aboutsummaryrefslogtreecommitdiffstats
path: root/mm
diff options
context:
space:
mode:
Diffstat (limited to 'mm')
-rw-r--r--mm/dmapool.c31
-rw-r--r--mm/memory-failure.c8
-rw-r--r--mm/memory.c5
-rw-r--r--mm/mempolicy.c86
-rw-r--r--mm/rmap.c21
-rw-r--r--mm/shmem.c22
-rw-r--r--mm/sparse.c10
-rw-r--r--mm/vmscan.c2
8 files changed, 81 insertions, 104 deletions
diff --git a/mm/dmapool.c b/mm/dmapool.c
index 03bf3bb..f8e675e 100644
--- a/mm/dmapool.c
+++ b/mm/dmapool.c
@@ -49,7 +49,6 @@ struct dma_pool { /* the pool */
size_t allocation;
size_t boundary;
char name[32];
- wait_queue_head_t waitq;
struct list_head pools;
};
@@ -61,8 +60,6 @@ struct dma_page { /* cacheable header for 'allocation' bytes */
unsigned int offset;
};
-#define POOL_TIMEOUT_JIFFIES ((100 /* msec */ * HZ) / 1000)
-
static DEFINE_MUTEX(pools_lock);
static ssize_t
@@ -171,7 +168,6 @@ struct dma_pool *dma_pool_create(const char *name, struct device *dev,
retval->size = size;
retval->boundary = boundary;
retval->allocation = allocation;
- init_waitqueue_head(&retval->waitq);
if (dev) {
int ret;
@@ -226,7 +222,6 @@ static struct dma_page *pool_alloc_page(struct dma_pool *pool, gfp_t mem_flags)
memset(page->vaddr, POOL_POISON_FREED, pool->allocation);
#endif
pool_initialise_page(pool, page);
- list_add(&page->page_list, &pool->page_list);
page->in_use = 0;
page->offset = 0;
} else {
@@ -314,30 +309,21 @@ void *dma_pool_alloc(struct dma_pool *pool, gfp_t mem_flags,
might_sleep_if(mem_flags & __GFP_WAIT);
spin_lock_irqsave(&pool->lock, flags);
- restart:
list_for_each_entry(page, &pool->page_list, page_list) {
if (page->offset < pool->allocation)
goto ready;
}
- page = pool_alloc_page(pool, GFP_ATOMIC);
- if (!page) {
- if (mem_flags & __GFP_WAIT) {
- DECLARE_WAITQUEUE(wait, current);
- __set_current_state(TASK_UNINTERRUPTIBLE);
- __add_wait_queue(&pool->waitq, &wait);
- spin_unlock_irqrestore(&pool->lock, flags);
+ /* pool_alloc_page() might sleep, so temporarily drop &pool->lock */
+ spin_unlock_irqrestore(&pool->lock, flags);
- schedule_timeout(POOL_TIMEOUT_JIFFIES);
+ page = pool_alloc_page(pool, mem_flags);
+ if (!page)
+ return NULL;
- spin_lock_irqsave(&pool->lock, flags);
- __remove_wait_queue(&pool->waitq, &wait);
- goto restart;
- }
- retval = NULL;
- goto done;
- }
+ spin_lock_irqsave(&pool->lock, flags);
+ list_add(&page->page_list, &pool->page_list);
ready:
page->in_use++;
offset = page->offset;
@@ -347,7 +333,6 @@ void *dma_pool_alloc(struct dma_pool *pool, gfp_t mem_flags,
#ifdef DMAPOOL_DEBUG
memset(retval, POOL_POISON_ALLOCATED, pool->size);
#endif
- done:
spin_unlock_irqrestore(&pool->lock, flags);
return retval;
}
@@ -434,8 +419,6 @@ void dma_pool_free(struct dma_pool *pool, void *vaddr, dma_addr_t dma)
page->in_use--;
*(int *)vaddr = page->offset;
page->offset = offset;
- if (waitqueue_active(&pool->waitq))
- wake_up_locked(&pool->waitq);
/*
* Resist a temptation to do
* if (!is_page_busy(page)) pool_free_page(pool, page);
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 2f49dcf..eace560 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1382,9 +1382,17 @@ int soft_offline_page(struct page *page, int flags)
{
int ret;
unsigned long pfn = page_to_pfn(page);
+ struct page *hpage = compound_trans_head(page);
