.
*/
- down_read(&slub_lock);
+ mutex_lock(&slab_mutex);
list_for_each_entry(s, &slab_caches, list) {
/*
* XXX: kmem_cache_alloc_node will fallback to other nodes
@@ -3632,7 +3612,7 @@ static int slab_mem_going_online_callback(void *arg)
s->node[nid] = n;
}
out:
- up_read(&slub_lock);
+ mutex_unlock(&slab_mutex);
return ret;
}
@@ -3843,11 +3823,11 @@ void __init kmem_cache_init(void)
if (s && s->size) {
char *name = kasprintf(GFP_NOWAIT,
- "dma-kmalloc-%d", s->objsize);
+ "dma-kmalloc-%d", s->object_size);
BUG_ON(!name);
kmalloc_dma_caches[i] = create_kmalloc_cache(name,
- s->objsize, SLAB_CACHE_DMA);
+ s->object_size, SLAB_CACHE_DMA);
}
}
#endif
@@ -3924,16 +3904,12 @@ static struct kmem_cache *find_mergeable(size_t size,
return NULL;
}
-struct kmem_cache *kmem_cache_create(const char *name, size_t size,
+struct kmem_cache *__kmem_cache_create(const char *name, size_t size,
size_t align, unsigned long flags, void (*ctor)(void *))
{
struct kmem_cache *s;
char *n;
- if (WARN_ON(!name))
- return NULL;
-
- down_write(&slub_lock);
s = find_mergeable(size, align, flags, name, ctor);
if (s) {
s->refcount++;
@@ -3941,49 +3917,42 @@ struct kmem_cache *kmem_cache_create(const char *name, size_t size,
* Adjust the object sizes so that we clear
* the complete object on kzalloc.
*/
- s->objsize = max(s->objsize, (int)size);
+ s->object_size = max(s->object_size, (int)size);
s->inuse = max_t(int, s->inuse, ALIGN(size, sizeof(void *)));
if (sysfs_slab_alias(s, name)) {
s->refcount--;
- goto err;
+ return NULL;
}
- up_write(&slub_lock);
return s;
}
n = kstrdup(name, GFP_KERNEL);
if (!n)
- goto err;
+ return NULL;
s = kmalloc(kmem_size, GFP_KERNEL);
if (s) {
if (kmem_cache_open(s, n,
size, align, flags, ctor)) {
+ int r;
+
list_add(&s->list, &slab_caches);
- up_write(&slub_lock);
- if (sysfs_slab_add(s)) {
- down_write(&slub_lock);
- list_del(&s->list);
- kfree(n);
- kfree(s);
- goto err;
- }
- return s;
+ mutex_unlock(&slab_mutex);
+ r = sysfs_slab_add(s);
+ mutex_lock(&slab_mutex);
+
+ if (!r)
+ return s;
+
+ list_del(&s->list);
+ kmem_cache_close(s);
}
kfree(s);
}
kfree(n);
-err:
- up_write(&slub_lock);
-
- if (flags & SLAB_PANIC)
- panic("Cannot create slabcache %s\n", name);
- else
- s = NULL;
- return s;
+ return NULL;
}
-EXPORT_SYMBOL(kmem_cache_create);
#ifdef CONFIG_SMP
/*
@@ -4002,13 +3971,13 @@ static int __cpuinit slab_cpuup_callback(struct notifier_block *nfb,
case CPU_UP_CANCELED_FROZEN:
case CPU_DEAD:
case CPU_DEAD_FROZEN:
- down_read(&slub_lock);
+ mutex_lock(&slab_mutex);
list_for_each_entry(s, &slab_caches, list) {
local_irq_save(flags);
__flush_cpu_slab(s, cpu);
local_irq_restore(flags);
}
- up_read(&slub_lock);
+ mutex_unlock(&slab_mutex);
break;
default:
break;
@@ -4500,30 +4469,31 @@ static ssize_t show_slab_objects(struct kmem_cache *s,
for_each_possible_cpu(cpu) {
struct kmem_cache_cpu *c = per_cpu_ptr(s->cpu_slab, cpu);
- int node = ACCESS_ONCE(c->node);
+ int node;
struct page *page;
- if (node < 0)
- continue;
page = ACCESS_ONCE(c->page);
- if (page) {
- if (flags & SO_TOTAL)
- x = page->objects;
- else if (flags & SO_OBJECTS)
- x = page->inuse;
- else
- x = 1;
+ if (!page)
+ continue;
- total += x;
- nodes[node] += x;
- }
- page = c->partial;
+ node = page_to_nid(page);
+ if (flags & SO_TOTAL)
+ x = page->objects;
+ else if (flags & SO_OBJECTS)
+ x = page->inuse;
+ else
+ x = 1;
+ total += x;
