aboutsummaryrefslogtreecommitdiff
path: root/mm
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2009-06-16 19:50:13 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2009-06-16 19:50:13 -0700
commit517d08699b250021303f9a7cf0d758b6dc0748ed (patch)
tree5e5b0134c3fffb78fe9d8b1641a64ff28fdd7bbc /mm
parent8eeee4e2f04fc551f50c9d9847da2d73d7d33728 (diff)
parenta34601c5d84134055782ee031d58d82f5440e918 (diff)
downloadlinux-517d08699b250021303f9a7cf0d758b6dc0748ed.tar.gz
Merge branch 'akpm'
* akpm: (182 commits) fbdev: bf54x-lq043fb: use kzalloc over kmalloc/memset fbdev: *bfin*: fix __dev{init,exit} markings fbdev: *bfin*: drop unnecessary calls to memset fbdev: bfin-t350mcqb-fb: drop unused local variables fbdev: blackfin has __raw I/O accessors, so use them in fb.h fbdev: s1d13xxxfb: add accelerated bitblt functions tcx: use standard fields for framebuffer physical address and length fbdev: add support for handoff from firmware to hw framebuffers intelfb: fix a bug when changing video timing fbdev: use framebuffer_release() for freeing fb_info structures radeon: P2G2CLK_ALWAYS_ONb tested twice, should 2nd be P2G2CLK_DAC_ALWAYS_ONb? s3c-fb: CPUFREQ frequency scaling support s3c-fb: fix resource releasing on error during probing carminefb: fix possible access beyond end of carmine_modedb[] acornfb: remove fb_mmap function mb862xxfb: use CONFIG_OF instead of CONFIG_PPC_OF mb862xxfb: restrict compliation of platform driver to PPC Samsung SoC Framebuffer driver: add Alpha Channel support atmel-lcdc: fix pixclock upper bound detection offb: use framebuffer_alloc() to allocate fb_info struct ... Manually fix up conflicts due to kmemcheck in mm/slab.c
Diffstat (limited to 'mm')
-rw-r--r--mm/Kconfig14
-rw-r--r--mm/Makefile1
-rw-r--r--mm/fadvise.c2
-rw-r--r--mm/filemap.c169
-rw-r--r--mm/hugetlb.c106
-rw-r--r--mm/init-mm.c20
-rw-r--r--mm/internal.h33
-rw-r--r--mm/madvise.c26
-rw-r--r--mm/memcontrol.c11
-rw-r--r--mm/memory.c128
-rw-r--r--mm/memory_hotplug.c6
-rw-r--r--mm/mempolicy.c145
-rw-r--r--mm/migrate.c6
-rw-r--r--mm/mlock.c22
-rw-r--r--mm/oom_kill.c64
-rw-r--r--mm/page-writeback.c19
-rw-r--r--mm/page_alloc.c754
-rw-r--r--mm/page_io.c2
-rw-r--r--mm/readahead.c145
-rw-r--r--mm/rmap.c40
-rw-r--r--mm/shmem.c4
-rw-r--r--mm/slab.c11
-rw-r--r--mm/slob.c4
-rw-r--r--mm/slub.c2
-rw-r--r--mm/swap_state.c17
-rw-r--r--mm/swapfile.c276
-rw-r--r--mm/truncate.c39
-rw-r--r--mm/util.c16
-rw-r--r--mm/vmscan.c372
-rw-r--r--mm/vmstat.c19
30 files changed, 1598 insertions, 875 deletions
diff --git a/mm/Kconfig b/mm/Kconfig
index 6f4610a9ce5..c948d4ca8bd 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -203,25 +203,13 @@ config VIRT_TO_BUS
def_bool y
depends on !ARCH_NO_VIRT_TO_BUS
-config UNEVICTABLE_LRU
- bool "Add LRU list to track non-evictable pages"
- default y
- help
- Keeps unevictable pages off of the active and inactive pageout
- lists, so kswapd will not waste CPU time or have its balancing
- algorithms thrown off by scanning these pages. Selecting this
- will use one page flag and increase the code size a little,
- say Y unless you know what you are doing.
-
- See Documentation/vm/unevictable-lru.txt for more information.
-
config HAVE_MLOCK
bool
default y if MMU=y
config HAVE_MLOCKED_PAGE_BIT
bool
- default y if HAVE_MLOCK=y && UNEVICTABLE_LRU=y
+ default y if HAVE_MLOCK=y
config MMU_NOTIFIER
bool
diff --git a/mm/Makefile b/mm/Makefile
index c379ce08354..5e0bd642669 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -12,6 +12,7 @@ obj-y := bootmem.o filemap.o mempool.o oom_kill.o fadvise.o \
readahead.o swap.o truncate.o vmscan.o shmem.o \
prio_tree.o util.o mmzone.o vmstat.o backing-dev.o \
page_isolation.o mm_init.o $(mmu-y)
+obj-y += init-mm.o
obj-$(CONFIG_PROC_PAGE_MONITOR) += pagewalk.o
obj-$(CONFIG_BOUNCE) += bounce.o
diff --git a/mm/fadvise.c b/mm/fadvise.c
index 54a0f8040af..e43359214f6 100644
--- a/mm/fadvise.c
+++ b/mm/fadvise.c
@@ -101,7 +101,7 @@ SYSCALL_DEFINE(fadvise64_64)(int fd, loff_t offset, loff_t len, int advice)
ret = force_page_cache_readahead(mapping, file,
start_index,
- max_sane_readahead(nrpages));
+ nrpages);
if (ret > 0)
ret = 0;
break;
diff --git a/mm/filemap.c b/mm/filemap.c
index 1b60f30cebf..22396713feb 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -521,7 +521,7 @@ struct page *__page_cache_alloc(gfp_t gfp)
{
if (cpuset_do_page_mem_spread()) {
int n = cpuset_mem_spread_node();
- return alloc_pages_node(n, gfp, 0);
+ return alloc_pages_exact_node(n, gfp, 0);
}
return alloc_pages(gfp, 0);
}
@@ -1004,9 +1004,6 @@ EXPORT_SYMBOL(grab_cache_page_nowait);
static void shrink_readahead_size_eio(struct file *filp,
struct file_ra_state *ra)
{
- if (!ra->ra_pages)
- return;
-
ra->ra_pages /= 4;
}
@@ -1390,8 +1387,7 @@ do_readahead(struct address_space *mapping, struct file *filp,
if (!mapping || !mapping->a_ops || !mapping->a_ops->readpage)
return -EINVAL;
- force_page_cache_readahead(mapping, filp, index,
- max_sane_readahead(nr));
+ force_page_cache_readahead(mapping, filp, index, nr);
return 0;
}
@@ -1457,6 +1453,73 @@ static int page_cache_read(struct file *file, pgoff_t offset)
#define MMAP_LOTSAMISS (100)
+/*
+ * Synchronous readahead happens when we don't even find
+ * a page in the page cache at all.
+ */
+static void do_sync_mmap_readahead(struct vm_area_struct *vma,
+ struct file_ra_state *ra,
+ struct file *file,
+ pgoff_t offset)
+{
+ unsigned long ra_pages;
+ struct address_space *mapping = file->f_mapping;
+
+ /* If we don't want any read-ahead, don't bother */
+ if (VM_RandomReadHint(vma))
+ return;
+
+ if (VM_SequentialReadHint(vma) ||
+ offset - 1 == (ra->prev_pos >> PAGE_CACHE_SHIFT)) {
+ page_cache_sync_readahead(mapping, ra, file, offset,
+ ra->ra_pages);
+ return;
+ }
+
+ if (ra->mmap_miss < INT_MAX)
+ ra->mmap_miss++;
+
+ /*
+ * Do we miss much more than hit in this file? If so,
+ * stop bothering with read-ahead. It will only hurt.
+ */
+ if (ra->mmap_miss > MMAP_LOTSAMISS)
+ return;
+
+ /*
+ * mmap read-around
+ */
+ ra_pages = max_sane_readahead(ra->ra_pages);
+ if (ra_pages) {
+ ra->start = max_t(long, 0, offset - ra_pages/2);
+ ra->size = ra_pages;
+ ra->async_size = 0;
+ ra_submit(ra, mapping, file);
+ }
+}
+
+/*
+ * Asynchronous readahead happens when we find the page and PG_readahead,
+ * so we want to possibly extend the readahead further..
+ */
+static void do_async_mmap_readahead(struct vm_area_struct *vma,
+ struct file_ra_state *ra,
+ struct file *file,
+ struct page *page,
+ pgoff_t offset)
+{
+ struct address_space *mapping = file->f_mapping;
+
+ /* If we don't want any read-ahead, don't bother */
+ if (VM_RandomReadHint(vma))
+ return;
+ if (ra->mmap_miss > 0)
+ ra->mmap_miss--;
+ if (PageReadahead(page))
+ page_cache_async_readahead(mapping, ra, file,
+ page, offset, ra->ra_pages);
+}
+
/**
* filemap_fault - read in file data for page fault handling
* @vma: vma in which the fault was taken
@@ -1476,78 +1539,44 @@ int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
struct address_space *mapping = file->f_mapping;
struct file_ra_state *ra = &file->f_ra;
struct inode *inode = mapping->host;
+ pgoff_t offset = vmf->pgoff;
struct page *page;
pgoff_t size;
- int did_readaround = 0;
int ret = 0;
size = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
- if (vmf->pgoff >= size)
+ if (offset >= size)
return VM_FAULT_SIGBUS;
- /* If we don't want any read-ahead, don't bother */
- if (VM_RandomReadHint(vma))
- goto no_cached_page;
-
/*
* Do we have something in the page cache already?
*/
-retry_find:
- page = find_lock_page(mapping, vmf->pgoff);
- /*
- * For sequential accesses, we use the generic readahead logic.
- */
- if (VM_SequentialReadHint(vma)) {
- if (!page) {
- page_cache_sync_readahead(mapping, ra, file,
- vmf->pgoff, 1);
- page = find_lock_page(mapping, vmf->pgoff);
- if (!page)
- goto no_cached_page;
- }
- if (PageReadahead(page)) {
- page_cache_async_readahead(mapping, ra, file, page,
- vmf->pgoff, 1);
- }
- }
-
- if (!page) {
- unsigned long ra_pages;
-
- ra->mmap_miss++;
-
+ page = find_get_page(mapping, offset);
+ if (likely(page)) {
/*
- * Do we miss much more than hit in this file? If so,
- * stop bothering with read-ahead. It will only hurt.
+ * We found the page, so try async readahead before
+ * waiting for the lock.
*/
- if (ra->mmap_miss > MMAP_LOTSAMISS)
- goto no_cached_page;
+ do_async_mmap_readahead(vma, ra, file, page, offset);
+ lock_page(page);
- /*
- * To keep the pgmajfault counter straight, we need to
- * check did_readaround, as this is an inner loop.
- */
- if (!did_readaround) {
- ret = VM_FAULT_MAJOR;
- count_vm_event(PGMAJFAULT);
- }
- did_readaround = 1;
- ra_pages = max_sane_readahead(file->f_ra.ra_pages);
- if (ra_pages) {
- pgoff_t start = 0;
-
- if (vmf->pgoff > ra_pages / 2)
- start = vmf->pgoff - ra_pages / 2;
- do_page_cache_readahead(mapping, file, start, ra_pages);
+ /* Did it get truncated? */
+ if (unlikely(page->mapping != mapping)) {
+ unlock_page(page);
+ put_page(page);
+ goto no_cached_page;
}
- page = find_lock_page(mapping, vmf->pgoff);
+ } else {
+ /* No page in the page cache at all */
+ do_sync_mmap_readahead(vma, ra, file, offset);
+ count_vm_event(PGMAJFAULT);
+ ret = VM_FAULT_MAJOR;
+retry_find:
+ page = find_lock_page(mapping, offset);
if (!page)
goto no_cached_page;
}
- if (!did_readaround)
- ra->mmap_miss--;
-
/*
* We have a locked page in the page cache, now we need to check
* that it's up-to-date. If not, it is going to be due to an error.
@@ -1555,18 +1584,18 @@ retry_find:
if (unlikely(!PageUptodate(page)))
goto page_not_uptodate;
- /* Must recheck i_size under page lock */
+ /*
+ * Found the page and have a reference on it.
+ * We must recheck i_size under page lock.
+ */
size = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
- if (unlikely(vmf->pgoff >= size)) {
+ if (unlikely(offset >= size)) {
unlock_page(page);
page_cache_release(page);
return VM_FAULT_SIGBUS;
}
- /*
- * Found the page and have a reference on it.
- */
- ra->prev_pos = (loff_t)page->index << PAGE_CACHE_SHIFT;
+ ra->prev_pos = (loff_t)offset << PAGE_CACHE_SHIFT;
vmf->page = page;
return ret | VM_FAULT_LOCKED;
@@ -1575,7 +1604,7 @@ no_cached_page:
* We're only likely to ever get here if MADV_RANDOM is in
* effect.
*/
- error = page_cache_read(file, vmf->pgoff);
+ error = page_cache_read(file, offset);
/*
* The page we want has now been added to the page cache.
@@ -1595,12 +1624,6 @@ no_cached_page:
return VM_FAULT_SIGBUS;
page_not_uptodate:
- /* IO error path */
- if (!did_readaround) {
- ret = VM_FAULT_MAJOR;
- count_vm_event(PGMAJFAULT);
- }
-
/*
* Umm, take care of errors if the page isn't up-to-date.
* Try to re-read it _once_. We do this synchronously,
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index e83ad2c9228..a56e6f3ce97 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -578,41 +578,6 @@ static void free_huge_page(struct page *page)
hugetlb_put_quota(mapping, 1);
}
-/*
- * Increment or decrement surplus_huge_pages. Keep node-specific counters
- * balanced by operating on them in a round-robin fashion.
- * Returns 1 if an adjustment was made.
- */
-static int adjust_pool_surplus(struct hstate *h, int delta)
-{
- static int prev_nid;
- int nid = prev_nid;
- int ret = 0;
-
- VM_BUG_ON(delta != -1 && delta != 1);
- do {
- nid = next_node(nid, node_online_map);
- if (nid == MAX_NUMNODES)
- nid = first_node(node_online_map);
-
- /* To shrink on this node, there must be a surplus page */
- if (delta < 0 && !h->surplus_huge_pages_node[nid])
- continue;
- /* Surplus cannot exceed the total number of pages */
- if (delta > 0 && h->surplus_huge_pages_node[nid] >=
- h->nr_huge_pages_node[nid])
- continue;
-
- h->surplus_huge_pages += delta;
- h->surplus_huge_pages_node[nid] += delta;
- ret = 1;
- break;
- } while (nid != prev_nid);
-
- prev_nid = nid;
- return ret;
-}
-
static void prep_new_huge_page(struct hstate *h, struct page *page, int nid)
{
set_compound_page_dtor(page, free_huge_page);
@@ -623,6 +588,34 @@ static void prep_new_huge_page(struct hstate *h, struct page *page, int nid)
put_page(page); /* free it into the hugepage allocator */
}
+static void prep_compound_gigantic_page(struct page *page, unsigned long order)
+{
+ int i;
+ int nr_pages = 1 << order;
+ struct page *p = page + 1;
+
+ /* we rely on prep_new_huge_page to set the destructor */
+ set_compound_order(page, order);
+ __SetPageHead(page);
+ for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) {
+ __SetPageTail(p);
+ p->first_page = page;
+ }
+}
+
+int PageHuge(struct page *page)
+{
+ compound_page_dtor *dtor;
+
+ if (!PageCompound(page))
+ return 0;
+
+ page = compound_head(page);
+ dtor = get_compound_page_dtor(page);
+
+ return dtor == free_huge_page;
+}
+
static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid)
{
struct page *page;
@@ -630,7 +623,7 @@ static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid)
if (h->order >= MAX_ORDER)
return NULL;
- page = alloc_pages_node(nid,
+ page = alloc_pages_exact_node(nid,
htlb_alloc_mask|__GFP_COMP|__GFP_THISNODE|
__GFP_REPEAT|__GFP_NOWARN,
huge_page_order(h));
@@ -649,7 +642,7 @@ static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid)
* Use a helper variable to find the next node and then
* copy it back to hugetlb_next_nid afterwards:
* otherwise there's a window in which a racer might
- * pass invalid nid MAX_NUMNODES to alloc_pages_node.
+ * pass invalid nid MAX_NUMNODES to alloc_pages_exact_node.
* But we don't need to use a spin_lock here: it really
* doesn't matter if occasionally a racer chooses the
* same nid as we do. Move nid forward in the mask even
@@ -875,7 +868,7 @@ static void return_unused_surplus_pages(struct hstate *h,
* can no longer free unreserved surplus pages. This occurs when
* the nodes with surplus pages have no free pages.
*/
- unsigned long remaining_iterations = num_online_nodes();
+ unsigned long remaining_iterations = nr_online_nodes;
/* Uncommit the reservation */
h->resv_huge_pages -= unused_resv_pages;
@@ -904,7 +897,7 @@ static void return_unused_surplus_pages(struct hstate *h,
h->surplus_huge_pages--;
h->surplus_huge_pages_node[nid]--;
nr_pages--;
- remaining_iterations = num_online_nodes();
+ remaining_iterations = nr_online_nodes;
}
}
}
@@ -1140,6 +1133,41 @@ static inline void try_to_free_low(struct hstate *h, unsigned long count)
}
#endif
+/*
+ * Increment or decrement surplus_huge_pages. Keep node-specific counters
+ * balanced by operating on them in a round-robin fashion.
+ * Returns 1 if an adjustment was made.
+ */
+static int adjust_pool_surplus(struct hstate *h, int delta)
+{
+ static int prev_nid;
+ int nid = prev_nid;
+ int ret = 0;
+
+ VM_BUG_ON(delta != -1 && delta != 1);
+ do {
+ nid = next_node(nid, node_online_map);
+ if (nid == MAX_NUMNODES)
+ nid = first_node(node_online_map);
+
+ /* To shrink on this node, there must be a surplus page */
+ if (delta < 0 && !h->surplus_huge_pages_node[nid])
+ continue;
+ /* Surplus cannot exceed the total number of pages */
+ if (delta > 0 && h->surplus_huge_pages_node[nid] >=
+ h->nr_huge_pages_node[nid])
+ continue;
+
+ h->surplus_huge_pages += delta;
+ h->surplus_huge_pages_node[nid] += delta;
+ ret = 1;
+ break;
+ } while (nid != prev_nid);
+
+ prev_nid = nid;
+ return ret;
+}
+
#define persistent_huge_pages(h) (h->nr_huge_pages - h->surplus_huge_pages)
static unsigned long set_max_huge_pages(struct hstate *h, unsigned long count)
{
diff --git a/mm/init-mm.c b/mm/init-mm.c
new file mode 100644
index 00000000000..57aba0da966
--- /dev/null
+++ b/mm/init-mm.c
@@ -0,0 +1,20 @@
+#include <linux/mm_types.h>
+#include <linux/rbtree.h>
+#include <linux/rwsem.h>
+#include <linux/spinlock.h>
+#include <linux/list.h>
+#include <linux/cpumask.h>
+
+#include <asm/atomic.h>
+#include <asm/pgtable.h>
+
+struct mm_struct init_mm = {
+ .mm_rb = RB_ROOT,
+ .pgd = swapper_pg_dir,
+ .mm_users = ATOMIC_INIT(2),
+ .mm_count = ATOMIC_INIT(1),
+ .mmap_sem = __RWSEM_INITIALIZER(init_mm.mmap_sem),
+ .page_table_lock = __SPIN_LOCK_UNLOCKED(init_mm.page_table_lock),
+ .mmlist = LIST_HEAD_INIT(init_mm.mmlist),
+ .cpu_vm_mask = CPU_MASK_ALL,
+};
diff --git a/mm/internal.h b/mm/internal.h
index 987bb03fbdd..f290c4db528 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -16,9 +16,6 @@
void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma,
unsigned long floor, unsigned long ceiling);
-extern void prep_compound_page(struct page *page, unsigned long order);
-extern void prep_compound_gigantic_page(struct page *page, unsigned long order);
-
static inline void set_page_count(struct page *page, int v)
{
atomic_set(&page->_count, v);
@@ -51,6 +48,8 @@ extern void putback_lru_page(struct page *page);
*/
extern unsigned long highest_memmap_pfn;
extern void __free_pages_bootmem(struct page *page, unsigned int order);
+extern void prep_compound_page(struct page *page, unsigned long order);
+
/*
* function for dealing with page's order in buddy system.
