aboutsummaryrefslogtreecommitdiff
path: root/mm
diff options
context:
space:
mode:
Diffstat (limited to 'mm')
-rw-r--r--mm/Kconfig6
-rw-r--r--mm/backing-dev.c7
-rw-r--r--mm/bootmem.c20
-rw-r--r--mm/dmapool.c2
-rw-r--r--mm/filemap.c1
-rw-r--r--mm/hugetlb.c19
-rw-r--r--mm/kmemleak.c470
-rw-r--r--mm/memcontrol.c151
-rw-r--r--mm/memory.c87
-rw-r--r--mm/mempolicy.c84
-rw-r--r--mm/mempool.c4
-rw-r--r--mm/mmap.c3
-rw-r--r--mm/nommu.c43
-rw-r--r--mm/oom_kill.c64
-rw-r--r--mm/page-writeback.c13
-rw-r--r--mm/page_alloc.c86
-rw-r--r--mm/page_cgroup.c24
-rw-r--r--mm/percpu.c72
-rw-r--r--mm/rmap.c6
-rw-r--r--mm/shmem.c6
-rw-r--r--mm/shmem_acl.c29
-rw-r--r--mm/slab.c32
-rw-r--r--mm/slob.c8
-rw-r--r--mm/slub.c139
-rw-r--r--mm/swapfile.c20
-rw-r--r--mm/thrash.c32
-rw-r--r--mm/util.c4
-rw-r--r--mm/vmscan.c21
28 files changed, 882 insertions, 571 deletions
diff --git a/mm/Kconfig b/mm/Kconfig
index c948d4ca8bd..fe5f674d7a7 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -225,9 +225,9 @@ config DEFAULT_MMAP_MIN_ADDR
For most ia64, ppc64 and x86 users with lots of address space
a value of 65536 is reasonable and should cause no problems.
On arm and other archs it should not be higher than 32768.
- Programs which use vm86 functionality would either need additional
- permissions from either the LSM or the capabilities module or have
- this protection disabled.
+ Programs which use vm86 functionality or have some need to map
+ this low address space will need CAP_SYS_RAWIO or disable this
+ protection by setting the value to 0.
This value can be changed after boot using the
/proc/sys/vm/mmap_min_addr tunable.
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 493b468a503..c86edd24429 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -283,7 +283,6 @@ static wait_queue_head_t congestion_wqh[2] = {
__WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[1])
};
-
void clear_bdi_congested(struct backing_dev_info *bdi, int sync)
{
enum bdi_state bit;
@@ -308,18 +307,18 @@ EXPORT_SYMBOL(set_bdi_congested);
/**
* congestion_wait - wait for a backing_dev to become uncongested
- * @rw: READ or WRITE
+ * @sync: SYNC or ASYNC IO
* @timeout: timeout in jiffies
*
* Waits for up to @timeout jiffies for a backing_dev (any backing_dev) to exit
* write congestion. If no backing_devs are congested then just wait for the
* next write to be completed.
*/
-long congestion_wait(int rw, long timeout)
+long congestion_wait(int sync, long timeout)
{
long ret;
DEFINE_WAIT(wait);
- wait_queue_head_t *wqh = &congestion_wqh[rw];
+ wait_queue_head_t *wqh = &congestion_wqh[sync];
prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE);
ret = io_schedule_timeout(timeout);
diff --git a/mm/bootmem.c b/mm/bootmem.c
index 282df0a09e6..701740c9e81 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -12,6 +12,7 @@
#include <linux/pfn.h>
#include <linux/bootmem.h>
#include <linux/module.h>
+#include <linux/kmemleak.h>
#include <asm/bug.h>
#include <asm/io.h>
@@ -335,6 +336,8 @@ void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr,
{
unsigned long start, end;
+ kmemleak_free_part(__va(physaddr), size);
+
start = PFN_UP(physaddr);
end = PFN_DOWN(physaddr + size);
@@ -354,6 +357,8 @@ void __init free_bootmem(unsigned long addr, unsigned long size)
{
unsigned long start, end;
+ kmemleak_free_part(__va(addr), size);
+
start = PFN_UP(addr);
end = PFN_DOWN(addr + size);
@@ -516,6 +521,7 @@ find_block:
region = phys_to_virt(PFN_PHYS(bdata->node_min_pfn) +
start_off);
memset(region, 0, size);
+ kmemleak_alloc(region, size, 1, 0);
return region;
}
@@ -536,11 +542,15 @@ static void * __init alloc_arch_preferred_bootmem(bootmem_data_t *bdata,
return kzalloc(size, GFP_NOWAIT);
#ifdef CONFIG_HAVE_ARCH_BOOTMEM
- bootmem_data_t *p_bdata;
-
- p_bdata = bootmem_arch_preferred_node(bdata, size, align, goal, limit);
- if (p_bdata)
- return alloc_bootmem_core(p_bdata, size, align, goal, limit);
+ {
+ bootmem_data_t *p_bdata;
+
+ p_bdata = bootmem_arch_preferred_node(bdata, size, align,
+ goal, limit);
+ if (p_bdata)
+ return alloc_bootmem_core(p_bdata, size, align,
+ goal, limit);
+ }
#endif
return NULL;
}
diff --git a/mm/dmapool.c b/mm/dmapool.c
index b1f0885dda2..3df063706f5 100644
--- a/mm/dmapool.c
+++ b/mm/dmapool.c
@@ -86,10 +86,12 @@ show_pools(struct device *dev, struct device_attribute *attr, char *buf)
unsigned pages = 0;
unsigned blocks = 0;
+ spin_lock_irq(&pool->lock);
list_for_each_entry(page, &pool->page_list, page_list) {
pages++;
blocks += page->in_use;
}
+ spin_unlock_irq(&pool->lock);
/* per-pool info, no real statistics yet */
temp = scnprintf(next, size, "%-16s %4u %4Zu %4Zu %2u\n",
diff --git a/mm/filemap.c b/mm/filemap.c
index 22396713feb..ccea3b665c1 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2272,6 +2272,7 @@ again:
pagefault_enable();
flush_dcache_page(page);
+ mark_page_accessed(page);
status = a_ops->write_end(file, mapping, pos, bytes, copied,
page, fsdata);
if (unlikely(status < 0))
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index a56e6f3ce97..cafdcee154e 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1985,7 +1985,7 @@ static struct page *hugetlbfs_pagecache_page(struct hstate *h,
}
static int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma,
- unsigned long address, pte_t *ptep, int write_access)
+ unsigned long address, pte_t *ptep, unsigned int flags)
{
struct hstate *h = hstate_vma(vma);
int ret = VM_FAULT_SIGBUS;
@@ -2053,7 +2053,7 @@ retry:
* any allocations necessary to record that reservation occur outside
* the spinlock.
*/
- if (write_access && !(vma->vm_flags & VM_SHARED))
+ if ((flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED))
if (vma_needs_reservation(h, vma, address) < 0) {
ret = VM_FAULT_OOM;
goto backout_unlocked;
@@ -2072,7 +2072,7 @@ retry:
&& (vma->vm_flags & VM_SHARED)));
set_huge_pte_at(mm, address, ptep, new_pte);
- if (write_access && !(vma->vm_flags & VM_SHARED)) {
+ if ((flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) {
/* Optimization, do the COW without a second fault */
ret = hugetlb_cow(mm, vma, address, ptep, new_pte, page);
}
@@ -2091,7 +2091,7 @@ backout_unlocked:
}
int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
- unsigned long address, int write_access)
+ unsigned long address, unsigned int flags)
{
pte_t *ptep;
pte_t entry;
@@ -2112,7 +2112,7 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
mutex_lock(&hugetlb_instantiation_mutex);
entry = huge_ptep_get(ptep);
if (huge_pte_none(entry)) {
- ret = hugetlb_no_page(mm, vma, address, ptep, write_access);
+ ret = hugetlb_no_page(mm, vma, address, ptep, flags);
goto out_mutex;
}
@@ -2126,7 +2126,7 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
* page now as it is used to determine if a reservation has been
* consumed.
*/
- if (write_access && !pte_write(entry)) {
+ if ((flags & FAULT_FLAG_WRITE) && !pte_write(entry)) {
if (vma_needs_reservation(h, vma, address) < 0) {
ret = VM_FAULT_OOM;
goto out_mutex;
@@ -2143,7 +2143,7 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
goto out_page_table_lock;
- if (write_access) {
+ if (flags & FAULT_FLAG_WRITE) {
if (!pte_write(entry)) {
ret = hugetlb_cow(mm, vma, address, ptep, entry,
pagecache_page);
@@ -2152,7 +2152,8 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
entry = pte_mkdirty(entry);
}
entry = pte_mkyoung(entry);
- if (huge_ptep_set_access_flags(vma, address, ptep, entry, write_access))
+ if (huge_ptep_set_access_flags(vma, address, ptep, entry,
+ flags & FAULT_FLAG_WRITE))
update_mmu_cache(vma, address, entry);
out_page_table_lock:
@@ -2369,7 +2370,7 @@ void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed)
long chg = region_truncate(&inode->i_mapping->private_list, offset);
spin_lock(&inode->i_lock);
- inode->i_blocks -= blocks_per_huge_page(h);
+ inode->i_blocks -= (blocks_per_huge_page(h) * freed);
spin_unlock(&inode->i_lock);
hugetlb_put_quota(inode->i_mapping, (chg - freed));
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index 58ec86c9e58..487267310a8 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -48,10 +48,10 @@
* scanned. This list is only modified during a scanning episode when the
* scan_mutex is held. At the end of a scan, the gray_list is always empty.
* Note that the kmemleak_object.use_count is incremented when an object is
- * added to the gray_list and therefore cannot be freed
- * - kmemleak_mutex (mutex): prevents multiple users of the "kmemleak" debugfs
- * file together with modifications to the memory scanning parameters
- * including the scan_thread pointer
+ * added to the gray_list and therefore cannot be freed. This mutex also
+ * prevents multiple users of the "kmemleak" debugfs file together with
+ * modifications to the memory scanning parameters including the scan_thread
+ * pointer
*
* The kmemleak_object structures have a use_count incremented or decremented
* using the get_object()/put_object() functions. When the use_count becomes
@@ -61,6 +61,8 @@
* structure.