+ nodes[node] += x;
+
+ page = ACCESS_ONCE(c->partial);
if (page) {
x = page->pobjects;
total += x;
nodes[node] += x;
}
+
per_cpu[node]++;
}
}
@@ -4623,7 +4593,7 @@ SLAB_ATTR_RO(align);
static ssize_t object_size_show(struct kmem_cache *s, char *buf)
{
- return sprintf(buf, "%d\n", s->objsize);
+ return sprintf(buf, "%d\n", s->object_size);
}
SLAB_ATTR_RO(object_size);
@@ -5286,7 +5256,7 @@ static int sysfs_slab_add(struct kmem_cache *s)
const char *name;
int unmergeable;
- if (slab_state < SYSFS)
+ if (slab_state < FULL)
/* Defer until later */
return 0;
@@ -5331,7 +5301,7 @@ static int sysfs_slab_add(struct kmem_cache *s)
static void sysfs_slab_remove(struct kmem_cache *s)
{
- if (slab_state < SYSFS)
+ if (slab_state < FULL)
/*
* Sysfs has not been setup yet so no need to remove the
* cache from sysfs.
@@ -5359,7 +5329,7 @@ static int sysfs_slab_alias(struct kmem_cache *s, const char *name)
{
struct saved_alias *al;
- if (slab_state == SYSFS) {
+ if (slab_state == FULL) {
/*
* If we have a leftover link then remove it.
*/
@@ -5383,16 +5353,16 @@ static int __init slab_sysfs_init(void)
struct kmem_cache *s;
int err;
- down_write(&slub_lock);
+ mutex_lock(&slab_mutex);
slab_kset = kset_create_and_add("slab", &slab_uevent_ops, kernel_kobj);
if (!slab_kset) {
- up_write(&slub_lock);
+ mutex_unlock(&slab_mutex);
printk(KERN_ERR "Cannot register slab subsystem.\n");
return -ENOSYS;
}
- slab_state = SYSFS;
+ slab_state = FULL;
list_for_each_entry(s, &slab_caches, list) {
err = sysfs_slab_add(s);
@@ -5408,11 +5378,11 @@ static int __init slab_sysfs_init(void)
err = sysfs_slab_alias(al->s, al->name);
if (err)
printk(KERN_ERR "SLUB: Unable to add boot slab alias"
- " %s to sysfs\n", s->name);
+ " %s to sysfs\n", al->name);
kfree(al);
}
- up_write(&slub_lock);
+ mutex_unlock(&slab_mutex);
resiliency_test();
return 0;
}
@@ -5427,7 +5397,7 @@ __initcall(slab_sysfs_init);
static void print_slabinfo_header(struct seq_file *m)
{
seq_puts(m, "slabinfo - version: 2.1\n");
- seq_puts(m, "# name <active_objs> <num_objs> <objsize> "
+ seq_puts(m, "# name <active_objs> <num_objs> <object_size> "
"<objperslab> <pagesperslab>");
seq_puts(m, " : tunables <limit> <batchcount> <sharedfactor>");
seq_puts(m, " : slabdata <active_slabs> <num_slabs> <sharedavail>");
@@ -5438,7 +5408,7 @@ static void *s_start(struct seq_file *m, loff_t *pos)
{
loff_t n = *pos;
- down_read(&slub_lock);
+ mutex_lock(&slab_mutex);
if (!n)
print_slabinfo_header(m);
@@ -5452,7 +5422,7 @@ static void *s_next(struct seq_file *m, void *p, loff_t *pos)
static void s_stop(struct seq_file *m, void *p)
{
- up_read(&slub_lock);
+ mutex_unlock(&slab_mutex);
}
static int s_show(struct seq_file *m, void *p)
diff --git a/mm/sparse.c b/mm/sparse.c
index 6a4bf9160e85..c7bb952400c8 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -275,8 +275,9 @@ static unsigned long * __init
sparse_early_usemaps_alloc_pgdat_section(struct pglist_data *pgdat,
unsigned long size)
{
- pg_data_t *host_pgdat;
- unsigned long goal;
+ unsigned long goal, limit;
+ unsigned long *p;
+ int nid;
/*
* A page may contain usemaps for other sections preventing the
* page being freed and making a section unremovable while
@@ -287,10 +288,17 @@ sparse_early_usemaps_alloc_pgdat_section(struct pglist_data *pgdat,
* from the same section as the pgdat where possible to avoid
* this problem.
