summaryrefslogtreecommitdiff
path: root/mm
diff options
context:
space:
mode:
Diffstat (limited to 'mm')
-rw-r--r--mm/backing-dev.c259
-rw-r--r--mm/bounce.c75
-rw-r--r--mm/memcontrol.c36
-rw-r--r--mm/mmap.c11
-rw-r--r--mm/mmu_context.c3
-rw-r--r--mm/page_io.c2
-rw-r--r--mm/shmem.c1
-rw-r--r--mm/slab.c790
-rw-r--r--mm/slab.h43
-rw-r--r--mm/slab_common.c174
-rw-r--r--mm/slub.c221
-rw-r--r--mm/swap.c1
-rw-r--r--mm/vmalloc.c2
13 files changed, 679 insertions, 939 deletions
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 41733c5dc820..502517492258 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -31,13 +31,14 @@ EXPORT_SYMBOL_GPL(noop_backing_dev_info);
static struct class *bdi_class;
/*
- * bdi_lock protects updates to bdi_list and bdi_pending_list, as well as
- * reader side protection for bdi_pending_list. bdi_list has RCU reader side
+ * bdi_lock protects updates to bdi_list. bdi_list has RCU reader side
* locking.
*/
DEFINE_SPINLOCK(bdi_lock);
LIST_HEAD(bdi_list);
-LIST_HEAD(bdi_pending_list);
+
+/* bdi_wq serves all asynchronous writeback tasks */
+struct workqueue_struct *bdi_wq;
void bdi_lock_two(struct bdi_writeback *wb1, struct bdi_writeback *wb2)
{
@@ -257,6 +258,11 @@ static int __init default_bdi_init(void)
{
int err;
+ bdi_wq = alloc_workqueue("writeback", WQ_MEM_RECLAIM | WQ_FREEZABLE |
+ WQ_UNBOUND | WQ_SYSFS, 0);
+ if (!bdi_wq)
+ return -ENOMEM;
+
err = bdi_init(&default_backing_dev_info);
if (!err)
bdi_register(&default_backing_dev_info, NULL, "default");
@@ -271,26 +277,6 @@ int bdi_has_dirty_io(struct backing_dev_info *bdi)
return wb_has_dirty_io(&bdi->wb);
}
-static void wakeup_timer_fn(unsigned long data)
-{
- struct backing_dev_info *bdi = (struct backing_dev_info *)data;
-
- spin_lock_bh(&bdi->wb_lock);
- if (bdi->wb.task) {
- trace_writeback_wake_thread(bdi);
- wake_up_process(bdi->wb.task);
- } else if (bdi->dev) {
- /*
- * When bdi tasks are inactive for long time, they are killed.
- * In this case we have to wake-up the forker thread which
- * should create and run the bdi thread.
- */
- trace_writeback_wake_forker_thread(bdi);
- wake_up_process(default_backing_dev_info.wb.task);
- }
- spin_unlock_bh(&bdi->wb_lock);
-}
-
/*
* This function is used when the first inode for this bdi is marked dirty. It
* wakes-up the corresponding bdi thread which should then take care of the
@@ -307,176 +293,7 @@ void bdi_wakeup_thread_delayed(struct backing_dev_info *bdi)
unsigned long timeout;
timeout = msecs_to_jiffies(dirty_writeback_interval * 10);
- mod_timer(&bdi->wb.wakeup_timer, jiffies + timeout);
-}
-
-/*
- * Calculate the longest interval (jiffies) bdi threads are allowed to be
- * inactive.
- */
-static unsigned long bdi_longest_inactive(void)
-{
- unsigned long interval;
-
- interval = msecs_to_jiffies(dirty_writeback_interval * 10);
- return max(5UL * 60 * HZ, interval);
-}
-
-/*
- * Clear pending bit and wakeup anybody waiting for flusher thread creation or
- * shutdown
- */
-static void bdi_clear_pending(struct backing_dev_info *bdi)
-{
- clear_bit(BDI_pending, &bdi->state);
- smp_mb__after_clear_bit();
- wake_up_bit(&bdi->state, BDI_pending);
-}
-
-static int bdi_forker_thread(void *ptr)
-{
- struct bdi_writeback *me = ptr;
-
- current->flags |= PF_SWAPWRITE;
- set_freezable();
-
- /*
- * Our parent may run at a different priority, just set us to normal
- */
- set_user_nice(current, 0);
-
- for (;;) {
- struct task_struct *task = NULL;
- struct backing_dev_info *bdi;
- enum {
- NO_ACTION, /* Nothing to do */
- FORK_THREAD, /* Fork bdi thread */
- KILL_THREAD, /* Kill inactive bdi thread */
- } action = NO_ACTION;
-
- /*
- * Temporary measure, we want to make sure we don't see
- * dirty data on the default backing_dev_info
- */
- if (wb_has_dirty_io(me) || !list_empty(&me->bdi->work_list)) {
- del_timer(&me->wakeup_timer);
- wb_do_writeback(me, 0);
- }
-
- spin_lock_bh(&bdi_lock);
- /*
- * In the following loop we are going to check whether we have
- * some work to do without any synchronization with tasks
- * waking us up to do work for them. Set the task state here
- * so that we don't miss wakeups after verifying conditions.
- */
- set_current_state(TASK_INTERRUPTIBLE);
-
- list_for_each_entry(bdi, &bdi_list, bdi_list) {
- bool have_dirty_io;
-
- if (!bdi_cap_writeback_dirty(bdi) ||
- bdi_cap_flush_forker(bdi))
- continue;
-
- WARN(!test_bit(BDI_registered, &bdi->state),
- "bdi %p/%s is not registered!\n", bdi, bdi->name);
-
- have_dirty_io = !list_empty(&bdi->work_list) ||
- wb_has_dirty_io(&bdi->wb);
-
- /*
- * If the bdi has work to do, but the thread does not
- * exist - create it.
- */
- if (!bdi->wb.task && have_dirty_io) {
- /*
- * Set the pending bit - if someone will try to
- * unregister this bdi - it'll wait on this bit.
- */
- set_bit(BDI_pending, &bdi->state);
- action = FORK_THREAD;
- break;
- }
-
- spin_lock(&bdi->wb_lock);
-
- /*
- * If there is no work to do and the bdi thread was
- * inactive long enough - kill it. The wb_lock is taken
- * to make sure no-one adds more work to this bdi and
- * wakes the bdi thread up.
- */
- if (bdi->wb.task && !have_dirty_io &&
- time_after(jiffies, bdi->wb.last_active +
- bdi_longest_inactive())) {
- task = bdi->wb.task;
- bdi->wb.task = NULL;
- spin_unlock(&bdi->wb_lock);
- set_bit(BDI_pending, &bdi->state);
- action = KILL_THREAD;
- break;
- }
- spin_unlock(&bdi->wb_lock);
- }
- spin_unlock_bh(&bdi_lock);
-
- /* Keep working if default bdi still has things to do */
- if (!list_empty(&me->bdi->work_list))
- __set_current_state(TASK_RUNNING);
-
- switch (action) {
- case FORK_THREAD:
- __set_current_state(TASK_RUNNING);
- task = kthread_create(bdi_writeback_thread, &bdi->wb,
- "flush-%s", dev_name(bdi->dev));
- if (IS_ERR(task)) {
- /*
- * If thread creation fails, force writeout of
- * the bdi from the thread. Hopefully 1024 is
- * large enough for efficient IO.
- */
- writeback_inodes_wb(&bdi->wb, 1024,
- WB_REASON_FORKER_THREAD);
- } else {
- /*
- * The spinlock makes sure we do not lose
- * wake-ups when racing with 'bdi_queue_work()'.
- * And as soon as the bdi thread is visible, we
- * can start it.
- */
- spin_lock_bh(&bdi->wb_lock);
- bdi->wb.task = task;
- spin_unlock_bh(&bdi->wb_lock);
- wake_up_process(task);
- }
- bdi_clear_pending(bdi);
- break;
-
- case KILL_THREAD:
- __set_current_state(TASK_RUNNING);
- kthread_stop(task);
- bdi_clear_pending(bdi);
- break;
-
- case NO_ACTION:
- if (!wb_has_dirty_io(me) || !dirty_writeback_interval)
- /*
- * There are no dirty data. The only thing we
- * should now care about is checking for
- * inactive bdi threads and killing them. Thus,
- * let's sleep for longer time, save energy and
- * be friendly for battery-driven devices.
- */
- schedule_timeout(bdi_longest_inactive());
- else
- schedule_timeout(msecs_to_jiffies(dirty_writeback_interval * 10));
- try_to_freeze();
- break;
- }
- }
-
- return 0;
+ mod_delayed_work(bdi_wq, &bdi->wb.dwork, timeout);
}
/*
@@ -489,6 +306,9 @@ static void bdi_remove_from_list(struct backing_dev_info *bdi)
spin_unlock_bh(&bdi_lock);
synchronize_rcu_expedited();
+
+ /* bdi_list is now unused, clear it to mark @bdi dying */
+ INIT_LIST_HEAD(&bdi->bdi_list);
}
int bdi_register(struct backing_dev_info *bdi, struct device *parent,
@@ -508,20 +328,6 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent,
bdi->dev = dev;
- /*
- * Just start the forker thread for our default backing_dev_info,
- * and add other bdi's to the list. They will get a thread created
- * on-demand when they need it.
- */
- if (bdi_cap_flush_forker(bdi)) {
- struct bdi_writeback *wb = &bdi->wb;
-
- wb->task = kthread_run(bdi_forker_thread, wb, "bdi-%s",
- dev_name(dev));
- if (IS_ERR(wb->task))
- return PTR_ERR(wb->task);
- }
-
bdi_debug_register(bdi, dev_name(dev));
set_bit(BDI_registered, &bdi->state);
@@ -545,8 +351,6 @@ EXPORT_SYMBOL(bdi_register_dev);
*/
static void bdi_wb_shutdown(struct backing_dev_info *bdi)
{
- struct task_struct *task;
-
if (!bdi_cap_writeback_dirty(bdi))
return;
@@ -556,22 +360,20 @@ static void bdi_wb_shutdown(struct backing_dev_info *bdi)
bdi_remove_from_list(bdi);
/*
- * If setup is pending, wait for that to complete first
+ * Drain work list and shutdown the delayed_work. At this point,
+ * @bdi->bdi_list is empty telling bdi_Writeback_workfn() that @bdi
+ * is dying and its work_list needs to be drained no matter what.
*/
- wait_on_bit(&bdi->state, BDI_pending, bdi_sched_wait,
- TASK_UNINTERRUPTIBLE);
+ mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0);
+ flush_delayed_work(&bdi->wb.dwork);
+ WARN_ON(!list_empty(&bdi->work_list));
/*
- * Finally, kill the kernel thread. We don't need to be RCU
- * safe anymore, since the bdi is gone from visibility.
+ * This shouldn't be necessary unless @bdi for some reason has
+ * unflushed dirty IO after work_list is drained. Do it anyway
+ * just in case.
*/
- spin_lock_bh(&bdi->wb_lock);
- task = bdi->wb.task;
- bdi->wb.task = NULL;
- spin_unlock_bh(&bdi->wb_lock);
-
- if (task)
- kthread_stop(task);
+ cancel_delayed_work_sync(&bdi->wb.dwork);
}
/*
@@ -597,10 +399,8 @@ void bdi_unregister(struct backing_dev_info *bdi)
bdi_set_min_ratio(bdi, 0);
trace_writeback_bdi_unregister(bdi);
bdi_prune_sb(bdi);
- del_timer_sync(&bdi->wb.wakeup_timer);
- if (!bdi_cap_flush_forker(bdi))
- bdi_wb_shutdown(bdi);
+ bdi_wb_shutdown(bdi);
bdi_debug_unregister(bdi);
spin_lock_bh(&bdi->wb_lock);
@@ -622,7 +422,7 @@ static void bdi_wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi)
INIT_LIST_HEAD(&wb->b_io);
INIT_LIST_HEAD(&wb->b_more_io);
spin_lock_init(&wb->list_lock);
- setup_timer(&wb->wakeup_timer, wakeup_timer_fn, (unsigned long)bdi);
+ INIT_DELAYED_WORK(&wb->dwork, bdi_writeback_workfn);
}
/*
@@ -695,12 +495,11 @@ void bdi_destroy(struct backing_dev_info *bdi)
bdi_unregister(bdi);
/*
- * If bdi_unregister() had already been called earlier, the
- * wakeup_timer could still be armed because bdi_prune_sb()
- * can race with the bdi_wakeup_thread_delayed() calls from
- * __mark_inode_dirty().
+ * If bdi_unregister() had already been called earlier, the dwork
+ * could still be pending because bdi_prune_sb() can race with the
+ * bdi_wakeup_thread_delayed() calls from __mark_inode_dirty().
*/
- del_timer_sync(&bdi->wb.wakeup_timer);
+ cancel_delayed_work_sync(&bdi->wb.dwork);
for (i = 0; i < NR_BDI_STAT_ITEMS; i++)
percpu_counter_destroy(&bdi->bdi_stat[i]);
diff --git a/mm/bounce.c b/mm/bounce.c
index a5c2ec3589cb..c9f0a4339a7d 100644
--- a/mm/bounce.c
+++ b/mm/bounce.c
@@ -101,7 +101,7 @@ static void copy_to_high_bio_irq(struct bio *to, struct bio *from)
struct bio_vec *tovec, *fromvec;
int i;
- __bio_for_each_segment(tovec, to, i, 0) {
+ bio_for_each_segment(tovec, to, i) {
fromvec = from->bi_io_vec + i;
/*
@@ -134,7 +134,7 @@ static void bounce_end_io(struct bio *bio, mempool_t *pool, int err)
/*
* free up bounce indirect pages used
*/
- __bio_for_each_segment(bvec, bio, i, 0) {
+ bio_for_each_segment_all(bvec, bio, i) {
org_vec = bio_orig->bi_io_vec + i;
if (bvec->bv_page == org_vec->bv_page)
continue;
@@ -199,78 +199,43 @@ static int must_snapshot_stable_pages(struct request_queue *q, struct bio *bio)
static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig,
mempool_t *pool, int force)
{
- struct page *page;
- struct bio *bio = NULL;
- int i, rw = bio_data_dir(*bio_orig);
+ struct bio *bio;
+ int rw = bio_data_dir(*bio_orig);
struct bio_vec *to, *from;
+ unsigned i;
- bio_for_each_segment(from, *bio_orig, i) {
- page = from->bv_page;
+ bio_for_each_segment(from, *bio_orig, i)
+ if (page_to_pfn(from->bv_page) > queue_bounce_pfn(q))
+ goto bounce;
- /*
- * is destination page below bounce pfn?