@@ -74,7 +73,6 @@ static inline void munlock_vma_pages_all(struct vm_area_struct *vma)
}
#endif
-#ifdef CONFIG_UNEVICTABLE_LRU
/*
* unevictable_migrate_page() called only from migrate_page_copy() to
* migrate unevictable flag to new page.
@@ -86,11 +84,6 @@ static inline void unevictable_migrate_page(struct page *new, struct page *old)
if (TestClearPageUnevictable(old))
SetPageUnevictable(new);
}
-#else
-static inline void unevictable_migrate_page(struct page *new, struct page *old)
-{
-}
-#endif
#ifdef CONFIG_HAVE_MLOCKED_PAGE_BIT
/*
@@ -150,23 +143,6 @@ static inline void mlock_migrate_page(struct page *newpage, struct page *page)
}
}
-/*
- * free_page_mlock() -- clean up attempts to free and mlocked() page.
- * Page should not be on lru, so no need to fix that up.
- * free_pages_check() will verify...
- */
-static inline void free_page_mlock(struct page *page)
-{
- if (unlikely(TestClearPageMlocked(page))) {
- unsigned long flags;
-
- local_irq_save(flags);
- __dec_zone_page_state(page, NR_MLOCK);
- __count_vm_event(UNEVICTABLE_MLOCKFREED);
- local_irq_restore(flags);
- }
-}
-
#else /* CONFIG_HAVE_MLOCKED_PAGE_BIT */
static inline int is_mlocked_vma(struct vm_area_struct *v, struct page *p)
{
@@ -175,7 +151,6 @@ static inline int is_mlocked_vma(struct vm_area_struct *v, struct page *p)
static inline void clear_page_mlock(struct page *page) { }
static inline void mlock_vma_page(struct page *page) { }
static inline void mlock_migrate_page(struct page *new, struct page *old) { }
-static inline void free_page_mlock(struct page *page) { }
#endif /* CONFIG_HAVE_MLOCKED_PAGE_BIT */
@@ -284,4 +259,8 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
unsigned long start, int len, int flags,
struct page **pages, struct vm_area_struct **vmas);
+#define ZONE_RECLAIM_NOSCAN -2
+#define ZONE_RECLAIM_FULL -1
+#define ZONE_RECLAIM_SOME 0
+#define ZONE_RECLAIM_SUCCESS 1
#endif
diff --git a/mm/madvise.c b/mm/madvise.c
index b9ce574827c..76eb4193acd 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -123,8 +123,7 @@ static long madvise_willneed(struct vm_area_struct * vma,
end = vma->vm_end;
end = ((end - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
- force_page_cache_readahead(file->f_mapping,
- file, start, max_sane_readahead(end - start));
+ force_page_cache_readahead(file->f_mapping, file, start, end - start);
return 0;
}
@@ -239,12 +238,30 @@ madvise_vma(struct vm_area_struct *vma, struct vm_area_struct **prev,
break;
default:
- error = -EINVAL;
+ BUG();
break;
}
return error;
}
+static int
+madvise_behavior_valid(int behavior)
+{
+ switch (behavior) {
+ case MADV_DOFORK:
+ case MADV_DONTFORK:
+ case MADV_NORMAL:
+ case MADV_SEQUENTIAL:
+ case MADV_RANDOM:
+ case MADV_REMOVE:
+ case MADV_WILLNEED:
+ case MADV_DONTNEED:
+ return 1;
+
+ default:
+ return 0;
+ }
+}
/*
* The madvise(2) system call.
*
@@ -290,6 +307,9 @@ SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior)
int write;
size_t len;
+ if (!madvise_behavior_valid(behavior))
+ return error;
+
write = madvise_need_mmap_write(behavior);
if (write)
down_write(&current->mm->mmap_sem);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 78eb8552818..70db6e0a5ee 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -570,6 +570,17 @@ int mem_cgroup_inactive_anon_is_low(struct mem_cgroup *memcg)
return 0;
}
+int mem_cgroup_inactive_file_is_low(struct mem_cgroup *memcg)
+{
+ unsigned long active;
+ unsigned long inactive;
+
+ inactive = mem_cgroup_get_local_zonestat(memcg, LRU_INACTIVE_FILE);
+ active = mem_cgroup_get_local_zonestat(memcg, LRU_ACTIVE_FILE);
+
+ return (active > inactive);
+}
+
unsigned long mem_cgroup_zone_nr_pages(struct mem_cgroup *memcg,
struct zone *zone,
enum lru_list lru)
diff --git a/mm/memory.c b/mm/memory.c
index 4126dd16778..d5d1653d60a 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1360,6 +1360,56 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
return i;
}
+/**
+ * get_user_pages() - pin user pages in memory
+ * @tsk: task_struct of target task
+ * @mm: mm_struct of target mm
+ * @start: starting user address
+ * @len: number of pages from start to pin
+ * @write: whether pages will be written to by the caller
+ * @force: whether to force write access even if user mapping is
+ * readonly. This will result in the page being COWed even
+ * in MAP_SHARED mappings. You do not want this.
+ * @pages: array that receives pointers to the pages pinned.
+ * Should be at least nr_pages long. Or NULL, if caller
+ * only intends to ensure the pages are faulted in.
+ * @vmas: array of pointers to vmas corresponding to each page.
+ * Or NULL if the caller does not require them.
+ *
+ * Returns number of pages pinned. This may be fewer than the number
+ * requested. If len is 0 or negative, returns 0. If no pages
+ * were pinned, returns -errno. Each page returned must be released
+ * with a put_page() call when it is finished with. vmas will only
+ * remain valid while mmap_sem is held.
+ *
+ * Must be called with mmap_sem held for read or write.
+ *
+ * get_user_pages walks a process's page tables and takes a reference to
+ * each struct page that each user address corresponds to at a given
+ * instant. That is, it takes the page that would be accessed if a user
+ * thread accesses the given user virtual address at that instant.
+ *
+ * This does not guarantee that the page exists in the user mappings when
+ * get_user_pages returns, and there may even be a completely different
+ * page there in some cases (eg. if mmapped pagecache has been invalidated
+ * and subsequently re faulted). However it does guarantee that the page
+ * won't be freed completely. And mostly callers simply care that the page
+ * contains data that was valid *at some point in time*. Typically, an IO
+ * or similar operation cannot guarantee anything stronger anyway because
+ * locks can't be held over the syscall boundary.
+ *
+ * If write=0, the page must not be written to. If the page is written to,
+ * set_page_dirty (or set_page_dirty_lock, as appropriate) must be called
+ * after the page is finished with, and before put_page is called.
+ *
+ * get_user_pages is typically used for fewer-copy IO operations, to get a
+ * handle on the memory by some means other than accesses via the user virtual
+ * addresses. The pages may be submitted for DMA to devices or accessed via
+ * their kernel linear mapping (via the kmap APIs). Care should be taken to
+ * use the correct cache flushing APIs.
+ *
+ * See also get_user_pages_fast, for performance critical applications.
+ */
int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
unsigned long start, int len, int write, int force,
struct page **pages, struct vm_area_struct **vmas)
@@ -3053,22 +3103,13 @@ int in_gate_area_no_task(unsigned long addr)
#endif /* __HAVE_ARCH_GATE_AREA */
-#ifdef CONFIG_HAVE_IOREMAP_PROT
-int follow_phys(struct vm_area_struct *vma,
- unsigned long address, unsigned int flags,
- unsigned long *prot, resource_size_t *phys)
+static int follow_pte(struct mm_struct *mm, unsigned long address,
+ pte_t **ptepp, spinlock_t **ptlp)
{
pgd_t *pgd;
pud_t *pud;
pmd_t *pmd;
- pte_t *ptep, pte;
- spinlock_t *ptl;
- resource_size_t phys_addr = 0;
- struct mm_struct *mm = vma->vm_mm;
- int ret = -EINVAL;
-
- if (!(vma->vm_flags & (VM_IO | VM_PFNMAP)))
- goto out;
+ pte_t *ptep;
pgd = pgd_offset(mm, address);
if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd)))
@@ -3086,22 +3127,71 @@ int follow_phys(struct vm_area_struct *vma,
if (pmd_huge(*pmd))
goto out;
- ptep = pte_offset_map_lock(mm, pmd, address, &ptl);
+ ptep = pte_offset_map_lock(mm, pmd, address, ptlp);
if (!ptep)
goto out;
+ if (!pte_present(*ptep))
+ goto unlock;
+ *ptepp = ptep;
+ return 0;
+unlock:
+ pte_unmap_unlock(ptep, *ptlp);
+out:
+ return -EINVAL;
+}
+/**
+ * follow_pfn - look up PFN at a user virtual address
+ * @vma: memory mapping
+ * @address: user virtual address
+ * @pfn: location to store found PFN
+ *
+ * Only IO mappings and raw PFN mappings are allowed.
+ *
+ * Returns zero and the pfn at @pfn on success, -ve otherwise.
+ */
+int follow_pfn(struct vm_area_struct *vma, unsigned long address,
+ unsigned long *pfn)
+{
+ int ret = -EINVAL;
+ spinlock_t *ptl;
+ pte_t *ptep;
+
+ if (!(vma->vm_flags & (VM_IO | VM_PFNMAP)))
+ return ret;
+
+ ret = follow_pte(vma->vm_mm, address, &ptep, &ptl);
+ if (ret)
+ return ret;
+ *pfn = pte_pfn(*ptep);
+ pte_unmap_unlock(ptep, ptl);
+ return 0;
+}
+EXPORT_SYMBOL(follow_pfn);
+
+#ifdef CONFIG_HAVE_IOREMAP_PROT
+int follow_phys(struct vm_area_struct *vma,
+ unsigned long address, unsigned int flags,
+ unsigned long *prot, resource_size_t *phys)
+{
+ int ret = -EINVAL;
+ pte_t *ptep, pte;
+ spinlock_t *ptl;
+
+ if (!(vma->vm_flags & (VM_IO | VM_PFNMAP)))
+ goto out;
+
+ if (follow_pte(vma->vm_mm, address, &ptep, &ptl))
+ goto out;
pte = *ptep;
- if (!pte_present(pte))
- goto unlock;
+
if ((flags & FOLL_WRITE) && !pte_write(pte))
goto unlock;
- phys_addr = pte_pfn(pte);
- phys_addr <<= PAGE_SHIFT; /* Shift here to avoid overflow on PAE */
*prot = pgprot_val(pte_pgprot(pte));
- *phys = phys_addr;
- ret = 0;
+ *phys = (resource_size_t)pte_pfn(pte) << PAGE_SHIFT;
+ ret = 0;
unlock:
pte_unmap_unlock(ptep, ptl);
out:
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index c083cf5fd6d..e4412a676c8 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -422,7 +422,8 @@ int online_pages(unsigned long pfn, unsigned long nr_pages)
zone->present_pages += onlined_pages;
zone->zone_pgdat->node_present_pages += onlined_pages;
- setup_per_zone_pages_min();
+ setup_per_zone_wmarks();
+ calculate_zone_inactive_ratio(zone);
if (onlined_pages) {
kswapd_run(zone_to_nid(zone));
node_set_state(zone_to_nid(zone), N_HIGH_MEMORY);
@@ -832,6 +833,9 @@ repeat:
totalram_pages -= offlined_pages;
num_physpages -= offlined_pages;
+ setup_per_zone_wmarks();
+ calculate_zone_inactive_ratio(zone);
+
vm_total_pages = nr_free_pagecache_pages();
writeback_set_ratelimit();
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 3eb4a6fdc04..e08e2c4da63 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -182,13 +182,54 @@ static int mpol_new_bind(struct mempolicy *pol, const nodemask_t *nodes)
return 0;
}
-/* Create a new policy */
+/*
+ * mpol_set_nodemask is called after mpol_new() to set up the nodemask, if
+ * any, for the new policy. mpol_new() has already validated the nodes
+ * parameter with respect to the policy mode and flags. But, we need to
+ * handle an empty nodemask with MPOL_PREFERRED here.
+ *
+ * Must be called holding task's alloc_lock to protect task's mems_allowed
+ * and mempolicy. May also be called holding the mmap_semaphore for write.
+ */
+static int mpol_set_nodemask(struct mempolicy *pol, const nodemask_t *nodes)
+{
+ nodemask_t cpuset_context_nmask;
+ int ret;
+
+ /* if mode is MPOL_DEFAULT, pol is NULL. This is right. */
+ if (pol == NULL)
+ return 0;
+
+ VM_BUG_ON(!nodes);
+ if (pol->mode == MPOL_PREFERRED && nodes_empty(*nodes))
+ nodes = NULL; /* explicit local allocation */
+ else {
+ if (pol->flags & MPOL_F_RELATIVE_NODES)
+ mpol_relative_nodemask(&cpuset_context_nmask, nodes,
+ &cpuset_current_mems_allowed);
+ else
+ nodes_and(cpuset_context_nmask, *nodes,
+ cpuset_current_mems_allowed);
+ if (mpol_store_user_nodemask(pol))
+ pol->w.user_nodemask = *nodes;
+ else
+ pol->w.cpuset_mems_allowed =
+ cpuset_current_mems_allowed;
+ }
+
+ ret = mpol_ops[pol->mode].create(pol,
+ nodes ? &cpuset_context_nmask : NULL);
+ return ret;
+}
+
+/*
+ * This function just creates a new policy, does some check and simple
+ * initialization. You must invoke mpol_set_nodemask() to set nodes.
+ */
static struct mempolicy *mpol_new(unsigned short mode, unsigned short flags,
nodemask_t *nodes)
{
struct mempolicy *policy;
- nodemask_t cpuset_context_nmask;
- int ret;
pr_debug("setting mode %d flags %d nodes[0] %lx\n",
mode, flags, nodes ? nodes_addr(*nodes)[0] : -1);
@@ -210,7 +251,6 @@ static struct mempolicy *mpol_new(unsigned short mode, unsigned short flags,
if (((flags & MPOL_F_STATIC_NODES) ||
(flags & MPOL_F_RELATIVE_NODES)))
return ERR_PTR(-EINVAL);
- nodes = NULL; /* flag local alloc */
}
} else if (nodes_empty(*nodes))
return ERR_PTR(-EINVAL);
@@ -221,30 +261,6 @@ static struct mempolicy *mpol_new(unsigned short mode, unsigned short flags,
policy->mode = mode;
policy->flags = flags;
- if (nodes) {
- /*
- * cpuset related setup doesn't apply to local allocation
- */
- cpuset_update_task_memory_state();
- if (flags & MPOL_F_RELATIVE_NODES)
- mpol_relative_nodemask(&cpuset_context_nmask, nodes,
- &cpuset_current_mems_allowed);
- else
- nodes_and(cpuset_context_nmask, *nodes,
- cpuset_current_mems_allowed);
- if (mpol_store_user_nodemask(policy))
- policy->w.user_nodemask = *nodes;
- else
- policy->w.cpuset_mems_allowed =
- cpuset_mems_allowed(current);
- }
-
- ret = mpol_ops[mode].create(policy,
- nodes ? &cpuset_context_nmask : NULL);
- if (ret < 0) {
- kmem_cache_free(policy_cache, policy);
- return ERR_PTR(ret);
- }
return policy;
}
@@ -324,6 +340,8 @@ static void mpol_rebind_policy(struct mempolicy *pol,
/*
* Wrapper for mpol_rebind_policy() that just requires task
* pointer, and updates task mempolicy.
+ *
+ * Called with task's alloc_lock held.
*/
void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new)
@@ -600,8 +618,9 @@ static void mpol_set_task_struct_flag(void)
static long do_set_mempolicy(unsigned short mode, unsigned short flags,
nodemask_t *nodes)
{
- struct mempolicy *new;
+ struct mempolicy *new, *old;
struct mm_struct *mm = current->mm;
+ int ret;
new = mpol_new(mode, flags, nodes);
if (IS_ERR(new))
@@ -615,20 +634,33 @@ static long do_set_mempolicy(unsigned short mode, unsigned short flags,
*/
if (mm)
down_write(&mm->mmap_sem);
- mpol_put(current->mempolicy);
+ task_lock(current);
+ ret = mpol_set_nodemask(new, nodes);
+ if (ret) {
+ task_unlock(current);
+ if (mm)
+ up_write(&mm->mmap_sem);
+ mpol_put(new);
+ return ret;
+ }
+ old = current->mempolicy;
current->mempolicy = new;
mpol_set_task_struct_flag();
if (new && new->mode == MPOL_INTERLEAVE &&
nodes_weight(new->v.nodes))
current->il_next = first_node(new->v.nodes);
+ task_unlock(current);
if (mm)
up_write(&mm->mmap_sem);
+ mpol_put(old);
return 0;
}
/*
* Return nodemask for policy for get_mempolicy() query
+ *
+ * Called with task's alloc_lock held
*/
static void get_policy_nodemask(struct mempolicy *p, nodemask_t *nodes)
{
@@ -674,7 +706,6 @@ static long do_get_mempolicy(int *policy, nodemask_t *nmask,
struct vm_area_struct *vma = NULL;
struct mempolicy *pol = current->mempolicy;
- cpuset_update_task_memory_state();
if (flags &
~(unsigned long)(MPOL_F_NODE|MPOL_F_ADDR|MPOL_F_MEMS_ALLOWED))
return -EINVAL;
@@ -683,7 +714,9 @@ static long do_get_mempolicy(int *policy, nodemask_t *nmask,
if (flags & (MPOL_F_NODE|MPOL_F_ADDR))
return -EINVAL;
*policy = 0; /* just so it's initialized */
+ task_lock(current);
*nmask = cpuset_current_mems_allowed;
+ task_unlock(current);
return 0;
}
@@ -738,8 +771,11 @@ static long do_get_mempolicy(int *policy, nodemask_t *nmask,
}
err = 0;
- if (nmask)
+ if (nmask) {
+ task_lock(current);
get_policy_nodemask(pol, nmask);
+ task_unlock(current);
+ }
out:
mpol_cond_put(pol);
@@ -767,7 +803,7 @@ static void migrate_page_add(struct page *page, struct list_head *pagelist,
static struct page *new_node_page(struct page *page, unsigned long node, int **x)
{
- return alloc_pages_node(node, GFP_HIGHUSER_MOVABLE, 0);
+ return alloc_pages_exact_node(node, GFP_HIGHUSER_MOVABLE, 0);
}
/*
@@ -979,6 +1015,14 @@ static long do_mbind(unsigned long start, unsigned long len,
return err;
}
down_write(&mm->mmap_sem);
+ task_lock(current);
+ err = mpol_set_nodemask(new, nmask);
+ task_unlock(current);
+ if (err) {
+ up_write(&mm->mmap_sem);
+ mpol_put(new);
+ return err;
+ }
vma = check_range(mm, start, end, nmask,
flags | MPOL_MF_INVERT, &pagelist);
@@ -1545,8 +1589,6 @@ alloc_page_vma(gfp_t gfp, struct vm_area_struct *vma, unsigned long addr)
struct mempolicy *pol = get_vma_policy(current, vma, addr);
struct zonelist *zl;
- cpuset_update_task_memory_state();
-
if (unlikely(pol->mode == MPOL_INTERLEAVE)) {
unsigned nid;
@@ -1593,8 +1635,6 @@ struct page *alloc_pages_current(gfp_t gfp, unsigned order)
{
struct mempolicy *pol = current->mempolicy;
- if ((gfp & __GFP_WAIT) && !in_interrupt())
- cpuset_update_task_memory_state();
if (!pol || in_interrupt() || (gfp & __GFP_THISNODE))
pol = &default_policy;
@@ -1854,6 +1894,8 @@ restart:
*/
void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol)
{
+ int ret;
+
sp->root = RB_ROOT; /* empty tree == default mempolicy */
spin_lock_init(&sp->lock);
@@ -1863,9 +1905,19 @@ void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol)
/* contextualize the tmpfs mount point mempolicy */
new = mpol_new(mpol->mode, mpol->flags, &mpol->w.user_nodemask);
- mpol_put(mpol); /* drop our ref on sb mpol */
- if (IS_ERR(new))
+ if (IS_ERR(new)) {
+ mpol_put(mpol); /* drop our ref on sb mpol */
return; /* no valid nodemask intersection */
+ }
+
+ task_lock(current);
+ ret = mpol_set_nodemask(new, &mpol->w.user_nodemask);
+ task_unlock(current);
+ mpol_put(mpol); /* drop our ref on sb mpol */
+ if (ret) {
+ mpol_put(new);
+ return;
+ }
/* Create pseudo-vma that contains just the policy */
memset(&pvma, 0, sizeof(struct vm_area_struct));
@@ -2086,8 +2138,19 @@ int mpol_parse_str(char *str, struct mempolicy **mpol, int no_context)
new = mpol_new(mode, mode_flags, &nodes);
if (IS_ERR(new))
err = 1;
- else if (no_context)
- new->w.user_nodemask = nodes; /* save for contextualization */
+ else {
+ int ret;
+
+ task_lock(current);
+ ret = mpol_set_nodemask(new, &nodes);
+ task_unlock(current);
+ if (ret)
+ err = 1;
+ else if (no_context) {
+ /* save for contextualization */
+ new->w.user_nodemask = nodes;
+ }
+ }
out:
/* Restore string for error message */
diff --git a/mm/migrate.c b/mm/migrate.c
index 068655d8f88..939888f9dda 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -802,7 +802,7 @@ static struct page *new_page_node(struct page *p, unsigned long private,
*result = &pm->status;
- return alloc_pages_node(pm->node,
+ return alloc_pages_exact_node(pm->node,
GFP_HIGHUSER_MOVABLE | GFP_THISNODE, 0);
}
@@ -820,7 +820,6 @@ static int do_move_page_to_node_array(struct mm_struct *mm,
struct page_to_node *pp;
LIST_HEAD(pagelist);
- migrate_prep();
down_read(&mm->mmap_sem);
/*
@@ -907,6 +906,9 @@ static int do_pages_move(struct mm_struct *mm, struct task_struct *task,
pm = (struct page_to_node *)__get_free_page(GFP_KERNEL);
if (!pm)
goto out;
+
+ migrate_prep();
+
/*
* Store a chunk of page_to_node array in a page,
* but keep the last one as a marker
diff --git a/mm/mlock.c b/mm/mlock.c
index ac130433c7d..45eb650b965 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -31,7 +31,6 @@ int can_do_mlock(void)
}
EXPORT_SYMBOL(can_do_mlock);
-#ifdef CONFIG_UNEVICTABLE_LRU
/*
* Mlocked pages are marked with PageMlocked() flag for efficient testing
* in vmscan and, possibly, the fault path; and to support semi-accurate
@@ -261,27 +260,6 @@ static int __mlock_posix_error_return(long retval)
return retval;
}
-#else /* CONFIG_UNEVICTABLE_LRU */
-
-/*
- * Just make pages present if VM_LOCKED. No-op if unlocking.
