summaryrefslogtreecommitdiff
path: root/mm
diff options
context:
space:
mode:
Diffstat (limited to 'mm')
-rw-r--r--mm/Kconfig18
-rw-r--r--mm/Makefile1
-rw-r--r--mm/bounce.c287
-rw-r--r--mm/compaction.c22
-rw-r--r--mm/filemap.c56
-rw-r--r--mm/huge_memory.c13
-rw-r--r--mm/hugetlb.c20
-rw-r--r--mm/kmemleak.c4
-rw-r--r--mm/madvise.c2
-rw-r--r--mm/memblock.c205
-rw-r--r--mm/memcontrol.c47
-rw-r--r--mm/memory-failure.c17
-rw-r--r--mm/memory.c58
-rw-r--r--mm/mremap.c9
-rw-r--r--mm/page-writeback.c6
-rw-r--r--mm/percpu.c2
-rw-r--r--mm/slab.c6
-rw-r--r--mm/slab.h1
-rw-r--r--mm/slab_common.c13
-rw-r--r--mm/slub.c41
-rw-r--r--mm/truncate.c8
-rw-r--r--mm/util.c10
-rw-r--r--mm/vmacache.c8
-rw-r--r--mm/vmscan.c20
24 files changed, 375 insertions, 499 deletions
diff --git a/mm/Kconfig b/mm/Kconfig
index ebe5880c29d6..28cec518f4d4 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -134,6 +134,9 @@ config HAVE_MEMBLOCK
config HAVE_MEMBLOCK_NODE_MAP
boolean
+config HAVE_MEMBLOCK_PHYS_MAP
+ boolean
+
config ARCH_DISCARD_MEMBLOCK
boolean
@@ -581,3 +584,18 @@ config PGTABLE_MAPPING
config GENERIC_EARLY_IOREMAP
bool
+
+config MAX_STACK_SIZE_MB
+ int "Maximum user stack size for 32-bit processes (MB)"
+ default 80
+ range 8 256 if METAG
+ range 8 2048
+ depends on STACK_GROWSUP && (!64BIT || COMPAT)
+ help
+ This is the maximum stack size in Megabytes in the VM layout of 32-bit
+ user processes when the stack grows upwards (currently only on parisc
+ and metag arch). The stack will be located at the highest memory
+ address minus the given value, unless the RLIMIT_STACK hard limit is
+ changed to a smaller value in which case that is used.
+
+ A sane initial value is 80 MB.
diff --git a/mm/Makefile b/mm/Makefile
index b484452dac57..0173940407f6 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -30,7 +30,6 @@ endif
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_ZSWAP) += zswap.o
diff --git a/mm/bounce.c b/mm/bounce.c
deleted file mode 100644
index 523918b8c6dc..000000000000
--- a/mm/bounce.c
+++ /dev/null
@@ -1,287 +0,0 @@
-/* bounce buffer handling for block devices
- *
- * - Split from highmem.c
- */
-
-#include <linux/mm.h>
-#include <linux/export.h>
-#include <linux/swap.h>
-#include <linux/gfp.h>
-#include <linux/bio.h>
-#include <linux/pagemap.h>
-#include <linux/mempool.h>
-#include <linux/blkdev.h>
-#include <linux/init.h>
-#include <linux/hash.h>
-#include <linux/highmem.h>
-#include <linux/bootmem.h>
-#include <asm/tlbflush.h>
-
-#include <trace/events/block.h>
-
-#define POOL_SIZE 64
-#define ISA_POOL_SIZE 16
-
-static mempool_t *page_pool, *isa_page_pool;
-
-#if defined(CONFIG_HIGHMEM) || defined(CONFIG_NEED_BOUNCE_POOL)
-static __init int init_emergency_pool(void)
-{
-#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("bounce pool size: %d pages\n", POOL_SIZE);
-
- return 0;
-}
-
-__initcall(init_emergency_pool);
-#endif
-
-#ifdef CONFIG_HIGHMEM
-/*
- * highmem version, map in to vec
- */
-static void bounce_copy_vec(struct bio_vec *to, unsigned char *vfrom)
-{
- unsigned long flags;
- unsigned char *vto;
-
- local_irq_save(flags);
- vto = kmap_atomic(to->bv_page);
- memcpy(vto + to->bv_offset, vfrom, to->bv_len);
- kunmap_atomic(vto);
- local_irq_restore(flags);
-}
-
-#else /* CONFIG_HIGHMEM */
-
-#define bounce_copy_vec(to, vfrom) \
- memcpy(page_address((to)->bv_page) + (to)->bv_offset, vfrom, (to)->bv_len)
-
-#endif /* CONFIG_HIGHMEM */
-
-/*
- * allocate pages in the DMA region for the ISA pool
- */
-static void *mempool_alloc_pages_isa(gfp_t gfp_mask, void *data)
-{
- return mempool_alloc_pages(gfp_mask | GFP_DMA, data);
-}
-
-/*
- * gets called "every" time someone init's a queue with BLK_BOUNCE_ISA
- * as the max address, so check if the pool has already been created.
- */
-int init_emergency_isa_pool(void)
-{
- if (isa_page_pool)
- return 0;
-
- isa_page_pool = mempool_create(ISA_POOL_SIZE, mempool_alloc_pages_isa,
- mempool_free_pages, (void *) 0);
- BUG_ON(!isa_page_pool);
-
- printk("isa bounce pool size: %d pages\n", ISA_POOL_SIZE);
- return 0;
-}
-
-/*
- * Simple bounce buffer support for highmem pages. Depending on the
- * queue gfp mask set, *to may or may not be a highmem page. kmap it
- * always, it will do the Right Thing
- */
-static void copy_to_high_bio_irq(struct bio *to, struct bio *from)
-{
- unsigned char *vfrom;
- struct bio_vec tovec, *fromvec = from->bi_io_vec;
- struct bvec_iter iter;
-
- bio_for_each_segment(tovec, to, iter) {
- if (tovec.bv_page != fromvec->bv_page) {
- /*
- * fromvec->bv_offset and fromvec->bv_len might have
- * been modified by the block layer, so use the original
- * copy, bounce_copy_vec already uses tovec->bv_len
- */
- vfrom = page_address(fromvec->bv_page) +
- tovec.bv_offset;
-
- bounce_copy_vec(&tovec, vfrom);
- flush_dcache_page(tovec.bv_page);
- }
-
- fromvec++;
- }
-}
-
-static void bounce_end_io(struct bio *bio, mempool_t *pool, int err)
-{
- struct bio *bio_orig = bio->bi_private;
- struct bio_vec *bvec, *org_vec;
- int i;
-
- if (test_bit(BIO_EOPNOTSUPP, &bio->bi_flags))
- set_bit(BIO_EOPNOTSUPP, &bio_orig->bi_flags);
-
- /*
- * free up bounce indirect pages used
- */
- 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;
-
- dec_zone_page_state(bvec->bv_page, NR_BOUNCE);
- mempool_free(bvec->bv_page, pool);
- }
-
- bio_endio(bio_orig, err);
- bio_put(bio);
-}
-
-static void bounce_end_io_write(struct bio *bio, int err)
-{
- bounce_end_io(bio, page_pool, err);
-}
-
-static void bounce_end_io_write_isa(struct bio *bio, int err)
-{
-
- bounce_end_io(bio, isa_page_pool, err);
-}
-
-static void __bounce_end_io_read(struct bio *bio, mempool_t *pool, int err)
-{
- struct bio *bio_orig = bio->bi_private;
-
- if (test_bit(BIO_UPTODATE, &bio->bi_flags))