*/
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/list.h>
@@ -101,14 +103,16 @@
* Kmemleak configuration and common defines.
*/
#define MAX_TRACE 16 /* stack trace length */
-#define REPORTS_NR 50 /* maximum number of reported leaks */
#define MSECS_MIN_AGE 5000 /* minimum object age for reporting */
-#define MSECS_SCAN_YIELD 10 /* CPU yielding period */
#define SECS_FIRST_SCAN 60 /* delay before the first scan */
#define SECS_SCAN_WAIT 600 /* subsequent auto scanning delay */
+#define GRAY_LIST_PASSES 25 /* maximum number of gray list scans */
#define BYTES_PER_POINTER sizeof(void *)
+/* GFP bitmask for kmemleak internal allocations */
+#define GFP_KMEMLEAK_MASK (GFP_KERNEL | GFP_ATOMIC)
+
/* scanning area inside a memory block */
struct kmemleak_scan_area {
struct hlist_node node;
@@ -154,6 +158,8 @@ struct kmemleak_object {
#define OBJECT_REPORTED (1 << 1)
/* flag set to not scan the object */
#define OBJECT_NO_SCAN (1 << 2)
+/* flag set on newly allocated objects */
+#define OBJECT_NEW (1 << 3)
/* the list of all allocated objects */
static LIST_HEAD(object_list);
@@ -181,27 +187,21 @@ static atomic_t kmemleak_error = ATOMIC_INIT(0);
static unsigned long min_addr = ULONG_MAX;
static unsigned long max_addr;
-/* used for yielding the CPU to other tasks during scanning */
-static unsigned long next_scan_yield;
static struct task_struct *scan_thread;
-static unsigned long jiffies_scan_yield;
+/* used to avoid reporting of recently allocated objects */
static unsigned long jiffies_min_age;
+static unsigned long jiffies_last_scan;
/* delay between automatic memory scannings */
static signed long jiffies_scan_wait;
/* enables or disables the task stacks scanning */
-static int kmemleak_stack_scan;
-/* mutex protecting the memory scanning */
+static int kmemleak_stack_scan = 1;
+/* protects the memory scanning, parameters and debug/kmemleak file access */
static DEFINE_MUTEX(scan_mutex);
-/* mutex protecting the access to the /sys/kernel/debug/kmemleak file */
-static DEFINE_MUTEX(kmemleak_mutex);
-
-/* number of leaks reported (for limitation purposes) */
-static int reported_leaks;
/*
- * Early object allocation/freeing logging. Kkmemleak is initialized after the
+ * Early object allocation/freeing logging. Kmemleak is initialized after the
* kernel allocator. However, both the kernel allocator and kmemleak may
- * allocate memory blocks which need to be tracked. Kkmemleak defines an
+ * allocate memory blocks which need to be tracked. Kmemleak defines an
* arbitrary buffer to hold the allocation/freeing information before it is
* fully initialized.
*/
@@ -210,6 +210,7 @@ static int reported_leaks;
enum {
KMEMLEAK_ALLOC,
KMEMLEAK_FREE,
+ KMEMLEAK_FREE_PART,
KMEMLEAK_NOT_LEAK,
KMEMLEAK_IGNORE,
KMEMLEAK_SCAN_AREA,
@@ -230,7 +231,7 @@ struct early_log {
};
/* early logging buffer and current position */
-static struct early_log early_log[200];
+static struct early_log early_log[CONFIG_DEBUG_KMEMLEAK_EARLY_LOG_SIZE];
static int crt_early_log;
static void kmemleak_disable(void);
@@ -245,10 +246,10 @@ static void kmemleak_disable(void);
/*
* Macro invoked when a serious kmemleak condition occured and cannot be
- * recovered from. Kkmemleak will be disabled and further allocation/freeing
+ * recovered from. Kmemleak will be disabled and further allocation/freeing
* tracing no longer available.
*/
-#define kmemleak_panic(x...) do { \
+#define kmemleak_stop(x...) do { \
kmemleak_warn(x); \
kmemleak_disable(); \
} while (0)
@@ -273,13 +274,9 @@ static int color_gray(const struct kmemleak_object *object)
return object->min_count != -1 && object->count >= object->min_count;
}
-/*
- * Objects are considered referenced if their color is gray and they have not
- * been deleted.
- */
-static int referenced_object(struct kmemleak_object *object)
+static int color_black(const struct kmemleak_object *object)
{
- return (object->flags & OBJECT_ALLOCATED) && color_gray(object);
+ return object->min_count == -1;
}
/*
@@ -290,42 +287,28 @@ static int referenced_object(struct kmemleak_object *object)
static int unreferenced_object(struct kmemleak_object *object)
{
return (object->flags & OBJECT_ALLOCATED) && color_white(object) &&
- time_is_before_eq_jiffies(object->jiffies + jiffies_min_age);
+ time_before_eq(object->jiffies + jiffies_min_age,
+ jiffies_last_scan);
}
/*
- * Printing of the (un)referenced objects information, either to the seq file
- * or to the kernel log. The print_referenced/print_unreferenced functions
- * must be called with the object->lock held.
+ * Printing of the unreferenced objects information to the seq file. The
+ * print_unreferenced function must be called with the object->lock held.
*/
-#define print_helper(seq, x...) do { \
- struct seq_file *s = (seq); \
- if (s) \
- seq_printf(s, x); \
- else \
- pr_info(x); \
-} while (0)
-
-static void print_referenced(struct kmemleak_object *object)
-{
- pr_info("kmemleak: referenced object 0x%08lx (size %zu)\n",
- object->pointer, object->size);
-}
-
static void print_unreferenced(struct seq_file *seq,
struct kmemleak_object *object)
{
int i;
- print_helper(seq, "kmemleak: unreferenced object 0x%08lx (size %zu):\n",
- object->pointer, object->size);
- print_helper(seq, " comm \"%s\", pid %d, jiffies %lu\n",
- object->comm, object->pid, object->jiffies);
- print_helper(seq, " backtrace:\n");
+ seq_printf(seq, "unreferenced object 0x%08lx (size %zu):\n",
+ object->pointer, object->size);
+ seq_printf(seq, " comm \"%s\", pid %d, jiffies %lu\n",
+ object->comm, object->pid, object->jiffies);
+ seq_printf(seq, " backtrace:\n");
for (i = 0; i < object->trace_len; i++) {
void *ptr = (void *)object->trace[i];
- print_helper(seq, " [<%p>] %pS\n", ptr, ptr);
+ seq_printf(seq, " [<%p>] %pS\n", ptr, ptr);
}
}
@@ -341,7 +324,7 @@ static void dump_object_info(struct kmemleak_object *object)
trace.nr_entries = object->trace_len;
trace.entries = object->trace;
- pr_notice("kmemleak: Object 0x%08lx (size %zu):\n",
+ pr_notice("Object 0x%08lx (size %zu):\n",
object->tree_node.start, object->size);
pr_notice(" comm \"%s\", pid %d, jiffies %lu\n",
object->comm, object->pid, object->jiffies);
@@ -369,7 +352,7 @@ static struct kmemleak_object *lookup_object(unsigned long ptr, int alias)
object = prio_tree_entry(node, struct kmemleak_object,
tree_node);
if (!alias && object->pointer != ptr) {
- kmemleak_warn("kmemleak: Found object by alias");
+ kmemleak_warn("Found object by alias");
object = NULL;
}
} else
@@ -462,10 +445,9 @@ static void create_object(unsigned long ptr, size_t size, int min_count,
struct prio_tree_node *node;
struct stack_trace trace;
- object = kmem_cache_alloc(object_cache, gfp & ~GFP_SLAB_BUG_MASK);
+ object = kmem_cache_alloc(object_cache, gfp & GFP_KMEMLEAK_MASK);
if (!object) {
- kmemleak_panic("kmemleak: Cannot allocate a kmemleak_object "
- "structure\n");
+ kmemleak_stop("Cannot allocate a kmemleak_object structure\n");
return;
}
@@ -474,7 +456,7 @@ static void create_object(unsigned long ptr, size_t size, int min_count,
INIT_HLIST_HEAD(&object->area_list);
spin_lock_init(&object->lock);
atomic_set(&object->use_count, 1);
- object->flags = OBJECT_ALLOCATED;
+ object->flags = OBJECT_ALLOCATED | OBJECT_NEW;
object->pointer = ptr;
object->size = size;
object->min_count = min_count;
@@ -524,8 +506,8 @@ static void create_object(unsigned long ptr, size_t size, int min_count,
if (node != &object->tree_node) {
unsigned long flags;
- kmemleak_panic("kmemleak: Cannot insert 0x%lx into the object "
- "search tree (already existing)\n", ptr);
+ kmemleak_stop("Cannot insert 0x%lx into the object search tree "
+ "(already existing)\n", ptr);
object = lookup_object(ptr, 1);
spin_lock_irqsave(&object->lock, flags);
dump_object_info(object);
@@ -542,39 +524,87 @@ out:
* Remove the metadata (struct kmemleak_object) for a memory block from the
* object_list and object_tree_root and decrement its use_count.
*/
-static void delete_object(unsigned long ptr)
+static void __delete_object(struct kmemleak_object *object)
{
unsigned long flags;
- struct kmemleak_object *object;
write_lock_irqsave(&kmemleak_lock, flags);
- object = lookup_object(ptr, 0);
- if (!object) {
- kmemleak_warn("kmemleak: Freeing unknown object at 0x%08lx\n",
- ptr);
- write_unlock_irqrestore(&kmemleak_lock, flags);
- return;
- }
prio_tree_remove(&object_tree_root, &object->tree_node);
list_del_rcu(&object->object_list);
write_unlock_irqrestore(&kmemleak_lock, flags);
WARN_ON(!(object->flags & OBJECT_ALLOCATED));
- WARN_ON(atomic_read(&object->use_count) < 1);
+ WARN_ON(atomic_read(&object->use_count) < 2);
/*
* Locking here also ensures that the corresponding memory block
* cannot be freed when it is being scanned.