- */
-static long __mlock_vma_pages_range(struct vm_area_struct *vma,
- unsigned long start, unsigned long end,
- int mlock)
-{
- if (mlock && (vma->vm_flags & VM_LOCKED))
- return make_pages_present(start, end);
- return 0;
-}
-
-static inline int __mlock_posix_error_return(long retval)
-{
- return 0;
-}
-
-#endif /* CONFIG_UNEVICTABLE_LRU */
-
/**
* mlock_vma_pages_range() - mlock pages in specified vma range.
* @vma - the vma containing the specfied address range
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index a7b2460e922..175a67a78a9 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -58,6 +58,7 @@ unsigned long badness(struct task_struct *p, unsigned long uptime)
unsigned long points, cpu_time, run_time;
struct mm_struct *mm;
struct task_struct *child;
+ int oom_adj;
task_lock(p);
mm = p->mm;
@@ -65,6 +66,11 @@ unsigned long badness(struct task_struct *p, unsigned long uptime)
task_unlock(p);
return 0;
}
+ oom_adj = mm->oom_adj;
+ if (oom_adj == OOM_DISABLE) {
+ task_unlock(p);
+ return 0;
+ }
/*
* The memory size of the process is the basis for the badness.
@@ -148,15 +154,15 @@ unsigned long badness(struct task_struct *p, unsigned long uptime)
points /= 8;
/*
- * Adjust the score by oomkilladj.
+ * Adjust the score by oom_adj.
*/
- if (p->oomkilladj) {
- if (p->oomkilladj > 0) {
+ if (oom_adj) {
+ if (oom_adj > 0) {
if (!points)
points = 1;
- points <<= p->oomkilladj;
+ points <<= oom_adj;
} else
- points >>= -(p->oomkilladj);
+ points >>= -(oom_adj);
}
#ifdef DEBUG
@@ -251,11 +257,8 @@ static struct task_struct *select_bad_process(unsigned long *ppoints,
*ppoints = ULONG_MAX;
}
- if (p->oomkilladj == OOM_DISABLE)
- continue;
-
points = badness(p, uptime.tv_sec);
- if (points > *ppoints || !chosen) {
+ if (points > *ppoints) {
chosen = p;
*ppoints = points;
}
@@ -304,8 +307,7 @@ static void dump_tasks(const struct mem_cgroup *mem)
}
printk(KERN_INFO "[%5d] %5d %5d %8lu %8lu %3d %3d %s\n",
p->pid, __task_cred(p)->uid, p->tgid, mm->total_vm,
- get_mm_rss(mm), (int)task_cpu(p), p->oomkilladj,
- p->comm);
+ get_mm_rss(mm), (int)task_cpu(p), mm->oom_adj, p->comm);
task_unlock(p);
} while_each_thread(g, p);
}
@@ -323,11 +325,8 @@ static void __oom_kill_task(struct task_struct *p, int verbose)
return;
}
- if (!p->mm) {
- WARN_ON(1);
- printk(KERN_WARNING "tried to kill an mm-less task!\n");
+ if (!p->mm)
return;
- }
if (verbose)
printk(KERN_ERR "Killed process %d (%s)\n",
@@ -349,28 +348,13 @@ static int oom_kill_task(struct task_struct *p)
struct mm_struct *mm;
struct task_struct *g, *q;
+ task_lock(p);
mm = p->mm;
-
- /* WARNING: mm may not be dereferenced since we did not obtain its
- * value from get_task_mm(p). This is OK since all we need to do is
- * compare mm to q->mm below.
- *
- * Furthermore, even if mm contains a non-NULL value, p->mm may
- * change to NULL at any time since we do not hold task_lock(p).
- * However, this is of no concern to us.
- */
-
- if (mm == NULL)
+ if (!mm || mm->oom_adj == OOM_DISABLE) {
+ task_unlock(p);
return 1;
-
- /*
- * Don't kill the process if any threads are set to OOM_DISABLE
- */
- do_each_thread(g, q) {
- if (q->mm == mm && q->oomkilladj == OOM_DISABLE)
- return 1;
- } while_each_thread(g, q);
-
+ }
+ task_unlock(p);
__oom_kill_task(p, 1);
/*
@@ -393,10 +377,11 @@ static int oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
struct task_struct *c;
if (printk_ratelimit()) {
- printk(KERN_WARNING "%s invoked oom-killer: "
- "gfp_mask=0x%x, order=%d, oomkilladj=%d\n",
- current->comm, gfp_mask, order, current->oomkilladj);
task_lock(current);
+ printk(KERN_WARNING "%s invoked oom-killer: "
+ "gfp_mask=0x%x, order=%d, oom_adj=%d\n",
+ current->comm, gfp_mask, order,
+ current->mm ? current->mm->oom_adj : OOM_DISABLE);
cpuset_print_task_mems_allowed(current);
task_unlock(current);
dump_stack();
@@ -409,8 +394,9 @@ static int oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
/*
* If the task is already exiting, don't alarm the sysadmin or kill
* its children or threads, just set TIF_MEMDIE so it can die quickly
+ * if its mm is still attached.
*/
- if (p->flags & PF_EXITING) {
+ if (p->mm && (p->flags & PF_EXITING)) {
__oom_kill_task(p, 0);
return 0;
}
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index bb553c3e955..7b0dcea4935 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -265,18 +265,19 @@ static void bdi_writeout_fraction(struct backing_dev_info *bdi,
* This avoids exceeding the total dirty_limit when the floating averages
* fluctuate too quickly.
*/
-static void
-clip_bdi_dirty_limit(struct backing_dev_info *bdi, long dirty, long *pbdi_dirty)
+static void clip_bdi_dirty_limit(struct backing_dev_info *bdi,
+ unsigned long dirty, unsigned long *pbdi_dirty)
{
- long avail_dirty;
+ unsigned long avail_dirty;
- avail_dirty = dirty -
- (global_page_state(NR_FILE_DIRTY) +
+ avail_dirty = global_page_state(NR_FILE_DIRTY) +
global_page_state(NR_WRITEBACK) +
global_page_state(NR_UNSTABLE_NFS) +
- global_page_state(NR_WRITEBACK_TEMP));
+ global_page_state(NR_WRITEBACK_TEMP);
- if (avail_dirty < 0)
+ if (avail_dirty < dirty)
+ avail_dirty = dirty - avail_dirty;
+ else
avail_dirty = 0;
avail_dirty += bdi_stat(bdi, BDI_RECLAIMABLE) +
@@ -299,10 +300,10 @@ static inline void task_dirties_fraction(struct task_struct *tsk,
*
* dirty -= (dirty/8) * p_{t}
*/
-static void task_dirty_limit(struct task_struct *tsk, long *pdirty)
+static void task_dirty_limit(struct task_struct *tsk, unsigned long *pdirty)
{
long numerator, denominator;
- long dirty = *pdirty;
+ unsigned long dirty = *pdirty;
u64 inv = dirty >> 3;
task_dirties_fraction(tsk, &numerator, &denominator);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 0727896a88a..a5f3c278c57 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -162,17 +162,25 @@ static unsigned long __meminitdata dma_reserve;
#if MAX_NUMNODES > 1
int nr_node_ids __read_mostly = MAX_NUMNODES;
+int nr_online_nodes __read_mostly = 1;
EXPORT_SYMBOL(nr_node_ids);
+EXPORT_SYMBOL(nr_online_nodes);
#endif
int page_group_by_mobility_disabled __read_mostly;
static void set_pageblock_migratetype(struct page *page, int migratetype)
{
+
+ if (unlikely(page_group_by_mobility_disabled))
+ migratetype = MIGRATE_UNMOVABLE;
+
set_pageblock_flags_group(page, (unsigned long)migratetype,
PB_migrate, PB_migrate_end);
}
+bool oom_killer_disabled __read_mostly;
+
#ifdef CONFIG_DEBUG_VM
static int page_outside_zone_boundaries(struct zone *zone, struct page *page)
{
@@ -295,23 +303,6 @@ void prep_compound_page(struct page *page, unsigned long order)
}
}
-#ifdef CONFIG_HUGETLBFS
-void prep_compound_gigantic_page(struct page *page, unsigned long order)
-{
- int i;
- int nr_pages = 1 << order;
- struct page *p = page + 1;
-
- set_compound_page_dtor(page, free_compound_page);
- set_compound_order(page, order);
- __SetPageHead(page);
- for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) {
- __SetPageTail(p);
- p->first_page = page;
- }
-}
-#endif
-
static int destroy_compound_page(struct page *page, unsigned long order)
{
int i;
@@ -418,7 +409,7 @@ static inline int page_is_buddy(struct page *page, struct page *buddy,
return 0;
if (PageBuddy(buddy) && page_order(buddy) == order) {
- BUG_ON(page_count(buddy) != 0);
+ VM_BUG_ON(page_count(buddy) != 0);
return 1;
}
return 0;
@@ -449,22 +440,22 @@ static inline int page_is_buddy(struct page *page, struct page *buddy,
*/
static inline void __free_one_page(struct page *page,
- struct zone *zone, unsigned int order)
+ struct zone *zone, unsigned int order,
+ int migratetype)
{
unsigned long page_idx;
- int order_size = 1 << order;
- int migratetype = get_pageblock_migratetype(page);
if (unlikely(PageCompound(page)))
if (unlikely(destroy_compound_page(page, order)))
return;
+ VM_BUG_ON(migratetype == -1);
+
page_idx = page_to_pfn(page) & ((1 << MAX_ORDER) - 1);
- VM_BUG_ON(page_idx & (order_size - 1));
+ VM_BUG_ON(page_idx & ((1 << order) - 1));
VM_BUG_ON(bad_range(zone, page));
- __mod_zone_page_state(zone, NR_FREE_PAGES, order_size);
while (order < MAX_ORDER-1) {
unsigned long combined_idx;
struct page *buddy;
@@ -488,12 +479,27 @@ static inline void __free_one_page(struct page *page,
zone->free_area[order].nr_free++;
}
+#ifdef CONFIG_HAVE_MLOCKED_PAGE_BIT
+/*
+ * free_page_mlock() -- clean up attempts to free and mlocked() page.
+ * Page should not be on lru, so no need to fix that up.
+ * free_pages_check() will verify...
+ */
+static inline void free_page_mlock(struct page *page)
+{
+ __ClearPageMlocked(page);
+ __dec_zone_page_state(page, NR_MLOCK);
+ __count_vm_event(UNEVICTABLE_MLOCKFREED);
+}
+#else
+static void free_page_mlock(struct page *page) { }
+#endif
+
static inline int free_pages_check(struct page *page)
{
- free_page_mlock(page);
if (unlikely(page_mapcount(page) |
(page->mapping != NULL) |
- (page_count(page) != 0) |
+ (atomic_read(&page->_count) != 0) |
(page->flags & PAGE_FLAGS_CHECK_AT_FREE))) {
bad_page(page);
return 1;
@@ -520,6 +526,8 @@ static void free_pages_bulk(struct zone *zone, int count,
spin_lock(&zone->lock);
zone_clear_flag(zone, ZONE_ALL_UNRECLAIMABLE);
zone->pages_scanned = 0;
+
+ __mod_zone_page_state(zone, NR_FREE_PAGES, count << order);
while (count--) {
struct page *page;
@@ -527,17 +535,20 @@ static void free_pages_bulk(struct zone *zone, int count,
page = list_entry(list->prev, struct page, lru);
/* have to delete it as __free_one_page list manipulates */
list_del(&page->lru);
- __free_one_page(page, zone, order);
+ __free_one_page(page, zone, order, page_private(page));
}
spin_unlock(&zone->lock);
}
-static void free_one_page(struct zone *zone, struct page *page, int order)
+static void free_one_page(struct zone *zone, struct page *page, int order,
+ int migratetype)
{
spin_lock(&zone->lock);
zone_clear_flag(zone, ZONE_ALL_UNRECLAIMABLE);
zone->pages_scanned = 0;
- __free_one_page(page, zone, order);
+
+ __mod_zone_page_state(zone, NR_FREE_PAGES, 1 << order);
+ __free_one_page(page, zone, order, migratetype);
spin_unlock(&zone->lock);
}
@@ -546,6 +557,7 @@ static void __free_pages_ok(struct page *page, unsigned int order)
unsigned long flags;
int i;
int bad = 0;
+ int clearMlocked = PageMlocked(page);
kmemcheck_free_shadow(page, order);
@@ -563,8 +575,11 @@ static void __free_pages_ok(struct page *page, unsigned int order)
kernel_map_pages(page, 1 << order, 0);
local_irq_save(flags);
+ if (unlikely(clearMlocked))
+ free_page_mlock(page);
__count_vm_events(PGFREE, 1 << order);
- free_one_page(page_zone(page), page, order);
+ free_one_page(page_zone(page), page, order,
+ get_pageblock_migratetype(page));
local_irq_restore(flags);
}
@@ -635,7 +650,7 @@ static int prep_new_page(struct page *page, int order, gfp_t gfp_flags)
{
if (unlikely(page_mapcount(page) |
(page->mapping != NULL) |
- (page_count(page) != 0) |
+ (atomic_read(&page->_count) != 0) |
(page->flags & PAGE_FLAGS_CHECK_AT_PREP))) {
bad_page(page);
return 1;
@@ -660,7 +675,8 @@ static int prep_new_page(struct page *page, int order, gfp_t gfp_flags)
* Go through the free lists for the given migratetype and remove
* the smallest available page from the freelists
*/
-static struct page *__rmqueue_smallest(struct zone *zone, unsigned int order,
+static inline
+struct page *__rmqueue_smallest(struct zone *zone, unsigned int order,
int migratetype)
{
unsigned int current_order;
@@ -678,7 +694,6 @@ static struct page *__rmqueue_smallest(struct zone *zone, unsigned int order,
list_del(&page->lru);
rmv_page_order(page);
area->nr_free--;
- __mod_zone_page_state(zone, NR_FREE_PAGES, - (1UL << order));
expand(zone, page, order, current_order, area, migratetype);
return page;
}
@@ -769,8 +784,8 @@ static int move_freepages_block(struct zone *zone, struct page *page,
}
/* Remove an element from the buddy allocator from the fallback list */
-static struct page *__rmqueue_fallback(struct zone *zone, int order,
- int start_migratetype)
+static inline struct page *
+__rmqueue_fallback(struct zone *zone, int order, int start_migratetype)
{
struct free_area * area;
int current_order;
@@ -818,8 +833,6 @@ static struct page *__rmqueue_fallback(struct zone *zone, int order,
/* Remove the page from the freelists */
list_del(&page->lru);
rmv_page_order(page);
- __mod_zone_page_state(zone, NR_FREE_PAGES,
- -(1UL << order));
if (current_order == pageblock_order)
set_pageblock_migratetype(page,
@@ -830,8 +843,7 @@ static struct page *__rmqueue_fallback(struct zone *zone, int order,
}
}
- /* Use MIGRATE_RESERVE rather than fail an allocation */
- return __rmqueue_smallest(zone, order, MIGRATE_RESERVE);
+ return NULL;
}
/*
@@ -843,11 +855,23 @@ static struct page *__rmqueue(struct zone *zone, unsigned int order,
{
struct page *page;
+retry_reserve:
page = __rmqueue_smallest(zone, order, migratetype);
- if (unlikely(!page))
+ if (unlikely(!page) && migratetype != MIGRATE_RESERVE) {
page = __rmqueue_fallback(zone, order, migratetype);
+ /*
+ * Use MIGRATE_RESERVE rather than fail an allocation. goto
+ * is used because __rmqueue_smallest is an inline function
+ * and we want just one call site
+ */
+ if (!page) {
+ migratetype = MIGRATE_RESERVE;
+ goto retry_reserve;
+ }
+ }
+
return page;
}
@@ -881,6 +905,7 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order,
set_page_private(page, migratetype);
list = &page->lru;
}
+ __mod_zone_page_state(zone, NR_FREE_PAGES, -(i << order));
spin_unlock(&zone->lock);
return i;
}
@@ -996,6 +1021,7 @@ static void free_hot_cold_page(struct page *page, int cold)
struct zone *zone = page_zone(page);
struct per_cpu_pages *pcp;
unsigned long flags;
+ int clearMlocked = PageMlocked(page);
kmemcheck_free_shadow(page, 0);
@@ -1012,13 +1038,16 @@ static void free_hot_cold_page(struct page *page, int cold)
kernel_map_pages(page, 1, 0);
pcp = &zone_pcp(zone, get_cpu())->pcp;
+ set_page_private(page, get_pageblock_migratetype(page));
local_irq_save(flags);
+ if (unlikely(clearMlocked))
+ free_page_mlock(page);
__count_vm_event(PGFREE);
+
if (cold)
list_add_tail(&page->lru, &pcp->list);
else
list_add(&page->lru, &pcp->list);
- set_page_private(page, get_pageblock_migratetype(page));
pcp->count++;
if (pcp->count >= pcp->high) {
free_pages_bulk(zone, pcp->batch, &pcp->list, 0);
@@ -1071,14 +1100,15 @@ void split_page(struct page *page, unsigned int order)
* we cheat by calling it from here, in the order > 0 path. Saves a branch
* or two.
*/
-static struct page *buffered_rmqueue(struct zone *preferred_zone,
- struct zone *zone, int order, gfp_t gfp_flags)
+static inline
+struct page *buffered_rmqueue(struct zone *preferred_zone,
+ struct zone *zone, int order, gfp_t gfp_flags,
+ int migratetype)
{
unsigned long flags;
struct page *page;
int cold = !!(gfp_flags & __GFP_COLD);
int cpu;
- int migratetype = allocflags_to_migratetype(gfp_flags);
again:
cpu = get_cpu();
@@ -1115,8 +1145,22 @@ again:
list_del(&page->lru);
pcp->count--;
} else {
+ if (unlikely(gfp_flags & __GFP_NOFAIL)) {
+ /*
+ * __GFP_NOFAIL is not to be used in new code.