- copy_to_high_bio_irq(bio_orig, bio);
-
- bounce_end_io(bio, pool, err);
-}
-
-static void bounce_end_io_read(struct bio *bio, int err)
-{
- __bounce_end_io_read(bio, page_pool, err);
-}
-
-static void bounce_end_io_read_isa(struct bio *bio, int err)
-{
- __bounce_end_io_read(bio, isa_page_pool, err);
-}
-
-#ifdef CONFIG_NEED_BOUNCE_POOL
-static int must_snapshot_stable_pages(struct request_queue *q, struct bio *bio)
-{
- if (bio_data_dir(bio) != WRITE)
- return 0;
-
- if (!bdi_cap_stable_pages_required(&q->backing_dev_info))
- return 0;
-
- return test_bit(BIO_SNAP_STABLE, &bio->bi_flags);
-}
-#else
-static int must_snapshot_stable_pages(struct request_queue *q, struct bio *bio)
-{
- return 0;
-}
-#endif /* CONFIG_NEED_BOUNCE_POOL */
-
-static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig,
- mempool_t *pool, int force)
-{
- struct bio *bio;
- int rw = bio_data_dir(*bio_orig);
- struct bio_vec *to, from;
- struct bvec_iter iter;
- unsigned i;
-
- if (force)
- goto bounce;
- bio_for_each_segment(from, *bio_orig, iter)
- if (page_to_pfn(from.bv_page) > queue_bounce_pfn(q))
- goto bounce;
-
- return;
-bounce:
- bio = bio_clone_bioset(*bio_orig, GFP_NOIO, fs_bio_set);
-
- bio_for_each_segment_all(to, bio, i) {
- struct page *page = to->bv_page;
-
- if (page_to_pfn(page) <= queue_bounce_pfn(q) && !force)
- continue;
-
- 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(page);
-
- vto = page_address(to->bv_page) + to->bv_offset;
- vfrom = kmap_atomic(page) + to->bv_offset;
- memcpy(vto, vfrom, to->bv_len);
- kunmap_atomic(vfrom);
- }
- }
-
- trace_block_bio_bounce(q, *bio_orig);
-
- bio->bi_flags |= (1 << BIO_BOUNCED);
-
- if (pool == page_pool) {
- bio->bi_end_io = bounce_end_io_write;
- if (rw == READ)
- bio->bi_end_io = bounce_end_io_read;
- } else {
- bio->bi_end_io = bounce_end_io_write_isa;
- if (rw == READ)
- bio->bi_end_io = bounce_end_io_read_isa;
- }
-
- bio->bi_private = *bio_orig;
- *bio_orig = bio;
-}
-
-void blk_queue_bounce(struct request_queue *q, struct bio **bio_orig)
-{
- int must_bounce;
- mempool_t *pool;
-
- /*
- * Data-less bio, nothing to bounce
- */
- if (!bio_has_data(*bio_orig))
- return;
-
- must_bounce = must_snapshot_stable_pages(q, *bio_orig);
-
- /*
- * for non-isa bounce case, just check if the bounce pfn is equal
- * to or bigger than the highest pfn in the system -- in that case,
- * don't waste time iterating over bio segments
- */
- if (!(q->bounce_gfp & GFP_DMA)) {
- if (queue_bounce_pfn(q) >= blk_max_pfn && !must_bounce)
- return;
- pool = page_pool;
- } else {
- BUG_ON(!isa_page_pool);
- pool = isa_page_pool;
- }
-
- /*
- * slow path
- */
- __blk_queue_bounce(q, bio_orig, pool, must_bounce);
-}
-
-EXPORT_SYMBOL(blk_queue_bounce);
diff --git a/mm/compaction.c b/mm/compaction.c
index 37f976287068..627dc2e4320f 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -671,16 +671,20 @@ static void isolate_freepages(struct zone *zone,
struct compact_control *cc)
{
struct page *page;
- unsigned long high_pfn, low_pfn, pfn, z_end_pfn, end_pfn;
+ unsigned long high_pfn, low_pfn, pfn, z_end_pfn;
int nr_freepages = cc->nr_freepages;
struct list_head *freelist = &cc->freepages;
/*
* Initialise the free scanner. The starting point is where we last
- * scanned from (or the end of the zone if starting). The low point
- * is the end of the pageblock the migration scanner is using.
+ * successfully isolated from, zone-cached value, or the end of the
+ * zone when isolating for the first time. We need this aligned to
+ * the pageblock boundary, because we do pfn -= pageblock_nr_pages
+ * in the for loop.
+ * The low boundary is the end of the pageblock the migration scanner
+ * is using.
*/
- pfn = cc->free_pfn;
+ pfn = cc->free_pfn & ~(pageblock_nr_pages-1);
low_pfn = ALIGN(cc->migrate_pfn + 1, pageblock_nr_pages);
/*
@@ -700,6 +704,7 @@ static void isolate_freepages(struct zone *zone,
for (; pfn >= low_pfn && cc->nr_migratepages > nr_freepages;
pfn -= pageblock_nr_pages) {
unsigned long isolated;
+ unsigned long end_pfn;
/*
* This can iterate a massively long zone without finding any
@@ -734,13 +739,10 @@ static void isolate_freepages(struct zone *zone,
isolated = 0;
/*
- * As pfn may not start aligned, pfn+pageblock_nr_page
- * may cross a MAX_ORDER_NR_PAGES boundary and miss
- * a pfn_valid check. Ensure isolate_freepages_block()
- * only scans within a pageblock
+ * Take care when isolating in last pageblock of a zone which
+ * ends in the middle of a pageblock.
*/
- end_pfn = ALIGN(pfn + 1, pageblock_nr_pages);
- end_pfn = min(end_pfn, z_end_pfn);
+ end_pfn = min(pfn + pageblock_nr_pages, z_end_pfn);
isolated = isolate_freepages_block(cc, pfn, end_pfn,
freelist, false);
nr_freepages += isolated;
diff --git a/mm/filemap.c b/mm/filemap.c
index c73535c914cc..021056c324e6 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -257,9 +257,11 @@ static int filemap_check_errors(struct address_space *mapping)
{
int ret = 0;
/* Check for outstanding write errors */
- if (test_and_clear_bit(AS_ENOSPC, &mapping->flags))
+ if (test_bit(AS_ENOSPC, &mapping->flags) &&
+ test_and_clear_bit(AS_ENOSPC, &mapping->flags))
ret = -ENOSPC;
- if (test_and_clear_bit(AS_EIO, &mapping->flags))
+ if (test_bit(AS_EIO, &mapping->flags) &&
+ test_and_clear_bit(AS_EIO, &mapping->flags))
ret = -EIO;
return ret;
}
@@ -906,8 +908,8 @@ EXPORT_SYMBOL(page_cache_prev_hole);
* Looks up the page cache slot at @mapping & @offset. If there is a
* page cache page, it is returned with an increased refcount.
*
- * If the slot holds a shadow entry of a previously evicted page, it
- * is returned.
+ * If the slot holds a shadow entry of a previously evicted page, or a
+ * swap entry from shmem/tmpfs, it is returned.
*
* Otherwise, %NULL is returned.