- */
- if (page_to_pfn(page) <= queue_bounce_pfn(q) && !force)
- continue;
-
- /*
- * irk, bounce it
- */
- if (!bio) {
- unsigned int cnt = (*bio_orig)->bi_vcnt;
+ return;
+bounce:
+ bio = bio_clone_bioset(*bio_orig, GFP_NOIO, fs_bio_set);
- bio = bio_alloc(GFP_NOIO, cnt);
- memset(bio->bi_io_vec, 0, cnt * sizeof(struct bio_vec));
- }
-
+ bio_for_each_segment_all(to, bio, i) {
+ struct page *page = to->bv_page;
- to = bio->bi_io_vec + i;
+ if (page_to_pfn(page) <= queue_bounce_pfn(q) && !force)
+ continue;
- to->bv_page = mempool_alloc(pool, q->bounce_gfp);
- to->bv_len = from->bv_len;
- to->bv_offset = from->bv_offset;
inc_zone_page_state(to->bv_page, NR_BOUNCE);
+ to->bv_page = mempool_alloc(pool, q->bounce_gfp);
if (rw == WRITE) {
char *vto, *vfrom;
- flush_dcache_page(from->bv_page);
+ flush_dcache_page(page);
+
vto = page_address(to->bv_page) + to->bv_offset;
- vfrom = kmap(from->bv_page) + from->bv_offset;
+ vfrom = kmap_atomic(page) + to->bv_offset;
memcpy(vto, vfrom, to->bv_len);
- kunmap(from->bv_page);
+ kunmap_atomic(vfrom);
}
}
- /*
- * no pages bounced
- */
- if (!bio)
- return;
-
trace_block_bio_bounce(q, *bio_orig);
- /*
- * at least one page was bounced, fill in possible non-highmem
- * pages
- */
- __bio_for_each_segment(from, *bio_orig, i, 0) {
- to = bio_iovec_idx(bio, i);
- if (!to->bv_page) {
- to->bv_page = from->bv_page;
- to->bv_len = from->bv_len;
- to->bv_offset = from->bv_offset;
- }
- }
-
- bio->bi_bdev = (*bio_orig)->bi_bdev;
bio->bi_flags |= (1 << BIO_BOUNCED);
- bio->bi_sector = (*bio_orig)->bi_sector;
- bio->bi_rw = (*bio_orig)->bi_rw;
-
- bio->bi_vcnt = (*bio_orig)->bi_vcnt;
- bio->bi_idx = (*bio_orig)->bi_idx;
- bio->bi_size = (*bio_orig)->bi_size;
if (pool == page_pool) {
bio->bi_end_io = bounce_end_io_write;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 0f1d92163f30..cb1c9dedf9b6 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -92,16 +92,18 @@ enum mem_cgroup_stat_index {
/*
* For MEM_CONTAINER_TYPE_ALL, usage = pagecache + rss.
*/
- MEM_CGROUP_STAT_CACHE, /* # of pages charged as cache */
- MEM_CGROUP_STAT_RSS, /* # of pages charged as anon rss */
- MEM_CGROUP_STAT_FILE_MAPPED, /* # of pages charged as file rss */
- MEM_CGROUP_STAT_SWAP, /* # of pages, swapped out */
+ MEM_CGROUP_STAT_CACHE, /* # of pages charged as cache */
+ MEM_CGROUP_STAT_RSS, /* # of pages charged as anon rss */
+ MEM_CGROUP_STAT_RSS_HUGE, /* # of pages charged as anon huge */
+ MEM_CGROUP_STAT_FILE_MAPPED, /* # of pages charged as file rss */
+ MEM_CGROUP_STAT_SWAP, /* # of pages, swapped out */
MEM_CGROUP_STAT_NSTATS,
};
static const char * const mem_cgroup_stat_names[] = {
"cache",
"rss",
+ "rss_huge",
"mapped_file",
"swap",
};
@@ -917,6 +919,7 @@ static unsigned long mem_cgroup_read_events(struct mem_cgroup *memcg,
}
static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg,
+ struct page *page,
bool anon, int nr_pages)
{
preempt_disable();
@@ -932,6 +935,10 @@ static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg,
__this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_CACHE],
nr_pages);
+ if (PageTransHuge(page))
+ __this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_RSS_HUGE],
+ nr_pages);
+
/* pagein of a big page is an event. So, ignore page size */
if (nr_pages > 0)
__this_cpu_inc(memcg->stat->events[MEM_CGROUP_EVENTS_PGPGIN]);
@@ -2914,7 +2921,7 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg,
else
anon = false;
- mem_cgroup_charge_statistics(memcg, anon, nr_pages);
+ mem_cgroup_charge_statistics(memcg, page, anon, nr_pages);
unlock_page_cgroup(pc);
/*
@@ -3708,16 +3715,21 @@ void mem_cgroup_split_huge_fixup(struct page *head)
{
struct page_cgroup *head_pc = lookup_page_cgroup(head);
struct page_cgroup *pc;
+ struct mem_cgroup *memcg;
int i;
if (mem_cgroup_disabled())
return;
+
+ memcg = head_pc->mem_cgroup;
for (i = 1; i < HPAGE_PMD_NR; i++) {
pc = head_pc + i;
- pc->mem_cgroup = head_pc->mem_cgroup;
+ pc->mem_cgroup = memcg;
smp_wmb();/* see __commit_charge() */
pc->flags = head_pc->flags & ~PCGF_NOCOPY_AT_SPLIT;
}
+ __this_cpu_sub(memcg->stat->count[MEM_CGROUP_STAT_RSS_HUGE],
+ HPAGE_PMD_NR);
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
@@ -3773,11 +3785,11 @@ static int mem_cgroup_move_account(struct page *page,
__this_cpu_inc(to->stat->count[MEM_CGROUP_STAT_FILE_MAPPED]);
preempt_enable();
}
- mem_cgroup_charge_statistics(from, anon, -nr_pages);
+ mem_cgroup_charge_statistics(from, page, anon, -nr_pages);
/* caller should have done css_get */
pc->mem_cgroup = to;
- mem_cgroup_charge_statistics(to, anon, nr_pages);
+ mem_cgroup_charge_statistics(to, page, anon, nr_pages);
move_unlock_mem_cgroup(from, &flags);
ret = 0;
unlock:
@@ -4152,7 +4164,7 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype,
break;
}
- mem_cgroup_charge_statistics(memcg, anon, -nr_pages);
+ mem_cgroup_charge_statistics(memcg, page, anon, -nr_pages);
ClearPageCgroupUsed(pc);
/*
@@ -4502,7 +4514,7 @@ void mem_cgroup_replace_page_cache(struct page *oldpage,
lock_page_cgroup(pc);
if (PageCgroupUsed(pc)) {
memcg = pc->mem_cgroup;
- mem_cgroup_charge_statistics(memcg, false, -1);
+ mem_cgroup_charge_statistics(memcg, oldpage, false, -1);
ClearPageCgroupUsed(pc);
}
unlock_page_cgroup(pc);
@@ -5030,6 +5042,10 @@ static inline u64 mem_cgroup_usage(struct mem_cgroup *memcg, bool swap)
return res_counter_read_u64(&memcg->memsw, RES_USAGE);
}
+ /*
+ * Transparent hugepages are still accounted for in MEM_CGROUP_STAT_RSS
+ * as well as in MEM_CGROUP_STAT_RSS_HUGE.
+ */
val = mem_cgroup_recursive_stat(memcg, MEM_CGROUP_STAT_CACHE);
val += mem_cgroup_recursive_stat(memcg, MEM_CGROUP_STAT_RSS);
diff --git a/mm/mmap.c b/mm/mmap.c
index da3e9c04bf37..f681e1842fad 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1363,15 +1363,24 @@ SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len,
file = fget(fd);
if (!file)
goto out;
+ if (is_file_hugepages(file))
+ len = ALIGN(len, huge_page_size(hstate_file(file)));
} else if (flags & MAP_HUGETLB) {
struct user_struct *user = NULL;
+ struct hstate *hs = hstate_sizelog((flags >> MAP_HUGE_SHIFT) &
+ SHM_HUGE_MASK);
+
+ if (!hs)
+ return -EINVAL;
+
+ len = ALIGN(len, huge_page_size(hs));
/*
* VM_NORESERVE is used because the reservations will be
* taken when vm_ops->mmap() is called
* A dummy user value is used because we are not locking
* memory so no accounting is necessary
*/
- file = hugetlb_file_setup(HUGETLB_ANON_FILE, addr, len,
+ file = hugetlb_file_setup(HUGETLB_ANON_FILE, len,
VM_NORESERVE,
&user, HUGETLB_ANONHUGE_INODE,
(flags >> MAP_HUGE_SHIFT) & MAP_HUGE_MASK);
diff --git a/mm/mmu_context.c b/mm/mmu_context.c
index 3dcfaf4ed355..8a8cd0265e52 100644
--- a/mm/mmu_context.c
+++ b/mm/mmu_context.c
@@ -14,9 +14,6 @@
* use_mm
* Makes the calling kernel thread take on the specified
* mm context.
- * Called by the retry thread execute retries within the
- * iocb issuer's mm context, so that copy_from/to_user
- * operations work seamlessly for aio.
* (Note: this routine is intended to be called only
* from a kernel thread context)
*/
diff --git a/mm/page_io.c b/mm/page_io.c
index bb5d75274686..a8a3ef45fed7 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -20,6 +20,7 @@
#include <linux/buffer_head.h>
#include <linux/writeback.h>
#include <linux/frontswap.h>
+#include <linux/aio.h>
#include <asm/pgtable.h>
static struct bio *get_swap_bio(gfp_t gfp_flags,
@@ -35,7 +36,6 @@ static struct bio *get_swap_bio(gfp_t gfp_flags,
bio->bi_io_vec[0].bv_len = PAGE_SIZE;
bio->bi_io_vec[0].bv_offset = 0;
bio->bi_vcnt = 1;
- bio->bi_idx = 0;
bio->bi_size = PAGE_SIZE;
bio->bi_end_io = end_io;
}
diff --git a/mm/shmem.c b/mm/shmem.c
index 39b2a0b86fe8..5e6a8422658b 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -31,6 +31,7 @@
#include <linux/mm.h>
#include <linux/export.h>
#include <linux/swap.h>
+#include <linux/aio.h>
static struct vfsmount *shm_mnt;
diff --git a/mm/slab.c b/mm/slab.c
index 96079244c860..8ccd296c6d9c 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -286,68 +286,27 @@ struct arraycache_init {
};
/*
- * The slab lists for all objects.
- */
-struct kmem_list3 {
- struct list_head slabs_partial; /* partial list first, better asm code */
- struct list_head slabs_full;
- struct list_head slabs_free;
- unsigned long free_objects;
- unsigned int free_limit;
- unsigned int colour_next; /* Per-node cache coloring */
- spinlock_t list_lock;
- struct array_cache *shared; /* shared per node */
- struct array_cache **alien; /* on other nodes */
- unsigned long next_reap; /* updated without locking */
- int free_touched; /* updated without locking */
-};
-
-/*
* Need this for bootstrapping a per node allocator.
*/
#define NUM_INIT_LISTS (3 * MAX_NUMNODES)
-static struct kmem_list3 __initdata initkmem_list3[NUM_INIT_LISTS];
+static struct kmem_cache_node __initdata init_kmem_cache_node[NUM_INIT_LISTS];
#define CACHE_CACHE 0
#define SIZE_AC MAX_NUMNODES
-#define SIZE_L3 (2 * MAX_NUMNODES)
+#define SIZE_NODE (2 * MAX_NUMNODES)
static int drain_freelist(struct kmem_cache *cache,
- struct kmem_list3 *l3, int tofree);
+ struct kmem_cache_node *n, int tofree);
static void free_block(struct kmem_cache *cachep, void **objpp, int len,
int node);
static int enable_cpucache(struct kmem_cache *cachep, gfp_t gfp);
static void cache_reap(struct work_struct *unused);
-/*
- * This function must be completely optimized away if a constant is passed to
- * it. Mostly the same as what is in linux/slab.h except it returns an index.
- */
-static __always_inline int index_of(const size_t size)
-{
- extern void __bad_size(void);
-
- if (__builtin_constant_p(size)) {
- int i = 0;
-
-#define CACHE(x) \
- if (size <=x) \
- return i; \
- else \
- i++;
-#include <linux/kmalloc_sizes.h>
-#undef CACHE
- __bad_size();
- } else
- __bad_size();
- return 0;
-}
-
static int slab_early_init = 1;
-#define INDEX_AC index_of(sizeof(struct arraycache_init))
-#define INDEX_L3 index_of(sizeof(struct kmem_list3))
+#define INDEX_AC kmalloc_index(sizeof(struct arraycache_init))
+#define INDEX_NODE kmalloc_index(sizeof(struct kmem_cache_node))
-static void kmem_list3_init(struct kmem_list3 *parent)
+static void kmem_cache_node_init(struct kmem_cache_node *parent)
{
INIT_LIST_HEAD(&parent->slabs_full);
INIT_LIST_HEAD(&parent->slabs_partial);
@@ -363,7 +322,7 @@ static void kmem_list3_init(struct kmem_list3 *parent)
#define MAKE_LIST(cachep, listp, slab, nodeid) \
do { \
INIT_LIST_HEAD(listp); \
- list_splice(&(cachep->nodelists[nodeid]->slab), listp); \
+ list_splice(&(cachep->node[nodeid]->slab), listp); \
} while (0)
#define MAKE_ALL_LISTS(cachep, ptr, nodeid) \
@@ -524,30 +483,6 @@ static inline unsigned int obj_to_index(const struct kmem_cache *cache,
return reciprocal_divide(offset, cache->reciprocal_buffer_size);
}
-/*
- * These are the default caches for kmalloc. Custom caches can have other sizes.