*/
- goal = __pa(pgdat) & PAGE_SECTION_MASK;
- host_pgdat = NODE_DATA(early_pfn_to_nid(goal >> PAGE_SHIFT));
- return __alloc_bootmem_node_nopanic(host_pgdat, size,
- SMP_CACHE_BYTES, goal);
+ goal = __pa(pgdat) & (PAGE_SECTION_MASK << PAGE_SHIFT);
+ limit = goal + (1UL << PA_SECTION_SHIFT);
+ nid = early_pfn_to_nid(goal >> PAGE_SHIFT);
+again:
+ p = ___alloc_bootmem_node_nopanic(NODE_DATA(nid), size,
+ SMP_CACHE_BYTES, goal, limit);
+ if (!p && limit) {
+ limit = 0;
+ goto again;
+ }
+ return p;
}
static void __init check_usemap_section_nr(int nid, unsigned long *usemap)
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 457b10baef59..71373d03fcee 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -31,6 +31,8 @@
#include <linux/memcontrol.h>
#include <linux/poll.h>
#include <linux/oom.h>
+#include <linux/frontswap.h>
+#include <linux/swapfile.h>
#include <asm/pgtable.h>
#include <asm/tlbflush.h>
@@ -42,7 +44,7 @@ static bool swap_count_continued(struct swap_info_struct *, pgoff_t,
static void free_swap_count_continuations(struct swap_info_struct *);
static sector_t map_swap_entry(swp_entry_t, struct block_device**);
-static DEFINE_SPINLOCK(swap_lock);
+DEFINE_SPINLOCK(swap_lock);
static unsigned int nr_swapfiles;
long nr_swap_pages;
long total_swap_pages;
@@ -53,9 +55,9 @@ static const char Unused_file[] = "Unused swap file entry ";
static const char Bad_offset[] = "Bad swap offset entry ";
static const char Unused_offset[] = "Unused swap offset entry ";
-static struct swap_list_t swap_list = {-1, -1};
+struct swap_list_t swap_list = {-1, -1};
-static struct swap_info_struct *swap_info[MAX_SWAPFILES];
+struct swap_info_struct *swap_info[MAX_SWAPFILES];
static DEFINE_MUTEX(swapon_mutex);
@@ -556,6 +558,7 @@ static unsigned char swap_entry_free(struct swap_info_struct *p,
swap_list.next = p->type;
nr_swap_pages++;
p->inuse_pages--;
+ frontswap_invalidate_page(p->type, offset);
if ((p->flags & SWP_BLKDEV) &&
disk->fops->swap_slot_free_notify)
disk->fops->swap_slot_free_notify(p->bdev, offset);
@@ -985,11 +988,12 @@ static int unuse_mm(struct mm_struct *mm,
}
/*
- * Scan swap_map from current position to next entry still in use.
+ * Scan swap_map (or frontswap_map if frontswap parameter is true)
+ * from current position to next entry still in use.
* Recycle to start on reaching the end, returning 0 when empty.
*/
static unsigned int find_next_to_unuse(struct swap_info_struct *si,
- unsigned int prev)
+ unsigned int prev, bool frontswap)
{
unsigned int max = si->max;
unsigned int i = prev;
@@ -1015,6 +1019,12 @@ static unsigned int find_next_to_unuse(struct swap_info_struct *si,
prev = 0;
i = 1;
}
+ if (frontswap) {
+ if (frontswap_test(si, i))
+ break;
+ else
+ continue;
+ }
count = si->swap_map[i];
if (count && swap_count(count) != SWAP_MAP_BAD)
break;
@@ -1026,8 +1036,12 @@ static unsigned int find_next_to_unuse(struct swap_info_struct *si,
* We completely avoid races by reading each swap page in advance,
* and then search for the process using it. All the necessary
* page table adjustments can then be made atomically.