*/
@@ -928,9 +930,9 @@ repeat:
if (radix_tree_deref_retry(page))
goto repeat;
/*
- * Otherwise, shmem/tmpfs must be storing a swap entry
- * here as an exceptional entry: so return it without
- * attempting to raise page count.
+ * A shadow entry of a recently evicted page,
+ * or a swap entry from shmem/tmpfs. Return
+ * it without attempting to raise page count.
*/
goto out;
}
@@ -983,8 +985,8 @@ EXPORT_SYMBOL(find_get_page);
* page cache page, it is returned locked and with an increased
* refcount.
*
- * If the slot holds a shadow entry of a previously evicted page, it
- * is returned.
+ * If the slot holds a shadow entry of a previously evicted page, or a
+ * swap entry from shmem/tmpfs, it is returned.
*
* Otherwise, %NULL is returned.
*
@@ -1099,8 +1101,8 @@ EXPORT_SYMBOL(find_or_create_page);
* with ascending indexes. There may be holes in the indices due to
* not-present pages.
*
- * Any shadow entries of evicted pages are included in the returned
- * array.
+ * Any shadow entries of evicted pages, or swap entries from
+ * shmem/tmpfs, are included in the returned array.
*
* find_get_entries() returns the number of pages and shadow entries
* which were found.
@@ -1128,9 +1130,9 @@ repeat:
if (radix_tree_deref_retry(page))
goto restart;
/*
- * Otherwise, we must be storing a swap entry
- * here as an exceptional entry: so return it
- * without attempting to raise page count.
+ * A shadow entry of a recently evicted page,
+ * or a swap entry from shmem/tmpfs. Return
+ * it without attempting to raise page count.
*/
goto export;
}
@@ -1198,9 +1200,9 @@ repeat:
goto restart;
}
/*
- * Otherwise, shmem/tmpfs must be storing a swap entry
- * here as an exceptional entry: so skip over it -
- * we only reach this from invalidate_mapping_pages().
+ * A shadow entry of a recently evicted page,
+ * or a swap entry from shmem/tmpfs. Skip
+ * over it.
*/
continue;
}
@@ -1265,9 +1267,9 @@ repeat:
goto restart;
}
/*
- * Otherwise, shmem/tmpfs must be storing a swap entry
- * here as an exceptional entry: so stop looking for
- * contiguous pages.
+ * A shadow entry of a recently evicted page,
+ * or a swap entry from shmem/tmpfs. Stop
+ * looking for contiguous pages.
*/
break;
}
@@ -1341,10 +1343,17 @@ repeat:
goto restart;
}
/*
- * This function is never used on a shmem/tmpfs
- * mapping, so a swap entry won't be found here.
+ * A shadow entry of a recently evicted page.
+ *
+ * Those entries should never be tagged, but
+ * this tree walk is lockless and the tags are
+ * looked up in bulk, one radix tree node at a
+ * time, so there is a sizable window for page
+ * reclaim to evict a page we saw tagged.
+ *
+ * Skip over it.
*/
- BUG();
+ continue;
}
if (!page_cache_get_speculative(page))
@@ -2581,7 +2590,6 @@ EXPORT_SYMBOL(generic_perform_write);
* @iocb: IO state structure (file, offset, etc.)
* @iov: vector with data to write
* @nr_segs: number of segments in the vector
- * @ppos: position where to write
*
* This function does all the work needed for actually writing data to a
* file. It does all basic checks, removes SUID from the file, updates
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 64635f5278ff..b4b1feba6472 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1536,16 +1536,23 @@ pmd_t *page_check_address_pmd(struct page *page,
enum page_check_address_pmd_flag flag,
spinlock_t **ptl)
{
+ pgd_t *pgd;
+ pud_t *pud;
pmd_t *pmd;
if (address & ~HPAGE_PMD_MASK)
return NULL;
- pmd = mm_find_pmd(mm, address);
- if (!pmd)
+ pgd = pgd_offset(mm, address);
+ if (!pgd_present(*pgd))
return NULL;
+ pud = pud_offset(pgd, address);
+ if (!pud_present(*pud))
+ return NULL;
+ pmd = pmd_offset(pud, address);
+
*ptl = pmd_lock(mm, pmd);
- if (pmd_none(*pmd))
+ if (!pmd_present(*pmd))
goto unlock;
if (pmd_page(*pmd) != page)
goto unlock;
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index dd30f22b35e0..c82290b9c1fc 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1172,6 +1172,7 @@ static void return_unused_surplus_pages(struct hstate *h,
while (nr_pages--) {
if (!free_pool_huge_page(h, &node_states[N_MEMORY], 1))
break;
+ cond_resched_lock(&hugetlb_lock);
}
}
@@ -1980,11 +1981,7 @@ static int __init hugetlb_init(void)
{
int i;
- /* Some platform decide whether they support huge pages at boot
- * time. On these, such as powerpc, HPAGE_SHIFT is set to 0 when
- * there is no such support
- */
- if (HPAGE_SHIFT == 0)
+ if (!hugepages_supported())
return 0;
if (!size_to_hstate(default_hstate_size)) {
@@ -2111,6 +2108,9 @@ static int hugetlb_sysctl_handler_common(bool obey_mempolicy,
unsigned long tmp;
int ret;
+ if (!hugepages_supported())
+ return -ENOTSUPP;
+
tmp = h->max_huge_pages;
if (write && h->order >= MAX_ORDER)
@@ -2164,6 +2164,9 @@ int hugetlb_overcommit_handler(struct ctl_table *table, int write,
unsigned long tmp;
int ret;
+ if (!hugepages_supported())
+ return -ENOTSUPP;
+
tmp = h->nr_overcommit_huge_pages;
if (write && h->order >= MAX_ORDER)
@@ -2189,6 +2192,8 @@ out:
void hugetlb_report_meminfo(struct seq_file *m)
{
struct hstate *h = &default_hstate;
+ if (!hugepages_supported())
+ return;
seq_printf(m,
"HugePages_Total: %5lu\n"
"HugePages_Free: %5lu\n"
@@ -2205,6 +2210,8 @@ void hugetlb_report_meminfo(struct seq_file *m)
int hugetlb_report_node_meminfo(int nid, char *buf)
{
struct hstate *h = &default_hstate;
+ if (!hugepages_supported())
+ return 0;
return sprintf(buf,
"Node %d HugePages_Total: %5u\n"
"Node %d HugePages_Free: %5u\n"
@@ -2219,6 +2226,9 @@ void hugetlb_show_meminfo(void)
struct hstate *h;
int nid;
+ if (!hugepages_supported())
+ return;
+
for_each_node_state(nid, N_MEMORY)
for_each_hstate(h)
pr_info("Node %d hugepages_total=%u hugepages_free=%u hugepages_surp=%u hugepages_size=%lukB\n",
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index 91d67eaee050..8d2fcdfeff7f 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -1775,10 +1775,9 @@ void __init kmemleak_init(void)
int i;
unsigned long flags;
- kmemleak_early_log = 0;
-
#ifdef CONFIG_DEBUG_KMEMLEAK_DEFAULT_OFF
if (!kmemleak_skip_disable) {
+ kmemleak_early_log = 0;
kmemleak_disable();
return;
}
@@ -1796,6 +1795,7 @@ void __init kmemleak_init(void)
/* the kernel is still in UP mode, so disabling the IRQs is enough */
local_irq_save(flags);
+ kmemleak_early_log = 0;
if (kmemleak_error) {
local_irq_restore(flags);
return;
diff --git a/mm/madvise.c b/mm/madvise.c
index 539eeb96b323..a402f8fdc68e 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -195,7 +195,7 @@ static void force_shm_swapin_readahead(struct vm_area_struct *vma,
for (; start < end; start += PAGE_SIZE) {
index = ((start - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
- page = find_get_page(mapping, index);
+ page = find_get_entry(mapping, index);
if (!radix_tree_exceptional_entry(page)) {
if (page)
page_cache_release(page);
diff --git a/mm/memblock.c b/mm/memblock.c
index e9d6ca9a01a9..a810ba923cdd 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -27,6 +27,9 @@
static struct memblock_region memblock_memory_init_regions[INIT_MEMBLOCK_REGIONS] __initdata_memblock;
static struct memblock_region memblock_reserved_init_regions[INIT_MEMBLOCK_REGIONS] __initdata_memblock;
+#ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP
+static struct memblock_region memblock_physmem_init_regions[INIT_PHYSMEM_REGIONS] __initdata_memblock;
+#endif
struct memblock memblock __initdata_memblock = {
.memory.regions = memblock_memory_init_regions,
@@ -37,6 +40,12 @@ struct memblock memblock __initdata_memblock = {
.reserved.cnt = 1, /* empty dummy entry */
.reserved.max = INIT_MEMBLOCK_REGIONS,
+#ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP
+ .physmem.regions = memblock_physmem_init_regions,
+ .physmem.cnt = 1, /* empty dummy entry */
+ .physmem.max = INIT_PHYSMEM_REGIONS,
+#endif
+
.bottom_up = false,
.current_limit = MEMBLOCK_ALLOC_ANYWHERE,
};
@@ -472,7 +481,7 @@ static void __init_memblock memblock_insert_region(struct memblock_type *type,
}
/**
- * memblock_add_region - add new memblock region
+ * memblock_add_range - add new memblock region
* @type: memblock type to add new region into
* @base: base address of the new region
* @size: size of the new region
@@ -487,7 +496,7 @@ static void __init_memblock memblock_insert_region(struct memblock_type *type,
* RETURNS:
* 0 on success, -errno on failure.