- */
-struct cache_sizes malloc_sizes[] = {
-#define CACHE(x) { .cs_size = (x) },
-#include <linux/kmalloc_sizes.h>
- CACHE(ULONG_MAX)
-#undef CACHE
-};
-EXPORT_SYMBOL(malloc_sizes);
-
-/* Must match cache_sizes above. Out of line to keep cache footprint low. */
-struct cache_names {
- char *name;
- char *name_dma;
-};
-
-static struct cache_names __initdata cache_names[] = {
-#define CACHE(x) { .name = "size-" #x, .name_dma = "size-" #x "(DMA)" },
-#include <linux/kmalloc_sizes.h>
- {NULL,}
-#undef CACHE
-};
-
static struct arraycache_init initarray_generic =
{ {0, BOOT_CPUCACHE_ENTRIES, 1, 0} };
@@ -586,15 +521,15 @@ static void slab_set_lock_classes(struct kmem_cache *cachep,
int q)
{
struct array_cache **alc;
- struct kmem_list3 *l3;
+ struct kmem_cache_node *n;
int r;
- l3 = cachep->nodelists[q];
- if (!l3)
+ n = cachep->node[q];
+ if (!n)
return;
- lockdep_set_class(&l3->list_lock, l3_key);
- alc = l3->alien;
+ lockdep_set_class(&n->list_lock, l3_key);
+ alc = n->alien;
/*
* FIXME: This check for BAD_ALIEN_MAGIC
* should go away when common slab code is taught to
@@ -625,28 +560,30 @@ static void slab_set_debugobj_lock_classes(struct kmem_cache *cachep)
static void init_node_lock_keys(int q)
{
- struct cache_sizes *s = malloc_sizes;
+ int i;
if (slab_state < UP)
return;
- for (s = malloc_sizes; s->cs_size != ULONG_MAX; s++) {
- struct kmem_list3 *l3;
+ for (i = 1; i < PAGE_SHIFT + MAX_ORDER; i++) {
+ struct kmem_cache_node *n;
+ struct kmem_cache *cache = kmalloc_caches[i];
+
+ if (!cache)
+ continue;
- l3 = s->cs_cachep->nodelists[q];
- if (!l3 || OFF_SLAB(s->cs_cachep))
+ n = cache->node[q];
+ if (!n || OFF_SLAB(cache))
continue;
- slab_set_lock_classes(s->cs_cachep, &on_slab_l3_key,
+ slab_set_lock_classes(cache, &on_slab_l3_key,
&on_slab_alc_key, q);
}
}
static void on_slab_lock_classes_node(struct kmem_cache *cachep, int q)
{
- struct kmem_list3 *l3;
- l3 = cachep->nodelists[q];
- if (!l3)
+ if (!cachep->node[q])
return;
slab_set_lock_classes(cachep, &on_slab_l3_key,
@@ -702,41 +639,6 @@ static inline struct array_cache *cpu_cache_get(struct kmem_cache *cachep)
return cachep->array[smp_processor_id()];
}
-static inline struct kmem_cache *__find_general_cachep(size_t size,
- gfp_t gfpflags)
-{
- struct cache_sizes *csizep = malloc_sizes;
-
-#if DEBUG
- /* This happens if someone tries to call
- * kmem_cache_create(), or __kmalloc(), before
- * the generic caches are initialized.
- */
- BUG_ON(malloc_sizes[INDEX_AC].cs_cachep == NULL);
-#endif
- if (!size)
- return ZERO_SIZE_PTR;
-
- while (size > csizep->cs_size)
- csizep++;
-
- /*
- * Really subtle: The last entry with cs->cs_size==ULONG_MAX
- * has cs_{dma,}cachep==NULL. Thus no special case
- * for large kmalloc calls required.
- */
-#ifdef CONFIG_ZONE_DMA
- if (unlikely(gfpflags & GFP_DMA))
- return csizep->cs_dmacachep;
-#endif
- return csizep->cs_cachep;
-}
-
-static struct kmem_cache *kmem_find_general_cachep(size_t size, gfp_t gfpflags)
-{
- return __find_general_cachep(size, gfpflags);
-}
-
static size_t slab_mgmt_size(size_t nr_objs, size_t align)
{
return ALIGN(sizeof(struct slab)+nr_objs*sizeof(kmem_bufctl_t), align);
@@ -938,29 +840,29 @@ static inline bool is_slab_pfmemalloc(struct slab *slabp)
static void recheck_pfmemalloc_active(struct kmem_cache *cachep,
struct array_cache *ac)
{
- struct kmem_list3 *l3 = cachep->nodelists[numa_mem_id()];
+ struct kmem_cache_node *n = cachep->node[numa_mem_id()];
struct slab *slabp;
unsigned long flags;
if (!pfmemalloc_active)
return;
- spin_lock_irqsave(&l3->list_lock, flags);
- list_for_each_entry(slabp, &l3->slabs_full, list)
+ spin_lock_irqsave(&n->list_lock, flags);
+ list_for_each_entry(slabp, &n->slabs_full, list)
if (is_slab_pfmemalloc(slabp))
goto out;
- list_for_each_entry(slabp, &l3->slabs_partial, list)
+ list_for_each_entry(slabp, &n->slabs_partial, list)
if (is_slab_pfmemalloc(slabp))
goto out;
- list_for_each_entry(slabp, &l3->slabs_free, list)
+ list_for_each_entry(slabp, &n->slabs_free, list)
if (is_slab_pfmemalloc(slabp))
goto out;
pfmemalloc_active = false;
out:
- spin_unlock_irqrestore(&l3->list_lock, flags);
+ spin_unlock_irqrestore(&n->list_lock, flags);
}
static void *__ac_get_obj(struct kmem_cache *cachep, struct array_cache *ac,
@@ -971,7 +873,7 @@ static void *__ac_get_obj(struct kmem_cache *cachep, struct array_cache *ac,
/* Ensure the caller is allowed to use objects from PFMEMALLOC slab */
if (unlikely(is_obj_pfmemalloc(objp))) {
- struct kmem_list3 *l3;
+ struct kmem_cache_node *n;
if (gfp_pfmemalloc_allowed(flags)) {
clear_obj_pfmemalloc(&objp);
@@ -993,8 +895,8 @@ static void *__ac_get_obj(struct kmem_cache *cachep, struct array_cache *ac,
* If there are empty slabs on the slabs_free list and we are
* being forced to refill the cache, mark this one !pfmemalloc.
*/
- l3 = cachep->nodelists[numa_mem_id()];
- if (!list_empty(&l3->slabs_free) && force_refill) {
+ n = cachep->node[numa_mem_id()];
+ if (!list_empty(&n->slabs_free) && force_refill) {
struct slab *slabp = virt_to_slab(objp);
ClearPageSlabPfmemalloc(virt_to_head_page(slabp->s_mem));
clear_obj_pfmemalloc(&objp);
@@ -1071,7 +973,7 @@ static int transfer_objects(struct array_cache *to,
#ifndef CONFIG_NUMA
#define drain_alien_cache(cachep, alien) do { } while (0)
-#define reap_alien(cachep, l3) do { } while (0)
+#define reap_alien(cachep, n) do { } while (0)
static inline struct array_cache **alloc_alien_cache(int node, int limit, gfp_t gfp)
{
@@ -1143,33 +1045,33 @@ static void free_alien_cache(struct array_cache **ac_ptr)
static void __drain_alien_cache(struct kmem_cache *cachep,
struct array_cache *ac, int node)
{
- struct kmem_list3 *rl3 = cachep->nodelists[node];
+ struct kmem_cache_node *n = cachep->node[node];
if (ac->avail) {
- spin_lock(&rl3->list_lock);
+ spin_lock(&n->list_lock);
/*
* Stuff objects into the remote nodes shared array first.
* That way we could avoid the overhead of putting the objects
* into the free lists and getting them back later.
*/
- if (rl3->shared)
- transfer_objects(rl3->shared, ac, ac->limit);
+ if (n->shared)
+ transfer_objects(n->shared, ac, ac->limit);
free_block(cachep, ac->entry, ac->avail, node);
ac->avail = 0;
- spin_unlock(&rl3->list_lock);
+ spin_unlock(&n->list_lock);
}
}
/*
* Called from cache_reap() to regularly drain alien caches round robin.
*/
-static void reap_alien(struct kmem_cache *cachep, struct kmem_list3 *l3)
+static void reap_alien(struct kmem_cache *cachep, struct kmem_cache_node *n)
{
int node = __this_cpu_read(slab_reap_node);
- if (l3->alien) {
- struct array_cache *ac = l3->alien[node];
+ if (n->alien) {
+ struct array_cache *ac = n->alien[node];
if (ac && ac->avail && spin_trylock_irq(&ac->lock)) {
__drain_alien_cache(cachep, ac, node);
@@ -1199,7 +1101,7 @@ static inline int cache_free_alien(struct kmem_cache *cachep, void *objp)
{
struct slab *slabp = virt_to_slab(objp);
int nodeid = slabp->nodeid;
- struct kmem_list3 *l3;
+ struct kmem_cache_node *n;
struct array_cache *alien = NULL;
int node;
@@ -1212,10 +1114,10 @@ static inline int cache_free_alien(struct kmem_cache *cachep, void *objp)
if (likely(slabp->nodeid == node))
return 0;
- l3 = cachep->nodelists[node];
+ n = cachep->node[node];
STATS_INC_NODEFREES(cachep);
- if (l3->alien && l3->alien[nodeid]) {
- alien = l3->alien[nodeid];
+ if (n->alien && n->alien[nodeid]) {
+ alien = n->alien[nodeid];
spin_lock(&alien->lock);
if (unlikely(alien->avail == alien->limit)) {
STATS_INC_ACOVERFLOW(cachep);
@@ -1224,28 +1126,28 @@ static inline int cache_free_alien(struct kmem_cache *cachep, void *objp)
ac_put_obj(cachep, alien, objp);
spin_unlock(&alien->lock);
} else {
- spin_lock(&(cachep->nodelists[nodeid])->list_lock);
+ spin_lock(&(cachep->node[nodeid])->list_lock);
free_block(cachep, &objp, 1, nodeid);
- spin_unlock(&(cachep->nodelists[nodeid])->list_lock);
+ spin_unlock(&(cachep->node[nodeid])->list_lock);
}
return 1;
}
#endif
/*
- * Allocates and initializes nodelists for a node on each slab cache, used for
- * either memory or cpu hotplug. If memory is being hot-added, the kmem_list3
+ * Allocates and initializes node for a node on each slab cache, used for
+ * either memory or cpu hotplug. If memory is being hot-added, the kmem_cache_node
* will be allocated off-node since memory is not yet online for the new node.
- * When hotplugging memory or a cpu, existing nodelists are not replaced if
+ * When hotplugging memory or a cpu, existing node are not replaced if
* already in use.
*
* Must hold slab_mutex.
*/
-static int init_cache_nodelists_node(int node)
+static int init_cache_node_node(int node)
{
struct kmem_cache *cachep;
- struct kmem_list3 *l3;
- const int memsize = sizeof(struct kmem_list3);
+ struct kmem_cache_node *n;
+ const int memsize = sizeof(struct kmem_cache_node);
list_for_each_entry(cachep, &slab_caches, list) {
/*
@@ -1253,12 +1155,12 @@ static int init_cache_nodelists_node(int node)
* begin anything. Make sure some other cpu on this
* node has not already allocated this
*/
- if (!cachep->nodelists[node]) {
- l3 = kmalloc_node(memsize, GFP_KERNEL, node);
- if (!l3)
+ if (!cachep->node[node]) {
+ n = kmalloc_node(memsize, GFP_KERNEL, node);
+ if (!n)
return -ENOMEM;
- kmem_list3_init(l3);
- l3->next_reap = jiffies + REAPTIMEOUT_LIST3 +
+ kmem_cache_node_init(n);
+ n->next_reap = jiffies + REAPTIMEOUT_LIST3 +
((unsigned long)cachep) % REAPTIMEOUT_LIST3;
/*
@@ -1266,14 +1168,14 @@ static int init_cache_nodelists_node(int node)
* go. slab_mutex is sufficient
* protection here.
*/
- cachep->nodelists[node] = l3;
+ cachep->node[node] = n;
}
- spin_lock_irq(&cachep->nodelists[node]->list_lock);
- cachep->nodelists[node]->free_limit =
+ spin_lock_irq(&cachep->node[node]->list_lock);
+ cachep->node[node]->free_limit =
(1 + nr_cpus_node(node)) *
cachep->batchcount + cachep->num;
- spin_unlock_irq(&cachep->nodelists[node]->list_lock);
+ spin_unlock_irq(&cachep->node[node]->list_lock);
}
return 0;
}
@@ -1281,7 +1183,7 @@ static int init_cache_nodelists_node(int node)
static void __cpuinit cpuup_canceled(long cpu)
{
struct kmem_cache *cachep;
- struct kmem_list3 *l3 = NULL;
+ struct kmem_cache_node *n = NULL;
int node = cpu_to_mem(cpu);
const struct cpumask *mask = cpumask_of_node(node);
@@ -1293,34 +1195,34 @@ static void __cpuinit cpuup_canceled(long cpu)
/* cpu is dead; no one can alloc from it. */
nc = cachep->array[cpu];
cachep->array[cpu] = NULL;
- l3 = cachep->nodelists[node];
+ n = cachep->node[node];
- if (!l3)
+ if (!n)
goto free_array_cache;
- spin_lock_irq(&l3->list_lock);
+ spin_lock_irq(&n->list_lock);
- /* Free limit for this kmem_list3 */
- l3->free_limit -= cachep->batchcount;
+ /* Free limit for this kmem_cache_node */
+ n->free_limit -= cachep->batchcount;
if (nc)
free_block(cachep, nc->entry, nc->avail, node);
if (!cpumask_empty(mask)) {
- spin_unlock_irq(&l3->list_lock);
+ spin_unlock_irq(&n->list_lock);
goto free_array_cache;
}
- shared = l3->shared;
+ shared = n->shared;
if (shared) {
free_block(cachep, shared->entry,
shared->avail, node);
- l3->shared = NULL;
+ n->shared = NULL;
}
- alien = l3->alien;
- l3->alien = NULL;
+ alien = n->alien;
+ n->alien = NULL;
- spin_unlock_irq(&l3->list_lock);
+ spin_unlock_irq(&n->list_lock);
kfree(shared);
if (alien) {
@@ -1336,17 +1238,17 @@ free_array_cache:
* shrink each nodelist to its limit.
*/
list_for_each_entry(cachep, &slab_caches, list) {
- l3 = cachep->nodelists[node];
- if (!l3)
+ n = cachep->node[node];
+ if (!n)
continue;
- drain_freelist(cachep, l3, l3->free_objects);
+ drain_freelist(cachep, n, n->free_objects);
}
}
static int __cpuinit cpuup_prepare(long cpu)
{
struct kmem_cache *cachep;
- struct kmem_list3 *l3 = NULL;
+ struct kmem_cache_node *n = NULL;
int node = cpu_to_mem(cpu);
int err;
@@ -1354,9 +1256,9 @@ static int __cpuinit cpuup_prepare(long cpu)
* We need to do this right in the beginning since
* alloc_arraycache's are going to use this list.