*/
spin_lock_irqsave(&object->lock, flags);
- if (object->flags & OBJECT_REPORTED)
- print_referenced(object);
object->flags &= ~OBJECT_ALLOCATED;
spin_unlock_irqrestore(&object->lock, flags);
put_object(object);
}
/*
+ * Look up the metadata (struct kmemleak_object) corresponding to ptr and
+ * delete it.
+ */
+static void delete_object_full(unsigned long ptr)
+{
+ struct kmemleak_object *object;
+
+ object = find_and_get_object(ptr, 0);
+ if (!object) {
+#ifdef DEBUG
+ kmemleak_warn("Freeing unknown object at 0x%08lx\n",
+ ptr);
+#endif
+ return;
+ }
+ __delete_object(object);
+ put_object(object);
+}
+
+/*
+ * Look up the metadata (struct kmemleak_object) corresponding to ptr and
+ * delete it. If the memory block is partially freed, the function may create
+ * additional metadata for the remaining parts of the block.
+ */
+static void delete_object_part(unsigned long ptr, size_t size)
+{
+ struct kmemleak_object *object;
+ unsigned long start, end;
+
+ object = find_and_get_object(ptr, 1);
+ if (!object) {
+#ifdef DEBUG
+ kmemleak_warn("Partially freeing unknown object at 0x%08lx "
+ "(size %zu)\n", ptr, size);
+#endif
+ return;
+ }
+ __delete_object(object);
+
+ /*
+ * Create one or two objects that may result from the memory block
+ * split. Note that partial freeing is only done by free_bootmem() and
+ * this happens before kmemleak_init() is called. The path below is
+ * only executed during early log recording in kmemleak_init(), so
+ * GFP_KERNEL is enough.
+ */
+ start = object->pointer;
+ end = object->pointer + object->size;
+ if (ptr > start)
+ create_object(start, ptr - start, object->min_count,
+ GFP_KERNEL);
+ if (ptr + size < end)
+ create_object(ptr + size, end - ptr - size, object->min_count,
+ GFP_KERNEL);
+
+ put_object(object);
+}
+/*
* Make a object permanently as gray-colored so that it can no longer be
* reported as a leak. This is used in general to mark a false positive.
*/
@@ -585,8 +615,7 @@ static void make_gray_object(unsigned long ptr)
object = find_and_get_object(ptr, 0);
if (!object) {
- kmemleak_warn("kmemleak: Graying unknown object at 0x%08lx\n",
- ptr);
+ kmemleak_warn("Graying unknown object at 0x%08lx\n", ptr);
return;
}
@@ -607,8 +636,7 @@ static void make_black_object(unsigned long ptr)
object = find_and_get_object(ptr, 0);
if (!object) {
- kmemleak_warn("kmemleak: Blacking unknown object at 0x%08lx\n",
- ptr);
+ kmemleak_warn("Blacking unknown object at 0x%08lx\n", ptr);
return;
}
@@ -631,21 +659,20 @@ static void add_scan_area(unsigned long ptr, unsigned long offset,
object = find_and_get_object(ptr, 0);
if (!object) {
- kmemleak_warn("kmemleak: Adding scan area to unknown "
- "object at 0x%08lx\n", ptr);
+ kmemleak_warn("Adding scan area to unknown object at 0x%08lx\n",
+ ptr);
return;
}
- area = kmem_cache_alloc(scan_area_cache, gfp & ~GFP_SLAB_BUG_MASK);
+ area = kmem_cache_alloc(scan_area_cache, gfp & GFP_KMEMLEAK_MASK);
if (!area) {
- kmemleak_warn("kmemleak: Cannot allocate a scan area\n");
+ kmemleak_warn("Cannot allocate a scan area\n");
goto out;
}
spin_lock_irqsave(&object->lock, flags);
if (offset + length > object->size) {
- kmemleak_warn("kmemleak: Scan area larger than object "
- "0x%08lx\n", ptr);
+ kmemleak_warn("Scan area larger than object 0x%08lx\n", ptr);
dump_object_info(object);
kmem_cache_free(scan_area_cache, area);
goto out_unlock;
@@ -674,8 +701,7 @@ static void object_no_scan(unsigned long ptr)
object = find_and_get_object(ptr, 0);
if (!object) {
- kmemleak_warn("kmemleak: Not scanning unknown object at "
- "0x%08lx\n", ptr);
+ kmemleak_warn("Not scanning unknown object at 0x%08lx\n", ptr);
return;
}
@@ -696,7 +722,8 @@ static void log_early(int op_type, const void *ptr, size_t size,
struct early_log *log;
if (crt_early_log >= ARRAY_SIZE(early_log)) {
- kmemleak_panic("kmemleak: Early log buffer exceeded\n");
+ pr_warning("Early log buffer exceeded\n");
+ kmemleak_disable();
return;
}
@@ -741,13 +768,28 @@ void kmemleak_free(const void *ptr)
pr_debug("%s(0x%p)\n", __func__, ptr);
if (atomic_read(&kmemleak_enabled) && ptr && !IS_ERR(ptr))
- delete_object((unsigned long)ptr);
+ delete_object_full((unsigned long)ptr);
else if (atomic_read(&kmemleak_early_log))
log_early(KMEMLEAK_FREE, ptr, 0, 0, 0, 0);
}
EXPORT_SYMBOL_GPL(kmemleak_free);
/*
+ * Partial memory freeing function callback. This function is usually called
+ * from bootmem allocator when (part of) a memory block is freed.
+ */
+void kmemleak_free_part(const void *ptr, size_t size)
+{
+ pr_debug("%s(0x%p)\n", __func__, ptr);
+
+ if (atomic_read(&kmemleak_enabled) && ptr && !IS_ERR(ptr))
+ delete_object_part((unsigned long)ptr, size);
+ else if (atomic_read(&kmemleak_early_log))
+ log_early(KMEMLEAK_FREE_PART, ptr, size, 0, 0, 0);
+}
+EXPORT_SYMBOL_GPL(kmemleak_free_part);
+
+/*
* Mark an already allocated memory block as a false positive. This will cause
* the block to no longer be reported as leak and always be scanned.
*/
@@ -808,21 +850,6 @@ void kmemleak_no_scan(const void *ptr)
EXPORT_SYMBOL(kmemleak_no_scan);
/*
- * Yield the CPU so that other tasks get a chance to run. The yielding is
- * rate-limited to avoid excessive number of calls to the schedule() function
- * during memory scanning.
- */
-static void scan_yield(void)
-{
- might_sleep();
-
- if (time_is_before_eq_jiffies(next_scan_yield)) {
- schedule();
- next_scan_yield = jiffies + jiffies_scan_yield;
- }
-}
-
-/*
* Memory scanning is a long process and it needs to be interruptable. This
* function checks whether such interrupt condition occured.
*/
@@ -848,7 +875,7 @@ static int scan_should_stop(void)
* found to the gray list.
*/
static void scan_block(void *_start, void *_end,
- struct kmemleak_object *scanned)
+ struct kmemleak_object *scanned, int allow_resched)
{
unsigned long *ptr;
unsigned long *start = PTR_ALIGN(_start, BYTES_PER_POINTER);
@@ -859,18 +886,11 @@ static void scan_block(void *_start, void *_end,
unsigned long pointer = *ptr;
struct kmemleak_object *object;
+ if (allow_resched)
+ cond_resched();
if (scan_should_stop())
break;
- /*
- * When scanning a memory block with a corresponding
- * kmemleak_object, the CPU yielding is handled in the calling
- * code since it holds the object->lock to avoid the block
- * freeing.
- */
- if (!scanned)
- scan_yield();
-
object = find_and_get_object(pointer, 1);
if (!object)
continue;
@@ -931,12 +951,12 @@ static void scan_object(struct kmemleak_object *object)
goto out;
if (hlist_empty(&object->area_list))
scan_block((void *)object->pointer,
- (void *)(object->pointer + object->size), object);
+ (void *)(object->pointer + object->size), object, 0);
else
hlist_for_each_entry(area, elem, &object->area_list, node)
scan_block((void *)(object->pointer + area->offset),
(void *)(object->pointer + area->offset
- + area->length), object);
+ + area->length), object, 0);
out:
spin_unlock_irqrestore(&object->lock, flags);
}
@@ -952,6 +972,10 @@ static void kmemleak_scan(void)
struct kmemleak_object *object, *tmp;
struct task_struct *task;
int i;
+ int new_leaks = 0;
+ int gray_list_pass = 0;
+
+ jiffies_last_scan = jiffies;
/* prepare the kmemleak_object's */
rcu_read_lock();
@@ -963,13 +987,14 @@ static void kmemleak_scan(void)
* 1 reference to any object at this point.
*/
if (atomic_read(&object->use_count) > 1) {
- pr_debug("kmemleak: object->use_count = %d\n",
+ pr_debug("object->use_count = %d\n",
atomic_read(&object->use_count));
dump_object_info(object);
}
#endif
/* reset the reference count (whiten the object) */
object->count = 0;
+ object->flags &= ~OBJECT_NEW;
if (color_gray(object) && get_object(object))
list_add_tail(&object->gray_list, &gray_list);
@@ -978,14 +1003,14 @@ static void kmemleak_scan(void)
rcu_read_unlock();
/* data/bss scanning */
- scan_block(_sdata, _edata, NULL);
- scan_block(__bss_start, __bss_stop, NULL);
+ scan_block(_sdata, _edata, NULL, 1);
+ scan_block(__bss_start, __bss_stop, NULL, 1);
#ifdef CONFIG_SMP
/* per-cpu sections scanning */
for_each_possible_cpu(i)
scan_block(__per_cpu_start + per_cpu_offset(i),
- __per_cpu_end + per_cpu_offset(i), NULL);
+ __per_cpu_end + per_cpu_offset(i), NULL, 1);
#endif
/*
@@ -1007,7 +1032,7 @@ static void kmemleak_scan(void)
/* only scan if page is in use */
if (page_count(page) == 0)
continue;
- scan_block(page, page + 1, NULL);
+ scan_block(page, page + 1, NULL, 1);
}
}
@@ -1019,7 +1044,8 @@ static void kmemleak_scan(void)
read_lock(&tasklist_lock);
for_each_process(task)
scan_block(task_stack_page(task),
- task_stack_page(task) + THREAD_SIZE, NULL);
+ task_stack_page(task) + THREAD_SIZE,
+ NULL, 0);
read_unlock(&tasklist_lock);
}
@@ -1031,9 +1057,10 @@ static void kmemleak_scan(void)
* kmemleak objects cannot be freed from outside the loop because their
* use_count was increased.