+ *
+ * if the boolean frontswap is true, only unuse pages_to_unuse pages;
+ * pages_to_unuse==0 means all pages; ignored if frontswap is false
*/
-static int try_to_unuse(unsigned int type)
+int try_to_unuse(unsigned int type, bool frontswap,
+ unsigned long pages_to_unuse)
{
struct swap_info_struct *si = swap_info[type];
struct mm_struct *start_mm;
@@ -1060,7 +1074,7 @@ static int try_to_unuse(unsigned int type)
* one pass through swap_map is enough, but not necessarily:
* there are races when an instance of an entry might be missed.
*/
- while ((i = find_next_to_unuse(si, i)) != 0) {
+ while ((i = find_next_to_unuse(si, i, frontswap)) != 0) {
if (signal_pending(current)) {
retval = -EINTR;
break;
@@ -1227,6 +1241,10 @@ static int try_to_unuse(unsigned int type)
* interactive performance.
*/
cond_resched();
+ if (frontswap && pages_to_unuse > 0) {
+ if (!--pages_to_unuse)
+ break;
+ }
}
mmput(start_mm);
@@ -1486,7 +1504,8 @@ bad_bmap:
}
static void enable_swap_info(struct swap_info_struct *p, int prio,
- unsigned char *swap_map)
+ unsigned char *swap_map,
+ unsigned long *frontswap_map)
{
int i, prev;
@@ -1496,6 +1515,7 @@ static void enable_swap_info(struct swap_info_struct *p, int prio,
else
p->prio = --least_priority;
p->swap_map = swap_map;
+ frontswap_map_set(p, frontswap_map);
p->flags |= SWP_WRITEOK;
nr_swap_pages += p->pages;
total_swap_pages += p->pages;
@@ -1512,6 +1532,7 @@ static void enable_swap_info(struct swap_info_struct *p, int prio,
swap_list.head = swap_list.next = p->type;
else
swap_info[prev]->next = p->type;
+ frontswap_init(p->type);
spin_unlock(&swap_lock);
}
@@ -1585,7 +1606,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
spin_unlock(&swap_lock);
oom_score_adj = test_set_oom_score_adj(OOM_SCORE_ADJ_MAX);
- err = try_to_unuse(type);
+ err = try_to_unuse(type, false, 0); /* force all pages to be unused */
compare_swap_oom_score_adj(OOM_SCORE_ADJ_MAX, oom_score_adj);
if (err) {
@@ -1596,7 +1617,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
* sys_swapoff for this swap_info_struct at this point.
*/
/* re-insert swap space back into swap_list */
- enable_swap_info(p, p->prio, p->swap_map);
+ enable_swap_info(p, p->prio, p->swap_map, frontswap_map_get(p));
goto out_dput;
}
@@ -1622,9 +1643,11 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
swap_map = p->swap_map;
p->swap_map = NULL;
p->flags = 0;
+ frontswap_invalidate_area(type);
spin_unlock(&swap_lock);
mutex_unlock(&swapon_mutex);
vfree(swap_map);
+ vfree(frontswap_map_get(p));
/* Destroy swap account informatin */
swap_cgroup_swapoff(type);
@@ -1893,24 +1916,20 @@ static unsigned long read_swap_header(struct swap_info_struct *p,
/*
* Find out how many pages are allowed for a single swap
- * device. There are three limiting factors: 1) the number
+ * device. There are two limiting factors: 1) the number
* of bits for the swap offset in the swp_entry_t type, and
* 2) the number of bits in the swap pte as defined by the
- * the different architectures, and 3) the number of free bits
- * in an exceptional radix_tree entry. In order to find the
+ * different architectures. In order to find the
* largest possible bit mask, a swap entry with swap type 0
* and swap offset ~0UL is created, encoded to a swap pte,
* decoded to a swp_entry_t again, and finally the swap
* offset is extracted. This will mask all the bits from
* the initial ~0UL mask that can't be encoded in either
* the swp_entry_t or the architecture definition of a
- * swap pte. Then the same is done for a radix_tree entry.
+ * swap pte.