* kmalloc_node allows us to add the slab to the right
- * kmem_list3 and not this cpu's kmem_list3
+ * kmem_cache_node and not this cpu's kmem_cache_node
*/
- err = init_cache_nodelists_node(node);
+ err = init_cache_node_node(node);
if (err < 0)
goto bad;
@@ -1391,25 +1293,25 @@ static int __cpuinit cpuup_prepare(long cpu)
}
}
cachep->array[cpu] = nc;
- l3 = cachep->nodelists[node];
- BUG_ON(!l3);
+ n = cachep->node[node];
+ BUG_ON(!n);
- spin_lock_irq(&l3->list_lock);
- if (!l3->shared) {
+ spin_lock_irq(&n->list_lock);
+ if (!n->shared) {
/*
* We are serialised from CPU_DEAD or
* CPU_UP_CANCELLED by the cpucontrol lock
*/
- l3->shared = shared;
+ n->shared = shared;
shared = NULL;
}
#ifdef CONFIG_NUMA
- if (!l3->alien) {
- l3->alien = alien;
+ if (!n->alien) {
+ n->alien = alien;
alien = NULL;
}
#endif
- spin_unlock_irq(&l3->list_lock);
+ spin_unlock_irq(&n->list_lock);
kfree(shared);
free_alien_cache(alien);
if (cachep->flags & SLAB_DEBUG_OBJECTS)
@@ -1464,9 +1366,9 @@ static int __cpuinit cpuup_callback(struct notifier_block *nfb,
case CPU_DEAD_FROZEN:
/*
* Even if all the cpus of a node are down, we don't free the
- * kmem_list3 of any cache. This to avoid a race between
+ * kmem_cache_node of any cache. This to avoid a race between
* cpu_down, and a kmalloc allocation from another cpu for
- * memory from the node of the cpu going down. The list3
+ * memory from the node of the cpu going down. The node
* structure is usually allocated from kmem_cache_create() and
* gets destroyed at kmem_cache_destroy().
*/
@@ -1494,22 +1396,22 @@ static struct notifier_block __cpuinitdata cpucache_notifier = {
*
* Must hold slab_mutex.
*/
-static int __meminit drain_cache_nodelists_node(int node)
+static int __meminit drain_cache_node_node(int node)
{
struct kmem_cache *cachep;
int ret = 0;
list_for_each_entry(cachep, &slab_caches, list) {
- struct kmem_list3 *l3;
+ struct kmem_cache_node *n;
- l3 = cachep->nodelists[node];
- if (!l3)
+ n = cachep->node[node];
+ if (!n)
continue;
- drain_freelist(cachep, l3, l3->free_objects);
+ drain_freelist(cachep, n, n->free_objects);
- if (!list_empty(&l3->slabs_full) ||
- !list_empty(&l3->slabs_partial)) {
+ if (!list_empty(&n->slabs_full) ||
+ !list_empty(&n->slabs_partial)) {
ret = -EBUSY;
break;
}
@@ -1531,12 +1433,12 @@ static int __meminit slab_memory_callback(struct notifier_block *self,
switch (action) {
case MEM_GOING_ONLINE:
mutex_lock(&slab_mutex);
- ret = init_cache_nodelists_node(nid);
+ ret = init_cache_node_node(nid);
mutex_unlock(&slab_mutex);
break;
case MEM_GOING_OFFLINE:
mutex_lock(&slab_mutex);
- ret = drain_cache_nodelists_node(nid);
+ ret = drain_cache_node_node(nid);
mutex_unlock(&slab_mutex);
break;
case MEM_ONLINE:
@@ -1551,37 +1453,37 @@ out:
#endif /* CONFIG_NUMA && CONFIG_MEMORY_HOTPLUG */
/*
- * swap the static kmem_list3 with kmalloced memory
+ * swap the static kmem_cache_node with kmalloced memory
*/
-static void __init init_list(struct kmem_cache *cachep, struct kmem_list3 *list,
+static void __init init_list(struct kmem_cache *cachep, struct kmem_cache_node *list,
int nodeid)
{
- struct kmem_list3 *ptr;
+ struct kmem_cache_node *ptr;
- ptr = kmalloc_node(sizeof(struct kmem_list3), GFP_NOWAIT, nodeid);
+ ptr = kmalloc_node(sizeof(struct kmem_cache_node), GFP_NOWAIT, nodeid);
BUG_ON(!ptr);
- memcpy(ptr, list, sizeof(struct kmem_list3));
+ memcpy(ptr, list, sizeof(struct kmem_cache_node));
/*
* Do not assume that spinlocks can be initialized via memcpy:
*/
spin_lock_init(&ptr->list_lock);
MAKE_ALL_LISTS(cachep, ptr, nodeid);
- cachep->nodelists[nodeid] = ptr;
+ cachep->node[nodeid] = ptr;
}
/*
- * For setting up all the kmem_list3s for cache whose buffer_size is same as
- * size of kmem_list3.
+ * For setting up all the kmem_cache_node for cache whose buffer_size is same as
+ * size of kmem_cache_node.
*/
-static void __init set_up_list3s(struct kmem_cache *cachep, int index)
+static void __init set_up_node(struct kmem_cache *cachep, int index)
{
int node;
for_each_online_node(node) {
- cachep->nodelists[node] = &initkmem_list3[index + node];
- cachep->nodelists[node]->next_reap = jiffies +
+ cachep->node[node] = &init_kmem_cache_node[index + node];
+ cachep->node[node]->next_reap = jiffies +
REAPTIMEOUT_LIST3 +
((unsigned long)cachep) % REAPTIMEOUT_LIST3;
}
@@ -1589,11 +1491,11 @@ static void __init set_up_list3s(struct kmem_cache *cachep, int index)
/*
* The memory after the last cpu cache pointer is used for the
- * the nodelists pointer.
+ * the node pointer.
*/
-static void setup_nodelists_pointer(struct kmem_cache *cachep)
+static void setup_node_pointer(struct kmem_cache *cachep)
{
- cachep->nodelists = (struct kmem_list3 **)&cachep->array[nr_cpu_ids];
+ cachep->node = (struct kmem_cache_node **)&cachep->array[nr_cpu_ids];
}
/*
@@ -1602,20 +1504,18 @@ static void setup_nodelists_pointer(struct kmem_cache *cachep)
*/
void __init kmem_cache_init(void)
{
- struct cache_sizes *sizes;
- struct cache_names *names;
int i;
kmem_cache = &kmem_cache_boot;
- setup_nodelists_pointer(kmem_cache);
+ setup_node_pointer(kmem_cache);
if (num_possible_nodes() == 1)
use_alien_caches = 0;
for (i = 0; i < NUM_INIT_LISTS; i++)
- kmem_list3_init(&initkmem_list3[i]);
+ kmem_cache_node_init(&init_kmem_cache_node[i]);
- set_up_list3s(kmem_cache, CACHE_CACHE);
+ set_up_node(kmem_cache, CACHE_CACHE);
/*
* Fragmentation resistance on low memory - only use bigger
@@ -1631,7 +1531,7 @@ void __init kmem_cache_init(void)
* kmem_cache structures of all caches, except kmem_cache itself:
* kmem_cache is statically allocated.
* Initially an __init data area is used for the head array and the
- * kmem_list3 structures, it's replaced with a kmalloc allocated
+ * kmem_cache_node structures, it's replaced with a kmalloc allocated
* array at the end of the bootstrap.
* 2) Create the first kmalloc cache.
* The struct kmem_cache for the new cache is allocated normally.
@@ -1640,7 +1540,7 @@ void __init kmem_cache_init(void)
* head arrays.
* 4) Replace the __init data head arrays for kmem_cache and the first
* kmalloc cache with kmalloc allocated arrays.
- * 5) Replace the __init data for kmem_list3 for kmem_cache and
+ * 5) Replace the __init data for kmem_cache_node for kmem_cache and
* the other cache's with kmalloc allocated memory.
* 6) Resize the head arrays of the kmalloc caches to their final sizes.
*/
@@ -1652,50 +1552,28 @@ void __init kmem_cache_init(void)
*/
create_boot_cache(kmem_cache, "kmem_cache",
offsetof(struct kmem_cache, array[nr_cpu_ids]) +
- nr_node_ids * sizeof(struct kmem_list3 *),
+ nr_node_ids * sizeof(struct kmem_cache_node *),
SLAB_HWCACHE_ALIGN);
list_add(&kmem_cache->list, &slab_caches);
/* 2+3) create the kmalloc caches */
- sizes = malloc_sizes;
- names = cache_names;
/*
* Initialize the caches that provide memory for the array cache and the
- * kmem_list3 structures first. Without this, further allocations will
+ * kmem_cache_node structures first. Without this, further allocations will
* bug.
*/
- sizes[INDEX_AC].cs_cachep = create_kmalloc_cache(names[INDEX_AC].name,
- sizes[INDEX_AC].cs_size, ARCH_KMALLOC_FLAGS);
+ kmalloc_caches[INDEX_AC] = create_kmalloc_cache("kmalloc-ac",
+ kmalloc_size(INDEX_AC), ARCH_KMALLOC_FLAGS);
- if (INDEX_AC != INDEX_L3)
- sizes[INDEX_L3].cs_cachep =
- create_kmalloc_cache(names[INDEX_L3].name,
- sizes[INDEX_L3].cs_size, ARCH_KMALLOC_FLAGS);
+ if (INDEX_AC != INDEX_NODE)
+ kmalloc_caches[INDEX_NODE] =
+ create_kmalloc_cache("kmalloc-node",
+ kmalloc_size(INDEX_NODE), ARCH_KMALLOC_FLAGS);
slab_early_init = 0;
- while (sizes->cs_size != ULONG_MAX) {
- /*
- * For performance, all the general caches are L1 aligned.
- * This should be particularly beneficial on SMP boxes, as it
- * eliminates "false sharing".
- * Note for systems short on memory removing the alignment will
- * allow tighter packing of the smaller caches.
- */
- if (!sizes->cs_cachep)
- sizes->cs_cachep = create_kmalloc_cache(names->name,
- sizes->cs_size, ARCH_KMALLOC_FLAGS);
-
-#ifdef CONFIG_ZONE_DMA
- sizes->cs_dmacachep = create_kmalloc_cache(
- names->name_dma, sizes->cs_size,
- SLAB_CACHE_DMA|ARCH_KMALLOC_FLAGS);
-#endif
- sizes++;
- names++;
- }
/* 4) Replace the bootstrap head arrays */
{
struct array_cache *ptr;
@@ -1713,36 +1591,35 @@ void __init kmem_cache_init(void)
ptr = kmalloc(sizeof(struct arraycache_init), GFP_NOWAIT);
- BUG_ON(cpu_cache_get(malloc_sizes[INDEX_AC].cs_cachep)
+ BUG_ON(cpu_cache_get(kmalloc_caches[INDEX_AC])
!= &initarray_generic.cache);
- memcpy(ptr, cpu_cache_get(malloc_sizes[INDEX_AC].cs_cachep),
+ memcpy(ptr, cpu_cache_get(kmalloc_caches[INDEX_AC]),
sizeof(struct arraycache_init));
/*
* Do not assume that spinlocks can be initialized via memcpy:
*/
spin_lock_init(&ptr->lock);
- malloc_sizes[INDEX_AC].cs_cachep->array[smp_processor_id()] =
- ptr;
+ kmalloc_caches[INDEX_AC]->array[smp_processor_id()] = ptr;
}
- /* 5) Replace the bootstrap kmem_list3's */
+ /* 5) Replace the bootstrap kmem_cache_node */
{
int nid;
for_each_online_node(nid) {
- init_list(kmem_cache, &initkmem_list3[CACHE_CACHE + nid], nid);
+ init_list(kmem_cache, &init_kmem_cache_node[CACHE_CACHE + nid], nid);
- init_list(malloc_sizes[INDEX_AC].cs_cachep,
- &initkmem_list3[SIZE_AC + nid], nid);
+ init_list(kmalloc_caches[INDEX_AC],
+ &init_kmem_cache_node[SIZE_AC + nid], nid);
- if (INDEX_AC != INDEX_L3) {
- init_list(malloc_sizes[INDEX_L3].cs_cachep,
- &initkmem_list3[SIZE_L3 + nid], nid);
+ if (INDEX_AC != INDEX_NODE) {
+ init_list(kmalloc_caches[INDEX_NODE],
+ &init_kmem_cache_node[SIZE_NODE + nid], nid);
}
}
}
- slab_state = UP;
+ create_kmalloc_caches(ARCH_KMALLOC_FLAGS);
}
void __init kmem_cache_init_late(void)
@@ -1773,7 +1650,7 @@ void __init kmem_cache_init_late(void)
#ifdef CONFIG_NUMA
/*
* Register a memory hotplug callback that initializes and frees
- * nodelists.
+ * node.
*/
hotplug_memory_notifier(slab_memory_callback, SLAB_CALLBACK_PRI);
#endif
@@ -1803,7 +1680,7 @@ __initcall(cpucache_init);
static noinline void
slab_out_of_memory(struct kmem_cache *cachep, gfp_t gfpflags, int nodeid)
{
- struct kmem_list3 *l3;
+ struct kmem_cache_node *n;
struct slab *slabp;
unsigned long flags;
int node;
@@ -1818,24 +1695,24 @@ slab_out_of_memory(struct kmem_cache *cachep, gfp_t gfpflags, int nodeid)
unsigned long active_objs = 0, num_objs = 0, free_objects = 0;
unsigned long active_slabs = 0, num_slabs = 0;
- l3 = cachep->nodelists[node];
- if (!l3)
+ n = cachep->node[node];
+ if (!n)
continue;
- spin_lock_irqsave(&l3->list_lock, flags);
- list_for_each_entry(slabp, &l3->slabs_full, list) {
+ spin_lock_irqsave(&n->list_lock, flags);
+ list_for_each_entry(slabp, &n->slabs_full, list) {
active_objs += cachep->num;
active_slabs++;
}
- list_for_each_entry(slabp, &l3->slabs_partial, list) {
+ list_for_each_entry(slabp, &n->slabs_partial, list) {
active_objs += slabp->inuse;
active_slabs++;
}
- list_for_each_entry(slabp, &l3->slabs_free, list)
+ list_for_each_entry(slabp, &n->slabs_free, list)
num_slabs++;
- free_objects += l3->free_objects;
- spin_unlock_irqrestore(&l3->list_lock, flags);
+ free_objects += n->free_objects;
+ spin_unlock_irqrestore(&n->list_lock, flags);
num_slabs += active_slabs;
num_objs = num_slabs * cachep->num;
@@ -2258,7 +2135,7 @@ static int __init_refok setup_cpu_cache(struct kmem_cache *cachep, gfp_t gfp)
if (slab_state == DOWN) {
/*
* Note: Creation of first cache (kmem_cache).