+ *
+ * All __GFP_NOFAIL callers should be fixed so that they
+ * properly detect and handle allocation failures.
+ *
+ * We most definitely don't want callers attempting to
+ * allocate greater than single-page units with
+ * __GFP_NOFAIL.
+ */
+ WARN_ON_ONCE(order > 0);
+ }
spin_lock_irqsave(&zone->lock, flags);
page = __rmqueue(zone, order, migratetype);
+ __mod_zone_page_state(zone, NR_FREE_PAGES, -(1 << order));
spin_unlock(&zone->lock);
if (!page)
goto failed;
@@ -1138,10 +1182,15 @@ failed:
return NULL;
}
-#define ALLOC_NO_WATERMARKS 0x01 /* don't check watermarks at all */
-#define ALLOC_WMARK_MIN 0x02 /* use pages_min watermark */
-#define ALLOC_WMARK_LOW 0x04 /* use pages_low watermark */
-#define ALLOC_WMARK_HIGH 0x08 /* use pages_high watermark */
+/* The ALLOC_WMARK bits are used as an index to zone->watermark */
+#define ALLOC_WMARK_MIN WMARK_MIN
+#define ALLOC_WMARK_LOW WMARK_LOW
+#define ALLOC_WMARK_HIGH WMARK_HIGH
+#define ALLOC_NO_WATERMARKS 0x04 /* don't check watermarks at all */
+
+/* Mask to get the watermark bits */
+#define ALLOC_WMARK_MASK (ALLOC_NO_WATERMARKS-1)
+
#define ALLOC_HARDER 0x10 /* try to alloc harder */
#define ALLOC_HIGH 0x20 /* __GFP_HIGH set */
#define ALLOC_CPUSET 0x40 /* check for correct cpuset */
@@ -1399,23 +1448,18 @@ static void zlc_mark_zone_full(struct zonelist *zonelist, struct zoneref *z)
*/
static struct page *
get_page_from_freelist(gfp_t gfp_mask, nodemask_t *nodemask, unsigned int order,
- struct zonelist *zonelist, int high_zoneidx, int alloc_flags)
+ struct zonelist *zonelist, int high_zoneidx, int alloc_flags,
+ struct zone *preferred_zone, int migratetype)
{
struct zoneref *z;
struct page *page = NULL;
int classzone_idx;
- struct zone *zone, *preferred_zone;
+ struct zone *zone;
nodemask_t *allowednodes = NULL;/* zonelist_cache approximation */
int zlc_active = 0; /* set if using zonelist_cache */
int did_zlc_setup = 0; /* just call zlc_setup() one time */
- (void)first_zones_zonelist(zonelist, high_zoneidx, nodemask,
- &preferred_zone);
- if (!preferred_zone)
- return NULL;
-
classzone_idx = zone_idx(preferred_zone);
-
zonelist_scan:
/*
* Scan zonelist, looking for a zone with enough free.
@@ -1430,31 +1474,49 @@ zonelist_scan:
!cpuset_zone_allowed_softwall(zone, gfp_mask))
goto try_next_zone;
+ BUILD_BUG_ON(ALLOC_NO_WATERMARKS < NR_WMARK);
if (!(alloc_flags & ALLOC_NO_WATERMARKS)) {
unsigned long mark;
- if (alloc_flags & ALLOC_WMARK_MIN)
- mark = zone->pages_min;
- else if (alloc_flags & ALLOC_WMARK_LOW)
- mark = zone->pages_low;
- else
- mark = zone->pages_high;
- if (!zone_watermark_ok(zone, order, mark,
- classzone_idx, alloc_flags)) {
- if (!zone_reclaim_mode ||
- !zone_reclaim(zone, gfp_mask, order))
+ int ret;
+
+ mark = zone->watermark[alloc_flags & ALLOC_WMARK_MASK];
+ if (zone_watermark_ok(zone, order, mark,
+ classzone_idx, alloc_flags))
+ goto try_this_zone;
+
+ if (zone_reclaim_mode == 0)
+ goto this_zone_full;
+
+ ret = zone_reclaim(zone, gfp_mask, order);
+ switch (ret) {
+ case ZONE_RECLAIM_NOSCAN:
+ /* did not scan */
+ goto try_next_zone;
+ case ZONE_RECLAIM_FULL:
+ /* scanned but unreclaimable */
+ goto this_zone_full;
+ default:
+ /* did we reclaim enough */
+ if (!zone_watermark_ok(zone, order, mark,
+ classzone_idx, alloc_flags))
goto this_zone_full;
}
}
- page = buffered_rmqueue(preferred_zone, zone, order, gfp_mask);
+try_this_zone:
+ page = buffered_rmqueue(preferred_zone, zone, order,
+ gfp_mask, migratetype);
if (page)
break;
this_zone_full:
if (NUMA_BUILD)
zlc_mark_zone_full(zonelist, z);
try_next_zone:
- if (NUMA_BUILD && !did_zlc_setup) {
- /* we do zlc_setup after the first zone is tried */
+ if (NUMA_BUILD && !did_zlc_setup && nr_online_nodes > 1) {
+ /*
+ * we do zlc_setup after the first zone is tried but only
+ * if there are multiple nodes make it worthwhile
+ */
allowednodes = zlc_setup(zonelist, alloc_flags);
zlc_active = 1;
did_zlc_setup = 1;
@@ -1469,47 +1531,217 @@ try_next_zone:
return page;
}
+static inline int
+should_alloc_retry(gfp_t gfp_mask, unsigned int order,
+ unsigned long pages_reclaimed)
+{
+ /* Do not loop if specifically requested */
+ if (gfp_mask & __GFP_NORETRY)
+ return 0;
+
+ /*
+ * In this implementation, order <= PAGE_ALLOC_COSTLY_ORDER
+ * means __GFP_NOFAIL, but that may not be true in other
+ * implementations.
+ */
+ if (order <= PAGE_ALLOC_COSTLY_ORDER)
+ return 1;
+
+ /*
+ * For order > PAGE_ALLOC_COSTLY_ORDER, if __GFP_REPEAT is
+ * specified, then we retry until we no longer reclaim any pages
+ * (above), or we've reclaimed an order of pages at least as
+ * large as the allocation's order. In both cases, if the
+ * allocation still fails, we stop retrying.
+ */
+ if (gfp_mask & __GFP_REPEAT && pages_reclaimed < (1 << order))
+ return 1;
+
+ /*
+ * Don't let big-order allocations loop unless the caller
+ * explicitly requests that.
+ */
+ if (gfp_mask & __GFP_NOFAIL)
+ return 1;
+
+ return 0;
+}
+
+static inline struct page *
+__alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
+ struct zonelist *zonelist, enum zone_type high_zoneidx,
+ nodemask_t *nodemask, struct zone *preferred_zone,
+ int migratetype)
+{
+ struct page *page;
+
+ /* Acquire the OOM killer lock for the zones in zonelist */
+ if (!try_set_zone_oom(zonelist, gfp_mask)) {
+ schedule_timeout_uninterruptible(1);
+ return NULL;
+ }
+
+ /*
+ * Go through the zonelist yet one more time, keep very high watermark
+ * here, this is only to catch a parallel oom killing, we must fail if
+ * we're still under heavy pressure.
+ */
+ page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask,
+ order, zonelist, high_zoneidx,
+ ALLOC_WMARK_HIGH|ALLOC_CPUSET,
+ preferred_zone, migratetype);
+ if (page)
+ goto out;
+
+ /* The OOM killer will not help higher order allocs */
+ if (order > PAGE_ALLOC_COSTLY_ORDER && !(gfp_mask & __GFP_NOFAIL))
+ goto out;
+
+ /* Exhausted what can be done so it's blamo time */
+ out_of_memory(zonelist, gfp_mask, order);
+
+out:
+ clear_zonelist_oom(zonelist, gfp_mask);
+ return page;
+}
+
+/* The really slow allocator path where we enter direct reclaim */
+static inline struct page *
+__alloc_pages_direct_reclaim(gfp_t gfp_mask, unsigned int order,
+ struct zonelist *zonelist, enum zone_type high_zoneidx,
+ nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone,
+ int migratetype, unsigned long *did_some_progress)
+{
+ struct page *page = NULL;
+ struct reclaim_state reclaim_state;
+ struct task_struct *p = current;
+
+ cond_resched();
+
+ /* We now go into synchronous reclaim */
+ cpuset_memory_pressure_bump();
+
+ /*
+ * The task's cpuset might have expanded its set of allowable nodes
+ */
+ p->flags |= PF_MEMALLOC;
+ lockdep_set_current_reclaim_state(gfp_mask);
+ reclaim_state.reclaimed_slab = 0;
+ p->reclaim_state = &reclaim_state;
+
+ *did_some_progress = try_to_free_pages(zonelist, order, gfp_mask, nodemask);
+
+ p->reclaim_state = NULL;
+ lockdep_clear_current_reclaim_state();
+ p->flags &= ~PF_MEMALLOC;
+
+ cond_resched();
+
+ if (order != 0)
+ drain_all_pages();
+
+ if (likely(*did_some_progress))
+ page = get_page_from_freelist(gfp_mask, nodemask, order,
+ zonelist, high_zoneidx,
+ alloc_flags, preferred_zone,
+ migratetype);
+ return page;
+}
+
/*
- * This is the 'heart' of the zoned buddy allocator.
+ * This is called in the allocator slow-path if the allocation request is of
+ * sufficient urgency to ignore watermarks and take other desperate measures
*/
-struct page *
-__alloc_pages_internal(gfp_t gfp_mask, unsigned int order,
- struct zonelist *zonelist, nodemask_t *nodemask)
+static inline struct page *
+__alloc_pages_high_priority(gfp_t gfp_mask, unsigned int order,
+ struct zonelist *zonelist, enum zone_type high_zoneidx,
+ nodemask_t *nodemask, struct zone *preferred_zone,
+ int migratetype)
+{
+ struct page *page;
+
+ do {
+ page = get_page_from_freelist(gfp_mask, nodemask, order,
+ zonelist, high_zoneidx, ALLOC_NO_WATERMARKS,
+ preferred_zone, migratetype);
+
+ if (!page && gfp_mask & __GFP_NOFAIL)
+ congestion_wait(WRITE, HZ/50);
+ } while (!page && (gfp_mask & __GFP_NOFAIL));
+
+ return page;
+}
+
+static inline
+void wake_all_kswapd(unsigned int order, struct zonelist *zonelist,
+ enum zone_type high_zoneidx)
{
- const gfp_t wait = gfp_mask & __GFP_WAIT;
- enum zone_type high_zoneidx = gfp_zone(gfp_mask);
struct zoneref *z;
struct zone *zone;
- struct page *page;
- struct reclaim_state reclaim_state;
- struct task_struct *p = current;
- int do_retry;
- int alloc_flags;
- unsigned long did_some_progress;
- unsigned long pages_reclaimed = 0;
- lockdep_trace_alloc(gfp_mask);
+ for_each_zone_zonelist(zone, z, zonelist, high_zoneidx)
+ wakeup_kswapd(zone, order);
+}
- might_sleep_if(wait);
+static inline int
+gfp_to_alloc_flags(gfp_t gfp_mask)
+{
+ struct task_struct *p = current;
+ int alloc_flags = ALLOC_WMARK_MIN | ALLOC_CPUSET;
+ const gfp_t wait = gfp_mask & __GFP_WAIT;
- if (should_fail_alloc_page(gfp_mask, order))
- return NULL;
+ /* __GFP_HIGH is assumed to be the same as ALLOC_HIGH to save a branch. */
+ BUILD_BUG_ON(__GFP_HIGH != ALLOC_HIGH);
-restart:
- z = zonelist->_zonerefs; /* the list of zones suitable for gfp_mask */
+ /*
+ * The caller may dip into page reserves a bit more if the caller
+ * cannot run direct reclaim, or if the caller has realtime scheduling
+ * policy or is asking for __GFP_HIGH memory. GFP_ATOMIC requests will
+ * set both ALLOC_HARDER (!wait) and ALLOC_HIGH (__GFP_HIGH).
+ */
+ alloc_flags |= (gfp_mask & __GFP_HIGH);
- if (unlikely(!z->zone)) {
+ if (!wait) {
+ alloc_flags |= ALLOC_HARDER;
/*
- * Happens if we have an empty zonelist as a result of
- * GFP_THISNODE being used on a memoryless node
+ * Ignore cpuset if GFP_ATOMIC (!wait) rather than fail alloc.
+ * See also cpuset_zone_allowed() comment in kernel/cpuset.c.
*/
- return NULL;
+ alloc_flags &= ~ALLOC_CPUSET;
+ } else if (unlikely(rt_task(p)))
+ alloc_flags |= ALLOC_HARDER;
+
+ if (likely(!(gfp_mask & __GFP_NOMEMALLOC))) {
+ if (!in_interrupt() &&
+ ((p->flags & PF_MEMALLOC) ||
+ unlikely(test_thread_flag(TIF_MEMDIE))))
+ alloc_flags |= ALLOC_NO_WATERMARKS;
}
- page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask, order,
- zonelist, high_zoneidx, ALLOC_WMARK_LOW|ALLOC_CPUSET);
- if (page)
- goto got_pg;
+ return alloc_flags;
+}
+
+static inline struct page *
+__alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
+ struct zonelist *zonelist, enum zone_type high_zoneidx,
+ nodemask_t *nodemask, struct zone *preferred_zone,
+ int migratetype)
+{
+ const gfp_t wait = gfp_mask & __GFP_WAIT;
+ struct page *page = NULL;
+ int alloc_flags;
+ unsigned long pages_reclaimed = 0;
+ unsigned long did_some_progress;
+ struct task_struct *p = current;
+
+ /*
+ * In the slowpath, we sanity check order to avoid ever trying to
+ * reclaim >= MAX_ORDER areas which will never succeed. Callers may
+ * be using allocators in order of preference for an area that is
+ * too large.
+ */
+ if (WARN_ON_ONCE(order >= MAX_ORDER))
+ return NULL;
/*
* GFP_THISNODE (meaning __GFP_THISNODE, __GFP_NORETRY and
@@ -1522,154 +1754,83 @@ restart:
if (NUMA_BUILD && (gfp_mask & GFP_THISNODE) == GFP_THISNODE)
goto nopage;
- for_each_zone_zonelist(zone, z, zonelist, high_zoneidx)
- wakeup_kswapd(zone, order);
+ wake_all_kswapd(order, zonelist, high_zoneidx);
/*
* OK, we're below the kswapd watermark and have kicked background
* reclaim. Now things get more complex, so set up alloc_flags according
* to how we want to proceed.
- *
- * The caller may dip into page reserves a bit more if the caller
- * cannot run direct reclaim, or if the caller has realtime scheduling
- * policy or is asking for __GFP_HIGH memory. GFP_ATOMIC requests will
- * set both ALLOC_HARDER (!wait) and ALLOC_HIGH (__GFP_HIGH).
*/
- alloc_flags = ALLOC_WMARK_MIN;
- if ((unlikely(rt_task(p)) && !in_interrupt()) || !wait)
- alloc_flags |= ALLOC_HARDER;
- if (gfp_mask & __GFP_HIGH)
- alloc_flags |= ALLOC_HIGH;
- if (wait)
- alloc_flags |= ALLOC_CPUSET;
+ alloc_flags = gfp_to_alloc_flags(gfp_mask);
- /*
- * Go through the zonelist again. Let __GFP_HIGH and allocations
- * coming from realtime tasks go deeper into reserves.
- *
- * This is the last chance, in general, before the goto nopage.
- * Ignore cpuset if GFP_ATOMIC (!wait) rather than fail alloc.
- * See also cpuset_zone_allowed() comment in kernel/cpuset.c.
- */
+restart:
+ /* This is the last chance, in general, before the goto nopage. */
page = get_page_from_freelist(gfp_mask, nodemask, order, zonelist,
- high_zoneidx, alloc_flags);
+ high_zoneidx, alloc_flags & ~ALLOC_NO_WATERMARKS,
+ preferred_zone, migratetype);
if (page)
goto got_pg;
- /* This allocation should allow future memory freeing. */
-
rebalance:
- if (((p->flags & PF_MEMALLOC) || unlikely(test_thread_flag(TIF_MEMDIE)))
- && !in_interrupt()) {
- if (!(gfp_mask & __GFP_NOMEMALLOC)) {
-nofail_alloc:
- /* go through the zonelist yet again, ignoring mins */
- page = get_page_from_freelist(gfp_mask, nodemask, order,
- zonelist, high_zoneidx, ALLOC_NO_WATERMARKS);
- if (page)
- goto got_pg;
- if (gfp_mask & __GFP_NOFAIL) {
- congestion_wait(WRITE, HZ/50);
- goto nofail_alloc;
- }
- }
- goto nopage;
+ /* Allocate without watermarks if the context allows */
+ if (alloc_flags & ALLOC_NO_WATERMARKS) {
+ page = __alloc_pages_high_priority(gfp_mask, order,
+ zonelist, high_zoneidx, nodemask,
+ preferred_zone, migratetype);
+ if (page)
+ goto got_pg;
}
/* Atomic allocations - we can't balance anything */
if (!wait)
goto nopage;
- cond_resched();
+ /* Avoid recursion of direct reclaim */
+ if (p->flags & PF_MEMALLOC)
+ goto nopage;
+
+ /* Try direct reclaim and then allocating */
+ page = __alloc_pages_direct_reclaim(gfp_mask, order,
+ zonelist, high_zoneidx,
+ nodemask,
+ alloc_flags, preferred_zone,
+ migratetype, &did_some_progress);
+ if (page)
+ goto got_pg;
- /* We now go into synchronous reclaim */
- cpuset_memory_pressure_bump();
/*
- * The task's cpuset might have expanded its set of allowable nodes
+ * If we failed to make any progress reclaiming, then we are
+ * running out of options and have to consider going OOM
*/
- cpuset_update_task_memory_state();
- p->flags |= PF_MEMALLOC;
-
- lockdep_set_current_reclaim_state(gfp_mask);
- reclaim_state.reclaimed_slab = 0;
- p->reclaim_state = &reclaim_state;
-
- did_some_progress = try_to_free_pages(zonelist, order,
- gfp_mask, nodemask);
-
- p->reclaim_state = NULL;
- lockdep_clear_current_reclaim_state();
- p->flags &= ~PF_MEMALLOC;
-
- cond_resched();
+ if (!did_some_progress) {
+ if ((gfp_mask & __GFP_FS) && !(gfp_mask & __GFP_NORETRY)) {
+ if (oom_killer_disabled)
+ goto nopage;
+ page = __alloc_pages_may_oom(gfp_mask, order,
+ zonelist, high_zoneidx,
+ nodemask, preferred_zone,
+ migratetype);
+ if (page)
+ goto got_pg;
- if (order != 0)
- drain_all_pages();
+ /*
+ * The OOM killer does not trigger for high-order
+ * ~__GFP_NOFAIL allocations so if no progress is being
+ * made, there are no other options and retrying is
+ * unlikely to help.
+ */
+ if (order > PAGE_ALLOC_COSTLY_ORDER &&
+ !(gfp_mask & __GFP_NOFAIL))
+ goto nopage;
- if (likely(did_some_progress)) {
- page = get_page_from_freelist(gfp_mask, nodemask, order,
- zonelist, high_zoneidx, alloc_flags);
- if (page)
- goto got_pg;
- } else if ((gfp_mask & __GFP_FS) && !(gfp_mask & __GFP_NORETRY)) {
- if (!try_set_zone_oom(zonelist, gfp_mask)) {
- schedule_timeout_uninterruptible(1);
goto restart;
}
-
- /*
- * Go through the zonelist yet one more time, keep
- * very high watermark here, this is only to catch
- * a parallel oom killing, we must fail if we're still
- * under heavy pressure.