*/
+repeat:
object = list_entry(gray_list.next, typeof(*object), gray_list);
while (&object->gray_list != &gray_list) {
- scan_yield();
+ cond_resched();
/* may add new objects to the list */
if (!scan_should_stop())
@@ -1048,7 +1075,59 @@ static void kmemleak_scan(void)
object = tmp;
}
+
+ if (scan_should_stop() || ++gray_list_pass >= GRAY_LIST_PASSES)
+ goto scan_end;
+
+ /*
+ * Check for new objects allocated during this scanning and add them
+ * to the gray list.
+ */
+ rcu_read_lock();
+ list_for_each_entry_rcu(object, &object_list, object_list) {
+ spin_lock_irqsave(&object->lock, flags);
+ if ((object->flags & OBJECT_NEW) && !color_black(object) &&
+ get_object(object)) {
+ object->flags &= ~OBJECT_NEW;
+ list_add_tail(&object->gray_list, &gray_list);
+ }
+ spin_unlock_irqrestore(&object->lock, flags);
+ }
+ rcu_read_unlock();
+
+ if (!list_empty(&gray_list))
+ goto repeat;
+
+scan_end:
WARN_ON(!list_empty(&gray_list));
+
+ /*
+ * If scanning was stopped or new objects were being allocated at a
+ * higher rate than gray list scanning, do not report any new
+ * unreferenced objects.
+ */
+ if (scan_should_stop() || gray_list_pass >= GRAY_LIST_PASSES)
+ return;
+
+ /*
+ * Scanning result reporting.
+ */
+ rcu_read_lock();
+ list_for_each_entry_rcu(object, &object_list, object_list) {
+ spin_lock_irqsave(&object->lock, flags);
+ if (unreferenced_object(object) &&
+ !(object->flags & OBJECT_REPORTED)) {
+ object->flags |= OBJECT_REPORTED;
+ new_leaks++;
+ }
+ spin_unlock_irqrestore(&object->lock, flags);
+ }
+ rcu_read_unlock();
+
+ if (new_leaks)
+ pr_info("%d new suspected memory leaks (see "
+ "/sys/kernel/debug/kmemleak)\n", new_leaks);
+
}
/*
@@ -1059,7 +1138,8 @@ static int kmemleak_scan_thread(void *arg)
{
static int first_run = 1;
- pr_info("kmemleak: Automatic memory scanning thread started\n");
+ pr_info("Automatic memory scanning thread started\n");
+ set_user_nice(current, 10);
/*
* Wait before the first scan to allow the system to fully initialize.
@@ -1070,49 +1150,25 @@ static int kmemleak_scan_thread(void *arg)
}
while (!kthread_should_stop()) {
- struct kmemleak_object *object;
signed long timeout = jiffies_scan_wait;
mutex_lock(&scan_mutex);
-
kmemleak_scan();
- reported_leaks = 0;
-
- rcu_read_lock();
- list_for_each_entry_rcu(object, &object_list, object_list) {
- unsigned long flags;
-
- if (reported_leaks >= REPORTS_NR)
- break;
- spin_lock_irqsave(&object->lock, flags);
- if (!(object->flags & OBJECT_REPORTED) &&
- unreferenced_object(object)) {
- print_unreferenced(NULL, object);
- object->flags |= OBJECT_REPORTED;
- reported_leaks++;
- } else if ((object->flags & OBJECT_REPORTED) &&
- referenced_object(object)) {
- print_referenced(object);
- object->flags &= ~OBJECT_REPORTED;
- }
- spin_unlock_irqrestore(&object->lock, flags);
- }
- rcu_read_unlock();
-
mutex_unlock(&scan_mutex);
+
/* wait before the next scan */
while (timeout && !kthread_should_stop())
timeout = schedule_timeout_interruptible(timeout);
}
- pr_info("kmemleak: Automatic memory scanning thread ended\n");
+ pr_info("Automatic memory scanning thread ended\n");
return 0;
}
/*
* Start the automatic memory scanning thread. This function must be called
- * with the kmemleak_mutex held.
+ * with the scan_mutex held.
*/
void start_scan_thread(void)
{
@@ -1120,14 +1176,14 @@ void start_scan_thread(void)
return;
scan_thread = kthread_run(kmemleak_scan_thread, NULL, "kmemleak");
if (IS_ERR(scan_thread)) {
- pr_warning("kmemleak: Failed to create the scan thread\n");
+ pr_warning("Failed to create the scan thread\n");
scan_thread = NULL;
}
}
/*
* Stop the automatic memory scanning thread. This function must be called
- * with the kmemleak_mutex held.
+ * with the scan_mutex held.
*/
void stop_scan_thread(void)
{
@@ -1146,13 +1202,11 @@ static void *kmemleak_seq_start(struct seq_file *seq, loff_t *pos)
{
struct kmemleak_object *object;
loff_t n = *pos;
+ int err;
- if (!n) {
- kmemleak_scan();
- reported_leaks = 0;
- }
- if (reported_leaks >= REPORTS_NR)
- return NULL;
+ err = mutex_lock_interruptible(&scan_mutex);
+ if (err < 0)
+ return ERR_PTR(err);
rcu_read_lock();
list_for_each_entry_rcu(object, &object_list, object_list) {
@@ -1163,7 +1217,6 @@ static void *kmemleak_seq_start(struct seq_file *seq, loff_t *pos)
}
object = NULL;
out:
- rcu_read_unlock();
return object;
}
@@ -1178,17 +1231,13 @@ static void *kmemleak_seq_next(struct seq_file *seq, void *v, loff_t *pos)
struct list_head *n = &prev_obj->object_list;
++(*pos);
- if (reported_leaks >= REPORTS_NR)
- goto out;
- rcu_read_lock();
list_for_each_continue_rcu(n, &object_list) {
next_obj = list_entry(n, struct kmemleak_object, object_list);
if (get_object(next_obj))
break;
}
- rcu_read_unlock();
-out:
+
put_object(prev_obj);
return next_obj;
}
@@ -1198,8 +1247,16 @@ out:
*/
static void kmemleak_seq_stop(struct seq_file *seq, void *v)
{
- if (v)
- put_object(v);
+ if (!IS_ERR(v)) {
+ /*
+ * kmemleak_seq_start may return ERR_PTR if the scan_mutex
+ * waiting was interrupted, so only release it if !IS_ERR.
+ */
+ rcu_read_unlock();
+ mutex_unlock(&scan_mutex);
+ if (v)
+ put_object(v);
+ }
}
/*
@@ -1211,11 +1268,8 @@ static int kmemleak_seq_show(struct seq_file *seq, void *v)
unsigned long flags;
spin_lock_irqsave(&object->lock, flags);
- if (!unreferenced_object(object))
- goto out;
- print_unreferenced(seq, object);
- reported_leaks++;
-out:
+ if ((object->flags & OBJECT_REPORTED) && unreferenced_object(object))
+ print_unreferenced(seq, object);
spin_unlock_irqrestore(&object->lock, flags);
return 0;
}
@@ -1229,43 +1283,15 @@ static const struct seq_operations kmemleak_seq_ops = {
static int kmemleak_open(struct inode *inode, struct file *file)
{
- int ret = 0;
-
if (!atomic_read(&kmemleak_enabled))
return -EBUSY;
- ret = mutex_lock_interruptible(&kmemleak_mutex);
- if (ret < 0)
- goto out;
- if (file->f_mode & FMODE_READ) {
- ret = mutex_lock_interruptible(&scan_mutex);
- if (ret < 0)
- goto kmemleak_unlock;
- ret = seq_open(file, &kmemleak_seq_ops);
- if (ret < 0)
- goto scan_unlock;
- }
- return ret;
-
-scan_unlock:
- mutex_unlock(&scan_mutex);
-kmemleak_unlock:
- mutex_unlock(&kmemleak_mutex);
-out:
- return ret;
+ return seq_open(file, &kmemleak_seq_ops);
}
static int kmemleak_release(struct inode *inode, struct file *file)
{
- int ret = 0;
-
- if (file->f_mode & FMODE_READ) {
- seq_release(inode, file);
- mutex_unlock(&scan_mutex);
- }
- mutex_unlock(&kmemleak_mutex);
-
- return ret;
+ return seq_release(inode, file);
}
/*
@@ -1278,21 +1304,24 @@ static int kmemleak_release(struct inode *inode, struct file *file)
* scan=off - stop the automatic memory scanning thread
* scan=... - set the automatic memory scanning period in seconds (0 to
* disable it)
+ * scan - trigger a memory scan
*/
static ssize_t kmemleak_write(struct file *file, const char __user *user_buf,
size_t size, loff_t *ppos)
{
char buf[64];
int buf_size;
-
- if (!atomic_read(&kmemleak_enabled))
- return -EBUSY;
+ int ret;
buf_size = min(size, (sizeof(buf) - 1));
if (strncpy_from_user(buf, user_buf, buf_size) < 0)
return -EFAULT;
buf[buf_size] = 0;
+ ret = mutex_lock_interruptible(&scan_mutex);
+ if (ret < 0)
+ return ret;
+
if (strncmp(buf, "off", 3) == 0)
kmemleak_disable();
else if (strncmp(buf, "stack=on", 8) == 0)
@@ -1305,18 +1334,24 @@ static ssize_t kmemleak_write(struct file *file, const char __user *user_buf,
stop_scan_thread();
else if (strncmp(buf, "scan=", 5) == 0) {
unsigned long secs;
- int err;
- err = strict_strtoul(buf + 5, 0, &secs);
- if (err < 0)
- return err;
+ ret = strict_strtoul(buf + 5, 0, &secs);
+ if (ret < 0)
+ goto out;
stop_scan_thread();
if (secs) {
jiffies_scan_wait = msecs_to_jiffies(secs * 1000);
start_scan_thread();
}
- } else
- return -EINVAL;
+ } else if (strncmp(buf, "scan", 4) == 0)
+ kmemleak_scan();
+ else
+ ret = -EINVAL;
+
+out:
+ mutex_unlock(&scan_mutex);
+ if (ret < 0)
+ return ret;
/* ignore the rest of the buffer, only one command at a time */
*ppos += size;
@@ -1340,14 +1375,12 @@ static int kmemleak_cleanup_thread(void *arg)
{
struct kmemleak_object *object;
- mutex_lock(&kmemleak_mutex);
+ mutex_lock(&scan_mutex);
stop_scan_thread();
- mutex_unlock(&kmemleak_mutex);
- mutex_lock(&scan_mutex);
rcu_read_lock();
list_for_each_entry_rcu(object, &object_list, object_list)
- delete_object(object->pointer);
+ delete_object_full(object->pointer);
rcu_read_unlock();
mutex_unlock(&scan_mutex);
@@ -1364,7 +1397,7 @@ static void kmemleak_cleanup(void)
cleanup_thread = kthread_run(kmemleak_cleanup_thread, NULL,
"kmemleak-clean");
if (IS_ERR(cleanup_thread))
- pr_warning("kmemleak: Failed to create the clean-up thread\n");
+ pr_warning("Failed to create the clean-up thread\n");
}
/*
@@ -1404,14 +1437,13 @@ static int kmemleak_boot_config(char *str)
early_param("kmemleak", kmemleak_boot_config);
/*
- * Kkmemleak initialization.