- * The setup_list3s is taken care
+ * The setup_node is taken care
* of by the caller of __kmem_cache_create
*/
cachep->array[smp_processor_id()] = &initarray_generic.cache;
@@ -2272,13 +2149,13 @@ static int __init_refok setup_cpu_cache(struct kmem_cache *cachep, gfp_t gfp)
cachep->array[smp_processor_id()] = &initarray_generic.cache;
/*
- * If the cache that's used by kmalloc(sizeof(kmem_list3)) is
- * the second cache, then we need to set up all its list3s,
+ * If the cache that's used by kmalloc(sizeof(kmem_cache_node)) is
+ * the second cache, then we need to set up all its node/,
* otherwise the creation of further caches will BUG().
*/
- set_up_list3s(cachep, SIZE_AC);
- if (INDEX_AC == INDEX_L3)
- slab_state = PARTIAL_L3;
+ set_up_node(cachep, SIZE_AC);
+ if (INDEX_AC == INDEX_NODE)
+ slab_state = PARTIAL_NODE;
else
slab_state = PARTIAL_ARRAYCACHE;
} else {
@@ -2287,20 +2164,20 @@ static int __init_refok setup_cpu_cache(struct kmem_cache *cachep, gfp_t gfp)
kmalloc(sizeof(struct arraycache_init), gfp);
if (slab_state == PARTIAL_ARRAYCACHE) {
- set_up_list3s(cachep, SIZE_L3);
- slab_state = PARTIAL_L3;
+ set_up_node(cachep, SIZE_NODE);
+ slab_state = PARTIAL_NODE;
} else {
int node;
for_each_online_node(node) {
- cachep->nodelists[node] =
- kmalloc_node(sizeof(struct kmem_list3),
+ cachep->node[node] =
+ kmalloc_node(sizeof(struct kmem_cache_node),
gfp, node);
- BUG_ON(!cachep->nodelists[node]);
- kmem_list3_init(cachep->nodelists[node]);
+ BUG_ON(!cachep->node[node]);
+ kmem_cache_node_init(cachep->node[node]);
}
}
}
- cachep->nodelists[numa_mem_id()]->next_reap =
+ cachep->node[numa_mem_id()]->next_reap =
jiffies + REAPTIMEOUT_LIST3 +
((unsigned long)cachep) % REAPTIMEOUT_LIST3;
@@ -2403,7 +2280,7 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags)
else
gfp = GFP_NOWAIT;
- setup_nodelists_pointer(cachep);
+ setup_node_pointer(cachep);
#if DEBUG
/*
@@ -2426,7 +2303,7 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags)
size += BYTES_PER_WORD;
}
#if FORCED_DEBUG && defined(CONFIG_DEBUG_PAGEALLOC)
- if (size >= malloc_sizes[INDEX_L3 + 1].cs_size
+ if (size >= kmalloc_size(INDEX_NODE + 1)
&& cachep->object_size > cache_line_size()
&& ALIGN(size, cachep->align) < PAGE_SIZE) {
cachep->obj_offset += PAGE_SIZE - ALIGN(size, cachep->align);
@@ -2497,7 +2374,7 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags)
cachep->reciprocal_buffer_size = reciprocal_value(size);
if (flags & CFLGS_OFF_SLAB) {
- cachep->slabp_cache = kmem_find_general_cachep(slab_size, 0u);
+ cachep->slabp_cache = kmalloc_slab(slab_size, 0u);
/*
* This is a possibility for one of the malloc_sizes caches.
* But since we go off slab only for object size greater than
@@ -2543,7 +2420,7 @@ static void check_spinlock_acquired(struct kmem_cache *cachep)
{
#ifdef CONFIG_SMP
check_irq_off();
- assert_spin_locked(&cachep->nodelists[numa_mem_id()]->list_lock);
+ assert_spin_locked(&cachep->node[numa_mem_id()]->list_lock);
#endif
}
@@ -2551,7 +2428,7 @@ static void check_spinlock_acquired_node(struct kmem_cache *cachep, int node)
{
#ifdef CONFIG_SMP
check_irq_off();
- assert_spin_locked(&cachep->nodelists[node]->list_lock);
+ assert_spin_locked(&cachep->node[node]->list_lock);
#endif
}
@@ -2562,7 +2439,7 @@ static void check_spinlock_acquired_node(struct kmem_cache *cachep, int node)
#define check_spinlock_acquired_node(x, y) do { } while(0)
#endif
-static void drain_array(struct kmem_cache *cachep, struct kmem_list3 *l3,
+static void drain_array(struct kmem_cache *cachep, struct kmem_cache_node *n,
struct array_cache *ac,
int force, int node);
@@ -2574,29 +2451,29 @@ static void do_drain(void *arg)
check_irq_off();
ac = cpu_cache_get(cachep);
- spin_lock(&cachep->nodelists[node]->list_lock);
+ spin_lock(&cachep->node[node]->list_lock);
free_block(cachep, ac->entry, ac->avail, node);
- spin_unlock(&cachep->nodelists[node]->list_lock);
+ spin_unlock(&cachep->node[node]->list_lock);
ac->avail = 0;
}
static void drain_cpu_caches(struct kmem_cache *cachep)
{
- struct kmem_list3 *l3;
+ struct kmem_cache_node *n;
int node;
on_each_cpu(do_drain, cachep, 1);
check_irq_on();
for_each_online_node(node) {
- l3 = cachep->nodelists[node];
- if (l3 && l3->alien)
- drain_alien_cache(cachep, l3->alien);
+ n = cachep->node[node];
+ if (n && n->alien)
+ drain_alien_cache(cachep, n->alien);
}
for_each_online_node(node) {
- l3 = cachep->nodelists[node];
- if (l3)
- drain_array(cachep, l3, l3->shared, 1, node);
+ n = cachep->node[node];
+ if (n)
+ drain_array(cachep, n, n->shared, 1, node);
}
}
@@ -2607,19 +2484,19 @@ static void drain_cpu_caches(struct kmem_cache *cachep)
* Returns the actual number of slabs released.
*/
static int drain_freelist(struct kmem_cache *cache,
- struct kmem_list3 *l3, int tofree)
+ struct kmem_cache_node *n, int tofree)
{
struct list_head *p;
int nr_freed;
struct slab *slabp;
nr_freed = 0;
- while (nr_freed < tofree && !list_empty(&l3->slabs_free)) {
+ while (nr_freed < tofree && !list_empty(&n->slabs_free)) {
- spin_lock_irq(&l3->list_lock);
- p = l3->slabs_free.prev;
- if (p == &l3->slabs_free) {
- spin_unlock_irq(&l3->list_lock);
+ spin_lock_irq(&n->list_lock);
+ p = n->slabs_free.prev;
+ if (p == &n->slabs_free) {
+ spin_unlock_irq(&n->list_lock);
goto out;
}
@@ -2632,8 +2509,8 @@ static int drain_freelist(struct kmem_cache *cache,
* Safe to drop the lock. The slab is no longer linked
* to the cache.
*/
- l3->free_objects -= cache->num;
- spin_unlock_irq(&l3->list_lock);
+ n->free_objects -= cache->num;
+ spin_unlock_irq(&n->list_lock);
slab_destroy(cache, slabp);
nr_freed++;
}
@@ -2645,20 +2522,20 @@ out:
static int __cache_shrink(struct kmem_cache *cachep)
{
int ret = 0, i = 0;
- struct kmem_list3 *l3;
+ struct kmem_cache_node *n;
drain_cpu_caches(cachep);
check_irq_on();
for_each_online_node(i) {
- l3 = cachep->nodelists[i];
- if (!l3)
+ n = cachep->node[i];
+ if (!n)
continue;
- drain_freelist(cachep, l3, l3->free_objects);
+ drain_freelist(cachep, n, n->free_objects);
- ret += !list_empty(&l3->slabs_full) ||
- !list_empty(&l3->slabs_partial);
+ ret += !list_empty(&n->slabs_full) ||
+ !list_empty(&n->slabs_partial);
}
return (ret ? 1 : 0);
}
@@ -2687,7 +2564,7 @@ EXPORT_SYMBOL(kmem_cache_shrink);
int __kmem_cache_shutdown(struct kmem_cache *cachep)
{
int i;
- struct kmem_list3 *l3;
+ struct kmem_cache_node *n;
int rc = __cache_shrink(cachep);
if (rc)
@@ -2696,13 +2573,13 @@ int __kmem_cache_shutdown(struct kmem_cache *cachep)
for_each_online_cpu(i)
kfree(cachep->array[i]);
- /* NUMA: free the list3 structures */
+ /* NUMA: free the node structures */
for_each_online_node(i) {
- l3 = cachep->nodelists[i];
- if (l3) {
- kfree(l3->shared);
- free_alien_cache(l3->alien);
- kfree(l3);
+ n = cachep->node[i];
+ if (n) {
+ kfree(n->shared);
+ free_alien_cache(n->alien);
+ kfree(n);
}
}
return 0;
@@ -2884,7 +2761,7 @@ static int cache_grow(struct kmem_cache *cachep,
struct slab *slabp;
size_t offset;
gfp_t local_flags;
- struct kmem_list3 *l3;
+ struct kmem_cache_node *n;
/*
* Be lazy and only check for valid flags here, keeping it out of the
@@ -2893,17 +2770,17 @@ static int cache_grow(struct kmem_cache *cachep,
BUG_ON(flags & GFP_SLAB_BUG_MASK);
local_flags = flags & (GFP_CONSTRAINT_MASK|GFP_RECLAIM_MASK);
- /* Take the l3 list lock to change the colour_next on this node */
+ /* Take the node list lock to change the colour_next on this node */
check_irq_off();
- l3 = cachep->nodelists[nodeid];
- spin_lock(&l3->list_lock);
+ n = cachep->node[nodeid];
+ spin_lock(&n->list_lock);
/* Get colour for the slab, and cal the next value. */
- offset = l3->colour_next;
- l3->colour_next++;
- if (l3->colour_next >= cachep->colour)
- l3->colour_next = 0;
- spin_unlock(&l3->list_lock);
+ offset = n->colour_next;
+ n->colour_next++;
+ if (n->colour_next >= cachep->colour)
+ n->colour_next = 0;
+ spin_unlock(&n->list_lock);
offset *= cachep->colour_off;
@@ -2940,13 +2817,13 @@ static int cache_grow(struct kmem_cache *cachep,
if (local_flags & __GFP_WAIT)
local_irq_disable();
check_irq_off();
- spin_lock(&l3->list_lock);
+ spin_lock(&n->list_lock);
/* Make slab active. */
- list_add_tail(&slabp->list, &(l3->slabs_free));
+ list_add_tail(&slabp->list, &(n->slabs_free));
STATS_INC_GROWN(cachep);
- l3->free_objects += cachep->num;
- spin_unlock(&l3->list_lock);
+ n->free_objects += cachep->num;
+ spin_unlock(&n->list_lock);
return 1;
opps1:
kmem_freepages(cachep, objp);
@@ -3074,7 +2951,7 @@ static void *cache_alloc_refill(struct kmem_cache *cachep, gfp_t flags,
bool force_refill)
{
int batchcount;
- struct kmem_list3 *l3;
+ struct kmem_cache_node *n;
struct array_cache *ac;
int node;
@@ -3093,14 +2970,14 @@ retry:
*/
batchcount = BATCHREFILL_LIMIT;
}
- l3 = cachep->nodelists[node];
+ n = cachep->node[node];
- BUG_ON(ac->avail > 0 || !l3);
- spin_lock(&l3->list_lock);
+ BUG_ON(ac->avail > 0 || !n);
+ spin_lock(&n->list_lock);
/* See if we can refill from the shared array */
- if (l3->shared && transfer_objects(ac, l3->shared, batchcount)) {
- l3->shared->touched = 1;
+ if (n->shared && transfer_objects(ac, n->shared, batchcount)) {
+ n->shared->touched = 1;
goto alloc_done;
}
@@ -3108,11 +2985,11 @@ retry:
struct list_head *entry;
struct slab *slabp;
/* Get slab alloc is to come from. */
- entry = l3->slabs_partial.next;
- if (entry == &l3->slabs_partial) {
- l3->free_touched = 1;
- entry = l3->slabs_free.next;
- if (entry == &l3->slabs_free)
+ entry = n->slabs_partial.next;
+ if (entry == &n->slabs_partial) {
+ n->free_touched = 1;
+ entry = n->slabs_free.next;
+ if (entry == &n->slabs_free)
goto must_grow;
}
@@ -3140,15 +3017,15 @@ retry:
/* move slabp to correct slabp list: */
list_del(&slabp->list);
if (slabp->free == BUFCTL_END)
- list_add(&slabp->list, &l3->slabs_full);
+ list_add(&slabp->list, &n->slabs_full);
else
- list_add(&slabp->list, &l3->slabs_partial);
+ list_add(&slabp->list, &n->slabs_partial);
}
must_grow:
- l3->free_objects -= ac->avail;
+ n->free_objects -= ac->avail;
alloc_done:
- spin_unlock(&l3->list_lock);
+ spin_unlock(&n->list_lock);
if (unlikely(!ac->avail)) {
int x;
@@ -3315,7 +3192,7 @@ static void *alternate_node_alloc(struct kmem_cache *cachep, gfp_t flags)
/*
* Fallback function if there was no memory available and no objects on a
* certain node and fall back is permitted. First we scan all the
- * available nodelists for available objects. If that fails then we
+ * available node for available objects. If that fails then we
* perform an allocation without specifying a node. This allows the page
* allocator to do its reclaim / fallback magic. We then insert the
* slab into the proper nodelist and then allocate from it.