*/
-static int __init_memblock memblock_add_region(struct memblock_type *type,
+int __init_memblock memblock_add_range(struct memblock_type *type,
phys_addr_t base, phys_addr_t size,
int nid, unsigned long flags)
{
@@ -569,12 +578,12 @@ repeat:
int __init_memblock memblock_add_node(phys_addr_t base, phys_addr_t size,
int nid)
{
- return memblock_add_region(&memblock.memory, base, size, nid, 0);
+ return memblock_add_range(&memblock.memory, base, size, nid, 0);
}
int __init_memblock memblock_add(phys_addr_t base, phys_addr_t size)
{
- return memblock_add_region(&memblock.memory, base, size,
+ return memblock_add_range(&memblock.memory, base, size,
MAX_NUMNODES, 0);
}
@@ -654,8 +663,8 @@ static int __init_memblock memblock_isolate_range(struct memblock_type *type,
return 0;
}
-static int __init_memblock __memblock_remove(struct memblock_type *type,
- phys_addr_t base, phys_addr_t size)
+int __init_memblock memblock_remove_range(struct memblock_type *type,
+ phys_addr_t base, phys_addr_t size)
{
int start_rgn, end_rgn;
int i, ret;
@@ -671,9 +680,10 @@ static int __init_memblock __memblock_remove(struct memblock_type *type,
int __init_memblock memblock_remove(phys_addr_t base, phys_addr_t size)
{
- return __memblock_remove(&memblock.memory, base, size);
+ return memblock_remove_range(&memblock.memory, base, size);
}
+
int __init_memblock memblock_free(phys_addr_t base, phys_addr_t size)
{
memblock_dbg(" memblock_free: [%#016llx-%#016llx] %pF\n",
@@ -681,7 +691,7 @@ int __init_memblock memblock_free(phys_addr_t base, phys_addr_t size)
(unsigned long long)base + size - 1,
(void *)_RET_IP_);
- return __memblock_remove(&memblock.reserved, base, size);
+ return memblock_remove_range(&memblock.reserved, base, size);
}
static int __init_memblock memblock_reserve_region(phys_addr_t base,
@@ -696,7 +706,7 @@ static int __init_memblock memblock_reserve_region(phys_addr_t base,
(unsigned long long)base + size - 1,
flags, (void *)_RET_IP_);
- return memblock_add_region(_rgn, base, size, nid, flags);
+ return memblock_add_range(_rgn, base, size, nid, flags);
}
int __init_memblock memblock_reserve(phys_addr_t base, phys_addr_t size)
@@ -758,17 +768,19 @@ int __init_memblock memblock_clear_hotplug(phys_addr_t base, phys_addr_t size)
}
/**
- * __next_free_mem_range - next function for for_each_free_mem_range()
+ * __next__mem_range - next function for for_each_free_mem_range() etc.
* @idx: pointer to u64 loop variable
* @nid: node selector, %NUMA_NO_NODE for all nodes
+ * @type_a: pointer to memblock_type from where the range is taken
+ * @type_b: pointer to memblock_type which excludes memory from being taken
* @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
+ * Find the first area from *@idx which matches @nid, fill the out
* parameters, and update *@idx for the next iteration. The lower 32bit of
- * *@idx contains index into memory region and the upper 32bit indexes the
- * areas before each reserved region. For example, if reserved regions
+ * *@idx contains index into type_a and the upper 32bit indexes the
+ * areas before each region in type_b. For example, if type_b regions
* look like the following,
*
* 0:[0-16), 1:[32-48), 2:[128-130)
@@ -780,53 +792,77 @@ int __init_memblock memblock_clear_hotplug(phys_addr_t base, phys_addr_t size)
* As both region arrays are sorted, the function advances the two indices
* in lockstep and returns each intersection.
*/
-void __init_memblock __next_free_mem_range(u64 *idx, int nid,
- phys_addr_t *out_start,
- phys_addr_t *out_end, int *out_nid)
+void __init_memblock __next_mem_range(u64 *idx, int nid,
+ struct memblock_type *type_a,
+ struct memblock_type *type_b,
+ phys_addr_t *out_start,
+ phys_addr_t *out_end, int *out_nid)
{
- struct memblock_type *mem = &memblock.memory;
- struct memblock_type *rsv = &memblock.reserved;
- int mi = *idx & 0xffffffff;
- int ri = *idx >> 32;
+ int idx_a = *idx & 0xffffffff;
+ int idx_b = *idx >> 32;
- if (WARN_ONCE(nid == MAX_NUMNODES, "Usage of MAX_NUMNODES is deprecated. Use NUMA_NO_NODE instead\n"))
+ if (WARN_ONCE(nid == MAX_NUMNODES,
+ "Usage of MAX_NUMNODES is deprecated. Use NUMA_NO_NODE instead\n"))
nid = NUMA_NO_NODE;
- for ( ; mi < mem->cnt; mi++) {
- struct memblock_region *m = &mem->regions[mi];
+ for (; idx_a < type_a->cnt; idx_a++) {
+ struct memblock_region *m = &type_a->regions[idx_a];
+
phys_addr_t m_start = m->base;
phys_addr_t m_end = m->base + m->size;
+ int m_nid = memblock_get_region_node(m);
/* only memory regions are associated with nodes, check it */
- if (nid != NUMA_NO_NODE && nid != memblock_get_region_node(m))
+ if (nid != NUMA_NO_NODE && nid != m_nid)
continue;
- /* scan areas before each reservation for intersection */
- for ( ; ri < rsv->cnt + 1; ri++) {
- struct memblock_region *r = &rsv->regions[ri];
- phys_addr_t r_start = ri ? r[-1].base + r[-1].size : 0;
- phys_addr_t r_end = ri < rsv->cnt ? r->base : ULLONG_MAX;
+ if (!type_b) {
+ if (out_start)
+ *out_start = m_start;
+ if (out_end)
+ *out_end = m_end;
+ if (out_nid)
+ *out_nid = m_nid;
+ idx_a++;
+ *idx = (u32)idx_a | (u64)idx_b << 32;
+ return;
+ }
- /* if ri advanced past mi, break out to advance mi */
+ /* scan areas before each reservation */
+ for (; idx_b < type_b->cnt + 1; idx_b++) {
+ struct memblock_region *r;
+ phys_addr_t r_start;
+ phys_addr_t r_end;
+
+ r = &type_b->regions[idx_b];
+ r_start = idx_b ? r[-1].base + r[-1].size : 0;
+ r_end = idx_b < type_b->cnt ?