+ * Kmemleak initialization.
*/
void __init kmemleak_init(void)
{
int i;
unsigned long flags;
- jiffies_scan_yield = msecs_to_jiffies(MSECS_SCAN_YIELD);
jiffies_min_age = msecs_to_jiffies(MSECS_MIN_AGE);
jiffies_scan_wait = msecs_to_jiffies(SECS_SCAN_WAIT * 1000);
@@ -1443,6 +1475,9 @@ void __init kmemleak_init(void)
case KMEMLEAK_FREE:
kmemleak_free(log->ptr);
break;
+ case KMEMLEAK_FREE_PART:
+ kmemleak_free_part(log->ptr, log->size);
+ break;
case KMEMLEAK_NOT_LEAK:
kmemleak_not_leak(log->ptr);
break;
@@ -1485,11 +1520,10 @@ static int __init kmemleak_late_init(void)
dentry = debugfs_create_file("kmemleak", S_IRUGO, NULL, NULL,
&kmemleak_fops);
if (!dentry)
- pr_warning("kmemleak: Failed to create the debugfs kmemleak "
- "file\n");
- mutex_lock(&kmemleak_mutex);
+ pr_warning("Failed to create the debugfs kmemleak file\n");
+ mutex_lock(&scan_mutex);
start_scan_thread();
- mutex_unlock(&kmemleak_mutex);
+ mutex_unlock(&scan_mutex);
pr_info("Kernel memory leak detector initialized\n");
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 70db6e0a5ee..fd4529d86de 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -45,7 +45,7 @@ struct cgroup_subsys mem_cgroup_subsys __read_mostly;
#define MEM_CGROUP_RECLAIM_RETRIES 5
#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
-/* Turned on only when memory cgroup is enabled && really_do_swap_account = 0 */
+/* Turned on only when memory cgroup is enabled && really_do_swap_account = 1 */
int do_swap_account __read_mostly;
static int really_do_swap_account __initdata = 1; /* for remember boot option*/
#else
@@ -62,7 +62,8 @@ enum mem_cgroup_stat_index {
* For MEM_CONTAINER_TYPE_ALL, usage = pagecache + rss.
*/
MEM_CGROUP_STAT_CACHE, /* # of pages charged as cache */
- MEM_CGROUP_STAT_RSS, /* # of pages charged as rss */
+ MEM_CGROUP_STAT_RSS, /* # of pages charged as anon rss */
+ MEM_CGROUP_STAT_MAPPED_FILE, /* # of pages charged as file rss */
MEM_CGROUP_STAT_PGPGIN_COUNT, /* # of pages paged in */
MEM_CGROUP_STAT_PGPGOUT_COUNT, /* # of pages paged out */
@@ -176,6 +177,9 @@ struct mem_cgroup {
unsigned int swappiness;
+ /* set when res.limit == memsw.limit */
+ bool memsw_is_minimum;
+
/*
* statistics. This must be placed at the end of memcg.
*/
@@ -188,6 +192,7 @@ enum charge_type {
MEM_CGROUP_CHARGE_TYPE_SHMEM, /* used by page migration of shmem */
MEM_CGROUP_CHARGE_TYPE_FORCE, /* used by force_empty */
MEM_CGROUP_CHARGE_TYPE_SWAPOUT, /* for accounting swapcache */
+ MEM_CGROUP_CHARGE_TYPE_DROP, /* a page was unused swap cache */
NR_CHARGE_TYPE,
};
@@ -644,6 +649,7 @@ unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
int zid = zone_idx(z);
struct mem_cgroup_per_zone *mz;
int lru = LRU_FILE * !!file + !!active;
+ int ret;
BUG_ON(!mem_cont);
mz = mem_cgroup_zoneinfo(mem_cont, nid, zid);
@@ -661,9 +667,19 @@ unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
continue;
scan++;
- if (__isolate_lru_page(page, mode, file) == 0) {
+ ret = __isolate_lru_page(page, mode, file);
+ switch (ret) {
+ case 0:
list_move(&page->lru, dst);
+ mem_cgroup_del_lru(page);
nr_taken++;
+ break;
+ case -EBUSY:
+ /* we don't affect global LRU but rotate in our LRU */
+ mem_cgroup_rotate_lru_list(page, page_lru(page));
+ break;
+ default:
+ break;
}
}
@@ -845,6 +861,10 @@ static int mem_cgroup_hierarchical_reclaim(struct mem_cgroup *root_mem,
int ret, total = 0;
int loop = 0;
+ /* If memsw_is_minimum==1, swap-out is of-no-use. */
+ if (root_mem->memsw_is_minimum)
+ noswap = true;
+
while (loop < 2) {
victim = mem_cgroup_select_victim(root_mem);
if (victim == root_mem)
@@ -900,6 +920,44 @@ static void record_last_oom(struct mem_cgroup *mem)
mem_cgroup_walk_tree(mem, NULL, record_last_oom_cb);
}
+/*
+ * Currently used to update mapped file statistics, but the routine can be
+ * generalized to update other statistics as well.
+ */
+void mem_cgroup_update_mapped_file_stat(struct page *page, int val)
+{
+ struct mem_cgroup *mem;
+ struct mem_cgroup_stat *stat;
+ struct mem_cgroup_stat_cpu *cpustat;
+ int cpu;
+ struct page_cgroup *pc;
+
+ if (!page_is_file_cache(page))
+ return;
+
+ pc = lookup_page_cgroup(page);
+ if (unlikely(!pc))
+ return;
+
+ lock_page_cgroup(pc);
+ mem = pc->mem_cgroup;
+ if (!mem)
+ goto done;
+
+ if (!PageCgroupUsed(pc))
+ goto done;
+
+ /*
+ * Preemption is already disabled, we don't need get_cpu()
+ */
+ cpu = smp_processor_id();
+ stat = &mem->stat;
+ cpustat = &stat->cpustat[cpu];
+
+ __mem_cgroup_stat_add_safe(cpustat, MEM_CGROUP_STAT_MAPPED_FILE, val);
+done:
+ unlock_page_cgroup(pc);
+}
/*
* Unlike exported interface, "oom" parameter is added. if oom==true,
@@ -1098,6 +1156,10 @@ static int mem_cgroup_move_account(struct page_cgroup *pc,
struct mem_cgroup_per_zone *from_mz, *to_mz;
int nid, zid;
int ret = -EBUSY;
+ struct page *page;
+ int cpu;
+ struct mem_cgroup_stat *stat;
+ struct mem_cgroup_stat_cpu *cpustat;
VM_BUG_ON(from == to);
VM_BUG_ON(PageLRU(pc->page));
@@ -1118,6 +1180,23 @@ static int mem_cgroup_move_account(struct page_cgroup *pc,
res_counter_uncharge(&from->res, PAGE_SIZE);
mem_cgroup_charge_statistics(from, pc, false);
+
+ page = pc->page;
+ if (page_is_file_cache(page) && page_mapped(page)) {
+ cpu = smp_processor_id();
+ /* Update mapped_file data for mem_cgroup "from" */
+ stat = &from->stat;
+ cpustat = &stat->cpustat[cpu];
+ __mem_cgroup_stat_add_safe(cpustat, MEM_CGROUP_STAT_MAPPED_FILE,
+ -1);
+
+ /* Update mapped_file data for mem_cgroup "to" */
+ stat = &to->stat;
+ cpustat = &stat->cpustat[cpu];
+ __mem_cgroup_stat_add_safe(cpustat, MEM_CGROUP_STAT_MAPPED_FILE,
+ 1);
+ }
+
if (do_swap_account)
res_counter_uncharge(&from->memsw, PAGE_SIZE);
css_put(&from->css);
@@ -1128,6 +1207,12 @@ static int mem_cgroup_move_account(struct page_cgroup *pc,
ret = 0;
out:
unlock_page_cgroup(pc);
+ /*
+ * We charges against "to" which may not have any tasks. Then, "to"
+ * can be under rmdir(). But in current implementation, caller of
+ * this function is just force_empty() and it's garanteed that
+ * "to" is never removed. So, we don't check rmdir status here.