@@ -3349,8 +3226,8 @@ retry:
nid = zone_to_nid(zone);
if (cpuset_zone_allowed_hardwall(zone, flags) &&
- cache->nodelists[nid] &&
- cache->nodelists[nid]->free_objects) {
+ cache->node[nid] &&
+ cache->node[nid]->free_objects) {
obj = ____cache_alloc_node(cache,
flags | GFP_THISNODE, nid);
if (obj)
@@ -3406,21 +3283,22 @@ static void *____cache_alloc_node(struct kmem_cache *cachep, gfp_t flags,
{
struct list_head *entry;
struct slab *slabp;
- struct kmem_list3 *l3;
+ struct kmem_cache_node *n;
void *obj;
int x;
- l3 = cachep->nodelists[nodeid];
- BUG_ON(!l3);
+ VM_BUG_ON(nodeid > num_online_nodes());
+ n = cachep->node[nodeid];
+ BUG_ON(!n);
retry:
check_irq_off();
- spin_lock(&l3->list_lock);
- entry = l3->slabs_partial.next;
- if (entry == &l3->slabs_partial) {
- l3->free_touched = 1;
- entry = l3->slabs_free.next;
- if (entry == &l3->slabs_free)
+ spin_lock(&n->list_lock);
+ entry = n->slabs_partial.next;
+ if (entry == &n->slabs_partial) {
+ n->free_touched = 1;
+ entry = n->slabs_free.next;
+ if (entry == &n->slabs_free)
goto must_grow;
}
@@ -3436,20 +3314,20 @@ retry:
obj = slab_get_obj(cachep, slabp, nodeid);
check_slabp(cachep, slabp);
- l3->free_objects--;
+ n->free_objects--;
/* move slabp to correct slabp list: */
list_del(&slabp->list);
if (slabp->free == BUFCTL_END)
- list_add(&slabp->list, &l3->slabs_full);
+ list_add(&slabp->list, &n->slabs_full);
else
- list_add(&slabp->list, &l3->slabs_partial);
+ list_add(&slabp->list, &n->slabs_partial);
- spin_unlock(&l3->list_lock);
+ spin_unlock(&n->list_lock);
goto done;
must_grow:
- spin_unlock(&l3->list_lock);
+ spin_unlock(&n->list_lock);
x = cache_grow(cachep, flags | GFP_THISNODE, nodeid, NULL);
if (x)
goto retry;
@@ -3495,7 +3373,7 @@ slab_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid,
if (nodeid == NUMA_NO_NODE)
nodeid = slab_node;
- if (unlikely(!cachep->nodelists[nodeid])) {
+ if (unlikely(!cachep->node[nodeid])) {
/* Node not bootstrapped yet */
ptr = fallback_alloc(cachep, flags);
goto out;
@@ -3601,7 +3479,7 @@ static void free_block(struct kmem_cache *cachep, void **objpp, int nr_objects,
int node)
{
int i;
- struct kmem_list3 *l3;
+ struct kmem_cache_node *n;
for (i = 0; i < nr_objects; i++) {
void *objp;
@@ -3611,19 +3489,19 @@ static void free_block(struct kmem_cache *cachep, void **objpp, int nr_objects,
objp = objpp[i];
slabp = virt_to_slab(objp);
- l3 = cachep->nodelists[node];
+ n = cachep->node[node];
list_del(&slabp->list);
check_spinlock_acquired_node(cachep, node);
check_slabp(cachep, slabp);
slab_put_obj(cachep, slabp, objp, node);
STATS_DEC_ACTIVE(cachep);
- l3->free_objects++;
+ n->free_objects++;
check_slabp(cachep, slabp);
/* fixup slab chains */
if (slabp->inuse == 0) {
- if (l3->free_objects > l3->free_limit) {
- l3->free_objects -= cachep->num;
+ if (n->free_objects > n->free_limit) {
+ n->free_objects -= cachep->num;
/* No need to drop any previously held
* lock here, even if we have a off-slab slab
* descriptor it is guaranteed to come from
@@ -3632,14 +3510,14 @@ static void free_block(struct kmem_cache *cachep, void **objpp, int nr_objects,
*/
slab_destroy(cachep, slabp);
} else {
- list_add(&slabp->list, &l3->slabs_free);
+ list_add(&slabp->list, &n->slabs_free);
}
} else {
/* Unconditionally move a slab to the end of the
* partial list on free - maximum time for the
* other objects to be freed, too.
*/
- list_add_tail(&slabp->list, &l3->slabs_partial);
+ list_add_tail(&slabp->list, &n->slabs_partial);
}
}
}
@@ -3647,7 +3525,7 @@ static void free_block(struct kmem_cache *cachep, void **objpp, int nr_objects,
static void cache_flusharray(struct kmem_cache *cachep, struct array_cache *ac)
{
int batchcount;
- struct kmem_list3 *l3;
+ struct kmem_cache_node *n;
int node = numa_mem_id();
batchcount = ac->batchcount;
@@ -3655,10 +3533,10 @@ static void cache_flusharray(struct kmem_cache *cachep, struct array_cache *ac)
BUG_ON(!batchcount || batchcount > ac->avail);
#endif
check_irq_off();
- l3 = cachep->nodelists[node];
- spin_lock(&l3->list_lock);
- if (l3->shared) {
- struct array_cache *shared_array = l3->shared;
+ n = cachep->node[node];
+ spin_lock(&n->list_lock);
+ if (n->shared) {
+ struct array_cache *shared_array = n->shared;
int max = shared_array->limit - shared_array->avail;
if (max) {
if (batchcount > max)
@@ -3677,8 +3555,8 @@ free_done:
int i = 0;
struct list_head *p;
- p = l3->slabs_free.next;
- while (p != &(l3->slabs_free)) {
+ p = n->slabs_free.next;
+ while (p != &(n->slabs_free)) {
struct slab *slabp;
slabp = list_entry(p, struct slab, list);
@@ -3690,7 +3568,7 @@ free_done:
STATS_SET_FREEABLE(cachep, i);
}
#endif
- spin_unlock(&l3->list_lock);
+ spin_unlock(&n->list_lock);
ac->avail -= batchcount;
memmove(ac->entry, &(ac->entry[batchcount]), sizeof(void *)*ac->avail);
}
@@ -3800,7 +3678,7 @@ __do_kmalloc_node(size_t size, gfp_t flags, int node, unsigned long caller)
{
struct kmem_cache *cachep;
- cachep = kmem_find_general_cachep(size, flags);
+ cachep = kmalloc_slab(size, flags);
if (unlikely(ZERO_OR_NULL_PTR(cachep)))
return cachep;
return kmem_cache_alloc_node_trace(cachep, flags, node, size);
@@ -3845,7 +3723,7 @@ static __always_inline void *__do_kmalloc(size_t size, gfp_t flags,
* Then kmalloc uses the uninlined functions instead of the inline
* functions.
*/
- cachep = __find_general_cachep(size, flags);
+ cachep = kmalloc_slab(size, flags);
if (unlikely(ZERO_OR_NULL_PTR(cachep)))
return cachep;
ret = slab_alloc(cachep, flags, caller);
@@ -3934,12 +3812,12 @@ void kfree(const void *objp)
EXPORT_SYMBOL(kfree);
/*
- * This initializes kmem_list3 or resizes various caches for all nodes.
+ * This initializes kmem_cache_node or resizes various caches for all nodes.
*/
static int alloc_kmemlist(struct kmem_cache *cachep, gfp_t gfp)
{
int node;
- struct kmem_list3 *l3;
+ struct kmem_cache_node *n;
struct array_cache *new_shared;
struct array_cache **new_alien = NULL;
@@ -3962,43 +3840,43 @@ static int alloc_kmemlist(struct kmem_cache *cachep, gfp_t gfp)
}
}
- l3 = cachep->nodelists[node];
- if (l3) {
- struct array_cache *shared = l3->shared;
+ n = cachep->node[node];
+ if (n) {
+ struct array_cache *shared = n->shared;
- spin_lock_irq(&l3->list_lock);
+ spin_lock_irq(&n->list_lock);
if (shared)
free_block(cachep, shared->entry,
shared->avail, node);
- l3->shared = new_shared;
- if (!l3->alien) {
- l3->alien = new_alien;
+ n->shared = new_shared;
+ if (!n->alien) {
+ n->alien = new_alien;
new_alien = NULL;
}
- l3->free_limit = (1 + nr_cpus_node(node)) *
+ n->free_limit = (1 + nr_cpus_node(node)) *
cachep->batchcount + cachep->num;
- spin_unlock_irq(&l3->list_lock);
+ spin_unlock_irq(&n->list_lock);
kfree(shared);
free_alien_cache(new_alien);
continue;
}
- l3 = kmalloc_node(sizeof(struct kmem_list3), gfp, node);
- if (!l3) {
+ n = kmalloc_node(sizeof(struct kmem_cache_node), gfp, node);
+ if (!n) {
free_alien_cache(new_alien);
kfree(new_shared);
goto fail;
}
- kmem_list3_init(l3);
- l3->next_reap = jiffies + REAPTIMEOUT_LIST3 +
+ kmem_cache_node_init(n);
+ n->next_reap = jiffies + REAPTIMEOUT_LIST3 +
((unsigned long)cachep) % REAPTIMEOUT_LIST3;
- l3->shared = new_shared;
- l3->alien = new_alien;
- l3->free_limit = (1 + nr_cpus_node(node)) *
+ n->shared = new_shared;
+ n->alien = new_alien;
+ n->free_limit = (1 + nr_cpus_node(node)) *
cachep->batchcount + cachep->num;
- cachep->nodelists[node] = l3;
+ cachep->node[node] = n;
}
return 0;
@@ -4007,13 +3885,13 @@ fail:
/* Cache is not active yet. Roll back what we did */
node--;
while (node >= 0) {
- if (cachep->nodelists[node]) {
- l3 = cachep->nodelists[node];
+ if (cachep->node[node]) {
+ n = cachep->node[node];
- kfree(l3->shared);
- free_alien_cache(l3->alien);
- kfree(l3);
- cachep->nodelists[node] = NULL;
+ kfree(n->shared);
+ free_alien_cache(n->alien);
+ kfree(n);
+ cachep->node[node] = NULL;
}
node--;
}
@@ -4073,9 +3951,9 @@ static int __do_tune_cpucache(struct kmem_cache *cachep, int limit,
struct array_cache *ccold = new->new[i];
if (!ccold)
continue;
- spin_lock_irq(&cachep->nodelists[cpu_to_mem(i)]->list_lock);
+ spin_lock_irq(&cachep->node[cpu_to_mem(i)]->list_lock);
free_block(cachep, ccold->entry, ccold->avail, cpu_to_mem(i));
- spin_unlock_irq(&cachep->nodelists[cpu_to_mem(i)]->list_lock);
+ spin_unlock_irq(&cachep->node[cpu_to_mem(i)]->list_lock);
kfree(ccold);
}
kfree(new);
@@ -4176,11 +4054,11 @@ skip_setup:
}
/*
- * Drain an array if it contains any elements taking the l3 lock only if
- * necessary. Note that the l3 listlock also protects the array_cache
+ * Drain an array if it contains any elements taking the node lock only if
+ * necessary. Note that the node listlock also protects the array_cache
* if drain_array() is used on the shared array.
*/
-static void drain_array(struct kmem_cache *cachep, struct kmem_list3 *l3,
+static void drain_array(struct kmem_cache *cachep, struct kmem_cache_node *n,
struct array_cache *ac, int force, int node)
{
int tofree;
@@ -4190,7 +4068,7 @@ static void drain_array(struct kmem_cache *cachep, struct kmem_list3 *l3,
if (ac->touched && !force) {
ac->touched = 0;
} else {
- spin_lock_irq(&l3->list_lock);
+ spin_lock_irq(&n->list_lock);
if (ac->avail) {
tofree = force ? ac->avail : (ac->limit + 4) / 5;
if (tofree > ac->avail)
@@ -4200,7 +4078,7 @@ static void drain_array(struct kmem_cache *cachep, struct kmem_list3 *l3,
memmove(ac->entry, &(ac->entry[tofree]),
sizeof(void *) * ac->avail);
}
- spin_unlock_irq(&l3->list_lock);
+ spin_unlock_irq(&n->list_lock);
}
}
@@ -4219,7 +4097,7 @@ static void drain_array(struct kmem_cache *cachep, struct kmem_list3 *l3,
static void cache_reap(struct work_struct *w)
{
struct kmem_cache *searchp;
- struct kmem_list3 *l3;
+ struct kmem_cache_node *n;
int node = numa_mem_id();
struct delayed_work *work = to_delayed_work(w);
@@ -4231,33 +4109,33 @@ static void cache_reap(struct work_struct *w)
check_irq_on();
/*
- * We only take the l3 lock if absolutely necessary and we
+ * We only take the node lock if absolutely necessary and we
* have established with reasonable certainty that
* we can do some work if the lock was obtained.
*/
- l3 = searchp->nodelists[node];
+ n = searchp->node[node];
- reap_alien(searchp, l3);
+ reap_alien(searchp, n);
- drain_array(searchp, l3, cpu_cache_get(searchp), 0, node);
+ drain_array(searchp, n, cpu_cache_get(searchp), 0, node);
/*
* These are racy checks but it does not matter
* if we skip one check or scan twice.