- */
- page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask,
- order, zonelist, high_zoneidx,
- ALLOC_WMARK_HIGH|ALLOC_CPUSET);
- if (page) {
- clear_zonelist_oom(zonelist, gfp_mask);
- goto got_pg;
- }
-
- /* The OOM killer will not help higher order allocs so fail */
- if (order > PAGE_ALLOC_COSTLY_ORDER) {
- clear_zonelist_oom(zonelist, gfp_mask);
- goto nopage;
- }
-
- out_of_memory(zonelist, gfp_mask, order);
- clear_zonelist_oom(zonelist, gfp_mask);
- goto restart;
}
- /*
- * Don't let big-order allocations loop unless the caller explicitly
- * requests that. Wait for some write requests to complete then retry.
- *
- * In this implementation, order <= PAGE_ALLOC_COSTLY_ORDER
- * means __GFP_NOFAIL, but that may not be true in other
- * implementations.
- *
- * For order > PAGE_ALLOC_COSTLY_ORDER, if __GFP_REPEAT is
- * specified, then we retry until we no longer reclaim any pages
- * (above), or we've reclaimed an order of pages at least as
- * large as the allocation's order. In both cases, if the
- * allocation still fails, we stop retrying.
- */
+ /* Check if we should retry the allocation */
pages_reclaimed += did_some_progress;
- do_retry = 0;
- if (!(gfp_mask & __GFP_NORETRY)) {
- if (order <= PAGE_ALLOC_COSTLY_ORDER) {
- do_retry = 1;
- } else {
- if (gfp_mask & __GFP_REPEAT &&
- pages_reclaimed < (1 << order))
- do_retry = 1;
- }
- if (gfp_mask & __GFP_NOFAIL)
- do_retry = 1;
- }
- if (do_retry) {
+ if (should_alloc_retry(gfp_mask, order, pages_reclaimed)) {
+ /* Wait for some write requests to complete then retry */
congestion_wait(WRITE, HZ/50);
goto rebalance;
}
@@ -1687,8 +1848,53 @@ got_pg:
if (kmemcheck_enabled)
kmemcheck_pagealloc_alloc(page, order, gfp_mask);
return page;
+
+}
+
+/*
+ * This is the 'heart' of the zoned buddy allocator.
+ */
+struct page *
+__alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
+ struct zonelist *zonelist, nodemask_t *nodemask)
+{
+ enum zone_type high_zoneidx = gfp_zone(gfp_mask);
+ struct zone *preferred_zone;
+ struct page *page;
+ int migratetype = allocflags_to_migratetype(gfp_mask);
+
+ lockdep_trace_alloc(gfp_mask);
+
+ might_sleep_if(gfp_mask & __GFP_WAIT);
+
+ if (should_fail_alloc_page(gfp_mask, order))
+ return NULL;
+
+ /*
+ * Check the zones suitable for the gfp_mask contain at least one
+ * valid zone. It's possible to have an empty zonelist as a result
+ * of GFP_THISNODE and a memoryless node
+ */
+ if (unlikely(!zonelist->_zonerefs->zone))
+ return NULL;
+
+ /* The preferred zone is used for statistics later */
+ first_zones_zonelist(zonelist, high_zoneidx, nodemask, &preferred_zone);
+ if (!preferred_zone)
+ return NULL;
+
+ /* First allocation attempt */
+ page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask, order,
+ zonelist, high_zoneidx, ALLOC_WMARK_LOW|ALLOC_CPUSET,
+ preferred_zone, migratetype);
+ if (unlikely(!page))
+ page = __alloc_pages_slowpath(gfp_mask, order,
+ zonelist, high_zoneidx, nodemask,
+ preferred_zone, migratetype);
+
+ return page;
}
-EXPORT_SYMBOL(__alloc_pages_internal);
+EXPORT_SYMBOL(__alloc_pages_nodemask);
/*
* Common helper functions.
@@ -1817,7 +2023,7 @@ static unsigned int nr_free_zone_pages(int offset)
for_each_zone_zonelist(zone, z, zonelist, offset) {
unsigned long size = zone->present_pages;
- unsigned long high = zone->pages_high;
+ unsigned long high = high_wmark_pages(zone);
if (size > high)
sum += size - high;
}
@@ -1909,19 +2115,14 @@ void show_free_areas(void)
printk("Active_anon:%lu active_file:%lu inactive_anon:%lu\n"
" inactive_file:%lu"
-//TODO: check/adjust line lengths
-#ifdef CONFIG_UNEVICTABLE_LRU
" unevictable:%lu"
-#endif
" dirty:%lu writeback:%lu unstable:%lu\n"
" free:%lu slab:%lu mapped:%lu pagetables:%lu bounce:%lu\n",
global_page_state(NR_ACTIVE_ANON),
global_page_state(NR_ACTIVE_FILE),
global_page_state(NR_INACTIVE_ANON),
global_page_state(NR_INACTIVE_FILE),
-#ifdef CONFIG_UNEVICTABLE_LRU
global_page_state(NR_UNEVICTABLE),
-#endif
global_page_state(NR_FILE_DIRTY),
global_page_state(NR_WRITEBACK),
global_page_state(NR_UNSTABLE_NFS),
@@ -1945,25 +2146,21 @@ void show_free_areas(void)
" inactive_anon:%lukB"
" active_file:%lukB"
" inactive_file:%lukB"
-#ifdef CONFIG_UNEVICTABLE_LRU
" unevictable:%lukB"
-#endif
" present:%lukB"
" pages_scanned:%lu"
" all_unreclaimable? %s"
"\n",
zone->name,
K(zone_page_state(zone, NR_FREE_PAGES)),
- K(zone->pages_min),
- K(zone->pages_low),
- K(zone->pages_high),
+ K(min_wmark_pages(zone)),
+ K(low_wmark_pages(zone)),
+ K(high_wmark_pages(zone)),
K(zone_page_state(zone, NR_ACTIVE_ANON)),
K(zone_page_state(zone, NR_INACTIVE_ANON)),
K(zone_page_state(zone, NR_ACTIVE_FILE)),
K(zone_page_state(zone, NR_INACTIVE_FILE)),
-#ifdef CONFIG_UNEVICTABLE_LRU
K(zone_page_state(zone, NR_UNEVICTABLE)),
-#endif
K(zone->present_pages),
zone->pages_scanned,
(zone_is_all_unreclaimable(zone) ? "yes" : "no")
@@ -2121,7 +2318,7 @@ int numa_zonelist_order_handler(ctl_table *table, int write,
}
-#define MAX_NODE_LOAD (num_online_nodes())
+#define MAX_NODE_LOAD (nr_online_nodes)
static int node_load[MAX_NUMNODES];
/**
@@ -2330,7 +2527,7 @@ static void build_zonelists(pg_data_t *pgdat)
/* NUMA-aware ordering of nodes */
local_node = pgdat->node_id;
- load = num_online_nodes();
+ load = nr_online_nodes;
prev_node = local_node;
nodes_clear(used_mask);
@@ -2481,7 +2678,7 @@ void build_all_zonelists(void)
printk("Built %i zonelists in %s order, mobility grouping %s. "
"Total pages: %ld\n",
- num_online_nodes(),
+ nr_online_nodes,
zonelist_order_name[current_zonelist_order],
page_group_by_mobility_disabled ? "off" : "on",
vm_total_pages);
@@ -2560,8 +2757,8 @@ static inline unsigned long wait_table_bits(unsigned long size)
/*
* Mark a number of pageblocks as MIGRATE_RESERVE. The number
- * of blocks reserved is based on zone->pages_min. The memory within the
- * reserve will tend to store contiguous free pages. Setting min_free_kbytes
+ * of blocks reserved is based on min_wmark_pages(zone). The memory within
+ * the reserve will tend to store contiguous free pages. Setting min_free_kbytes
* higher will lead to a bigger reserve which will get freed as contiguous
* blocks as reclaim kicks in
*/
@@ -2574,7 +2771,7 @@ static void setup_zone_migrate_reserve(struct zone *zone)
/* Get the start pfn, end pfn and the number of blocks to reserve */
start_pfn = zone->zone_start_pfn;
end_pfn = start_pfn + zone->spanned_pages;
- reserve = roundup(zone->pages_min, pageblock_nr_pages) >>
+ reserve = roundup(min_wmark_pages(zone), pageblock_nr_pages) >>
pageblock_order;
for (pfn = start_pfn; pfn < end_pfn; pfn += pageblock_nr_pages) {
@@ -3506,7 +3703,7 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat,
zone_pcp_init(zone);
for_each_lru(l) {
INIT_LIST_HEAD(&zone->lru[l].list);
- zone->lru[l].nr_scan = 0;
+ zone->lru[l].nr_saved_scan = 0;
}
zone->reclaim_stat.recent_rotated[0] = 0;
zone->reclaim_stat.recent_rotated[1] = 0;
@@ -4043,6 +4240,11 @@ void __init free_area_init_nodes(unsigned long *max_zone_pfn)
early_node_map[i].start_pfn,
early_node_map[i].end_pfn);
+ /*
+ * find_zone_movable_pfns_for_nodes/early_calculate_totalpages init
+ * that node_mask, clear it at first
+ */
+ nodes_clear(node_states[N_HIGH_MEMORY]);
/* Initialise every node */
mminit_verify_pageflags_layout();
setup_nr_node_ids();
@@ -4177,8 +4379,8 @@ static void calculate_totalreserve_pages(void)
max = zone->lowmem_reserve[j];
}
- /* we treat pages_high as reserved pages. */
- max += zone->pages_high;
+ /* we treat the high watermark as reserved pages. */
+ max += high_wmark_pages(zone);
if (max > zone->present_pages)
max = zone->present_pages;
@@ -4228,12 +4430,13 @@ static void setup_per_zone_lowmem_reserve(void)
}
/**
- * setup_per_zone_pages_min - called when min_free_kbytes changes.
+ * setup_per_zone_wmarks - called when min_free_kbytes changes
+ * or when memory is hot-{added|removed}
*
- * Ensures that the pages_{min,low,high} values for each zone are set correctly
- * with respect to min_free_kbytes.
+ * Ensures that the watermark[min,low,high] values for each zone are set
+ * correctly with respect to min_free_kbytes.
*/
-void setup_per_zone_pages_min(void)
+void setup_per_zone_wmarks(void)
{
unsigned long pages_min = min_free_kbytes >> (PAGE_SHIFT - 10);
unsigned long lowmem_pages = 0;
@@ -4258,7 +4461,7 @@ void setup_per_zone_pages_min(void)
* need highmem pages, so cap pages_min to a small
* value here.
*
- * The (pages_high-pages_low) and (pages_low-pages_min)
+ * The WMARK_HIGH-WMARK_LOW and (WMARK_LOW-WMARK_MIN)
* deltas controls asynch page reclaim, and so should
* not be capped for highmem.
*/
@@ -4269,17 +4472,17 @@ void setup_per_zone_pages_min(void)
min_pages = SWAP_CLUSTER_MAX;
if (min_pages > 128)
min_pages = 128;
- zone->pages_min = min_pages;
+ zone->watermark[WMARK_MIN] = min_pages;
} else {
/*
* If it's a lowmem zone, reserve a number of pages
* proportionate to the zone's size.
*/
- zone->pages_min = tmp;
+ zone->watermark[WMARK_MIN] = tmp;
}
- zone->pages_low = zone->pages_min + (tmp >> 2);
- zone->pages_high = zone->pages_min + (tmp >> 1);
+ zone->watermark[WMARK_LOW] = min_wmark_pages(zone) + (tmp >> 2);
+ zone->watermark[WMARK_HIGH] = min_wmark_pages(zone) + (tmp >> 1);
setup_zone_migrate_reserve(zone);
spin_unlock_irqrestore(&zone->lock, flags);
}
@@ -4289,8 +4492,6 @@ void setup_per_zone_pages_min(void)
}
/**
- * setup_per_zone_inactive_ratio - called when min_free_kbytes changes.
- *
* The inactive anon list should be small enough that the VM never has to
* do too much work, but large enough that each inactive page has a chance
* to be referenced again before it is swapped out.
@@ -4311,21 +4512,26 @@ void setup_per_zone_pages_min(void)
* 1TB 101 10GB
* 10TB 320 32GB
*/
-static void setup_per_zone_inactive_ratio(void)
+void calculate_zone_inactive_ratio(struct zone *zone)
{
- struct zone *zone;
-
- for_each_zone(zone) {
- unsigned int gb, ratio;
+ unsigned int gb, ratio;
- /* Zone size in gigabytes */
- gb = zone->present_pages >> (30 - PAGE_SHIFT);
+ /* Zone size in gigabytes */
+ gb = zone->present_pages >> (30 - PAGE_SHIFT);
+ if (gb)
ratio = int_sqrt(10 * gb);
- if (!ratio)
- ratio = 1;
+ else
+ ratio = 1;
- zone->inactive_ratio = ratio;
- }
+ zone->inactive_ratio = ratio;
+}
+
+static void __init setup_per_zone_inactive_ratio(void)
+{
+ struct zone *zone;
+
+ for_each_zone(zone)
+ calculate_zone_inactive_ratio(zone);
}
/*
@@ -4352,7 +4558,7 @@ static void setup_per_zone_inactive_ratio(void)
* 8192MB: 11584k
* 16384MB: 16384k
*/
-static int __init init_per_zone_pages_min(void)
+static int __init init_per_zone_wmark_min(void)
{
unsigned long lowmem_kbytes;
@@ -4363,12 +4569,12 @@ static int __init init_per_zone_pages_min(void)
min_free_kbytes = 128;
if (min_free_kbytes > 65536)
min_free_kbytes = 65536;
- setup_per_zone_pages_min();
+ setup_per_zone_wmarks();
setup_per_zone_lowmem_reserve();
setup_per_zone_inactive_ratio();
return 0;
}
-module_init(init_per_zone_pages_min)
+module_init(init_per_zone_wmark_min)
/*
* min_free_kbytes_sysctl_handler - just a wrapper around proc_dointvec() so
@@ -4380,7 +4586,7 @@ int min_free_kbytes_sysctl_handler(ctl_table *table, int write,
{
proc_dointvec(table, write, file, buffer, length, ppos);
if (write)
- setup_per_zone_pages_min();
+ setup_per_zone_wmarks();
return 0;
}
@@ -4424,7 +4630,7 @@ int sysctl_min_slab_ratio_sysctl_handler(ctl_table *table, int write,
* whenever sysctl_lowmem_reserve_ratio changes.
*
* The reserve ratio obviously has absolutely no relation with the
- * pages_min watermarks. The lowmem reserve ratio can only make sense
+ * minimum watermarks. The lowmem reserve ratio can only make sense
* if in function of the boot time zone sizes.
*/
int lowmem_reserve_ratio_sysctl_handler(ctl_table *table, int write,
@@ -4531,23 +4737,13 @@ void *__init alloc_large_system_hash(const char *tablename,
else if (hashdist)
table = __vmalloc(size, GFP_ATOMIC, PAGE_KERNEL);
else {
- unsigned long order = get_order(size);
- table = (void*) __get_free_pages(GFP_ATOMIC, order);
/*
* If bucketsize is not a power-of-two, we may free
- * some pages at the end of hash table.
+ * some pages at the end of hash table which
+ * alloc_pages_exact() automatically does
*/
- if (table) {
- unsigned long alloc_end = (unsigned long)table +
- (PAGE_SIZE << order);
- unsigned long used = (unsigned long)table +
- PAGE_ALIGN(size);
- split_page(virt_to_page(table), order);
- while (used < alloc_end) {
- free_page(used);
- used += PAGE_SIZE;
- }
- }
+ if (get_order(size) < MAX_ORDER)
+ table = alloc_pages_exact(size, GFP_ATOMIC);
}
} while (!table && size > PAGE_SIZE && --log2qty);
diff --git a/mm/page_io.c b/mm/page_io.c
index 3023c475e04..c6f3e5071de 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -120,7 +120,7 @@ out:
return ret;
}
-int swap_readpage(struct file *file, struct page *page)
+int swap_readpage(struct page *page)
{
struct bio *bio;
int ret = 0;
diff --git a/mm/readahead.c b/mm/readahead.c
index 133b6d52551..aa1aa234523 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -133,15 +133,12 @@ out:
}
/*
- * do_page_cache_readahead actually reads a chunk of disk. It allocates all
+ * __do_page_cache_readahead() actually reads a chunk of disk. It allocates all
* the pages first, then submits them all for I/O. This avoids the very bad
* behaviour which would occur if page allocations are causing VM writeback.
* We really don't want to intermingle reads and writes like that.
*
* Returns the number of pages requested, or the maximum amount of I/O allowed.
- *
- * do_page_cache_readahead() returns -1 if it encountered request queue
- * congestion.
*/
static int
__do_page_cache_readahead(struct address_space *mapping, struct file *filp,
@@ -210,6 +207,7 @@ int force_page_cache_readahead(struct address_space *mapping, struct file *filp,
if (unlikely(!mapping->a_ops->readpage && !mapping->a_ops->readpages))
return -EINVAL;
+ nr_to_read = max_sane_readahead(nr_to_read);
while (nr_to_read) {
int err;
@@ -231,22 +229,6 @@ int force_page_cache_readahead(struct address_space *mapping, struct file *filp,
}
/*
- * This version skips the IO if the queue is read-congested, and will tell the
- * block layer to abandon the readahead if request allocation would block.
- *
- * force_page_cache_readahead() will ignore queue congestion and will block on
- * request queues.
- */
-int do_page_cache_readahead(struct address_space *mapping, struct file *filp,
- pgoff_t offset, unsigned long nr_to_read)
-{
- if (bdi_read_congested(mapping->backing_dev_info))
- return -1;
-
- return __do_page_cache_readahead(mapping, filp, offset, nr_to_read, 0);
-}
-
-/*
* Given a desired number of PAGE_CACHE_SIZE readahead pages, return a
* sensible upper limit.
*/
@@ -259,7 +241,7 @@ unsigned long max_sane_readahead(unsigned long nr)
/*
* Submit IO for the read-ahead request in file_ra_state.
*/
-static unsigned long ra_submit(struct file_ra_state *ra,
+unsigned long ra_submit(struct file_ra_state *ra,
struct address_space *mapping, struct file *filp)
{
int actual;
@@ -348,6 +330,59 @@ static unsigned long get_next_ra_size(struct file_ra_state *ra,
*/
/*
+ * Count contiguously cached pages from @offset-1 to @offset-@max,
+ * this count is a conservative estimation of
+ * - length of the sequential read sequence, or
+ * - thrashing threshold in memory tight systems
+ */
+static pgoff_t count_history_pages(struct address_space *mapping,
+ struct file_ra_state *ra,
+ pgoff_t offset, unsigned long max)
+{
+ pgoff_t head;
+
+ rcu_read_lock();
+ head = radix_tree_prev_hole(&mapping->page_tree, offset - 1, max);
+ rcu_read_unlock();
+
+ return offset - 1 - head;
+}
+
+/*
+ * page cache context based read-ahead
+ */
+static int try_context_readahead(struct address_space *mapping,
+ struct file_ra_state *ra,
+ pgoff_t offset,
+ unsigned long req_size,
+ unsigned long max)
+{
+ pgoff_t size;
+
+ size = count_history_pages(mapping, ra, offset, max);
+
+ /*
+ * no history pages:
+ * it could be a random read
+ */
+ if (!size)
+ return 0;
+
+ /*
+ * starts from beginning of file:
+ * it is a strong indication of long-run stream (or whole-file-read)
+ */
+ if (size >= offset)
+ size *= 2;
+
+ ra->start = offset;
+ ra->size = get_init_ra_size(size + req_size, max);
+ ra->async_size = ra->size;
+
+ return 1;
+}
+
+/*
* A minimal readahead algorithm for trivial sequential/random reads.
*/
static unsigned long
@@ -356,34 +391,26 @@ ondemand_readahead(struct address_space *mapping,
bool hit_readahead_marker, pgoff_t offset,
unsigned long req_size)
{
- int max = ra->ra_pages; /* max readahead pages */
- pgoff_t prev_offset;
- int sequential;
+ unsigned long max = max_sane_readahead(ra->ra_pages);
+
+ /*
+ * start of file
+ */
+ if (!offset)
+ goto initial_readahead;
/*
* It's the expected callback offset, assume sequential access.
* Ramp up sizes, and push forward the readahead window.