if (PageHuge(page))
return soft_offline_huge_page(page, flags);
+ if (PageTransHuge(hpage)) {
+ if (PageAnon(hpage) && unlikely(split_huge_page(hpage))) {
+ pr_info("soft offline: %#lx: failed to split THP\n",
+ pfn);
+ return -EBUSY;
+ }
+ }
ret = get_any_page(page, pfn, flags);
if (ret < 0)
diff --git a/mm/memory.c b/mm/memory.c
index d49b58a..7292acb 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -205,10 +205,14 @@ static int tlb_next_batch(struct mmu_gather *tlb)
return 1;
}
+ if (tlb->batch_count == MAX_GATHER_BATCH_COUNT)
+ return 0;
+
batch = (void *)__get_free_pages(GFP_NOWAIT | __GFP_NOWARN, 0);
if (!batch)
return 0;
+ tlb->batch_count++;
batch->next = NULL;
batch->nr = 0;
batch->max = MAX_GATHER_BATCH;
@@ -235,6 +239,7 @@ void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, bool fullmm)
tlb->local.nr = 0;
tlb->local.max = ARRAY_SIZE(tlb->__pages);
tlb->active = &tlb->local;
+ tlb->batch_count = 0;
#ifdef CONFIG_HAVE_RCU_TABLE_FREE
tlb->batch = NULL;
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 5dce7d4..0367beb 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1973,28 +1973,6 @@ struct mempolicy *__mpol_dup(struct mempolicy *old)
return new;
}
-/*
- * If *frompol needs [has] an extra ref, copy *frompol to *tompol ,
- * eliminate the * MPOL_F_* flags that require conditional ref and
- * [NOTE!!!] drop the extra ref. Not safe to reference *frompol directly
- * after return. Use the returned value.
- *
- * Allows use of a mempolicy for, e.g., multiple allocations with a single
- * policy lookup, even if the policy needs/has extra ref on lookup.
- * shmem_readahead needs this.
- */
-struct mempolicy *__mpol_cond_copy(struct mempolicy *tompol,
- struct mempolicy *frompol)
-{
- if (!mpol_needs_cond_ref(frompol))
- return frompol;
-
- *tompol = *frompol;
- tompol->flags &= ~MPOL_F_SHARED; /* copy doesn't need unref */
- __mpol_put(frompol);
- return tompol;
-}
-
/* Slow path of a mempolicy comparison */
int __mpol_equal(struct mempolicy *a, struct mempolicy *b)
{
@@ -2330,8 +2308,7 @@ void numa_default_policy(void)
*/
/*
- * "local" is pseudo-policy: MPOL_PREFERRED with MPOL_F_LOCAL flag
- * Used only for mpol_parse_str() and mpol_to_str()
+ * "local" is implemented internally by MPOL_PREFERRED with MPOL_F_LOCAL flag.
*/
#define MPOL_LOCAL MPOL_MAX
static const char * const policy_modes[] =
@@ -2346,28 +2323,21 @@ static const char * const policy_modes[] =
#ifdef CONFIG_TMPFS
/**
- * mpol_parse_str - parse string to mempolicy
+ * mpol_parse_str - parse string to mempolicy, for tmpfs mpol mount option.
* @str: string containing mempolicy to parse
* @mpol: pointer to struct mempolicy pointer, returned on success.
- * @no_context: flag whether to "contextualize" the mempolicy
+ * @unused: redundant argument, to be removed later.
*
* Format of input:
* <mode>[=<flags>][:<nodelist>]
*
- * if @no_context is true, save the input nodemask in w.user_nodemask in
- * the returned mempolicy. This will be used to "clone" the mempolicy in
- * a specific context [cpuset] at a later time. Used to parse tmpfs mpol
- * mount option. Note that if 'static' or 'relative' mode flags were
- * specified, the input nodemask will already have been saved. Saving
- * it again is redundant, but safe.