*/
- if (time_after(l3->next_reap, jiffies))
+ if (time_after(n->next_reap, jiffies))
goto next;
- l3->next_reap = jiffies + REAPTIMEOUT_LIST3;
+ n->next_reap = jiffies + REAPTIMEOUT_LIST3;
- drain_array(searchp, l3, l3->shared, 0, node);
+ drain_array(searchp, n, n->shared, 0, node);
- if (l3->free_touched)
- l3->free_touched = 0;
+ if (n->free_touched)
+ n->free_touched = 0;
else {
int freed;
- freed = drain_freelist(searchp, l3, (l3->free_limit +
+ freed = drain_freelist(searchp, n, (n->free_limit +
5 * searchp->num - 1) / (5 * searchp->num));
STATS_ADD_REAPED(searchp, freed);
}
@@ -4283,25 +4161,25 @@ void get_slabinfo(struct kmem_cache *cachep, struct slabinfo *sinfo)
const char *name;
char *error = NULL;
int node;
- struct kmem_list3 *l3;
+ struct kmem_cache_node *n;
active_objs = 0;
num_slabs = 0;
for_each_online_node(node) {
- l3 = cachep->nodelists[node];
- if (!l3)
+ n = cachep->node[node];
+ if (!n)
continue;
check_irq_on();
- spin_lock_irq(&l3->list_lock);
+ spin_lock_irq(&n->list_lock);
- list_for_each_entry(slabp, &l3->slabs_full, list) {
+ list_for_each_entry(slabp, &n->slabs_full, list) {
if (slabp->inuse != cachep->num && !error)
error = "slabs_full accounting error";
active_objs += cachep->num;
active_slabs++;
}
- list_for_each_entry(slabp, &l3->slabs_partial, list) {
+ list_for_each_entry(slabp, &n->slabs_partial, list) {
if (slabp->inuse == cachep->num && !error)
error = "slabs_partial inuse accounting error";
if (!slabp->inuse && !error)
@@ -4309,16 +4187,16 @@ void get_slabinfo(struct kmem_cache *cachep, struct slabinfo *sinfo)
active_objs += slabp->inuse;
active_slabs++;
}
- list_for_each_entry(slabp, &l3->slabs_free, list) {
+ list_for_each_entry(slabp, &n->slabs_free, list) {
if (slabp->inuse && !error)
error = "slabs_free/inuse accounting error";
num_slabs++;
}
- free_objects += l3->free_objects;
- if (l3->shared)
- shared_avail += l3->shared->avail;
+ free_objects += n->free_objects;
+ if (n->shared)
+ shared_avail += n->shared->avail;
- spin_unlock_irq(&l3->list_lock);
+ spin_unlock_irq(&n->list_lock);
}
num_slabs += active_slabs;
num_objs = num_slabs * cachep->num;
@@ -4344,7 +4222,7 @@ void get_slabinfo(struct kmem_cache *cachep, struct slabinfo *sinfo)
void slabinfo_show_stats(struct seq_file *m, struct kmem_cache *cachep)
{
#if STATS
- { /* list3 stats */
+ { /* node stats */
unsigned long high = cachep->high_mark;
unsigned long allocs = cachep->num_allocations;
unsigned long grown = cachep->grown;
@@ -4497,9 +4375,9 @@ static int leaks_show(struct seq_file *m, void *p)
{
struct kmem_cache *cachep = list_entry(p, struct kmem_cache, list);
struct slab *slabp;
- struct kmem_list3 *l3;
+ struct kmem_cache_node *n;
const char *name;
- unsigned long *n = m->private;
+ unsigned long *x = m->private;
int node;
int i;
@@ -4510,43 +4388,43 @@ static int leaks_show(struct seq_file *m, void *p)
/* OK, we can do it */
- n[1] = 0;
+ x[1] = 0;
for_each_online_node(node) {
- l3 = cachep->nodelists[node];
- if (!l3)
+ n = cachep->node[node];
+ if (!n)
continue;
check_irq_on();
- spin_lock_irq(&l3->list_lock);
+ spin_lock_irq(&n->list_lock);
- list_for_each_entry(slabp, &l3->slabs_full, list)
- handle_slab(n, cachep, slabp);
- list_for_each_entry(slabp, &l3->slabs_partial, list)
- handle_slab(n, cachep, slabp);
- spin_unlock_irq(&l3->list_lock);
+ list_for_each_entry(slabp, &n->slabs_full, list)
+ handle_slab(x, cachep, slabp);
+ list_for_each_entry(slabp, &n->slabs_partial, list)
+ handle_slab(x, cachep, slabp);
+ spin_unlock_irq(&n->list_lock);
}
name = cachep->name;
- if (n[0] == n[1]) {
+ if (x[0] == x[1]) {
/* Increase the buffer size */
mutex_unlock(&slab_mutex);
- m->private = kzalloc(n[0] * 4 * sizeof(unsigned long), GFP_KERNEL);
+ m->private = kzalloc(x[0] * 4 * sizeof(unsigned long), GFP_KERNEL);
if (!m->private) {
/* Too bad, we are really out */
- m->private = n;
+ m->private = x;
mutex_lock(&slab_mutex);
return -ENOMEM;
}
- *(unsigned long *)m->private = n[0] * 2;
- kfree(n);
+ *(unsigned long *)m->private = x[0] * 2;
+ kfree(x);
mutex_lock(&slab_mutex);
/* Now make sure this entry will be retried */
m->count = m->size;
return 0;
}
- for (i = 0; i < n[1]; i++) {
- seq_printf(m, "%s: %lu ", name, n[2*i+3]);
- show_symbol(m, n[2*i+2]);
+ for (i = 0; i < x[1]; i++) {
+ seq_printf(m, "%s: %lu ", name, x[2*i+3]);
+ show_symbol(m, x[2*i+2]);
seq_putc(m, '\n');
}
diff --git a/mm/slab.h b/mm/slab.h
index 34a98d642196..f96b49e4704e 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -16,7 +16,7 @@ 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 */
+ PARTIAL_NODE, /* SLAB: kmalloc size for node struct available */
UP, /* Slab caches usable but not all extras yet */
FULL /* Everything is working */
};
@@ -35,6 +35,15 @@ extern struct kmem_cache *kmem_cache;
unsigned long calculate_alignment(unsigned long flags,
unsigned long align, unsigned long size);
+#ifndef CONFIG_SLOB
+/* Kmalloc array related functions */
+void create_kmalloc_caches(unsigned long);
+
+/* Find the kmalloc slab corresponding for a certain size */
+struct kmem_cache *kmalloc_slab(size_t, gfp_t);
+#endif
+
+
/* Functions provided by the slab allocators */
extern int __kmem_cache_create(struct kmem_cache *, unsigned long flags);
@@ -230,3 +239,35 @@ static inline struct kmem_cache *cache_from_obj(struct kmem_cache *s, void *x)
return s;
}
#endif
+
+
+/*
+ * The slab lists for all objects.
+ */
+struct kmem_cache_node {
+ spinlock_t list_lock;
+
+#ifdef CONFIG_SLAB
+ struct list_head slabs_partial; /* partial list first, better asm code */
+ struct list_head slabs_full;
+ struct list_head slabs_free;
+ unsigned long free_objects;
+ unsigned int free_limit;
+ unsigned int colour_next; /* Per-node cache coloring */
+ struct array_cache *shared; /* shared per node */
+ struct array_cache **alien; /* on other nodes */
+ unsigned long next_reap; /* updated without locking */
+ int free_touched; /* updated without locking */
+#endif
+
+#ifdef CONFIG_SLUB
+ unsigned long nr_partial;
+ struct list_head partial;
+#ifdef CONFIG_SLUB_DEBUG
+ atomic_long_t nr_slabs;
+ atomic_long_t total_objects;
+ struct list_head full;
+#endif
+#endif
+
+};
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 3f3cd97d3fdf..ff3218a0f5e1 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -299,7 +299,7 @@ void __init create_boot_cache(struct kmem_cache *s, const char *name, size_t siz
err = __kmem_cache_create(s, flags);
if (err)
- panic("Creation of kmalloc slab %s size=%zd failed. Reason %d\n",
+ panic("Creation of kmalloc slab %s size=%zu failed. Reason %d\n",
name, size, err);
s->refcount = -1; /* Exempt from merging for now */
@@ -319,6 +319,178 @@ struct kmem_cache *__init create_kmalloc_cache(const char *name, size_t size,
return s;
}
+struct kmem_cache *kmalloc_caches[KMALLOC_SHIFT_HIGH + 1];
+EXPORT_SYMBOL(kmalloc_caches);
+
+#ifdef CONFIG_ZONE_DMA
+struct kmem_cache *kmalloc_dma_caches[KMALLOC_SHIFT_HIGH + 1];
+EXPORT_SYMBOL(kmalloc_dma_caches);
+#endif
+
+/*
+ * Conversion table for small slabs sizes / 8 to the index in the
+ * kmalloc array. This is necessary for slabs < 192 since we have non power
+ * of two cache sizes there. The size of larger slabs can be determined using
+ * fls.
+ */
+static s8 size_index[24] = {
+ 3, /* 8 */
+ 4, /* 16 */
+ 5, /* 24 */
+ 5, /* 32 */
+ 6, /* 40 */
+ 6, /* 48 */
+ 6, /* 56 */
+ 6, /* 64 */
+ 1, /* 72 */
+ 1, /* 80 */
+ 1, /* 88 */
+ 1, /* 96 */
+ 7, /* 104 */
+ 7, /* 112 */
+ 7, /* 120 */
+ 7, /* 128 */
+ 2, /* 136 */
+ 2, /* 144 */
+ 2, /* 152 */
+ 2, /* 160 */
+ 2, /* 168 */
+ 2, /* 176 */
+ 2, /* 184 */
+ 2 /* 192 */
+};
+
+static inline int size_index_elem(size_t bytes)
+{
+ return (bytes - 1) / 8;
+}
+
+/*
+ * Find the kmem_cache structure that serves a given size of
+ * allocation
+ */
+struct kmem_cache *kmalloc_slab(size_t size, gfp_t flags)
+{
+ int index;
+
+ if (WARN_ON_ONCE(size > KMALLOC_MAX_SIZE))
+ return NULL;
+
+ if (size <= 192) {
+ if (!size)
+ return ZERO_SIZE_PTR;
+
+ index = size_index[size_index_elem(size)];
+ } else
+ index = fls(size - 1);
+
+#ifdef CONFIG_ZONE_DMA
+ if (unlikely((flags & GFP_DMA)))
+ return kmalloc_dma_caches[index];
+
+#endif
+ return kmalloc_caches[index];
+}
+
+/*
+ * Create the kmalloc array. Some of the regular kmalloc arrays
+ * may already have been created because they were needed to
+ * enable allocations for slab creation.
+ */
+void __init create_kmalloc_caches(unsigned long flags)
+{
+ int i;
+
+ /*
+ * Patch up the size_index table if we have strange large alignment
+ * requirements for the kmalloc array. This is only the case for
+ * MIPS it seems. The standard arches will not generate any code here.
+ *
+ * Largest permitted alignment is 256 bytes due to the way we
+ * handle the index determination for the smaller caches.
+ *
+ * Make sure that nothing crazy happens if someone starts tinkering
+ * around with ARCH_KMALLOC_MINALIGN
+ */
+ BUILD_BUG_ON(KMALLOC_MIN_SIZE > 256 ||
+ (KMALLOC_MIN_SIZE & (KMALLOC_MIN_SIZE - 1)));
+
+ for (i = 8; i < KMALLOC_MIN_SIZE; i += 8) {
+ int elem = size_index_elem(i);
+
+ if (elem >= ARRAY_SIZE(size_index))
+ break;
+ size_index[elem] = KMALLOC_SHIFT_LOW;
+ }
+
+ if (KMALLOC_MIN_SIZE >= 64) {
+ /*
+ * The 96 byte size cache is not used if the alignment
+ * is 64 byte.
+ */
+ for (i = 64 + 8; i <= 96; i += 8)
+ size_index[size_index_elem(i)] = 7;
+
+ }
+
+ if (KMALLOC_MIN_SIZE >= 128) {
+ /*
+ * The 192 byte sized cache is not used if the alignment
+ * is 128 byte. Redirect kmalloc to use the 256 byte cache
+ * instead.
+ */
+ for (i = 128 + 8; i <= 192; i += 8)
+ size_index[size_index_elem(i)] = 8;
+ }
+ for (i = KMALLOC_SHIFT_LOW; i <= KMALLOC_SHIFT_HIGH; i++) {
+ if (!kmalloc_caches[i]) {
+ kmalloc_caches[i] = create_kmalloc_cache(NULL,
+ 1 << i, flags);
+ }
+
+ /*
+ * Caches that are not of the two-to-the-power-of size.
+ * These have to be created immediately after the
+ * earlier power of two caches
+ */
+ if (KMALLOC_MIN_SIZE <= 32 && !kmalloc_caches[1] && i == 6)
+ kmalloc_caches[1] = create_kmalloc_cache(NULL, 96, flags);
+
+ if (KMALLOC_MIN_SIZE <= 64 && !kmalloc_caches[2] && i == 7)
+ kmalloc_caches[2] = create_kmalloc_cache(NULL, 192, flags);
+ }
+
+ /* Kmalloc array is now usable */
+ slab_state = UP;
+
+ for (i = 0; i <= KMALLOC_SHIFT_HIGH; i++) {
+ struct kmem_cache *s = kmalloc_caches[i];
+ char *n;
+
+ if (s) {
+ n = kasprintf(GFP_NOWAIT, "kmalloc-%d", kmalloc_size(i));
+
+ BUG_ON(!n);
+ s->name = n;
+ }
+ }
+
+#ifdef CONFIG_ZONE_DMA
+ for (i = 0; i <= KMALLOC_SHIFT_HIGH; i++) {
+ struct kmem_cache *s = kmalloc_caches[i];
+
+ if (s) {
+ int size = kmalloc_size(i);
+ char *n = kasprintf(GFP_NOWAIT,
+ "dma-kmalloc-%d", size);
+
+ BUG_ON(!n);
+ kmalloc_dma_caches[i] = create_kmalloc_cache(n,
+ size, SLAB_CACHE_DMA | flags);
+ }
+ }
+#endif
+}
#endif /* !CONFIG_SLOB */
diff --git a/mm/slub.c b/mm/slub.c
index a0206df88aba..57707f01bcfb 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1006,7 +1006,7 @@ static inline void inc_slabs_node(struct kmem_cache *s, int node, int objects)
* dilemma by deferring the increment of the count during
* bootstrap (see early_kmem_cache_node_alloc).
*/
- if (n) {
+ if (likely(n)) {
atomic_long_inc(&n->nr_slabs);
atomic_long_add(objects, &n->total_objects);
}
@@ -1494,7 +1494,7 @@ static inline void remove_partial(struct kmem_cache_node *n,
*/
static inline void *acquire_slab(struct kmem_cache *s,
struct kmem_cache_node *n, struct page *page,
- int mode)
+ int mode, int *objects)
{
void *freelist;
unsigned long counters;
@@ -1508,6 +1508,7 @@ static inline void *acquire_slab(struct kmem_cache *s,
freelist = page->freelist;
counters = page->counters;
new.counters = counters;
+ *objects = new.objects - new.inuse;
if (mode) {
new.inuse = page->objects;
new.freelist = NULL;
@@ -1529,7 +1530,7 @@ static inline void *acquire_slab(struct kmem_cache *s,
return freelist;
}
-static int put_cpu_partial(struct kmem_cache *s, struct page *page, int drain);
+static void put_cpu_partial(struct kmem_cache *s, struct page *page, int drain);
static inline bool pfmemalloc_match(struct page *page, gfp_t gfpflags);
/*
@@ -1540,6 +1541,8 @@ static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n,
{
struct page *page, *page2;
void *object = NULL;
+ int available = 0;
+ int objects;
/*
* Racy check. If we mistakenly see no partial slabs then we
@@ -1553,22 +1556,21 @@ static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n,
spin_lock(&n->list_lock);
list_for_each_entry_safe(page, page2, &n->partial, lru) {
void *t;
- int available;
if (!pfmemalloc_match(page, flags))
continue;
- t = acquire_slab(s, n, page, object == NULL);
+ t = acquire_slab(s, n, page, object == NULL, &objects);
if (!t)
break;
+ available += objects;
if (!object) {
c->page = page;
stat(s, ALLOC_FROM_PARTIAL);
object = t;
- available = page->objects - page->inuse;
} else {
- available = put_cpu_partial(s, page, 0);
+ put_cpu_partial(s, page, 0);
stat(s, CPU_PARTIAL_NODE);
}
if (kmem_cache_debug(s) || available > s->cpu_partial / 2)
@@ -1947,7 +1949,7 @@ static void unfreeze_partials(struct kmem_cache *s,
* If we did not find a slot then simply move all the partials to the
* per node partial list.