+ r->base : ULLONG_MAX;
+
+ /*
+ * if idx_b advanced past idx_a,
+ * break out to advance idx_a
+ */
if (r_start >= m_end)
break;
/* if the two regions intersect, we're done */
if (m_start < r_end) {
if (out_start)
- *out_start = max(m_start, r_start);
+ *out_start =
+ max(m_start, r_start);
if (out_end)
*out_end = min(m_end, r_end);
if (out_nid)
- *out_nid = memblock_get_region_node(m);
+ *out_nid = m_nid;
/*
- * The region which ends first is advanced
- * for the next iteration.
+ * The region which ends first is
+ * advanced for the next iteration.
*/
if (m_end <= r_end)
- mi++;
+ idx_a++;
else
- ri++;
- *idx = (u32)mi | (u64)ri << 32;
+ idx_b++;
+ *idx = (u32)idx_a | (u64)idx_b << 32;
return;
}
}
@@ -837,57 +873,80 @@ 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()
+ * __next_mem_range_rev - generic next function for for_each_*_range_rev()
+ *
+ * Finds the next range from type_a which is not marked as unsuitable
+ * in type_b.
+ *
* @idx: pointer to u64 loop variable
* @nid: nid: node selector, %NUMA_NO_NODE for all nodes
+ * @type_a: pointer to memblock_type from where the range is taken
+ * @type_b: pointer to memblock_type which excludes memory from being taken
* @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().
- *
- * Linux kernel cannot migrate pages used by itself. Memory hotplug users won't
- * be able to hot-remove hotpluggable memory used by the kernel. So this
- * function skip hotpluggable regions if needed when allocating memory for the
- * kernel.
+ * Reverse of __next_mem_range().
*/
-void __init_memblock __next_free_mem_range_rev(u64 *idx, int nid,
- phys_addr_t *out_start,
- phys_addr_t *out_end, int *out_nid)
+void __init_memblock __next_mem_range_rev(u64 *idx, int nid,
+ struct memblock_type *type_a,
+ struct memblock_type *type_b,
+ phys_addr_t *out_start,
+ phys_addr_t *out_end, int *out_nid)
{
- struct memblock_type *mem = &memblock.memory;
- struct memblock_type *rsv = &memblock.reserved;
- int mi = *idx & 0xffffffff;
- int ri = *idx >> 32;
+ int idx_a = *idx & 0xffffffff;
+ int idx_b = *idx >> 32;
if (WARN_ONCE(nid == MAX_NUMNODES, "Usage of MAX_NUMNODES is deprecated. Use NUMA_NO_NODE instead\n"))
nid = NUMA_NO_NODE;
if (*idx == (u64)ULLONG_MAX) {
- mi = mem->cnt - 1;
- ri = rsv->cnt;
+ idx_a = type_a->cnt - 1;
+ idx_b = type_b->cnt;
}
- for ( ; mi >= 0; mi--) {
- struct memblock_region *m = &mem->regions[mi];
+ for (; idx_a >= 0; idx_a--) {
+ struct memblock_region *m = &type_a->regions[idx_a];
+
phys_addr_t m_start = m->base;
phys_addr_t m_end = m->base + m->size;
+ int m_nid = memblock_get_region_node(m);
/* only memory regions are associated with nodes, check it */
- if (nid != NUMA_NO_NODE && nid != memblock_get_region_node(m))
+ if (nid != NUMA_NO_NODE && nid != m_nid)
continue;
/* skip hotpluggable memory regions if needed */
if (movable_node_is_enabled() && memblock_is_hotpluggable(m))
continue;
- /* scan areas before each reservation for intersection */
- for ( ; ri >= 0; ri--) {
- struct memblock_region *r = &rsv->regions[ri];
- phys_addr_t r_start = ri ? r[-1].base + r[-1].size : 0;
- phys_addr_t r_end = ri < rsv->cnt ? r->base : ULLONG_MAX;
+ if (!type_b) {
+ if (out_start)
+ *out_start = m_start;
+ if (out_end)
+ *out_end = m_end;
+ if (out_nid)
+ *out_nid = m_nid;
+ idx_a++;
+ *idx = (u32)idx_a | (u64)idx_b << 32;
+ return;
+ }
+
+ /* scan areas before each reservation */
+ for (; idx_b >= 0; idx_b--) {
+ struct memblock_region *r;
+ phys_addr_t r_start;
+ phys_addr_t r_end;
+
+ r = &type_b->regions[idx_b];
+ r_start = idx_b ? r[-1].base + r[-1].size : 0;
+ r_end = idx_b < type_b->cnt ?
+ r->base : ULLONG_MAX;
+ /*
+ * if idx_b advanced past idx_a,
+ * break out to advance idx_a
+ */
- /* if ri advanced past mi, break out to advance mi */
if (r_end <= m_start)
break;
/* if the two regions intersect, we're done */
@@ -897,18 +956,17 @@ void __init_memblock __next_free_mem_range_rev(u64 *idx, int nid,
if (out_end)
*out_end = min(m_end, r_end);
if (out_nid)
- *out_nid = memblock_get_region_node(m);
-
+ *out_nid = m_nid;
if (m_start >= r_start)
- mi--;
+ idx_a--;
else
- ri--;
- *idx = (u32)mi | (u64)ri << 32;
+ idx_b--;
+ *idx = (u32)idx_a | (u64)idx_b << 32;
return;
}
}
}
-
+ /* signal end of iteration */
*idx = ULLONG_MAX;
}
@@ -1201,7 +1259,7 @@ void __init __memblock_free_early(phys_addr_t base, phys_addr_t size)
__func__, (u64)base, (u64)base + size - 1,
(void *)_RET_IP_);
kmemleak_free_part(__va(base), size);
- __memblock_remove(&memblock.reserved, base, size);
+ memblock_remove_range(&memblock.reserved, base, size);
}
/*
@@ -1287,8 +1345,10 @@ void __init memblock_enforce_memory_limit(phys_addr_t limit)
}
/* truncate both memory and reserved regions */
- __memblock_remove(&memblock.memory, max_addr, (phys_addr_t)ULLONG_MAX);
- __memblock_remove(&memblock.reserved, max_addr, (phys_addr_t)ULLONG_MAX);
+ memblock_remove_range(&memblock.memory, max_addr,
+ (phys_addr_t)ULLONG_MAX);
+ memblock_remove_range(&memblock.reserved, max_addr,
+ (phys_addr_t)ULLONG_MAX);
}
static int __init_memblock memblock_search(struct memblock_type *type, phys_addr_t addr)
@@ -1502,6 +1562,9 @@ static int __init memblock_init_debugfs(void)
return -ENXIO;
debugfs_create_file("memory", S_IRUGO, root, &memblock.memory, &memblock_debug_fops);
debugfs_create_file("reserved", S_IRUGO, root, &memblock.reserved, &memblock_debug_fops);
+#ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP
+ debugfs_create_file("physmem", S_IRUGO, root, &memblock.physmem, &memblock_debug_fops);
+#endif
return 0;
}
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 29501f040568..5177c6d4a2dd 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1077,9 +1077,18 @@ static struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm)
rcu_read_lock();
do {
- memcg = mem_cgroup_from_task(rcu_dereference(mm->owner));
- if (unlikely(!memcg))
+ /*
+ * Page cache insertions can happen withou an
+ * actual mm context, e.g. during disk probing
+ * on boot, loopback IO, acct() writes etc.