- *
* On success, returns 0, else 1
*/
-int mpol_parse_str(char *str, struct mempolicy **mpol, int no_context)
+int mpol_parse_str(char *str, struct mempolicy **mpol, int unused)
{
struct mempolicy *new = NULL;
unsigned short mode;
- unsigned short uninitialized_var(mode_flags);
+ unsigned short mode_flags;
nodemask_t nodes;
char *nodelist = strchr(str, ':');
char *flags = strchr(str, '=');
@@ -2455,24 +2425,23 @@ int mpol_parse_str(char *str, struct mempolicy **mpol, int no_context)
if (IS_ERR(new))
goto out;
- if (no_context) {
- /* save for contextualization */
- new->w.user_nodemask = nodes;
- } else {
- int ret;
- NODEMASK_SCRATCH(scratch);
- if (scratch) {
- task_lock(current);
- ret = mpol_set_nodemask(new, &nodes, scratch);
- task_unlock(current);
- } else
- ret = -ENOMEM;
- NODEMASK_SCRATCH_FREE(scratch);
- if (ret) {
- mpol_put(new);
- goto out;
- }
- }
+ /*
+ * Save nodes for mpol_to_str() to show the tmpfs mount options
+ * for /proc/mounts, /proc/pid/mounts and /proc/pid/mountinfo.
+ */
+ if (mode != MPOL_PREFERRED)
+ new->v.nodes = nodes;
+ else if (nodelist)
+ new->v.preferred_node = first_node(nodes);
+ else
+ new->flags |= MPOL_F_LOCAL;
+
+ /*
+ * Save nodes for contextualization: this will be used to "clone"
+ * the mempolicy in a specific context [cpuset] at a later time.
+ */
+ new->w.user_nodemask = nodes;
+
err = 0;
out:
@@ -2492,13 +2461,13 @@ out:
* @buffer: to contain formatted mempolicy string
* @maxlen: length of @buffer
* @pol: pointer to mempolicy to be formatted
- * @no_context: "context free" mempolicy - use nodemask in w.user_nodemask
+ * @unused: redundant argument, to be removed later.
*
* Convert a mempolicy into a string.
* Returns the number of characters in buffer (if positive)
* or an error (negative)
*/
-int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol, int no_context)
+int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol, int unused)
{
char *p = buffer;
int l;
@@ -2524,7 +2493,7 @@ int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol, int no_context)
case MPOL_PREFERRED:
nodes_clear(nodes);
if (flags & MPOL_F_LOCAL)
- mode = MPOL_LOCAL; /* pseudo-policy */
+ mode = MPOL_LOCAL;
else
node_set(pol->v.preferred_node, nodes);
break;
@@ -2532,10 +2501,7 @@ int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol, int no_context)
case MPOL_BIND:
/* Fall through */
case MPOL_INTERLEAVE:
- if (no_context)
- nodes = pol->w.user_nodemask;
- else
- nodes = pol->v.nodes;
+ nodes = pol->v.nodes;
break;
default:
diff --git a/mm/rmap.c b/mm/rmap.c
index 23295f6..30e44cb 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -57,6 +57,7 @@
#include <linux/mmu_notifier.h>
#include <linux/migrate.h>
#include <linux/hugetlb.h>
+#include <linux/backing-dev.h>
#include <asm/tlbflush.h>
@@ -936,11 +937,8 @@ int page_mkclean(struct page *page)
if (page_mapped(page)) {
struct address_space *mapping = page_mapping(page);
- if (mapping) {
+ if (mapping)
ret = page_mkclean_file(mapping, page);
- if (page_test_and_clear_dirty(page_to_pfn(page), 1))
- ret = 1;
- }
}
return ret;
@@ -1121,6 +1119,8 @@ void page_add_file_rmap(struct page *page)
*/
void page_remove_rmap(struct page *page)
{
+ struct address_space *mapping = page_mapping(page);
+
/* page still mapped by someone else? */
if (!atomic_add_negative(-1, &page->_mapcount))
return;
@@ -1131,8 +1131,19 @@ void page_remove_rmap(struct page *page)
* this if the page is anon, so about to be freed; but perhaps
* not if it's in swapcache - there might be another pte slot
* containing the swap entry, but page not yet written to swap.
+ *
+ * And we can skip it on file pages, so long as the filesystem
+ * participates in dirty tracking; but need to catch shm and tmpfs
+ * and ramfs pages which have been modified since creation by read
+ * fault.