*/
-static int put_cpu_partial(struct kmem_cache *s, struct page *page, int drain)
+static void put_cpu_partial(struct kmem_cache *s, struct page *page, int drain)
{
struct page *oldpage;
int pages;
@@ -1985,7 +1987,6 @@ static int put_cpu_partial(struct kmem_cache *s, struct page *page, int drain)
page->next = oldpage;
} while (this_cpu_cmpxchg(s->cpu_slab->partial, oldpage, page) != oldpage);
- return pobjects;
}
static inline void flush_slab(struct kmem_cache *s, struct kmem_cache_cpu *c)
@@ -2042,7 +2043,7 @@ static void flush_all(struct kmem_cache *s)
static inline int node_match(struct page *page, int node)
{
#ifdef CONFIG_NUMA
- if (node != NUMA_NO_NODE && page_to_nid(page) != node)
+ if (!page || (node != NUMA_NO_NODE && page_to_nid(page) != node))
return 0;
#endif
return 1;
@@ -2332,13 +2333,18 @@ static __always_inline void *slab_alloc_node(struct kmem_cache *s,
s = memcg_kmem_get_cache(s, gfpflags);
redo:
-
/*
* Must read kmem_cache cpu data via this cpu ptr. Preemption is
* enabled. We may switch back and forth between cpus while
* reading from one cpu area. That does not matter as long
* as we end up on the original cpu again when doing the cmpxchg.
+ *
+ * Preemption is disabled for the retrieval of the tid because that
+ * must occur from the current processor. We cannot allow rescheduling
+ * on a different processor between the determination of the pointer
+ * and the retrieval of the tid.
*/
+ preempt_disable();
c = __this_cpu_ptr(s->cpu_slab);
/*
@@ -2348,7 +2354,7 @@ redo:
* linked list in between.
*/
tid = c->tid;
- barrier();
+ preempt_enable();
object = c->freelist;
page = c->page;
@@ -2595,10 +2601,11 @@ redo:
* data is retrieved via this pointer. If we are on the same cpu
* during the cmpxchg then the free will succedd.
*/
+ preempt_disable();
c = __this_cpu_ptr(s->cpu_slab);
tid = c->tid;
- barrier();
+ preempt_enable();
if (likely(page == c->page)) {
set_freepointer(s, object, c->freelist);
@@ -2776,7 +2783,7 @@ init_kmem_cache_node(struct kmem_cache_node *n)
static inline int alloc_kmem_cache_cpus(struct kmem_cache *s)
{
BUILD_BUG_ON(PERCPU_DYNAMIC_EARLY_SIZE <
- SLUB_PAGE_SHIFT * sizeof(struct kmem_cache_cpu));
+ KMALLOC_SHIFT_HIGH * sizeof(struct kmem_cache_cpu));
/*
* Must align to double word boundary for the double cmpxchg
@@ -2983,7 +2990,7 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order)
s->allocflags |= __GFP_COMP;
if (s->flags & SLAB_CACHE_DMA)
- s->allocflags |= SLUB_DMA;
+ s->allocflags |= GFP_DMA;
if (s->flags & SLAB_RECLAIM_ACCOUNT)
s->allocflags |= __GFP_RECLAIMABLE;
@@ -3175,13 +3182,6 @@ int __kmem_cache_shutdown(struct kmem_cache *s)
* Kmalloc subsystem
*******************************************************************/
-struct kmem_cache *kmalloc_caches[SLUB_PAGE_SHIFT];
-EXPORT_SYMBOL(kmalloc_caches);
-
-#ifdef CONFIG_ZONE_DMA
-static struct kmem_cache *kmalloc_dma_caches[SLUB_PAGE_SHIFT];
-#endif
-
static int __init setup_slub_min_order(char *str)
{
get_option(&str, &slub_min_order);
@@ -3218,73 +3218,15 @@ static int __init setup_slub_nomerge(char *str)
__setup("slub_nomerge", setup_slub_nomerge);
-/*
- * Conversion table for small slabs sizes / 8 to the index in the
- * kmalloc array. This is necessary for slabs < 192 since we have non power
- * of two cache sizes there. The size of larger slabs can be determined using
- * fls.
- */
-static s8 size_index[24] = {
- 3, /* 8 */
- 4, /* 16 */
- 5, /* 24 */
- 5, /* 32 */
- 6, /* 40 */
- 6, /* 48 */
- 6, /* 56 */
- 6, /* 64 */
- 1, /* 72 */
- 1, /* 80 */
- 1, /* 88 */
- 1, /* 96 */
- 7, /* 104 */
- 7, /* 112 */
- 7, /* 120 */
- 7, /* 128 */
- 2, /* 136 */
- 2, /* 144 */
- 2, /* 152 */
- 2, /* 160 */
- 2, /* 168 */
- 2, /* 176 */
- 2, /* 184 */
- 2 /* 192 */
-};
-
-static inline int size_index_elem(size_t bytes)
-{
- return (bytes - 1) / 8;
-}
-
-static struct kmem_cache *get_slab(size_t size, gfp_t flags)
-{
- int index;
-
- if (size <= 192) {
- if (!size)
- return ZERO_SIZE_PTR;
-
- index = size_index[size_index_elem(size)];
- } else
- index = fls(size - 1);
-
-#ifdef CONFIG_ZONE_DMA
- if (unlikely((flags & SLUB_DMA)))
- return kmalloc_dma_caches[index];
-
-#endif
- return kmalloc_caches[index];
-}
-
void *__kmalloc(size_t size, gfp_t flags)
{
struct kmem_cache *s;
void *ret;
- if (unlikely(size > SLUB_MAX_SIZE))
+ if (unlikely(size > KMALLOC_MAX_CACHE_SIZE))
return kmalloc_large(size, flags);
- s = get_slab(size, flags);
+ s = kmalloc_slab(size, flags);
if (unlikely(ZERO_OR_NULL_PTR(s)))
return s;
@@ -3317,7 +3259,7 @@ void *__kmalloc_node(size_t size, gfp_t flags, int node)
struct kmem_cache *s;
void *ret;
- if (unlikely(size > SLUB_MAX_SIZE)) {
+ if (unlikely(size > KMALLOC_MAX_CACHE_SIZE)) {
ret = kmalloc_large_node(size, flags, node);
trace_kmalloc_node(_RET_IP_, ret,
@@ -3327,7 +3269,7 @@ void *__kmalloc_node(size_t size, gfp_t flags, int node)
return ret;
}
- s = get_slab(size, flags);
+ s = kmalloc_slab(size, flags);
if (unlikely(ZERO_OR_NULL_PTR(s)))
return s;
@@ -3620,6 +3562,12 @@ static struct kmem_cache * __init bootstrap(struct kmem_cache *static_cache)
memcpy(s, static_cache, kmem_cache->object_size);
+ /*
+ * This runs very early, and only the boot processor is supposed to be
+ * up. Even if it weren't true, IRQs are not up so we couldn't fire
+ * IPIs around.
+ */
+ __flush_cpu_slab(s, smp_processor_id());
for_each_node_state(node, N_NORMAL_MEMORY) {
struct kmem_cache_node *n = get_node(s, node);
struct page *p;
@@ -3642,8 +3590,6 @@ void __init kmem_cache_init(void)
{
static __initdata struct kmem_cache boot_kmem_cache,
boot_kmem_cache_node;
- int i;
- int caches = 2;
if (debug_guardpage_minorder())
slub_max_order = 0;
@@ -3674,103 +3620,16 @@ void __init kmem_cache_init(void)
kmem_cache_node = bootstrap(&boot_kmem_cache_node);
/* Now we can use the kmem_cache to allocate kmalloc slabs */
-
- /*
- * Patch up the size_index table if we have strange large alignment
- * requirements for the kmalloc array. This is only the case for
- * MIPS it seems. The standard arches will not generate any code here.
- *
- * Largest permitted alignment is 256 bytes due to the way we
- * handle the index determination for the smaller caches.
- *
- * Make sure that nothing crazy happens if someone starts tinkering
- * around with ARCH_KMALLOC_MINALIGN
- */
- BUILD_BUG_ON(KMALLOC_MIN_SIZE > 256 ||
- (KMALLOC_MIN_SIZE & (KMALLOC_MIN_SIZE - 1)));
-
- for (i = 8; i < KMALLOC_MIN_SIZE; i += 8) {
- int elem = size_index_elem(i);
- if (elem >= ARRAY_SIZE(size_index))
- break;
- size_index[elem] = KMALLOC_SHIFT_LOW;
- }
-
- if (KMALLOC_MIN_SIZE == 64) {
- /*
- * The 96 byte size cache is not used if the alignment
- * is 64 byte.
- */
- for (i = 64 + 8; i <= 96; i += 8)
- size_index[size_index_elem(i)] = 7;
- } else if (KMALLOC_MIN_SIZE == 128) {
- /*
- * The 192 byte sized cache is not used if the alignment
- * is 128 byte. Redirect kmalloc to use the 256 byte cache
- * instead.
- */
- for (i = 128 + 8; i <= 192; i += 8)
- size_index[size_index_elem(i)] = 8;
- }
-
- /* Caches that are not of the two-to-the-power-of size */
- if (KMALLOC_MIN_SIZE <= 32) {
- kmalloc_caches[1] = create_kmalloc_cache("kmalloc-96", 96, 0);
- caches++;
- }
-
- if (KMALLOC_MIN_SIZE <= 64) {
- kmalloc_caches[2] = create_kmalloc_cache("kmalloc-192", 192, 0);
- caches++;
- }
-
- for (i = KMALLOC_SHIFT_LOW; i < SLUB_PAGE_SHIFT; i++) {
- kmalloc_caches[i] = create_kmalloc_cache("kmalloc", 1 << i, 0);
- caches++;
- }
-
- slab_state = UP;
-
- /* Provide the correct kmalloc names now that the caches are up */
- if (KMALLOC_MIN_SIZE <= 32) {
- kmalloc_caches[1]->name = kstrdup(kmalloc_caches[1]->name, GFP_NOWAIT);
- BUG_ON(!kmalloc_caches[1]->name);
- }
-
- if (KMALLOC_MIN_SIZE <= 64) {
- kmalloc_caches[2]->name = kstrdup(kmalloc_caches[2]->name, GFP_NOWAIT);
- BUG_ON(!kmalloc_caches[2]->name);
- }
-
- for (i = KMALLOC_SHIFT_LOW; i < SLUB_PAGE_SHIFT; i++) {
- char *s = kasprintf(GFP_NOWAIT, "kmalloc-%d", 1 << i);
-
- BUG_ON(!s);
- kmalloc_caches[i]->name = s;
- }
+ create_kmalloc_caches(0);
#ifdef CONFIG_SMP
register_cpu_notifier(&slab_notifier);
#endif
-#ifdef CONFIG_ZONE_DMA
- for (i = 0; i < SLUB_PAGE_SHIFT; i++) {
- struct kmem_cache *s = kmalloc_caches[i];
-
- if (s && s->size) {
- char *name = kasprintf(GFP_NOWAIT,
- "dma-kmalloc-%d", s->object_size);
-
- BUG_ON(!name);
- kmalloc_dma_caches[i] = create_kmalloc_cache(name,
- s->object_size, SLAB_CACHE_DMA);
- }
- }
-#endif
printk(KERN_INFO
- "SLUB: Genslabs=%d, HWalign=%d, Order=%d-%d, MinObjects=%d,"
+ "SLUB: HWalign=%d, Order=%d-%d, MinObjects=%d,"
" CPUs=%d, Nodes=%d\n",
- caches, cache_line_size(),
+ cache_line_size(),
slub_min_order, slub_max_order, slub_min_objects,
nr_cpu_ids, nr_node_ids);
}
@@ -3933,10 +3792,10 @@ void *__kmalloc_track_caller(size_t size, gfp_t gfpflags, unsigned long caller)
struct kmem_cache *s;
void *ret;
- if (unlikely(size > SLUB_MAX_SIZE))
+ if (unlikely(size > KMALLOC_MAX_CACHE_SIZE))
return kmalloc_large(size, gfpflags);
- s = get_slab(size, gfpflags);
+ s = kmalloc_slab(size, gfpflags);
if (unlikely(ZERO_OR_NULL_PTR(s)))
return s;
@@ -3956,7 +3815,7 @@ void *__kmalloc_node_track_caller(size_t size, gfp_t gfpflags,
struct kmem_cache *s;
void *ret;
- if (unlikely(size > SLUB_MAX_SIZE)) {
+ if (unlikely(size > KMALLOC_MAX_CACHE_SIZE)) {
ret = kmalloc_large_node(size, gfpflags, node);
trace_kmalloc_node(caller, ret,
@@ -3966,7 +3825,7 @@ void *__kmalloc_node_track_caller(size_t size, gfp_t gfpflags,
return ret;
}
- s = get_slab(size, gfpflags);
+ s = kmalloc_slab(size, gfpflags);
if (unlikely(ZERO_OR_NULL_PTR(s)))
return s;
@@ -4315,7 +4174,7 @@ static void resiliency_test(void)
{
u8 *p;
- BUILD_BUG_ON(KMALLOC_MIN_SIZE > 16 || SLUB_PAGE_SHIFT < 10);
+ BUILD_BUG_ON(KMALLOC_MIN_SIZE > 16 || KMALLOC_SHIFT_HIGH < 10);
printk(KERN_ERR "SLUB resiliency testing\n");
printk(KERN_ERR "-----------------------\n");
diff --git a/mm/swap.c b/mm/swap.c
index acd40bfffa82..dfd7d71d6841 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -30,6 +30,7 @@
#include <linux/backing-dev.h>
#include <linux/memcontrol.h>
#include <linux/gfp.h>
+#include <linux/uio.h>
#include "internal.h"
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index b12fd8612604..d365724feb05 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -1522,6 +1522,8 @@ static void __vunmap(const void *addr, int deallocate_pages)
* Must not be called in NMI context (strictly speaking, only if we don't
* have CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG, but making the calling
* conventions for vfree() arch-depenedent would be a really bad idea)
+ *
+ * NOTE: assumes that the object at *addr has a size >= sizeof(llist_node)
*
*/
void vfree(const void *addr)
generated by cgit v1.2.3 (git 2.0.4) at 2025-12-13 03:26:37 +0000