+ */
+ if (unlikely(!mm))
memcg = root_mem_cgroup;
+ else {
+ memcg = mem_cgroup_from_task(rcu_dereference(mm->owner));
+ if (unlikely(!memcg))
+ memcg = root_mem_cgroup;
+ }
} while (!css_tryget(&memcg->css));
rcu_read_unlock();
return memcg;
@@ -3958,17 +3967,9 @@ int mem_cgroup_charge_file(struct page *page, struct mm_struct *mm,
return 0;
}
- /*
- * Page cache insertions can happen without an actual mm
- * context, e.g. during disk probing on boot.
- */
- if (unlikely(!mm))
- memcg = root_mem_cgroup;
- else {
- memcg = mem_cgroup_try_charge_mm(mm, gfp_mask, 1, true);
- if (!memcg)
- return -ENOMEM;
- }
+ memcg = mem_cgroup_try_charge_mm(mm, gfp_mask, 1, true);
+ if (!memcg)
+ return -ENOMEM;
__mem_cgroup_commit_charge(memcg, page, 1, type, false);
return 0;
}
@@ -6686,16 +6687,20 @@ static struct page *mc_handle_file_pte(struct vm_area_struct *vma,
pgoff = pte_to_pgoff(ptent);
/* page is moved even if it's not RSS of this task(page-faulted). */
- page = find_get_page(mapping, pgoff);
-
#ifdef CONFIG_SWAP
/* shmem/tmpfs may report page out on swap: account for that too. */
- if (radix_tree_exceptional_entry(page)) {
- swp_entry_t swap = radix_to_swp_entry(page);
- if (do_swap_account)
- *entry = swap;
- page = find_get_page(swap_address_space(swap), swap.val);
- }
+ if (shmem_mapping(mapping)) {
+ page = find_get_entry(mapping, pgoff);
+ if (radix_tree_exceptional_entry(page)) {
+ swp_entry_t swp = radix_to_swp_entry(page);
+ if (do_swap_account)
+ *entry = swp;
+ page = find_get_page(swap_address_space(swp), swp.val);
+ }
+ } else
+ page = find_get_page(mapping, pgoff);
+#else
+ page = find_get_page(mapping, pgoff);
#endif
return page;
}
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 35ef28acf137..9ccef39a9de2 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1081,15 +1081,16 @@ int memory_failure(unsigned long pfn, int trapno, int flags)
return 0;
} else if (PageHuge(hpage)) {
/*
- * Check "just unpoisoned", "filter hit", and
- * "race with other subpage."
+ * Check "filter hit" and "race with other subpage."
*/
lock_page(hpage);
- if (!PageHWPoison(hpage)
- || (hwpoison_filter(p) && TestClearPageHWPoison(p))
- || (p != hpage && TestSetPageHWPoison(hpage))) {
- atomic_long_sub(nr_pages, &num_poisoned_pages);
- return 0;
+ if (PageHWPoison(hpage)) {
+ if ((hwpoison_filter(p) && TestClearPageHWPoison(p))
+ || (p != hpage && TestSetPageHWPoison(hpage))) {
+ atomic_long_sub(nr_pages, &num_poisoned_pages);
+ unlock_page(hpage);
+ return 0;
+ }
}
set_page_hwpoison_huge_page(hpage);
res = dequeue_hwpoisoned_huge_page(hpage);
@@ -1152,6 +1153,8 @@ int memory_failure(unsigned long pfn, int trapno, int flags)
*/
if (!PageHWPoison(p)) {
printk(KERN_ERR "MCE %#lx: just unpoisoned\n", pfn);
+ atomic_long_sub(nr_pages, &num_poisoned_pages);
+ put_page(hpage);
res = 0;
goto out;
}
diff --git a/mm/memory.c b/mm/memory.c
index d0f0bef3be48..037b812a9531 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -232,17 +232,18 @@ void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long
#endif
}
-void tlb_flush_mmu(struct mmu_gather *tlb)
+static void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
{
- struct mmu_gather_batch *batch;
-
- if (!tlb->need_flush)
- return;
tlb->need_flush = 0;
tlb_flush(tlb);
#ifdef CONFIG_HAVE_RCU_TABLE_FREE
tlb_table_flush(tlb);
#endif
+}
+
+static void tlb_flush_mmu_free(struct mmu_gather *tlb)
+{
+ struct mmu_gather_batch *batch;
for (batch = &tlb->local; batch; batch = batch->next) {
free_pages_and_swap_cache(batch->pages, batch->nr);
@@ -251,6 +252,14 @@ void tlb_flush_mmu(struct mmu_gather *tlb)
tlb->active = &tlb->local;
}
+void tlb_flush_mmu(struct mmu_gather *tlb)
+{
+ if (!tlb->need_flush)
+ return;
+ tlb_flush_mmu_tlbonly(tlb);
+ tlb_flush_mmu_free(tlb);
+}
+
/* tlb_finish_mmu
* Called at the end of the shootdown operation to free up any resources
* that were required.
@@ -1127,8 +1136,10 @@ again:
if (PageAnon(page))
rss[MM_ANONPAGES]--;
else {
- if (pte_dirty(ptent))
+ if (pte_dirty(ptent)) {
+ force_flush = 1;
set_page_dirty(page);
+ }
if (pte_young(ptent) &&
likely(!(vma->vm_flags & VM_SEQ_READ)))
mark_page_accessed(page);
@@ -1137,9 +1148,10 @@ again:
page_remove_rmap(page);
if (unlikely(page_mapcount(page) < 0))
print_bad_pte(vma, addr, ptent, page);
- force_flush = !__tlb_remove_page(tlb, page);
- if (force_flush)
+ if (unlikely(!__tlb_remove_page(tlb, page))) {
+ force_flush = 1;
break;
+ }
continue;
}
/*
@@ -1174,18 +1186,11 @@ again:
add_mm_rss_vec(mm, rss);
arch_leave_lazy_mmu_mode();
- pte_unmap_unlock(start_pte, ptl);
- /*
- * mmu_gather ran out of room to batch pages, we break out of
- * the PTE lock to avoid doing the potential expensive TLB invalidate
- * and page-free while holding it.