*/
- if (offset && (offset == (ra->start + ra->size - ra->async_size) ||
- offset == (ra->start + ra->size))) {
+ if ((offset == (ra->start + ra->size - ra->async_size) ||
+ offset == (ra->start + ra->size))) {
ra->start += ra->size;
ra->size = get_next_ra_size(ra, max);
ra->async_size = ra->size;
goto readit;
}
- prev_offset = ra->prev_pos >> PAGE_CACHE_SHIFT;
- sequential = offset - prev_offset <= 1UL || req_size > max;
-
- /*
- * Standalone, small read.
- * Read as is, and do not pollute the readahead state.
- */
- if (!hit_readahead_marker && !sequential) {
- return __do_page_cache_readahead(mapping, filp,
- offset, req_size, 0);
- }
-
/*
* Hit a marked page without valid readahead state.
* E.g. interleaved reads.
@@ -394,7 +421,7 @@ ondemand_readahead(struct address_space *mapping,
pgoff_t start;
rcu_read_lock();
- start = radix_tree_next_hole(&mapping->page_tree, offset,max+1);
+ start = radix_tree_next_hole(&mapping->page_tree, offset+1,max);
rcu_read_unlock();
if (!start || start - offset > max)
@@ -402,23 +429,53 @@ ondemand_readahead(struct address_space *mapping,
ra->start = start;
ra->size = start - offset; /* old async_size */
+ ra->size += req_size;
ra->size = get_next_ra_size(ra, max);
ra->async_size = ra->size;
goto readit;
}
/*
- * It may be one of
- * - first read on start of file
- * - sequential cache miss
- * - oversize random read
- * Start readahead for it.
+ * oversize read
+ */
+ if (req_size > max)
+ goto initial_readahead;
+
+ /*
+ * sequential cache miss
+ */
+ if (offset - (ra->prev_pos >> PAGE_CACHE_SHIFT) <= 1UL)
+ goto initial_readahead;
+
+ /*
+ * Query the page cache and look for the traces(cached history pages)
+ * that a sequential stream would leave behind.
+ */
+ if (try_context_readahead(mapping, ra, offset, req_size, max))
+ goto readit;
+
+ /*
+ * standalone, small random read
+ * Read as is, and do not pollute the readahead state.
*/
+ return __do_page_cache_readahead(mapping, filp, offset, req_size, 0);
+
+initial_readahead:
ra->start = offset;
ra->size = get_init_ra_size(req_size, max);
ra->async_size = ra->size > req_size ? ra->size - req_size : ra->size;
readit:
+ /*
+ * Will this read hit the readahead marker made by itself?
+ * If so, trigger the readahead marker hit now, and merge
+ * the resulted next readahead window into the current one.
+ */
+ if (offset == ra->start && ra->size == ra->async_size) {
+ ra->async_size = get_next_ra_size(ra, max);
+ ra->size += ra->async_size;
+ }
+
return ra_submit(ra, mapping, filp);
}
diff --git a/mm/rmap.c b/mm/rmap.c
index 23122af3261..c9ccc1a72dc 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -333,7 +333,9 @@ static int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma)
* repeatedly from either page_referenced_anon or page_referenced_file.
*/
static int page_referenced_one(struct page *page,
- struct vm_area_struct *vma, unsigned int *mapcount)
+ struct vm_area_struct *vma,
+ unsigned int *mapcount,
+ unsigned long *vm_flags)
{
struct mm_struct *mm = vma->vm_mm;
unsigned long address;
@@ -381,11 +383,14 @@ out_unmap:
(*mapcount)--;
pte_unmap_unlock(pte, ptl);
out:
+ if (referenced)
+ *vm_flags |= vma->vm_flags;
return referenced;
}
static int page_referenced_anon(struct page *page,
- struct mem_cgroup *mem_cont)
+ struct mem_cgroup *mem_cont,
+ unsigned long *vm_flags)
{
unsigned int mapcount;
struct anon_vma *anon_vma;
@@ -405,7 +410,8 @@ static int page_referenced_anon(struct page *page,
*/
if (mem_cont && !mm_match_cgroup(vma->vm_mm, mem_cont))
continue;
- referenced += page_referenced_one(page, vma, &mapcount);
+ referenced += page_referenced_one(page, vma,
+ &mapcount, vm_flags);
if (!mapcount)
break;
}
@@ -418,6 +424,7 @@ static int page_referenced_anon(struct page *page,
* page_referenced_file - referenced check for object-based rmap
* @page: the page we're checking references on.
* @mem_cont: target memory controller
+ * @vm_flags: collect encountered vma->vm_flags who actually referenced the page
*
* For an object-based mapped page, find all the places it is mapped and
* check/clear the referenced flag. This is done by following the page->mapping
@@ -427,7 +434,8 @@ static int page_referenced_anon(struct page *page,
* This function is only called from page_referenced for object-based pages.
*/
static int page_referenced_file(struct page *page,
- struct mem_cgroup *mem_cont)
+ struct mem_cgroup *mem_cont,
+ unsigned long *vm_flags)
{
unsigned int mapcount;
struct address_space *mapping = page->mapping;
@@ -467,7 +475,8 @@ static int page_referenced_file(struct page *page,
*/
if (mem_cont && !mm_match_cgroup(vma->vm_mm, mem_cont))
continue;
- referenced += page_referenced_one(page, vma, &mapcount);
+ referenced += page_referenced_one(page, vma,
+ &mapcount, vm_flags);
if (!mapcount)
break;
}
@@ -481,29 +490,35 @@ static int page_referenced_file(struct page *page,
* @page: the page to test
* @is_locked: caller holds lock on the page
* @mem_cont: target memory controller
+ * @vm_flags: collect encountered vma->vm_flags who actually referenced the page
*
* Quick test_and_clear_referenced for all mappings to a page,
* returns the number of ptes which referenced the page.
*/
-int page_referenced(struct page *page, int is_locked,
- struct mem_cgroup *mem_cont)
+int page_referenced(struct page *page,
+ int is_locked,
+ struct mem_cgroup *mem_cont,
+ unsigned long *vm_flags)
{
int referenced = 0;
if (TestClearPageReferenced(page))
referenced++;
+ *vm_flags = 0;
if (page_mapped(page) && page->mapping) {
if (PageAnon(page))
- referenced += page_referenced_anon(page, mem_cont);
+ referenced += page_referenced_anon(page, mem_cont,
+ vm_flags);
else if (is_locked)
- referenced += page_referenced_file(page, mem_cont);
+ referenced += page_referenced_file(page, mem_cont,
+ vm_flags);
else if (!trylock_page(page))
referenced++;
else {
if (page->mapping)
- referenced +=
- page_referenced_file(page, mem_cont);
+ referenced += page_referenced_file(page,
+ mem_cont, vm_flags);
unlock_page(page);
}
}
@@ -1202,7 +1217,6 @@ int try_to_unmap(struct page *page, int migration)
return ret;
}
-#ifdef CONFIG_UNEVICTABLE_LRU
/**
* try_to_munlock - try to munlock a page
* @page: the page to be munlocked
@@ -1226,4 +1240,4 @@ int try_to_munlock(struct page *page)
else
return try_to_unmap_file(page, 1, 0);
}
-#endif
+
diff --git a/mm/shmem.c b/mm/shmem.c
index 0132fbd45a2..e89d7ec18ed 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1097,7 +1097,7 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc)
shmem_swp_unmap(entry);
unlock:
spin_unlock(&info->lock);
- swap_free(swap);
+ swapcache_free(swap, NULL);
redirty:
set_page_dirty(page);
if (wbc->for_reclaim)
@@ -2612,7 +2612,7 @@ int shmem_unuse(swp_entry_t entry, struct page *page)
* @size: size to be set for the file
* @flags: VM_NORESERVE suppresses pre-accounting of the entire object size
*/
-struct file *shmem_file_setup(char *name, loff_t size, unsigned long flags)
+struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags)
{
int error;
struct file *file;
diff --git a/mm/slab.c b/mm/slab.c
index af3376d0a83..f257d4dd474 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -818,7 +818,6 @@ static void __slab_error(const char *function, struct kmem_cache *cachep,
*/
static int use_alien_caches __read_mostly = 1;
-static int numa_platform __read_mostly = 1;
static int __init noaliencache_setup(char *s)
{
use_alien_caches = 0;
@@ -1377,10 +1376,8 @@ void __init kmem_cache_init(void)
int order;
int node;
- if (num_possible_nodes() == 1) {
+ if (num_possible_nodes() == 1)
use_alien_caches = 0;
- numa_platform = 0;
- }
for (i = 0; i < NUM_INIT_LISTS; i++) {
kmem_list3_init(&initkmem_list3[i]);
@@ -1627,7 +1624,7 @@ static void *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, int nodeid)
if (cachep->flags & SLAB_RECLAIM_ACCOUNT)
flags |= __GFP_RECLAIMABLE;
- page = alloc_pages_node(nodeid, flags | __GFP_NOTRACK, cachep->gfporder);
+ page = alloc_pages_exact_node(nodeid, flags | __GFP_NOTRACK, cachep->gfporder);
if (!page)
return NULL;
@@ -3193,7 +3190,7 @@ retry:
if (local_flags & __GFP_WAIT)
local_irq_enable();
kmem_flagcheck(cache, flags);
- obj = kmem_getpages(cache, local_flags, -1);
+ obj = kmem_getpages(cache, local_flags, numa_node_id());
if (local_flags & __GFP_WAIT)
local_irq_disable();
if (obj) {
@@ -3530,7 +3527,7 @@ static inline void __cache_free(struct kmem_cache *cachep, void *objp)
* variable to skip the call, which is mostly likely to be present in
* the cache.
*/
- if (numa_platform && cache_free_alien(cachep, objp))
+ if (nr_online_nodes > 1 && cache_free_alien(cachep, objp))
return;
if (likely(ac->avail < ac->limit)) {
diff --git a/mm/slob.c b/mm/slob.c
index 12f26149992..64f6db1943b 100644
--- a/mm/slob.c
+++ b/mm/slob.c
@@ -46,7 +46,7 @@
* NUMA support in SLOB is fairly simplistic, pushing most of the real
* logic down to the page allocator, and simply doing the node accounting
* on the upper levels. In the event that a node id is explicitly
- * provided, alloc_pages_node() with the specified node id is used
+ * provided, alloc_pages_exact_node() with the specified node id is used
* instead. The common case (or when the node id isn't explicitly provided)
* will default to the current node, as per numa_node_id().
*
@@ -244,7 +244,7 @@ static void *slob_new_pages(gfp_t gfp, int order, int node)
#ifdef CONFIG_NUMA
if (node != -1)
- page = alloc_pages_node(node, gfp, order);
+ page = alloc_pages_exact_node(node, gfp, order);
else
#endif
page = alloc_pages(gfp, order);
diff --git a/mm/slub.c b/mm/slub.c
index 15960a09abb..2701419b0ad 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -3765,7 +3765,7 @@ static int list_locations(struct kmem_cache *s, char *buf,
to_cpumask(l->cpus));
}
- if (num_online_nodes() > 1 && !nodes_empty(l->nodes) &&
+ if (nr_online_nodes > 1 && !nodes_empty(l->nodes) &&
len < PAGE_SIZE - 60) {
len += sprintf(buf + len, " nodes=");
len += nodelist_scnprintf(buf + len, PAGE_SIZE - len - 50,
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 1416e7e9e02..42cd38eba79 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -124,7 +124,6 @@ void __delete_from_swap_cache(struct page *page)
/**
* add_to_swap - allocate swap space for a page
* @page: page we want to move to swap
- * @gfp_mask: memory allocation flags
*
* Allocate swap space for the page and add the page to the
* swap cache. Caller needs to hold the page lock.
@@ -162,11 +161,11 @@ int add_to_swap(struct page *page)
return 1;
case -EEXIST:
/* Raced with "speculative" read_swap_cache_async */
- swap_free(entry);
+ swapcache_free(entry, NULL);
continue;
default:
/* -ENOMEM radix-tree allocation failure */
- swap_free(entry);
+ swapcache_free(entry, NULL);
return 0;
}
}
@@ -188,8 +187,7 @@ void delete_from_swap_cache(struct page *page)
__delete_from_swap_cache(page);
spin_unlock_irq(&swapper_space.tree_lock);
- mem_cgroup_uncharge_swapcache(page, entry);
- swap_free(entry);
+ swapcache_free(entry, page);
page_cache_release(page);
}
@@ -293,7 +291,10 @@ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
/*
* Swap entry may have been freed since our caller observed it.
*/
- if (!swap_duplicate(entry))
+ err = swapcache_prepare(entry);
+ if (err == -EEXIST) /* seems racy */
+ continue;
+ if (err) /* swp entry is obsolete ? */
break;
/*
@@ -312,12 +313,12 @@ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
* Initiate read into locked page and return.
*/
lru_cache_add_anon(new_page);
- swap_readpage(NULL, new_page);
+ swap_readpage(new_page);
return new_page;
}
ClearPageSwapBacked(new_page);
__clear_page_locked(new_page);
- swap_free(entry);
+ swapcache_free(entry, NULL);
} while (err != -ENOMEM);
if (new_page)
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 312fafe0ab6..28faa01cf57 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -53,6 +53,59 @@ static struct swap_info_struct swap_info[MAX_SWAPFILES];
static DEFINE_MUTEX(swapon_mutex);
+/* For reference count accounting in swap_map */
+/* enum for swap_map[] handling. internal use only */
+enum {
+ SWAP_MAP = 0, /* ops for reference from swap users */
+ SWAP_CACHE, /* ops for reference from swap cache */
+};
+
+static inline int swap_count(unsigned short ent)
+{
+ return ent & SWAP_COUNT_MASK;
+}
+
+static inline bool swap_has_cache(unsigned short ent)
+{
+ return !!(ent & SWAP_HAS_CACHE);
+}
+
+static inline unsigned short encode_swapmap(int count, bool has_cache)
+{
+ unsigned short ret = count;
+
+ if (has_cache)
+ return SWAP_HAS_CACHE | ret;
+ return ret;
+}
+
+/* returnes 1 if swap entry is freed */
+static int
+__try_to_reclaim_swap(struct swap_info_struct *si, unsigned long offset)
+{
+ int type = si - swap_info;
+ swp_entry_t entry = swp_entry(type, offset);
+ struct page *page;
+ int ret = 0;
+
+ page = find_get_page(&swapper_space, entry.val);
+ if (!page)
+ return 0;
+ /*
+ * This function is called from scan_swap_map() and it's called
+ * by vmscan.c at reclaiming pages. So, we hold a lock on a page, here.
+ * We have to use trylock for avoiding deadlock. This is a special
+ * case and you should use try_to_free_swap() with explicit lock_page()
+ * in usual operations.
+ */
+ if (trylock_page(page)) {
+ ret = try_to_free_swap(page);
+ unlock_page(page);
+ }
+ page_cache_release(page);
+ return ret;
+}
+
/*
* We need this because the bdev->unplug_fn can sleep and we cannot
* hold swap_lock while calling the unplug_fn. And swap_lock
@@ -167,7 +220,8 @@ static int wait_for_discard(void *word)
#define SWAPFILE_CLUSTER 256
#define LATENCY_LIMIT 256
-static inline unsigned long scan_swap_map(struct swap_info_struct *si)
+static inline unsigned long scan_swap_map(struct swap_info_struct *si,
+ int cache)
{
unsigned long offset;
unsigned long scan_base;
@@ -273,6 +327,19 @@ checks:
goto no_page;
if (offset > si->highest_bit)
scan_base = offset = si->lowest_bit;
+
+ /* reuse swap entry of cache-only swap if not busy. */
+ if (vm_swap_full() && si->swap_map[offset] == SWAP_HAS_CACHE) {
+ int swap_was_freed;
+ spin_unlock(&swap_lock);
+ swap_was_freed = __try_to_reclaim_swap(si, offset);
+ spin_lock(&swap_lock);
+ /* entry was freed successfully, try to use this again */
+ if (swap_was_freed)
+ goto checks;
+ goto scan; /* check next one */
+ }
+
if (si->swap_map[offset])
goto scan;
@@ -285,7 +352,10 @@ checks:
si->lowest_bit = si->max;
si->highest_bit = 0;
}
- si->swap_map[offset] = 1;
+ if (cache == SWAP_CACHE) /* at usual swap-out via vmscan.c */
+ si->swap_map[offset] = encode_swapmap(0, true);
+ else /* at suspend */
+ si->swap_map[offset] = encode_swapmap(1, false);
si->cluster_next = offset + 1;
si->flags -= SWP_SCANNING;
@@ -351,6 +421,10 @@ scan:
spin_lock(&swap_lock);
goto checks;
}
+ if (vm_swap_full() && si->swap_map[offset] == SWAP_HAS_CACHE) {
+ spin_lock(&swap_lock);
+ goto checks;
+ }
if (unlikely(--latency_ration < 0)) {
cond_resched();
latency_ration = LATENCY_LIMIT;
@@ -362,6 +436,10 @@ scan:
spin_lock(&swap_lock);
goto checks;
}
+ if (vm_swap_full() && si->swap_map[offset] == SWAP_HAS_CACHE) {
+ spin_lock(&swap_lock);
+ goto checks;
+ }
if (unlikely(--latency_ration < 0)) {
cond_resched();
latency_ration = LATENCY_LIMIT;
@@ -401,7 +479,8 @@ swp_entry_t get_swap_page(void)
continue;
swap_list.next = next;
- offset = scan_swap_map(si);
+ /* This is called for allocating swap entry for cache */
+ offset = scan_swap_map(si, SWAP_CACHE);
if (offset) {
spin_unlock(&swap_lock);
return swp_entry(type, offset);
@@ -415,6 +494,7 @@ noswap:
return (swp_entry_t) {0};
}
+/* The only caller of this function is now susupend routine */
swp_entry_t get_swap_page_of_type(int type)
{
struct swap_info_struct *si;
@@ -424,7 +504,8 @@ swp_entry_t get_swap_page_of_type(int type)
si = swap_info + type;
if (si->flags & SWP_WRITEOK) {
nr_swap_pages--;
- offset = scan_swap_map(si);
+ /* This is called for allocating swap entry, not cache */
+ offset = scan_swap_map(si, SWAP_MAP);
if (offset) {
spin_unlock(&swap_lock);
return swp_entry(type, offset);
@@ -471,25 +552,38 @@ out:
return NULL;
}
-static int swap_entry_free(struct swap_info_struct *p, swp_entry_t ent)
+static int swap_entry_free(struct swap_info_struct *p,
+ swp_entry_t ent, int cache)
{
unsigned long offset = swp_offset(ent);
- int count = p->swap_map[offset];
-
- if (count < SWAP_MAP_MAX) {
- count--;
- p->swap_map[offset] = count;
- if (!count) {
- if (offset < p->lowest_bit)
- p->lowest_bit = offset;
- if (offset > p->highest_bit)
- p->highest_bit = offset;
- if (p->prio > swap_info[swap_list.next].prio)
- swap_list.next = p - swap_info;
- nr_swap_pages++;
- p->inuse_pages--;
- mem_cgroup_uncharge_swap(ent);
+ int count = swap_count(p->swap_map[offset]);
+ bool has_cache;
+
+ has_cache = swap_has_cache(p->swap_map[offset]);
+
+ if (cache == SWAP_MAP) { /* dropping usage count of swap */
+ if (count < SWAP_MAP_MAX) {
+ count--;
+ p->swap_map[offset] = encode_swapmap(count, has_cache);
}
+ } else { /* dropping swap cache flag */
+ VM_BUG_ON(!has_cache);
+ p->swap_map[offset] = encode_swapmap(count, false);
+
+ }
+ /* return code. */
+ count = p->swap_map[offset];
+ /* free if no reference */
+ if (!count) {
+ if (offset < p->lowest_bit)
+ p->lowest_bit = offset;
+ if (offset > p->highest_bit)
+ p->highest_bit = offset;
+ if (p->prio > swap_info[swap_list.next].prio)
+ swap_list.next = p - swap_info;
+ nr_swap_pages++;
+ p->inuse_pages--;
+ mem_cgroup_uncharge_swap(ent);
}
return count;
}
@@ -504,9 +598,26 @@ void swap_free(swp_entry_t entry)
p = swap_info_get(entry);
if (p) {
- swap_entry_free(p, entry);
+ swap_entry_free(p, entry, SWAP_MAP);
+ spin_unlock(&swap_lock);
+ }
+}
+
+/*
+ * Called after dropping swapcache to decrease refcnt to swap entries.