+ */
return ret;
}
@@ -1349,6 +1434,7 @@ __mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr,
return;
if (!ptr)
return;
+ cgroup_exclude_rmdir(&ptr->css);
pc = lookup_page_cgroup(page);
mem_cgroup_lru_del_before_commit_swapcache(page);
__mem_cgroup_commit_charge(ptr, pc, ctype);
@@ -1378,8 +1464,12 @@ __mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr,
}
rcu_read_unlock();
}
- /* add this page(page_cgroup) to the LRU we want. */
-
+ /*
+ * At swapin, we may charge account against cgroup which has no tasks.
+ * So, rmdir()->pre_destroy() can be called while we do this charge.
+ * In that case, we need to call pre_destroy() again. check it here.
+ */
+ cgroup_release_and_wakeup_rmdir(&ptr->css);
}
void mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr)
@@ -1433,6 +1523,7 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype)
switch (ctype) {
case MEM_CGROUP_CHARGE_TYPE_MAPPED:
+ case MEM_CGROUP_CHARGE_TYPE_DROP:
if (page_mapped(page))
goto unlock_out;
break;
@@ -1496,18 +1587,23 @@ void mem_cgroup_uncharge_cache_page(struct page *page)
* called after __delete_from_swap_cache() and drop "page" account.
* memcg information is recorded to swap_cgroup of "ent"
*/
-void mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent)
+void
+mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout)
{
struct mem_cgroup *memcg;
+ int ctype = MEM_CGROUP_CHARGE_TYPE_SWAPOUT;
+
+ if (!swapout) /* this was a swap cache but the swap is unused ! */
+ ctype = MEM_CGROUP_CHARGE_TYPE_DROP;
+
+ memcg = __mem_cgroup_uncharge_common(page, ctype);
- memcg = __mem_cgroup_uncharge_common(page,
- MEM_CGROUP_CHARGE_TYPE_SWAPOUT);
/* record memcg information */
- if (do_swap_account && memcg) {
+ if (do_swap_account && swapout && memcg) {
swap_cgroup_record(ent, css_id(&memcg->css));
mem_cgroup_get(memcg);
}
- if (memcg)
+ if (swapout && memcg)
css_put(&memcg->css);
}
#endif
@@ -1579,7 +1675,7 @@ void mem_cgroup_end_migration(struct mem_cgroup *mem,
if (!mem)
return;
-
+ cgroup_exclude_rmdir(&mem->css);
/* at migration success, oldpage->mapping is NULL. */
if (oldpage->mapping) {
target = oldpage;
@@ -1619,6 +1715,12 @@ void mem_cgroup_end_migration(struct mem_cgroup *mem,
*/
if (ctype == MEM_CGROUP_CHARGE_TYPE_MAPPED)
mem_cgroup_uncharge_page(target);
+ /*
+ * At migration, we may charge account against cgroup which has no tasks
+ * So, rmdir()->pre_destroy() can be called while we do this charge.
+ * In that case, we need to call pre_destroy() again. check it here.
+ */
+ cgroup_release_and_wakeup_rmdir(&mem->css);
}
/*
@@ -1685,6 +1787,12 @@ static int mem_cgroup_resize_limit(struct mem_cgroup *memcg,
break;
}
ret = res_counter_set_limit(&memcg->res, val);
+ if (!ret) {
+ if (memswlimit == val)
+ memcg->memsw_is_minimum = true;
+ else
+ memcg->memsw_is_minimum = false;
+ }
mutex_unlock(&set_limit_mutex);
if (!ret)
@@ -1703,16 +1811,14 @@ static int mem_cgroup_resize_limit(struct mem_cgroup *memcg,
return ret;
}
-int mem_cgroup_resize_memsw_limit(struct mem_cgroup *memcg,
- unsigned long long val)
+static int mem_cgroup_resize_memsw_limit(struct mem_cgroup *memcg,
+ unsigned long long val)
{
int retry_count;
u64 memlimit, oldusage, curusage;
int children = mem_cgroup_count_children(memcg);
int ret = -EBUSY;
- if (!do_swap_account)
- return -EINVAL;
/* see mem_cgroup_resize_res_limit */
retry_count = children * MEM_CGROUP_RECLAIM_RETRIES;
oldusage = res_counter_read_u64(&memcg->memsw, RES_USAGE);
@@ -1734,6 +1840,12 @@ int mem_cgroup_resize_memsw_limit(struct mem_cgroup *memcg,
break;
}
ret = res_counter_set_limit(&memcg->memsw, val);
+ if (!ret) {
+ if (memlimit == val)
+ memcg->memsw_is_minimum = true;
+ else
+ memcg->memsw_is_minimum = false;
+ }
mutex_unlock(&set_limit_mutex);
if (!ret)
@@ -1878,7 +1990,7 @@ try_to_free:
if (!progress) {
nr_retries--;
/* maybe some writeback is necessary */
- congestion_wait(WRITE, HZ/10);
+ congestion_wait(BLK_RW_ASYNC, HZ/10);
}
}
@@ -1947,8 +2059,7 @@ static u64 mem_cgroup_read(struct cgroup *cont, struct cftype *cft)
val = res_counter_read_u64(&mem->res, name);
break;
case _MEMSWAP:
- if (do_swap_account)
- val = res_counter_read_u64(&mem->memsw, name);
+ val = res_counter_read_u64(&mem->memsw, name);
break;
default:
BUG();
@@ -2046,6 +2157,7 @@ static int mem_cgroup_reset(struct cgroup *cont, unsigned int event)
enum {
MCS_CACHE,
MCS_RSS,
+ MCS_MAPPED_FILE,
MCS_PGPGIN,
MCS_PGPGOUT,
MCS_INACTIVE_ANON,
@@ -2066,6 +2178,7 @@ struct {
} memcg_stat_strings[NR_MCS_STAT] = {
{"cache", "total_cache"},
{"rss", "total_rss"},
+ {"mapped_file", "total_mapped_file"},
{"pgpgin", "total_pgpgin"},
{"pgpgout", "total_pgpgout"},
{"inactive_anon", "total_inactive_anon"},
@@ -2086,6 +2199,8 @@ static int mem_cgroup_get_local_stat(struct mem_cgroup *mem, void *data)
s->stat[MCS_CACHE] += val * PAGE_SIZE;
val = mem_cgroup_read_stat(&mem->stat, MEM_CGROUP_STAT_RSS);
s->stat[MCS_RSS] += val * PAGE_SIZE;
+ val = mem_cgroup_read_stat(&mem->stat, MEM_CGROUP_STAT_MAPPED_FILE);
+ s->stat[MCS_MAPPED_FILE] += val * PAGE_SIZE;
val = mem_cgroup_read_stat(&mem->stat, MEM_CGROUP_STAT_PGPGIN_COUNT);
s->stat[MCS_PGPGIN] += val;
val = mem_cgroup_read_stat(&mem->stat, MEM_CGROUP_STAT_PGPGOUT_COUNT);
diff --git a/mm/memory.c b/mm/memory.c
index d5d1653d60a..aede2ce3aba 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -135,11 +135,12 @@ void pmd_clear_bad(pmd_t *pmd)
* Note: this doesn't free the actual pages themselves. That
* has been handled earlier when unmapping all the memory regions.
*/
-static void free_pte_range(struct mmu_gather *tlb, pmd_t *pmd)
+static void free_pte_range(struct mmu_gather *tlb, pmd_t *pmd,
+ unsigned long addr)
{
pgtable_t token = pmd_pgtable(*pmd);
pmd_clear(pmd);
- pte_free_tlb(tlb, token);
+ pte_free_tlb(tlb, token, addr);
tlb->mm->nr_ptes--;
}
@@ -157,7 +158,7 @@ static inline void free_pmd_range(struct mmu_gather *tlb, pud_t *pud,
next = pmd_addr_end(addr, end);
if (pmd_none_or_clear_bad(pmd))
continue;
- free_pte_range(tlb, pmd);
+ free_pte_range(tlb, pmd, addr);
} while (pmd++, addr = next, addr != end);
start &= PUD_MASK;
@@ -173,7 +174,7 @@ static inline void free_pmd_range(struct mmu_gather *tlb, pud_t *pud,
pmd = pmd_offset(pud, start);
pud_clear(pud);
- pmd_free_tlb(tlb, pmd);
+ pmd_free_tlb(tlb, pmd, start);
}
static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd,
@@ -206,7 +207,7 @@ static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd,
pud = pud_offset(pgd, start);
pgd_clear(pgd);
- pud_free_tlb(tlb, pud);
+ pud_free_tlb(tlb, pud, start);
}
/*
@@ -1207,8 +1208,8 @@ static inline int use_zero_page(struct vm_area_struct *vma)
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)
+ unsigned long start, int nr_pages, int flags,
+ struct page **pages, struct vm_area_struct **vmas)
{
int i;
unsigned int vm_flags = 0;
@@ -1217,7 +1218,7 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
int ignore = !!(flags & GUP_FLAGS_IGNORE_VMA_PERMISSIONS);
int ignore_sigkill = !!(flags & GUP_FLAGS_IGNORE_SIGKILL);
- if (len <= 0)
+ if (nr_pages <= 0)
return 0;
/*
* Require read or write permissions.
@@ -1269,7 +1270,7 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
vmas[i] = gate_vma;
i++;
start += PAGE_SIZE;
- len--;
+ nr_pages--;
continue;
}
@@ -1280,7 +1281,7 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
if (is_vm_hugetlb_page(vma)) {
i = follow_hugetlb_page(mm, vma, pages, vmas,
- &start, &len, i, write);
+ &start, &nr_pages, i, write);
continue;
}
@@ -1310,8 +1311,11 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
cond_resched();
while (!(page = follow_page(vma, start, foll_flags))) {
int ret;
+
ret = handle_mm_fault(mm, vma, start,
- foll_flags & FOLL_WRITE);
+ (foll_flags & FOLL_WRITE) ?