- */
+ /* Do the actual TLB flush before dropping ptl */
if (force_flush) {
unsigned long old_end;
- force_flush = 0;
-
/*
* Flush the TLB just for the previous segment,
* then update the range to be the remaining
@@ -1193,11 +1198,21 @@ again:
*/
old_end = tlb->end;
tlb->end = addr;
-
- tlb_flush_mmu(tlb);
-
+ tlb_flush_mmu_tlbonly(tlb);
tlb->start = addr;
tlb->end = old_end;
+ }
+ pte_unmap_unlock(start_pte, ptl);
+
+ /*
+ * If we forced a TLB flush (either due to running out of
+ * batch buffers or because we needed to flush dirty TLB
+ * entries before releasing the ptl), free the batched
+ * memory too. Restart if we didn't do everything.
+ */
+ if (force_flush) {
+ force_flush = 0;
+ tlb_flush_mmu_free(tlb);
if (addr != end)
goto again;
@@ -1955,12 +1970,17 @@ int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm,
unsigned long address, unsigned int fault_flags)
{
struct vm_area_struct *vma;
+ vm_flags_t vm_flags;
int ret;
vma = find_extend_vma(mm, address);
if (!vma || address < vma->vm_start)
return -EFAULT;
+ vm_flags = (fault_flags & FAULT_FLAG_WRITE) ? VM_WRITE : VM_READ;
+ if (!(vm_flags & vma->vm_flags))
+ return -EFAULT;
+
ret = handle_mm_fault(mm, vma, address, fault_flags);
if (ret & VM_FAULT_ERROR) {
if (ret & VM_FAULT_OOM)
diff --git a/mm/mremap.c b/mm/mremap.c
index 0843feb66f3d..05f1180e9f21 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -194,10 +194,17 @@ unsigned long move_page_tables(struct vm_area_struct *vma,
break;
if (pmd_trans_huge(*old_pmd)) {
int err = 0;
- if (extent == HPAGE_PMD_SIZE)
+ if (extent == HPAGE_PMD_SIZE) {
+ VM_BUG_ON(vma->vm_file || !vma->anon_vma);
+ /* See comment in move_ptes() */
+ if (need_rmap_locks)
+ anon_vma_lock_write(vma->anon_vma);
err = move_huge_pmd(vma, new_vma, old_addr,
new_addr, old_end,
old_pmd, new_pmd);
+ if (need_rmap_locks)
+ anon_vma_unlock_write(vma->anon_vma);
+ }
if (err > 0) {
need_flush = true;
continue;
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index ef413492a149..a4317da60532 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -593,14 +593,14 @@ unsigned long bdi_dirty_limit(struct backing_dev_info *bdi, unsigned long dirty)
* (5) the closer to setpoint, the smaller |df/dx| (and the reverse)
* => fast response on large errors; small oscillation near setpoint
*/
-static inline long long pos_ratio_polynom(unsigned long setpoint,
+static long long pos_ratio_polynom(unsigned long setpoint,
unsigned long dirty,
unsigned long limit)
{
long long pos_ratio;
long x;
- x = div_s64(((s64)setpoint - (s64)dirty) << RATELIMIT_CALC_SHIFT,
+ x = div64_s64(((s64)setpoint - (s64)dirty) << RATELIMIT_CALC_SHIFT,
limit - setpoint + 1);
pos_ratio = x;
pos_ratio = pos_ratio * x >> RATELIMIT_CALC_SHIFT;
@@ -842,7 +842,7 @@ static unsigned long bdi_position_ratio(struct backing_dev_info *bdi,
x_intercept = bdi_setpoint + span;
if (bdi_dirty < x_intercept - span / 4) {
- pos_ratio = div_u64(pos_ratio * (x_intercept - bdi_dirty),
+ pos_ratio = div64_u64(pos_ratio * (x_intercept - bdi_dirty),
x_intercept - bdi_setpoint + 1);
} else
pos_ratio /= 4;
diff --git a/mm/percpu.c b/mm/percpu.c
index 63e24fb4387b..2ddf9a990dbd 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -610,7 +610,7 @@ static struct pcpu_chunk *pcpu_alloc_chunk(void)
chunk->map = pcpu_mem_zalloc(PCPU_DFL_MAP_ALLOC *
sizeof(chunk->map[0]));
if (!chunk->map) {
- kfree(chunk);
+ pcpu_mem_free(chunk, pcpu_chunk_struct_size);
return NULL;
}
diff --git a/mm/slab.c b/mm/slab.c
index 388cb1ae6fbc..19d92181ce24 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -166,7 +166,7 @@ typedef unsigned char freelist_idx_t;
typedef unsigned short freelist_idx_t;
#endif
-#define SLAB_OBJ_MAX_NUM (1 << sizeof(freelist_idx_t) * BITS_PER_BYTE)
+#define SLAB_OBJ_MAX_NUM ((1 << sizeof(freelist_idx_t) * BITS_PER_BYTE) - 1)
/*
* true if a page was allocated from pfmemalloc reserves for network-based
@@ -2572,13 +2572,13 @@ static void *alloc_slabmgmt(struct kmem_cache *cachep,
return freelist;
}
-static inline freelist_idx_t get_free_obj(struct page *page, unsigned char idx)
+static inline freelist_idx_t get_free_obj(struct page *page, unsigned int idx)
{
return ((freelist_idx_t *)page->freelist)[idx];
}
static inline void set_free_obj(struct page *page,
- unsigned char idx, freelist_idx_t val)
+ unsigned int idx, freelist_idx_t val)
{
((freelist_idx_t *)(page->freelist))[idx] = val;
}
diff --git a/mm/slab.h b/mm/slab.h
index 3045316b7c9d..6bd4c353704f 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -91,6 +91,7 @@ __kmem_cache_alias(const char *name, size_t size, size_t align,
#define CACHE_CREATE_MASK (SLAB_CORE_FLAGS | SLAB_DEBUG_FLAGS | SLAB_CACHE_FLAGS)
int __kmem_cache_shutdown(struct kmem_cache *);
+void slab_kmem_cache_release(struct kmem_cache *);
struct seq_file;
struct file;
diff --git a/mm/slab_common.c b/mm/slab_common.c
index f3cfccf76dda..102cc6fca3d3 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -323,6 +323,12 @@ static int kmem_cache_destroy_memcg_children(struct kmem_cache *s)
}
#endif /* CONFIG_MEMCG_KMEM */
+void slab_kmem_cache_release(struct kmem_cache *s)
+{
+ kfree(s->name);
+ kmem_cache_free(kmem_cache, s);
+}
+
void kmem_cache_destroy(struct kmem_cache *s)
{
get_online_cpus();
@@ -352,8 +358,11 @@ void kmem_cache_destroy(struct kmem_cache *s)
rcu_barrier();
memcg_free_cache_params(s);
- kfree(s->name);
- kmem_cache_free(kmem_cache, s);
+#ifdef SLAB_SUPPORTS_SYSFS
+ sysfs_slab_remove(s);
+#else
+ slab_kmem_cache_release(s);
+#endif
goto out_put_cpus;
out_unlock:
diff --git a/mm/slub.c b/mm/slub.c
index 5e234f1f8853..2b1ce697fc4b 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -210,14 +210,11 @@ enum track_item { TRACK_ALLOC, TRACK_FREE };
#ifdef CONFIG_SYSFS
static int sysfs_slab_add(struct kmem_cache *);
static int sysfs_slab_alias(struct kmem_cache *, const char *);
-static void sysfs_slab_remove(struct kmem_cache *);
static void memcg_propagate_slab_attrs(struct kmem_cache *s);
#else
static inline int sysfs_slab_add(struct kmem_cache *s) { return 0; }
static inline int sysfs_slab_alias(struct kmem_cache *s, const char *p)
{ return 0; }
-static inline void sysfs_slab_remove(struct kmem_cache *s) { }
-
static inline void memcg_propagate_slab_attrs(struct kmem_cache *s) { }
#endif
@@ -3238,24 +3235,7 @@ static inline int kmem_cache_close(struct kmem_cache *s)
int __kmem_cache_shutdown(struct kmem_cache *s)
{
- int rc = kmem_cache_close(s);
-
- if (!rc) {
- /*
- * Since slab_attr_store may take the slab_mutex, we should
- * release the lock while removing the sysfs entry in order to
- * avoid a deadlock. Because this is pretty much the last
- * operation we do and the lock will be released shortly after
- * that in slab_common.c, we could just move sysfs_slab_remove
- * to a later point in common code. We should do that when we
- * have a common sysfs framework for all allocators.