+ */
+void swapcache_free(swp_entry_t entry, struct page *page)
+{
+ struct swap_info_struct *p;
+
+ if (page)
+ mem_cgroup_uncharge_swapcache(page, entry);
+ p = swap_info_get(entry);
+ if (p) {
+ swap_entry_free(p, entry, SWAP_CACHE);
spin_unlock(&swap_lock);
}
+ return;
}
/*
@@ -521,8 +632,7 @@ static inline int page_swapcount(struct page *page)
entry.val = page_private(page);
p = swap_info_get(entry);
if (p) {
- /* Subtract the 1 for the swap cache itself */
- count = p->swap_map[swp_offset(entry)] - 1;
+ count = swap_count(p->swap_map[swp_offset(entry)]);
spin_unlock(&swap_lock);
}
return count;
@@ -584,7 +694,7 @@ int free_swap_and_cache(swp_entry_t entry)
p = swap_info_get(entry);
if (p) {
- if (swap_entry_free(p, entry) == 1) {
+ if (swap_entry_free(p, entry, SWAP_MAP) == SWAP_HAS_CACHE) {
page = find_get_page(&swapper_space, entry.val);
if (page && !trylock_page(page)) {
page_cache_release(page);
@@ -891,7 +1001,7 @@ static unsigned int find_next_to_unuse(struct swap_info_struct *si,
i = 1;
}
count = si->swap_map[i];
- if (count && count != SWAP_MAP_BAD)
+ if (count && swap_count(count) != SWAP_MAP_BAD)
break;
}
return i;
@@ -995,13 +1105,13 @@ static int try_to_unuse(unsigned int type)
*/
shmem = 0;
swcount = *swap_map;
- if (swcount > 1) {
+ if (swap_count(swcount)) {
if (start_mm == &init_mm)
shmem = shmem_unuse(entry, page);
else
retval = unuse_mm(start_mm, entry, page);
}
- if (*swap_map > 1) {
+ if (swap_count(*swap_map)) {
int set_start_mm = (*swap_map >= swcount);
struct list_head *p = &start_mm->mmlist;
struct mm_struct *new_start_mm = start_mm;
@@ -1011,7 +1121,7 @@ static int try_to_unuse(unsigned int type)
atomic_inc(&new_start_mm->mm_users);
atomic_inc(&prev_mm->mm_users);
spin_lock(&mmlist_lock);
- while (*swap_map > 1 && !retval && !shmem &&
+ while (swap_count(*swap_map) && !retval && !shmem &&
(p = p->next) != &start_mm->mmlist) {
mm = list_entry(p, struct mm_struct, mmlist);
if (!atomic_inc_not_zero(&mm->mm_users))
@@ -1023,14 +1133,16 @@ static int try_to_unuse(unsigned int type)
cond_resched();
swcount = *swap_map;
- if (swcount <= 1)
+ if (!swap_count(swcount)) /* any usage ? */
;
else if (mm == &init_mm) {
set_start_mm = 1;
shmem = shmem_unuse(entry, page);
} else
retval = unuse_mm(mm, entry, page);
- if (set_start_mm && *swap_map < swcount) {
+
+ if (set_start_mm &&
+ swap_count(*swap_map) < swcount) {
mmput(new_start_mm);
atomic_inc(&mm->mm_users);
new_start_mm = mm;
@@ -1057,21 +1169,25 @@ static int try_to_unuse(unsigned int type)
}
/*
- * How could swap count reach 0x7fff when the maximum
- * pid is 0x7fff, and there's no way to repeat a swap
- * page within an mm (except in shmem, where it's the
- * shared object which takes the reference count)?
- * We believe SWAP_MAP_MAX cannot occur in Linux 2.4.
- *
+ * How could swap count reach 0x7ffe ?
+ * There's no way to repeat a swap page within an mm
+ * (except in shmem, where it's the shared object which takes
+ * the reference count)?
+ * We believe SWAP_MAP_MAX cannot occur.(if occur, unsigned
+ * short is too small....)
* If that's wrong, then we should worry more about
* exit_mmap() and do_munmap() cases described above:
* we might be resetting SWAP_MAP_MAX too early here.
* We know "Undead"s can happen, they're okay, so don't
* report them; but do report if we reset SWAP_MAP_MAX.
*/
- if (*swap_map == SWAP_MAP_MAX) {
+ /* We might release the lock_page() in unuse_mm(). */
+ if (!PageSwapCache(page) || page_private(page) != entry.val)
+ goto retry;
+
+ if (swap_count(*swap_map) == SWAP_MAP_MAX) {
spin_lock(&swap_lock);
- *swap_map = 1;
+ *swap_map = encode_swapmap(0, true);
spin_unlock(&swap_lock);
reset_overflow = 1;
}
@@ -1089,7 +1205,8 @@ static int try_to_unuse(unsigned int type)
* pages would be incorrect if swap supported "shared
* private" pages, but they are handled by tmpfs files.
*/
- if ((*swap_map > 1) && PageDirty(page) && PageSwapCache(page)) {
+ if (swap_count(*swap_map) &&
+ PageDirty(page) && PageSwapCache(page)) {
struct writeback_control wbc = {
.sync_mode = WB_SYNC_NONE,
};
@@ -1116,6 +1233,7 @@ static int try_to_unuse(unsigned int type)
* mark page dirty so shrink_page_list will preserve it.
*/
SetPageDirty(page);
+retry:
unlock_page(page);
page_cache_release(page);
@@ -1942,15 +2060,23 @@ void si_swapinfo(struct sysinfo *val)
*
* Note: if swap_map[] reaches SWAP_MAP_MAX the entries are treated as
* "permanent", but will be reclaimed by the next swapoff.
+ * Returns error code in following case.
+ * - success -> 0
+ * - swp_entry is invalid -> EINVAL
+ * - swp_entry is migration entry -> EINVAL
+ * - swap-cache reference is requested but there is already one. -> EEXIST
+ * - swap-cache reference is requested but the entry is not used. -> ENOENT
*/
-int swap_duplicate(swp_entry_t entry)
+static int __swap_duplicate(swp_entry_t entry, bool cache)
{
struct swap_info_struct * p;
unsigned long offset, type;
- int result = 0;
+ int result = -EINVAL;
+ int count;
+ bool has_cache;
if (is_migration_entry(entry))
- return 1;
+ return -EINVAL;
type = swp_type(entry);
if (type >= nr_swapfiles)
@@ -1959,17 +2085,40 @@ int swap_duplicate(swp_entry_t entry)
offset = swp_offset(entry);
spin_lock(&swap_lock);
- if (offset < p->max && p->swap_map[offset]) {
- if (p->swap_map[offset] < SWAP_MAP_MAX - 1) {
- p->swap_map[offset]++;
- result = 1;
- } else if (p->swap_map[offset] <= SWAP_MAP_MAX) {
+
+ if (unlikely(offset >= p->max))
+ goto unlock_out;
+
+ count = swap_count(p->swap_map[offset]);
+ has_cache = swap_has_cache(p->swap_map[offset]);
+
+ if (cache == SWAP_CACHE) { /* called for swapcache/swapin-readahead */
+
+ /* set SWAP_HAS_CACHE if there is no cache and entry is used */
+ if (!has_cache && count) {
+ p->swap_map[offset] = encode_swapmap(count, true);
+ result = 0;
+ } else if (has_cache) /* someone added cache */
+ result = -EEXIST;
+ else if (!count) /* no users */
+ result = -ENOENT;
+
+ } else if (count || has_cache) {
+ if (count < SWAP_MAP_MAX - 1) {
+ p->swap_map[offset] = encode_swapmap(count + 1,
+ has_cache);
+ result = 0;
+ } else if (count <= SWAP_MAP_MAX) {
if (swap_overflow++ < 5)
- printk(KERN_WARNING "swap_dup: swap entry overflow\n");
- p->swap_map[offset] = SWAP_MAP_MAX;
- result = 1;
+ printk(KERN_WARNING
+ "swap_dup: swap entry overflow\n");
+ p->swap_map[offset] = encode_swapmap(SWAP_MAP_MAX,
+ has_cache);
+ result = 0;
}
- }
+ } else
+ result = -ENOENT; /* unused swap entry */
+unlock_out:
spin_unlock(&swap_lock);
out:
return result;
@@ -1978,6 +2127,27 @@ bad_file:
printk(KERN_ERR "swap_dup: %s%08lx\n", Bad_file, entry.val);
goto out;
}
+/*
+ * increase reference count of swap entry by 1.
+ */
+void swap_duplicate(swp_entry_t entry)
+{
+ __swap_duplicate(entry, SWAP_MAP);
+}
+
+/*
+ * @entry: swap entry for which we allocate swap cache.
+ *
+ * Called when allocating swap cache for exising swap entry,
+ * This can return error codes. Returns 0 at success.
+ * -EBUSY means there is a swap cache.
+ * Note: return code is different from swap_duplicate().
+ */
+int swapcache_prepare(swp_entry_t entry)
+{
+ return __swap_duplicate(entry, SWAP_CACHE);
+}
+
struct swap_info_struct *
get_swap_info_struct(unsigned type)
@@ -2016,7 +2186,7 @@ int valid_swaphandles(swp_entry_t entry, unsigned long *offset)
/* Don't read in free or bad pages */
if (!si->swap_map[toff])
break;
- if (si->swap_map[toff] == SWAP_MAP_BAD)
+ if (swap_count(si->swap_map[toff]) == SWAP_MAP_BAD)
break;
}
/* Count contiguous allocated slots below our target */
@@ -2024,7 +2194,7 @@ int valid_swaphandles(swp_entry_t entry, unsigned long *offset)
/* Don't read in free or bad pages */
if (!si->swap_map[toff])
break;
- if (si->swap_map[toff] == SWAP_MAP_BAD)
+ if (swap_count(si->swap_map[toff]) == SWAP_MAP_BAD)
break;
}
spin_unlock(&swap_lock);
diff --git a/mm/truncate.c b/mm/truncate.c
index 12e1579f916..ccc3ecf7cb9 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -267,8 +267,21 @@ void truncate_inode_pages(struct address_space *mapping, loff_t lstart)
}
EXPORT_SYMBOL(truncate_inode_pages);
-unsigned long __invalidate_mapping_pages(struct address_space *mapping,
- pgoff_t start, pgoff_t end, bool be_atomic)
+/**
+ * invalidate_mapping_pages - Invalidate all the unlocked pages of one inode
+ * @mapping: the address_space which holds the pages to invalidate
+ * @start: the offset 'from' which to invalidate
+ * @end: the offset 'to' which to invalidate (inclusive)
+ *
+ * This function only removes the unlocked pages, if you want to
+ * remove all the pages of one inode, you must call truncate_inode_pages.
+ *
+ * invalidate_mapping_pages() will not block on IO activity. It will not
+ * invalidate pages which are dirty, locked, under writeback or mapped into
+ * pagetables.
+ */
+unsigned long invalidate_mapping_pages(struct address_space *mapping,
+ pgoff_t start, pgoff_t end)
{
struct pagevec pvec;
pgoff_t next = start;
@@ -309,30 +322,10 @@ unlock:
break;
}
pagevec_release(&pvec);
- if (likely(!be_atomic))
- cond_resched();
+ cond_resched();
}
return ret;
}
-
-/**
- * invalidate_mapping_pages - Invalidate all the unlocked pages of one inode
- * @mapping: the address_space which holds the pages to invalidate
- * @start: the offset 'from' which to invalidate
- * @end: the offset 'to' which to invalidate (inclusive)
- *
- * This function only removes the unlocked pages, if you want to
- * remove all the pages of one inode, you must call truncate_inode_pages.
- *
- * invalidate_mapping_pages() will not block on IO activity. It will not
- * invalidate pages which are dirty, locked, under writeback or mapped into
- * pagetables.
- */
-unsigned long invalidate_mapping_pages(struct address_space *mapping,
- pgoff_t start, pgoff_t end)
-{
- return __invalidate_mapping_pages(mapping, start, end, false);
-}
EXPORT_SYMBOL(invalidate_mapping_pages);
/*
diff --git a/mm/util.c b/mm/util.c
index abc65aa7cdf..d5d2213728c 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -233,13 +233,21 @@ void arch_pick_mmap_layout(struct mm_struct *mm)
* @pages: array that receives pointers to the pages pinned.
* Should be at least nr_pages long.
*
- * Attempt to pin user pages in memory without taking mm->mmap_sem.
- * If not successful, it will fall back to taking the lock and
- * calling get_user_pages().
- *
* Returns number of pages pinned. This may be fewer than the number
* requested. If nr_pages is 0 or negative, returns 0. If no pages
* were pinned, returns -errno.
+ *
+ * get_user_pages_fast provides equivalent functionality to get_user_pages,
+ * operating on current and current->mm, with force=0 and vma=NULL. However
+ * unlike get_user_pages, it must be called without mmap_sem held.
+ *
+ * get_user_pages_fast may take mmap_sem and page table locks, so no
+ * assumptions can be made about lack of locking. get_user_pages_fast is to be
+ * implemented in a way that is advantageous (vs get_user_pages()) when the
+ * user memory area is already faulted in and present in ptes. However if the
+ * pages have to be faulted in, it may turn out to be slightly slower so
+ * callers need to carefully consider what to use. On many architectures,
+ * get_user_pages_fast simply falls back to get_user_pages.
*/
int __attribute__((weak)) get_user_pages_fast(unsigned long start,
int nr_pages, int write, struct page **pages)
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 95c08a8cc2b..4139aa52b94 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -470,8 +470,7 @@ static int __remove_mapping(struct address_space *mapping, struct page *page)
swp_entry_t swap = { .val = page_private(page) };
__delete_from_swap_cache(page);
spin_unlock_irq(&mapping->tree_lock);
- mem_cgroup_uncharge_swapcache(page, swap);
- swap_free(swap);
+ swapcache_free(swap, page);
} else {
__remove_from_page_cache(page);
spin_unlock_irq(&mapping->tree_lock);
@@ -514,7 +513,6 @@ int remove_mapping(struct address_space *mapping, struct page *page)
*
* lru_lock must not be held, interrupts must be enabled.
*/
-#ifdef CONFIG_UNEVICTABLE_LRU
void putback_lru_page(struct page *page)
{
int lru;
@@ -568,20 +566,6 @@ redo:
put_page(page); /* drop ref from isolate */
}
-#else /* CONFIG_UNEVICTABLE_LRU */
-
-void putback_lru_page(struct page *page)
-{
- int lru;
- VM_BUG_ON(PageLRU(page));
-
- lru = !!TestClearPageActive(page) + page_is_file_cache(page);
- lru_cache_add_lru(page, lru);
- put_page(page);
-}
-#endif /* CONFIG_UNEVICTABLE_LRU */
-
-
/*
* shrink_page_list() returns the number of reclaimed pages
*/
@@ -593,6 +577,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
struct pagevec freed_pvec;
int pgactivate = 0;
unsigned long nr_reclaimed = 0;
+ unsigned long vm_flags;
cond_resched();
@@ -643,7 +628,8 @@ static unsigned long shrink_page_list(struct list_head *page_list,
goto keep_locked;
}
- referenced = page_referenced(page, 1, sc->mem_cgroup);
+ referenced = page_referenced(page, 1,
+ sc->mem_cgroup, &vm_flags);
/* In active use or really unfreeable? Activate it. */
if (sc->order <= PAGE_ALLOC_COSTLY_ORDER &&
referenced && page_mapping_inuse(page))
@@ -943,18 +929,10 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
/* Check that we have not crossed a zone boundary. */
if (unlikely(page_zone_id(cursor_page) != zone_id))
continue;
- switch (__isolate_lru_page(cursor_page, mode, file)) {
- case 0:
+ if (__isolate_lru_page(cursor_page, mode, file) == 0) {
list_move(&cursor_page->lru, dst);
nr_taken++;
scan++;
- break;
-
- case -EBUSY:
- /* else it is being freed elsewhere */
- list_move(&cursor_page->lru, src);
- default:
- break; /* ! on LRU or wrong list */
}
}
}
@@ -1061,6 +1039,19 @@ static unsigned long shrink_inactive_list(unsigned long max_scan,
unsigned long nr_scanned = 0;
unsigned long nr_reclaimed = 0;
struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(zone, sc);
+ int lumpy_reclaim = 0;
+
+ /*
+ * If we need a large contiguous chunk of memory, or have
+ * trouble getting a small set of contiguous pages, we
+ * will reclaim both active and inactive pages.
+ *
+ * We use the same threshold as pageout congestion_wait below.
+ */
+ if (sc->order > PAGE_ALLOC_COSTLY_ORDER)
+ lumpy_reclaim = 1;
+ else if (sc->order && priority < DEF_PRIORITY - 2)
+ lumpy_reclaim = 1;
pagevec_init(&pvec, 1);
@@ -1073,19 +1064,7 @@ static unsigned long shrink_inactive_list(unsigned long max_scan,
unsigned long nr_freed;
unsigned long nr_active;
unsigned int count[NR_LRU_LISTS] = { 0, };
- int mode = ISOLATE_INACTIVE;
-
- /*
- * If we need a large contiguous chunk of memory, or have
- * trouble getting a small set of contiguous pages, we
- * will reclaim both active and inactive pages.
- *
- * We use the same threshold as pageout congestion_wait below.
- */
- if (sc->order > PAGE_ALLOC_COSTLY_ORDER)
- mode = ISOLATE_BOTH;
- else if (sc->order && priority < DEF_PRIORITY - 2)
- mode = ISOLATE_BOTH;
+ int mode = lumpy_reclaim ? ISOLATE_BOTH : ISOLATE_INACTIVE;
nr_taken = sc->isolate_pages(sc->swap_cluster_max,
&page_list, &nr_scan, sc->order, mode,
@@ -1122,7 +1101,7 @@ static unsigned long shrink_inactive_list(unsigned long max_scan,
* but that should be acceptable to the caller
*/
if (nr_freed < nr_taken && !current_is_kswapd() &&
- sc->order > PAGE_ALLOC_COSTLY_ORDER) {
+ lumpy_reclaim) {
congestion_wait(WRITE, HZ/10);
/*
@@ -1217,18 +1196,54 @@ static inline void note_zone_scanning_priority(struct zone *zone, int priority)
* But we had to alter page->flags anyway.
*/
+static void move_active_pages_to_lru(struct zone *zone,
+ struct list_head *list,
+ enum lru_list lru)
+{
+ unsigned long pgmoved = 0;
+ struct pagevec pvec;
+ struct page *page;
+
+ pagevec_init(&pvec, 1);
+
+ while (!list_empty(list)) {
+ page = lru_to_page(list);
+ prefetchw_prev_lru_page(page, list, flags);
+
+ VM_BUG_ON(PageLRU(page));
+ SetPageLRU(page);
+
+ VM_BUG_ON(!PageActive(page));
+ if (!is_active_lru(lru))
+ ClearPageActive(page); /* we are de-activating */
+
+ list_move(&page->lru, &zone->lru[lru].list);
+ mem_cgroup_add_lru_list(page, lru);
+ pgmoved++;
+
+ if (!pagevec_add(&pvec, page) || list_empty(list)) {
+ spin_unlock_irq(&zone->lru_lock);
+ if (buffer_heads_over_limit)
+ pagevec_strip(&pvec);
+ __pagevec_release(&pvec);
+ spin_lock_irq(&zone->lru_lock);
+ }
+ }
+ __mod_zone_page_state(zone, NR_LRU_BASE + lru, pgmoved);
+ if (!is_active_lru(lru))
+ __count_vm_events(PGDEACTIVATE, pgmoved);
+}
static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
struct scan_control *sc, int priority, int file)
{
unsigned long pgmoved;
- int pgdeactivate = 0;
unsigned long pgscanned;
+ unsigned long vm_flags;
LIST_HEAD(l_hold); /* The pages which were snipped off */
+ LIST_HEAD(l_active);
LIST_HEAD(l_inactive);
struct page *page;
- struct pagevec pvec;
- enum lru_list lru;
struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(zone, sc);
lru_add_drain();
@@ -1245,13 +1260,14 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
}
reclaim_stat->recent_scanned[!!file] += pgmoved;
+ __count_zone_vm_events(PGREFILL, zone, pgscanned);
if (file)
__mod_zone_page_state(zone, NR_ACTIVE_FILE, -pgmoved);
else
__mod_zone_page_state(zone, NR_ACTIVE_ANON, -pgmoved);
spin_unlock_irq(&zone->lru_lock);
- pgmoved = 0;
+ pgmoved = 0; /* count referenced (mapping) mapped pages */
while (!list_empty(&l_hold)) {
cond_resched();
page = lru_to_page(&l_hold);
@@ -1264,58 +1280,44 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
/* page_referenced clears PageReferenced */
if (page_mapping_inuse(page) &&
- page_referenced(page, 0, sc->mem_cgroup))
+ page_referenced(page, 0, sc->mem_cgroup, &vm_flags)) {
pgmoved++;
+ /*
+ * Identify referenced, file-backed active pages and
+ * give them one more trip around the active list. So
+ * that executable code get better chances to stay in
+ * memory under moderate memory pressure. Anon pages
+ * are not likely to be evicted by use-once streaming
+ * IO, plus JVM can create lots of anon VM_EXEC pages,
+ * so we ignore them here.