+ FAULT_FLAG_WRITE : 0);
+
if (ret & VM_FAULT_ERROR) {
if (ret & VM_FAULT_OOM)
return i ? i : -ENOMEM;
@@ -1354,9 +1358,9 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
vmas[i] = vma;
i++;
start += PAGE_SIZE;
- len--;
- } while (len && start < vma->vm_end);
- } while (len);
+ nr_pages--;
+ } while (nr_pages && start < vma->vm_end);
+ } while (nr_pages);
return i;
}
@@ -1365,7 +1369,7 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
* @tsk: task_struct of target task
* @mm: mm_struct of target mm
* @start: starting user address
- * @len: number of pages from start to pin
+ * @nr_pages: 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
@@ -1377,7 +1381,7 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
* 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
+ * requested. If nr_pages 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.
@@ -1411,7 +1415,7 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
* 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,
+ unsigned long start, int nr_pages, int write, int force,
struct page **pages, struct vm_area_struct **vmas)
{
int flags = 0;
@@ -1421,9 +1425,7 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
if (force)
flags |= GUP_FLAGS_FORCE;
- return __get_user_pages(tsk, mm,
- start, len, flags,
- pages, vmas);
+ return __get_user_pages(tsk, mm, start, nr_pages, flags, pages, vmas);
}
EXPORT_SYMBOL(get_user_pages);
@@ -2496,7 +2498,7 @@ int vmtruncate_range(struct inode *inode, loff_t offset, loff_t end)
*/
static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long address, pte_t *page_table, pmd_t *pmd,
- int write_access, pte_t orig_pte)
+ unsigned int flags, pte_t orig_pte)
{
spinlock_t *ptl;
struct page *page;
@@ -2516,7 +2518,7 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
delayacct_set_flag(DELAYACCT_PF_SWAPIN);
page = lookup_swap_cache(entry);
if (!page) {
- grab_swap_token(); /* Contend for token _before_ read-in */
+ grab_swap_token(mm); /* Contend for token _before_ read-in */
page = swapin_readahead(entry,
GFP_HIGHUSER_MOVABLE, vma, address);
if (!page) {
@@ -2572,9 +2574,9 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
inc_mm_counter(mm, anon_rss);
pte = mk_pte(page, vma->vm_page_prot);
- if (write_access && reuse_swap_page(page)) {
+ if ((flags & FAULT_FLAG_WRITE) && reuse_swap_page(page)) {
pte = maybe_mkwrite(pte_mkdirty(pte), vma);
- write_access = 0;
+ flags &= ~FAULT_FLAG_WRITE;
}
flush_icache_page(vma, page);
set_pte_at(mm, address, page_table, pte);
@@ -2587,7 +2589,7 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
try_to_free_swap(page);
unlock_page(page);
- if (write_access) {
+ if (flags & FAULT_FLAG_WRITE) {
ret |= do_wp_page(mm, vma, address, page_table, pmd, ptl, pte);
if (ret & VM_FAULT_ERROR)
ret &= VM_FAULT_ERROR;
@@ -2616,7 +2618,7 @@ out_page:
*/
static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long address, pte_t *page_table, pmd_t *pmd,
- int write_access)
+ unsigned int flags)
{
struct page *page;
spinlock_t *ptl;
@@ -2776,7 +2778,7 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma,
* due to the bad i386 page protection. But it's valid
* for other architectures too.
*
- * Note that if write_access is true, we either now have
+ * Note that if FAULT_FLAG_WRITE is set, we either now have
* an exclusive copy of the page, or this is a shared mapping,
* so we can make it writable and dirty to avoid having to
* handle that later.
@@ -2847,11 +2849,10 @@ unwritable_page:
static int do_linear_fault(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long address, pte_t *page_table, pmd_t *pmd,
- int write_access, pte_t orig_pte)
+ unsigned int flags, pte_t orig_pte)
{
pgoff_t pgoff = (((address & PAGE_MASK)
- vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
- unsigned int flags = (write_access ? FAULT_FLAG_WRITE : 0);
pte_unmap(page_table);
return __do_fault(mm, vma, address, pmd, pgoff, flags, orig_pte);
@@ -2868,12 +2869,12 @@ static int do_linear_fault(struct mm_struct *mm, struct vm_area_struct *vma,
*/
static int do_nonlinear_fault(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long address, pte_t *page_table, pmd_t *pmd,
- int write_access, pte_t orig_pte)
+ unsigned int flags, pte_t orig_pte)
{
- unsigned int flags = FAULT_FLAG_NONLINEAR |
- (write_access ? FAULT_FLAG_WRITE : 0);
pgoff_t pgoff;
+ flags |= FAULT_FLAG_NONLINEAR;
+
if (!pte_unmap_same(mm, pmd, page_table, orig_pte))
return 0;
@@ -2904,7 +2905,7 @@ static int do_nonlinear_fault(struct mm_struct *mm, struct vm_area_struct *vma,
*/
static inline int handle_pte_fault(struct mm_struct *mm,
struct vm_area_struct *vma, unsigned long address,
- pte_t *pte, pmd_t *pmd, int write_access)
+ pte_t *pte, pmd_t *pmd, unsigned int flags)
{
pte_t entry;
spinlock_t *ptl;
@@ -2915,30 +2916,30 @@ static inline int handle_pte_fault(struct mm_struct *mm,
if (vma->vm_ops) {
if (likely(vma->vm_ops->fault))
return do_linear_fault(mm, vma, address,
- pte, pmd, write_access, entry);
+ pte, pmd, flags, entry);
}
return do_anonymous_page(mm, vma, address,
- pte, pmd, write_access);
+ pte, pmd, flags);
}
if (pte_file(entry))
return do_nonlinear_fault(mm, vma, address,
- pte, pmd, write_access, entry);
+ pte, pmd, flags, entry);
return do_swap_page(mm, vma, address,
- pte, pmd, write_access, entry);
+ pte, pmd, flags, entry);
}
ptl = pte_lockptr(mm, pmd);
spin_lock(ptl);
if (unlikely(!pte_same(*pte, entry)))
goto unlock;
- if (write_access) {
+ if (flags & FAULT_FLAG_WRITE) {
if (!pte_write(entry))
return do_wp_page(mm, vma, address,
pte, pmd, ptl, entry);
entry = pte_mkdirty(entry);
}
entry = pte_mkyoung(entry);
- if (ptep_set_access_flags(vma, address, pte, entry, write_access)) {
+ if (ptep_set_access_flags(vma, address, pte, entry, flags & FAULT_FLAG_WRITE)) {
update_mmu_cache(vma, address, entry);
} else {
/*
@@ -2947,7 +2948,7 @@ static inline int handle_pte_fault(struct mm_struct *mm,
* This still avoids useless tlb flushes for .text page faults
* with threads.
*/
- if (write_access)
+ if (flags & FAULT_FLAG_WRITE)
flush_tlb_page(vma, address);
}
unlock:
@@ -2959,7 +2960,7 @@ unlock:
* By the time we get here, we already hold the mm semaphore
*/
int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
- unsigned long address, int write_access)
+ unsigned long address, unsigned int flags)
{
pgd_t *pgd;
pud_t *pud;
@@ -2971,7 +2972,7 @@ int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
count_vm_event(PGFAULT);
if (unlikely(is_vm_hugetlb_page(vma)))
- return hugetlb_fault(mm, vma, address, write_access);
+ return hugetlb_fault(mm, vma, address, flags);
pgd = pgd_offset(mm, address);
pud = pud_alloc(mm, pgd, address);
@@ -2984,7 +2985,7 @@ int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
if (!pte)
return VM_FAULT_OOM;
- return handle_pte_fault(mm, vma, address, pte, pmd, write_access);
+ return handle_pte_fault(mm, vma, address, pte, pmd, flags);
}
#ifndef __PAGETABLE_PUD_FOLDED
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index e08e2c4da63..7dd9d9f8069 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -191,25 +191,27 @@ static int mpol_new_bind(struct mempolicy *pol, const nodemask_t *nodes)
* 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)
+static int mpol_set_nodemask(struct mempolicy *pol,
+ const nodemask_t *nodes, struct nodemask_scratch *nsc)
{
- nodemask_t cpuset_context_nmask;
int ret;
/* if mode is MPOL_DEFAULT, pol is NULL. This is right. */
if (pol == NULL)
return 0;
+ /* Check N_HIGH_MEMORY */
+ nodes_and(nsc->mask1,
+ cpuset_current_mems_allowed, node_states[N_HIGH_MEMORY]);
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);
+ mpol_relative_nodemask(&nsc->mask2, nodes,&nsc->mask1);
else
- nodes_and(cpuset_context_nmask, *nodes,
- cpuset_current_mems_allowed);
+ nodes_and(nsc->mask2, *nodes, nsc->mask1);
+
if (mpol_store_user_nodemask(pol))
pol->w.user_nodemask = *nodes;
else
@@ -217,8 +219,10 @@ static int mpol_set_nodemask(struct mempolicy *pol, const nodemask_t *nodes)
cpuset_current_mems_allowed;
}
- ret = mpol_ops[pol->mode].create(pol,
- nodes ? &cpuset_context_nmask : NULL);
+ if (nodes)
+ ret = mpol_ops[pol->mode].create(pol, &nsc->mask2);
+ else
+ ret = mpol_ops[pol->mode].create(pol, NULL);
return ret;
}
@@ -620,12 +624,17 @@ static long do_set_mempolicy(unsigned short mode, unsigned short flags,
{
struct mempolicy *new, *old;
struct mm_struct *mm = current->mm;
+ NODEMASK_SCRATCH(scratch);
int ret;
- new = mpol_new(mode, flags, nodes);
- if (IS_ERR(new))
- return PTR_ERR(new);
+ if (!scratch)
+ return -ENOMEM;
+ new = mpol_new(mode, flags, nodes);
+ if (IS_ERR(new)) {
+ ret = PTR_ERR(new);
+ goto out;
+ }
/*
* prevent changing our mempolicy while show_numa_maps()
* is using it.