*/
maxpages = swp_offset(pte_to_swp_entry(
- swp_entry_to_pte(swp_entry(0, ~0UL))));
- maxpages = swp_offset(radix_to_swp_entry(
- swp_to_radix_entry(swp_entry(0, maxpages)))) + 1;
-
+ swp_entry_to_pte(swp_entry(0, ~0UL)))) + 1;
if (maxpages > swap_header->info.last_page) {
maxpages = swap_header->info.last_page + 1;
/* p->max is an unsigned int: don't overflow it */
@@ -1988,6 +2007,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
sector_t span;
unsigned long maxpages;
unsigned char *swap_map = NULL;
+ unsigned long *frontswap_map = NULL;
struct page *page = NULL;
struct inode *inode = NULL;
@@ -2071,6 +2091,9 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
error = nr_extents;
goto bad_swap;
}
+ /* frontswap enabled? set up bit-per-page map for frontswap */
+ if (frontswap_enabled)
+ frontswap_map = vzalloc(maxpages / sizeof(long));
if (p->bdev) {
if (blk_queue_nonrot(bdev_get_queue(p->bdev))) {
@@ -2086,14 +2109,15 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
if (swap_flags & SWAP_FLAG_PREFER)
prio =
(swap_flags & SWAP_FLAG_PRIO_MASK) >> SWAP_FLAG_PRIO_SHIFT;
- enable_swap_info(p, prio, swap_map);
+ enable_swap_info(p, prio, swap_map, frontswap_map);
printk(KERN_INFO "Adding %uk swap on %s. "
- "Priority:%d extents:%d across:%lluk %s%s\n",
+ "Priority:%d extents:%d across:%lluk %s%s%s\n",
p->pages<<(PAGE_SHIFT-10), name, p->prio,
nr_extents, (unsigned long long)span<<(PAGE_SHIFT-10),
(p->flags & SWP_SOLIDSTATE) ? "SS" : "",
- (p->flags & SWP_DISCARDABLE) ? "D" : "");
+ (p->flags & SWP_DISCARDABLE) ? "D" : "",
+ (frontswap_map) ? "FS" : "");
mutex_unlock(&swapon_mutex);
atomic_inc(&proc_poll_event);
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 2aad49981b57..e03f4c7307a5 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -1280,7 +1280,7 @@ DEFINE_RWLOCK(vmlist_lock);
struct vm_struct *vmlist;
static void setup_vmalloc_vm(struct vm_struct *vm, struct vmap_area *va,
- unsigned long flags, void *caller)
+ unsigned long flags, const void *caller)
{
vm->flags = flags;
vm->addr = (void *)va->va_start;
@@ -1306,7 +1306,7 @@ static void insert_vmalloc_vmlist(struct vm_struct *vm)
}
static void insert_vmalloc_vm(struct vm_struct *vm, struct vmap_area *va,
- unsigned long flags, void *caller)
+ unsigned long flags, const void *caller)
{
setup_vmalloc_vm(vm, va, flags, caller);
insert_vmalloc_vmlist(vm);
@@ -1314,7 +1314,7 @@ static void insert_vmalloc_vm(struct vm_struct *vm, struct vmap_area *va,
static struct vm_struct *__get_vm_area_node(unsigned long size,
unsigned long align, unsigned long flags, unsigned long start,
- unsigned long end, int node, gfp_t gfp_mask, void *caller)
+ unsigned long end, int node, gfp_t gfp_mask, const void *caller)
{
struct vmap_area *va;
struct vm_struct *area;
@@ -1375,7 +1375,7 @@ EXPORT_SYMBOL_GPL(__get_vm_area);
struct vm_struct *__get_vm_area_caller(unsigned long size, unsigned long flags,
unsigned long start, unsigned long end,
- void *caller)
+ const void *caller)
{
return __get_vm_area_node(size, 1, flags, start, end, -1, GFP_KERNEL,
caller);
@@ -1397,13 +1397,21 @@ struct vm_struct *get_vm_area(unsigned long size, unsigned long flags)
}
struct vm_struct *get_vm_area_caller(unsigned long size, unsigned long flags,
- void *caller)
+ const void *caller)
{
return __get_vm_area_node(size, 1, flags, VMALLOC_START, VMALLOC_END,
-1, GFP_KERNEL, caller);
}
-static struct vm_struct *find_vm_area(const void *addr)
+/**
+ * find_vm_area - find a continuous kernel virtual area
+ * @addr: base address
+ *
+ * Search for the kernel VM area starting at @addr, and return it.
+ * It is up to the caller to do all required locking to keep the returned
+ * pointer valid.