+ *
+ * Note that mapping must be decided above, before decrementing
+ * mapcount (which luckily provides a barrier): once page is unmapped,
+ * it could be truncated and page->mapping reset to NULL at any moment.
+ * Note also that we are relying on page_mapping(page) to set mapping
+ * to &swapper_space when PageSwapCache(page).
*/
- if ((!PageAnon(page) || PageSwapCache(page)) &&
+ if (mapping && !mapping_cap_account_dirty(mapping) &&
page_test_and_clear_dirty(page_to_pfn(page), 1))
set_page_dirty(page);
/*
diff --git a/mm/shmem.c b/mm/shmem.c
index df31a44..492584c 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1168,19 +1168,20 @@ static struct mempolicy *shmem_get_sbmpol(struct shmem_sb_info *sbinfo)
static struct page *shmem_swapin(swp_entry_t entry, gfp_t gfp,
struct shmem_inode_info *info, unsigned long idx)
{
- struct mempolicy mpol, *spol;
struct vm_area_struct pvma;
struct page *page;
- spol = mpol_cond_copy(&mpol,
- mpol_shared_policy_lookup(&info->policy, idx));
-
/* Create a pseudo vma that just contains the policy */
pvma.vm_start = 0;
pvma.vm_pgoff = idx;
pvma.vm_ops = NULL;
- pvma.vm_policy = spol;
+ pvma.vm_policy = mpol_shared_policy_lookup(&info->policy, idx);
+
page = swapin_readahead(entry, gfp, &pvma, 0);
+
+ /* Drop reference taken by mpol_shared_policy_lookup() */
+ mpol_cond_put(pvma.vm_policy);
+
return page;
}
@@ -1188,6 +1189,7 @@ static struct page *shmem_alloc_page(gfp_t gfp,
struct shmem_inode_info *info, unsigned long idx)
{
struct vm_area_struct pvma;
+ struct page *page;
/* Create a pseudo vma that just contains the policy */
pvma.vm_start = 0;
@@ -1195,10 +1197,12 @@ static struct page *shmem_alloc_page(gfp_t gfp,
pvma.vm_ops = NULL;
pvma.vm_policy = mpol_shared_policy_lookup(&info->policy, idx);
- /*
- * alloc_page_vma() will drop the shared policy reference
- */
- return alloc_page_vma(gfp, &pvma, 0);
+ page = alloc_page_vma(gfp, &pvma, 0);
+
+ /* Drop reference taken by mpol_shared_policy_lookup() */
+ mpol_cond_put(pvma.vm_policy);
+
+ return page;
}
#else /* !CONFIG_NUMA */
#ifdef CONFIG_TMPFS
diff --git a/mm/sparse.c b/mm/sparse.c
index 4cd05e5..9054f83 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -619,7 +619,7 @@ static void __kfree_section_memmap(struct page *memmap, unsigned long nr_pages)
{
return; /* XXX: Not implemented yet */
}
-static void free_map_bootmem(struct page *page, unsigned long nr_pages)
+static void free_map_bootmem(struct page *memmap, unsigned long nr_pages)
{
}
#else
@@ -660,10 +660,11 @@ static void __kfree_section_memmap(struct page *memmap, unsigned long nr_pages)
get_order(sizeof(struct page) * nr_pages));
}
-static void free_map_bootmem(struct page *page, unsigned long nr_pages)
+static void free_map_bootmem(struct page *memmap, unsigned long nr_pages)
{
unsigned long maps_section_nr, removing_section_nr, i;
unsigned long magic;
+ struct page *page = virt_to_page(memmap);
for (i = 0; i < nr_pages; i++, page++) {
magic = (unsigned long) page->lru.next;
@@ -712,13 +713,10 @@ static void free_section_usemap(struct page *memmap, unsigned long *usemap)
*/
if (memmap) {
- struct page *memmap_page;
- memmap_page = virt_to_page(memmap);
-
nr_pages = PAGE_ALIGN(PAGES_PER_SECTION * sizeof(struct page))
>> PAGE_SHIFT;
- free_map_bootmem(memmap_page, nr_pages);
+ free_map_bootmem(memmap, nr_pages);
}
}
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 5326f98..2174733 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2977,6 +2977,8 @@ static int kswapd(void *p)
&balanced_classzone_idx);
}
}
+
+ current->reclaim_state = NULL;
return 0;
}