+ */
+ if ((vm_flags & VM_EXEC) && !PageAnon(page)) {
+ list_add(&page->lru, &l_active);
+ continue;
+ }
+ }
list_add(&page->lru, &l_inactive);
}
/*
- * Move the pages to the [file or anon] inactive list.
+ * Move pages back to the lru list.
*/
- pagevec_init(&pvec, 1);
- lru = LRU_BASE + file * LRU_FILE;
-
spin_lock_irq(&zone->lru_lock);
/*
- * Count referenced pages from currently used mappings as
- * rotated, even though they are moved to the inactive list.
- * This helps balance scan pressure between file and anonymous
- * pages in get_scan_ratio.
+ * Count referenced pages from currently used mappings as rotated,
+ * even though only some of them are actually re-activated. This
+ * helps balance scan pressure between file and anonymous pages in
+ * get_scan_ratio.
*/
reclaim_stat->recent_rotated[!!file] += pgmoved;
- pgmoved = 0;
- while (!list_empty(&l_inactive)) {
- page = lru_to_page(&l_inactive);
- prefetchw_prev_lru_page(page, &l_inactive, flags);
- VM_BUG_ON(PageLRU(page));
- SetPageLRU(page);
- VM_BUG_ON(!PageActive(page));
- ClearPageActive(page);
+ move_active_pages_to_lru(zone, &l_active,
+ LRU_ACTIVE + file * LRU_FILE);
+ move_active_pages_to_lru(zone, &l_inactive,
+ LRU_BASE + file * LRU_FILE);
- list_move(&page->lru, &zone->lru[lru].list);
- mem_cgroup_add_lru_list(page, lru);
- pgmoved++;
- if (!pagevec_add(&pvec, page)) {
- __mod_zone_page_state(zone, NR_LRU_BASE + lru, pgmoved);
- spin_unlock_irq(&zone->lru_lock);
- pgdeactivate += pgmoved;
- pgmoved = 0;
- if (buffer_heads_over_limit)
- pagevec_strip(&pvec);
- __pagevec_release(&pvec);
- spin_lock_irq(&zone->lru_lock);
- }
- }
- __mod_zone_page_state(zone, NR_LRU_BASE + lru, pgmoved);
- pgdeactivate += pgmoved;
- __count_zone_vm_events(PGREFILL, zone, pgscanned);
- __count_vm_events(PGDEACTIVATE, pgdeactivate);
spin_unlock_irq(&zone->lru_lock);
- if (buffer_heads_over_limit)
- pagevec_strip(&pvec);
- pagevec_release(&pvec);
}
static int inactive_anon_is_low_global(struct zone *zone)
@@ -1350,12 +1352,48 @@ static int inactive_anon_is_low(struct zone *zone, struct scan_control *sc)
return low;
}
+static int inactive_file_is_low_global(struct zone *zone)
+{
+ unsigned long active, inactive;
+
+ active = zone_page_state(zone, NR_ACTIVE_FILE);
+ inactive = zone_page_state(zone, NR_INACTIVE_FILE);
+
+ return (active > inactive);
+}
+
+/**
+ * inactive_file_is_low - check if file pages need to be deactivated
+ * @zone: zone to check
+ * @sc: scan control of this context
+ *
+ * When the system is doing streaming IO, memory pressure here
+ * ensures that active file pages get deactivated, until more
+ * than half of the file pages are on the inactive list.
+ *
+ * Once we get to that situation, protect the system's working
+ * set from being evicted by disabling active file page aging.
+ *
+ * This uses a different ratio than the anonymous pages, because
+ * the page cache uses a use-once replacement algorithm.
+ */
+static int inactive_file_is_low(struct zone *zone, struct scan_control *sc)
+{
+ int low;
+
+ if (scanning_global_lru(sc))
+ low = inactive_file_is_low_global(zone);
+ else
+ low = mem_cgroup_inactive_file_is_low(sc->mem_cgroup);
+ return low;
+}
+
static unsigned long shrink_list(enum lru_list lru, unsigned long nr_to_scan,
struct zone *zone, struct scan_control *sc, int priority)
{
int file = is_file_lru(lru);
- if (lru == LRU_ACTIVE_FILE) {
+ if (lru == LRU_ACTIVE_FILE && inactive_file_is_low(zone, sc)) {
shrink_active_list(nr_to_scan, zone, sc, priority, file);
return 0;
}
@@ -1384,13 +1422,6 @@ static void get_scan_ratio(struct zone *zone, struct scan_control *sc,
unsigned long ap, fp;
struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(zone, sc);
- /* If we have no swap space, do not bother scanning anon pages. */
- if (!sc->may_swap || (nr_swap_pages <= 0)) {
- percent[0] = 0;
- percent[1] = 100;
- return;
- }
-
anon = zone_nr_pages(zone, sc, LRU_ACTIVE_ANON) +
zone_nr_pages(zone, sc, LRU_INACTIVE_ANON);
file = zone_nr_pages(zone, sc, LRU_ACTIVE_FILE) +
@@ -1400,7 +1431,7 @@ static void get_scan_ratio(struct zone *zone, struct scan_control *sc,
free = zone_page_state(zone, NR_FREE_PAGES);
/* If we have very few page cache pages,
force-scan anon pages. */
- if (unlikely(file + free <= zone->pages_high)) {
+ if (unlikely(file + free <= high_wmark_pages(zone))) {
percent[0] = 100;
percent[1] = 0;
return;
@@ -1455,6 +1486,26 @@ static void get_scan_ratio(struct zone *zone, struct scan_control *sc,
percent[1] = 100 - percent[0];
}
+/*
+ * Smallish @nr_to_scan's are deposited in @nr_saved_scan,
+ * until we collected @swap_cluster_max pages to scan.
+ */
+static unsigned long nr_scan_try_batch(unsigned long nr_to_scan,
+ unsigned long *nr_saved_scan,
+ unsigned long swap_cluster_max)
+{
+ unsigned long nr;
+
+ *nr_saved_scan += nr_to_scan;
+ nr = *nr_saved_scan;
+
+ if (nr >= swap_cluster_max)
+ *nr_saved_scan = 0;
+ else
+ nr = 0;
+
+ return nr;
+}
/*
* This is a basic per-zone page freer. Used by both kswapd and direct reclaim.
@@ -1468,26 +1519,30 @@ static void shrink_zone(int priority, struct zone *zone,
enum lru_list l;
unsigned long nr_reclaimed = sc->nr_reclaimed;
unsigned long swap_cluster_max = sc->swap_cluster_max;
+ int noswap = 0;
- get_scan_ratio(zone, sc, percent);
+ /* If we have no swap space, do not bother scanning anon pages. */
+ if (!sc->may_swap || (nr_swap_pages <= 0)) {
+ noswap = 1;
+ percent[0] = 0;
+ percent[1] = 100;
+ } else
+ get_scan_ratio(zone, sc, percent);
for_each_evictable_lru(l) {
int file = is_file_lru(l);
unsigned long scan;
scan = zone_nr_pages(zone, sc, l);
- if (priority) {
+ if (priority || noswap) {
scan >>= priority;
scan = (scan * percent[file]) / 100;
}
- if (scanning_global_lru(sc)) {
- zone->lru[l].nr_scan += scan;
- nr[l] = zone->lru[l].nr_scan;
- if (nr[l] >= swap_cluster_max)
- zone->lru[l].nr_scan = 0;
- else
- nr[l] = 0;
- } else
+ if (scanning_global_lru(sc))
+ nr[l] = nr_scan_try_batch(scan,
+ &zone->lru[l].nr_saved_scan,
+ swap_cluster_max);
+ else
nr[l] = scan;
}
@@ -1521,7 +1576,7 @@ static void shrink_zone(int priority, struct zone *zone,
* Even if we did not try to evict anon pages at all, we want to
* rebalance the anon lru active/inactive ratio.
*/
- if (inactive_anon_is_low(zone, sc))
+ if (inactive_anon_is_low(zone, sc) && nr_swap_pages > 0)
shrink_active_list(SWAP_CLUSTER_MAX, zone, sc, priority, 0);
throttle_vm_writeout(sc->gfp_mask);
@@ -1532,11 +1587,13 @@ static void shrink_zone(int priority, struct zone *zone,
* try to reclaim pages from zones which will satisfy the caller's allocation
* request.
*
- * We reclaim from a zone even if that zone is over pages_high. Because:
+ * We reclaim from a zone even if that zone is over high_wmark_pages(zone).
+ * Because:
* a) The caller may be trying to free *extra* pages to satisfy a higher-order
* allocation or
- * b) The zones may be over pages_high but they must go *over* pages_high to
- * satisfy the `incremental min' zone defense algorithm.
+ * b) The target zone may be at high_wmark_pages(zone) but the lower zones
+ * must go *over* high_wmark_pages(zone) to satisfy the `incremental min'
+ * zone defense algorithm.
*
* If a zone is deemed to be full of pinned pages then just give it a light
* scan then give up on it.
@@ -1742,7 +1799,7 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont,
/*
* For kswapd, balance_pgdat() will work across all this node's zones until
- * they are all at pages_high.
+ * they are all at high_wmark_pages(zone).
*
* Returns the number of pages which were actually freed.
*
@@ -1755,11 +1812,11 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont,
* the zone for when the problem goes away.
*
* kswapd scans the zones in the highmem->normal->dma direction. It skips
- * zones which have free_pages > pages_high, but once a zone is found to have
- * free_pages <= pages_high, we scan that zone and the lower zones regardless
- * of the number of free pages in the lower zones. This interoperates with
- * the page allocator fallback scheme to ensure that aging of pages is balanced
- * across the zones.
+ * zones which have free_pages > high_wmark_pages(zone), but once a zone is
+ * found to have free_pages <= high_wmark_pages(zone), we scan that zone and the
+ * lower zones regardless of the number of free pages in the lower zones. This
+ * interoperates with the page allocator fallback scheme to ensure that aging
+ * of pages is balanced across the zones.
*/
static unsigned long balance_pgdat(pg_data_t *pgdat, int order)
{
@@ -1780,7 +1837,8 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order)
};
/*
* temp_priority is used to remember the scanning priority at which
- * this zone was successfully refilled to free_pages == pages_high.
+ * this zone was successfully refilled to
+ * free_pages == high_wmark_pages(zone).
*/
int temp_priority[MAX_NR_ZONES];
@@ -1825,8 +1883,8 @@ loop_again:
shrink_active_list(SWAP_CLUSTER_MAX, zone,
&sc, priority, 0);
- if (!zone_watermark_ok(zone, order, zone->pages_high,
- 0, 0)) {
+ if (!zone_watermark_ok(zone, order,
+ high_wmark_pages(zone), 0, 0)) {
end_zone = i;
break;
}
@@ -1860,8 +1918,8 @@ loop_again:
priority != DEF_PRIORITY)
continue;
- if (!zone_watermark_ok(zone, order, zone->pages_high,
- end_zone, 0))
+ if (!zone_watermark_ok(zone, order,
+ high_wmark_pages(zone), end_zone, 0))
all_zones_ok = 0;
temp_priority[i] = priority;
sc.nr_scanned = 0;
@@ -1870,8 +1928,8 @@ loop_again:
* We put equal pressure on every zone, unless one
* zone has way too many pages free already.
*/
- if (!zone_watermark_ok(zone, order, 8*zone->pages_high,
- end_zone, 0))
+ if (!zone_watermark_ok(zone, order,
+ 8*high_wmark_pages(zone), end_zone, 0))
shrink_zone(priority, zone, &sc);
reclaim_state->reclaimed_slab = 0;
nr_slab = shrink_slab(sc.nr_scanned, GFP_KERNEL,
@@ -2037,7 +2095,7 @@ void wakeup_kswapd(struct zone *zone, int order)
return;
pgdat = zone->zone_pgdat;
- if (zone_watermark_ok(zone, order, zone->pages_low, 0, 0))
+ if (zone_watermark_ok(zone, order, low_wmark_pages(zone), 0, 0))
return;
if (pgdat->kswapd_max_order < order)
pgdat->kswapd_max_order = order;
@@ -2084,11 +2142,11 @@ static void shrink_all_zones(unsigned long nr_pages, int prio,
l == LRU_ACTIVE_FILE))
continue;
- zone->lru[l].nr_scan += (lru_pages >> prio) + 1;
- if (zone->lru[l].nr_scan >= nr_pages || pass > 3) {
+ zone->lru[l].nr_saved_scan += (lru_pages >> prio) + 1;
+ if (zone->lru[l].nr_saved_scan >= nr_pages || pass > 3) {
unsigned long nr_to_scan;
- zone->lru[l].nr_scan = 0;
+ zone->lru[l].nr_saved_scan = 0;
nr_to_scan = min(nr_pages, lru_pages);
nr_reclaimed += shrink_list(l, nr_to_scan, zone,
sc, prio);
@@ -2290,6 +2348,48 @@ int sysctl_min_unmapped_ratio = 1;
*/
int sysctl_min_slab_ratio = 5;
+static inline unsigned long zone_unmapped_file_pages(struct zone *zone)
+{
+ unsigned long file_mapped = zone_page_state(zone, NR_FILE_MAPPED);
+ unsigned long file_lru = zone_page_state(zone, NR_INACTIVE_FILE) +
+ zone_page_state(zone, NR_ACTIVE_FILE);
+
+ /*
+ * It's possible for there to be more file mapped pages than
+ * accounted for by the pages on the file LRU lists because
+ * tmpfs pages accounted for as ANON can also be FILE_MAPPED
+ */
+ return (file_lru > file_mapped) ? (file_lru - file_mapped) : 0;
+}
+
+/* Work out how many page cache pages we can reclaim in this reclaim_mode */
+static long zone_pagecache_reclaimable(struct zone *zone)
+{
+ long nr_pagecache_reclaimable;
+ long delta = 0;
+
+ /*
+ * If RECLAIM_SWAP is set, then all file pages are considered
+ * potentially reclaimable. Otherwise, we have to worry about
+ * pages like swapcache and zone_unmapped_file_pages() provides
+ * a better estimate
+ */
+ if (zone_reclaim_mode & RECLAIM_SWAP)
+ nr_pagecache_reclaimable = zone_page_state(zone, NR_FILE_PAGES);
+ else
+ nr_pagecache_reclaimable = zone_unmapped_file_pages(zone);
+
+ /* If we can't clean pages, remove dirty pages from consideration */
+ if (!(zone_reclaim_mode & RECLAIM_WRITE))
+ delta += zone_page_state(zone, NR_FILE_DIRTY);
+
+ /* Watch for any possible underflows due to delta */
+ if (unlikely(delta > nr_pagecache_reclaimable))
+ delta = nr_pagecache_reclaimable;
+
+ return nr_pagecache_reclaimable - delta;
+}
+
/*
* Try to free up some pages from this zone through reclaim.
*/
@@ -2324,9 +2424,7 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
reclaim_state.reclaimed_slab = 0;
p->reclaim_state = &reclaim_state;
- if (zone_page_state(zone, NR_FILE_PAGES) -
- zone_page_state(zone, NR_FILE_MAPPED) >
- zone->min_unmapped_pages) {
+ if (zone_pagecache_reclaimable(zone) > zone->min_unmapped_pages) {
/*
* Free memory by calling shrink zone with increasing
* priorities until we have enough memory freed.
@@ -2384,20 +2482,18 @@ int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
* if less than a specified percentage of the zone is used by
* unmapped file backed pages.
*/
- if (zone_page_state(zone, NR_FILE_PAGES) -
- zone_page_state(zone, NR_FILE_MAPPED) <= zone->min_unmapped_pages
- && zone_page_state(zone, NR_SLAB_RECLAIMABLE)
- <= zone->min_slab_pages)
- return 0;
+ if (zone_pagecache_reclaimable(zone) <= zone->min_unmapped_pages &&
+ zone_page_state(zone, NR_SLAB_RECLAIMABLE) <= zone->min_slab_pages)
+ return ZONE_RECLAIM_FULL;
if (zone_is_all_unreclaimable(zone))
- return 0;
+ return ZONE_RECLAIM_FULL;
/*
* Do not scan if the allocation should not be delayed.
*/
if (!(gfp_mask & __GFP_WAIT) || (current->flags & PF_MEMALLOC))
- return 0;
+ return ZONE_RECLAIM_NOSCAN;
/*
* Only run zone reclaim on the local zone or on zones that do not
@@ -2407,18 +2503,21 @@ int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
*/
node_id = zone_to_nid(zone);
if (node_state(node_id, N_CPU) && node_id != numa_node_id())
- return 0;
+ return ZONE_RECLAIM_NOSCAN;
if (zone_test_and_set_flag(zone, ZONE_RECLAIM_LOCKED))
- return 0;
+ return ZONE_RECLAIM_NOSCAN;
+
ret = __zone_reclaim(zone, gfp_mask, order);
zone_clear_flag(zone, ZONE_RECLAIM_LOCKED);
+ if (!ret)
+ count_vm_event(PGSCAN_ZONE_RECLAIM_FAILED);
+
return ret;
}
#endif
-#ifdef CONFIG_UNEVICTABLE_LRU
/*
* page_evictable - test whether a page is evictable
* @page: the page to test
@@ -2665,4 +2764,3 @@ void scan_unevictable_unregister_node(struct node *node)
sysdev_remove_file(&node->sysdev, &attr_scan_unevictable_pages);
}
-#endif
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 74d66dba0cb..138bed53706 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -629,10 +629,8 @@ static const char * const vmstat_text[] = {
"nr_active_anon",
"nr_inactive_file",
"nr_active_file",
-#ifdef CONFIG_UNEVICTABLE_LRU
"nr_unevictable",
"nr_mlock",
-#endif
"nr_anon_pages",
"nr_mapped",
"nr_file_pages",
@@ -675,6 +673,9 @@ static const char * const vmstat_text[] = {
TEXTS_FOR_ZONES("pgscan_kswapd")
TEXTS_FOR_ZONES("pgscan_direct")
+#ifdef CONFIG_NUMA
+ "zone_reclaim_failed",
+#endif
"pginodesteal",
"slabs_scanned",
"kswapd_steal",
@@ -687,7 +688,6 @@ static const char * const vmstat_text[] = {
"htlb_buddy_alloc_success",
"htlb_buddy_alloc_fail",
#endif
-#ifdef CONFIG_UNEVICTABLE_LRU
"unevictable_pgs_culled",
"unevictable_pgs_scanned",
"unevictable_pgs_rescued",
@@ -697,7 +697,6 @@ static const char * const vmstat_text[] = {
"unevictable_pgs_stranded",
"unevictable_pgs_mlockfreed",
#endif
-#endif
};
static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat,
@@ -710,18 +709,14 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat,
"\n min %lu"
"\n low %lu"
"\n high %lu"
- "\n scanned %lu (aa: %lu ia: %lu af: %lu if: %lu)"
+ "\n scanned %lu"
"\n spanned %lu"
"\n present %lu",
zone_page_state(zone, NR_FREE_PAGES),
- zone->pages_min,
- zone->pages_low,
- zone->pages_high,
+ min_wmark_pages(zone),
+ low_wmark_pages(zone),
+ high_wmark_pages(zone),
zone->pages_scanned,
- zone->lru[LRU_ACTIVE_ANON].nr_scan,
- zone->lru[LRU_INACTIVE_ANON].nr_scan,
- zone->lru[LRU_ACTIVE_FILE].nr_scan,
- zone->lru[LRU_INACTIVE_FILE].nr_scan,
zone->spanned_pages,
zone->present_pages);