+ */
+struct vm_struct *find_vm_area(const void *addr)
{
struct vmap_area *va;
@@ -1568,9 +1576,9 @@ EXPORT_SYMBOL(vmap);
static void *__vmalloc_node(unsigned long size, unsigned long align,
gfp_t gfp_mask, pgprot_t prot,
- int node, void *caller);
+ int node, const void *caller);
static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
- pgprot_t prot, int node, void *caller)
+ pgprot_t prot, int node, const void *caller)
{
const int order = 0;
struct page **pages;
@@ -1643,7 +1651,7 @@ fail:
*/
void *__vmalloc_node_range(unsigned long size, unsigned long align,
unsigned long start, unsigned long end, gfp_t gfp_mask,
- pgprot_t prot, int node, void *caller)
+ pgprot_t prot, int node, const void *caller)
{
struct vm_struct *area;
void *addr;
@@ -1699,7 +1707,7 @@ fail:
*/
static void *__vmalloc_node(unsigned long size, unsigned long align,
gfp_t gfp_mask, pgprot_t prot,
- int node, void *caller)
+ int node, const void *caller)
{
return __vmalloc_node_range(size, align, VMALLOC_START, VMALLOC_END,
gfp_mask, prot, node, caller);
@@ -1975,9 +1983,7 @@ static int aligned_vwrite(char *buf, char *addr, unsigned long count)
* IOREMAP area is treated as memory hole and no copy is done.
*
* If [addr...addr+count) doesn't includes any intersects with alive
- * vm_struct area, returns 0.
- * @buf should be kernel's buffer. Because this function uses KM_USER0,
- * the caller should guarantee KM_USER0 is not used.
+ * vm_struct area, returns 0. @buf should be kernel's buffer.
*
* Note: In usual ops, vread() is never necessary because the caller
* should know vmalloc() area is valid and can use memcpy().
@@ -2051,9 +2057,7 @@ finished:
* IOREMAP area is treated as memory hole and no copy is done.
*
* If [addr...addr+count) doesn't includes any intersects with alive
- * vm_struct area, returns 0.
- * @buf should be kernel's buffer. Because this function uses KM_USER0,
- * the caller should guarantee KM_USER0 is not used.
+ * vm_struct area, returns 0. @buf should be kernel's buffer.
*
* Note: In usual ops, vwrite() is never necessary because the caller
* should know vmalloc() area is valid and can use memcpy().
diff --git a/mm/vmscan.c b/mm/vmscan.c
index eeb3bc9d1d36..347b3ff2a478 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1567,7 +1567,8 @@ static int vmscan_swappiness(struct scan_control *sc)
* by looking at the fraction of the pages scanned we did rotate back
* onto the active list instead of evict.
*
- * nr[0] = anon pages to scan; nr[1] = file pages to scan
+ * nr[0] = anon inactive pages to scan; nr[1] = anon active pages to scan
+ * nr[2] = file inactive pages to scan; nr[3] = file active pages to scan
*/
static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc,
unsigned long *nr)
@@ -2537,7 +2538,7 @@ loop_again:
* consider it to be no longer congested. It's
* possible there are dirty pages backed by
* congested BDIs but as pressure is relieved,
- * spectulatively avoid congestion waits
+ * speculatively avoid congestion waits
*/
zone_clear_flag(zone, ZONE_CONGESTED);
if (i <= *classzone_idx)
@@ -2688,7 +2689,10 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order, int classzone_idx)
* them before going back to sleep.
*/
set_pgdat_percpu_threshold(pgdat, calculate_normal_threshold);
- schedule();
+
+ if (!kthread_should_stop())
+ schedule();
+
set_pgdat_percpu_threshold(pgdat, calculate_pressure_threshold);
} else {
if (remaining)
@@ -2955,14 +2959,17 @@ int kswapd_run(int nid)
}
/*
- * Called by memory hotplug when all memory in a node is offlined.
+ * Called by memory hotplug when all memory in a node is offlined. Caller must
+ * hold lock_memory_hotplug().
*/
void kswapd_stop(int nid)
{
struct task_struct *kswapd = NODE_DATA(nid)->kswapd;
- if (kswapd)
+ if (kswapd) {
kthread_stop(kswapd);
+ NODE_DATA(nid)->kswapd = NULL;
+ }
}
static int __init kswapd_init(void)
generated by cgit v1.2.3 (git 2.0.4) at 2024-10-14 13:16:14 +0000