- */
- mutex_unlock(&slab_mutex);
- sysfs_slab_remove(s);
- mutex_lock(&slab_mutex);
- }
-
- return rc;
+ return kmem_cache_close(s);
}
/********************************************************************
@@ -5071,15 +5051,18 @@ static void memcg_propagate_slab_attrs(struct kmem_cache *s)
#ifdef CONFIG_MEMCG_KMEM
int i;
char *buffer = NULL;
+ struct kmem_cache *root_cache;
- if (!is_root_cache(s))
+ if (is_root_cache(s))
return;
+ root_cache = s->memcg_params->root_cache;
+
/*
* This mean this cache had no attribute written. Therefore, no point
* in copying default values around
*/
- if (!s->max_attr_size)
+ if (!root_cache->max_attr_size)
return;
for (i = 0; i < ARRAY_SIZE(slab_attrs); i++) {
@@ -5101,7 +5084,7 @@ static void memcg_propagate_slab_attrs(struct kmem_cache *s)
*/
if (buffer)
buf = buffer;
- else if (s->max_attr_size < ARRAY_SIZE(mbuf))
+ else if (root_cache->max_attr_size < ARRAY_SIZE(mbuf))
buf = mbuf;
else {
buffer = (char *) get_zeroed_page(GFP_KERNEL);
@@ -5110,7 +5093,7 @@ static void memcg_propagate_slab_attrs(struct kmem_cache *s)
buf = buffer;
}
- attr->show(s->memcg_params->root_cache, buf);
+ attr->show(root_cache, buf);
attr->store(s, buf, strlen(buf));
}
@@ -5119,6 +5102,11 @@ static void memcg_propagate_slab_attrs(struct kmem_cache *s)
#endif
}
+static void kmem_cache_release(struct kobject *k)
+{
+ slab_kmem_cache_release(to_slab(k));
+}
+
static const struct sysfs_ops slab_sysfs_ops = {
.show = slab_attr_show,
.store = slab_attr_store,
@@ -5126,6 +5114,7 @@ static const struct sysfs_ops slab_sysfs_ops = {
static struct kobj_type slab_ktype = {
.sysfs_ops = &slab_sysfs_ops,
+ .release = kmem_cache_release,
};
static int uevent_filter(struct kset *kset, struct kobject *kobj)
@@ -5252,7 +5241,7 @@ out_put_kobj:
goto out;
}
-static void sysfs_slab_remove(struct kmem_cache *s)
+void sysfs_slab_remove(struct kmem_cache *s)
{
if (slab_state < FULL)
/*
diff --git a/mm/truncate.c b/mm/truncate.c
index e5cc39ab0751..6a78c814bebf 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -484,14 +484,6 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping,
unsigned long count = 0;
int i;
- /*
- * Note: this function may get called on a shmem/tmpfs mapping:
- * pagevec_lookup() might then return 0 prematurely (because it
- * got a gangful of swap entries); but it's hardly worth worrying
- * about - it can rarely have anything to free from such a mapping
- * (most pages are dirty), and already skips over any difficulties.
- */
-
pagevec_init(&pvec, 0);
while (index <= end && pagevec_lookup_entries(&pvec, mapping, index,
min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1,
diff --git a/mm/util.c b/mm/util.c
index f380af7ea779..d5ea733c5082 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -10,6 +10,7 @@
#include <linux/swapops.h>
#include <linux/mman.h>
#include <linux/hugetlb.h>
+#include <linux/vmalloc.h>
#include <asm/uaccess.h>
@@ -387,6 +388,15 @@ unsigned long vm_mmap(struct file *file, unsigned long addr,
}
EXPORT_SYMBOL(vm_mmap);
+void kvfree(const void *addr)
+{
+ if (is_vmalloc_addr(addr))
+ vfree(addr);
+ else
+ kfree(addr);
+}
+EXPORT_SYMBOL(kvfree);
+
struct address_space *page_mapping(struct page *page)
{
struct address_space *mapping = page->mapping;
diff --git a/mm/vmacache.c b/mm/vmacache.c
index d4224b397c0e..1037a3bab505 100644
--- a/mm/vmacache.c
+++ b/mm/vmacache.c
@@ -81,10 +81,12 @@ struct vm_area_struct *vmacache_find(struct mm_struct *mm, unsigned long addr)
for (i = 0; i < VMACACHE_SIZE; i++) {
struct vm_area_struct *vma = current->vmacache[i];
- if (vma && vma->vm_start <= addr && vma->vm_end > addr) {
- BUG_ON(vma->vm_mm != mm);
+ if (!vma)
+ continue;
+ if (WARN_ON_ONCE(vma->vm_mm != mm))
+ break;
+ if (vma->vm_start <= addr && vma->vm_end > addr)
return vma;
- }
}
return NULL;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 9b6497eda806..32c661d66a45 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1158,7 +1158,7 @@ unsigned long reclaim_clean_pages_from_list(struct zone *zone,
TTU_UNMAP|TTU_IGNORE_ACCESS,
&dummy1, &dummy2, &dummy3, &dummy4, &dummy5, true);
list_splice(&clean_pages, page_list);
- __mod_zone_page_state(zone, NR_ISOLATED_FILE, -ret);
+ mod_zone_page_state(zone, NR_ISOLATED_FILE, -ret);
return ret;
}
@@ -1916,6 +1916,24 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc,
get_lru_size(lruvec, LRU_INACTIVE_FILE);
/*
+ * Prevent the reclaimer from falling into the cache trap: as
+ * cache pages start out inactive, every cache fault will tip
+ * the scan balance towards the file LRU. And as the file LRU
+ * shrinks, so does the window for rotation from references.
+ * This means we have a runaway feedback loop where a tiny
+ * thrashing file LRU becomes infinitely more attractive than
+ * anon pages. Try to detect this based on file LRU size.
+ */
+ if (global_reclaim(sc)) {
+ unsigned long free = zone_page_state(zone, NR_FREE_PAGES);
+
+ if (unlikely(file + free <= high_wmark_pages(zone))) {
+ scan_balance = SCAN_ANON;
+ goto out;
+ }
+ }
+
+ /*
* There is enough inactive page cache, do not reclaim
* anything from the anonymous working set right now.
*/
generated by cgit v1.2.3 (git 2.0.4) at 2024-11-17 18:29:53 +0000