@@ -635,13 +644,13 @@ static long do_set_mempolicy(unsigned short mode, unsigned short flags,
if (mm)
down_write(&mm->mmap_sem);
task_lock(current);
- ret = mpol_set_nodemask(new, nodes);
+ ret = mpol_set_nodemask(new, nodes, scratch);
if (ret) {
task_unlock(current);
if (mm)
up_write(&mm->mmap_sem);
mpol_put(new);
- return ret;
+ goto out;
}
old = current->mempolicy;
current->mempolicy = new;
@@ -654,7 +663,10 @@ static long do_set_mempolicy(unsigned short mode, unsigned short flags,
up_write(&mm->mmap_sem);
mpol_put(old);
- return 0;
+ ret = 0;
+out:
+ NODEMASK_SCRATCH_FREE(scratch);
+ return ret;
}
/*
@@ -1014,12 +1026,20 @@ static long do_mbind(unsigned long start, unsigned long len,
if (err)
return err;
}
- down_write(&mm->mmap_sem);
- task_lock(current);
- err = mpol_set_nodemask(new, nmask);
- task_unlock(current);
+ {
+ NODEMASK_SCRATCH(scratch);
+ if (scratch) {
+ down_write(&mm->mmap_sem);
+ task_lock(current);
+ err = mpol_set_nodemask(new, nmask, scratch);
+ task_unlock(current);
+ if (err)
+ up_write(&mm->mmap_sem);
+ } else
+ err = -ENOMEM;
+ NODEMASK_SCRATCH_FREE(scratch);
+ }
if (err) {
- up_write(&mm->mmap_sem);
mpol_put(new);
return err;
}
@@ -1891,6 +1911,7 @@ restart:
* Install non-NULL @mpol in inode's shared policy rb-tree.
* On entry, the current task has a reference on a non-NULL @mpol.
* This must be released on exit.
+ * This is called at get_inode() calls and we can use GFP_KERNEL.
*/
void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol)
{
@@ -1902,19 +1923,24 @@ void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol)
if (mpol) {
struct vm_area_struct pvma;
struct mempolicy *new;
+ NODEMASK_SCRATCH(scratch);
+ if (!scratch)
+ return;
/* contextualize the tmpfs mount point mempolicy */
new = mpol_new(mpol->mode, mpol->flags, &mpol->w.user_nodemask);
if (IS_ERR(new)) {
mpol_put(mpol); /* drop our ref on sb mpol */
+ NODEMASK_SCRATCH_FREE(scratch);
return; /* no valid nodemask intersection */
}
task_lock(current);
- ret = mpol_set_nodemask(new, &mpol->w.user_nodemask);
+ ret = mpol_set_nodemask(new, &mpol->w.user_nodemask, scratch);
task_unlock(current);
mpol_put(mpol); /* drop our ref on sb mpol */
if (ret) {
+ NODEMASK_SCRATCH_FREE(scratch);
mpol_put(new);
return;
}
@@ -1924,6 +1950,7 @@ void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol)
pvma.vm_end = TASK_SIZE; /* policy covers entire file */
mpol_set_shared_policy(sp, &pvma, new); /* adds ref */
mpol_put(new); /* drop initial ref */
+ NODEMASK_SCRATCH_FREE(scratch);
}
}
@@ -2140,13 +2167,18 @@ int mpol_parse_str(char *str, struct mempolicy **mpol, int no_context)
err = 1;
else {
int ret;
-
- task_lock(current);
- ret = mpol_set_nodemask(new, &nodes);
- task_unlock(current);
- if (ret)
+ NODEMASK_SCRATCH(scratch);
+ if (scratch) {
+ task_lock(current);
+ ret = mpol_set_nodemask(new, &nodes, scratch);
+ task_unlock(current);
+ } else
+ ret = -ENOMEM;
+ NODEMASK_SCRATCH_FREE(scratch);
+ if (ret) {
err = 1;
- else if (no_context) {
+ mpol_put(new);
+ } else if (no_context) {
/* save for contextualization */
new->w.user_nodemask = nodes;
}
diff --git a/mm/mempool.c b/mm/mempool.c
index a46eb1b4bb6..32e75d40050 100644
--- a/mm/mempool.c
+++ b/mm/mempool.c
@@ -303,14 +303,14 @@ EXPORT_SYMBOL(mempool_free_slab);
*/
void *mempool_kmalloc(gfp_t gfp_mask, void *pool_data)
{
- size_t size = (size_t)(long)pool_data;
+ size_t size = (size_t)pool_data;
return kmalloc(size, gfp_mask);
}
EXPORT_SYMBOL(mempool_kmalloc);
void *mempool_kzalloc(gfp_t gfp_mask, void *pool_data)
{
- size_t size = (size_t) pool_data;
+ size_t size = (size_t)pool_data;
return kzalloc(size, gfp_mask);
}
EXPORT_SYMBOL(mempool_kzalloc);
diff --git a/mm/mmap.c b/mm/mmap.c
index 34579b23ebd..8101de490c7 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -88,9 +88,6 @@ int sysctl_overcommit_ratio = 50; /* default is 50% */
int sysctl_max_map_count __read_mostly = DEFAULT_MAX_MAP_COUNT;
struct percpu_counter vm_committed_as;
-/* amount of vm to protect from userspace access */
-unsigned long mmap_min_addr = CONFIG_DEFAULT_MMAP_MIN_ADDR;
-
/*
* Check that a process has enough memory to allocate a new virtual
* mapping. 0 means there is enough memory for the allocation to
diff --git a/mm/nommu.c b/mm/nommu.c
index 2fd2ad5da98..66e81e7e9fe 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -69,9 +69,6 @@ int sysctl_max_map_count = DEFAULT_MAX_MAP_COUNT;
int sysctl_nr_trim_pages = CONFIG_NOMMU_INITIAL_TRIM_EXCESS;
int heap_stack_gap = 0;
-/* amount of vm to protect from userspace access */
-unsigned long mmap_min_addr = CONFIG_DEFAULT_MMAP_MIN_ADDR;
-
atomic_long_t mmap_pages_allocated;
EXPORT_SYMBOL(mem_map);
@@ -173,8 +170,8 @@ unsigned int kobjsize(const void *objp)
}
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)
+ unsigned long start, int nr_pages, int flags,
+ struct page **pages, struct vm_area_struct **vmas)
{
struct vm_area_struct *vma;
unsigned long vm_flags;
@@ -189,7 +186,7 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
vm_flags = write ? (VM_WRITE | VM_MAYWRITE) : (VM_READ | VM_MAYREAD);
vm_flags &= force ? (VM_MAYREAD | VM_MAYWRITE) : (VM_READ | VM_WRITE);
- for (i = 0; i < len; i++) {
+ for (i = 0; i < nr_pages; i++) {
vma = find_vma(mm, start);
if (!vma)
goto finish_or_fault;
@@ -224,7 +221,7 @@ finish_or_fault:
* - don't permit access to VMAs that don't support it, such as I/O mappings
*/
int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
- unsigned long start, int len, int write, int force,
+ unsigned long start, int nr_pages, int write, int force,
struct page **pages, struct vm_area_struct **vmas)
{
int flags = 0;
@@ -234,12 +231,31 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
if (force)
flags |= GUP_FLAGS_FORCE;
- return __get_user_pages(tsk, mm,
- start, len, flags,
- pages, vmas);
+ return __get_user_pages(tsk, mm, start, nr_pages, flags, pages, vmas);
}
EXPORT_SYMBOL(get_user_pages);
+/**
+ * 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)
+{
+ if (!(vma->vm_flags & (VM_IO | VM_PFNMAP)))
+ return -EINVAL;
+
+ *pfn = address >> PAGE_SHIFT;
+ return 0;
+}
+EXPORT_SYMBOL(follow_pfn);
+
DEFINE_RWLOCK(vmlist_lock);
struct vm_struct *vmlist;
@@ -903,6 +919,10 @@ static int validate_mmap_request(struct file *file,
if (!file->f_op->read)
capabilities &= ~BDI_CAP_MAP_COPY;
+ /* The file shall have been opened with read permission. */
+ if (!(file->f_mode & FMODE_READ))
+ return -EACCES;
+
if (flags & MAP_SHARED) {
/* do checks for writing, appending and locking */
if ((prot & PROT_WRITE) &&
@@ -1332,6 +1352,7 @@ unsigned long do_mmap_pgoff(struct file *file,
}
vma->vm_region = region;
+ add_nommu_region(region);
/* set up the mapping */
if (file && vma->vm_flags & VM_SHARED)
@@ -1341,8 +1362,6 @@ unsigned long do_mmap_pgoff(struct file *file,
if (ret < 0)
goto error_put_region;
- add_nommu_region(region);
-
/* okay... we have a mapping; now we have to register it */
result = vma->vm_start;
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 175a67a78a9..a7b2460e922 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -58,7 +58,6 @@ 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;
@@ -66,11 +65,6 @@ 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.
@@ -154,15 +148,15 @@ unsigned long badness(struct task_struct *p, unsigned long uptime)
points /= 8;
/*
- * Adjust the score by oom_adj.
+ * Adjust the score by oomkilladj.
*/
- if (oom_adj) {
- if (oom_adj > 0) {
+ if (p->oomkilladj) {
+ if (p->oomkilladj > 0) {
if (!points)
points = 1;
- points <<= oom_adj;
+ points <<= p->oomkilladj;
} else
- points >>= -(oom_adj);
+ points >>= -(p->oomkilladj);
}
#ifdef DEBUG
@@ -257,8 +251,11 @@ 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) {
+ if (points > *ppoints || !chosen) {
chosen = p;
*ppoints = points;
}
@@ -307,7 +304,8 @@ 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), mm->oom_adj, p->comm);
+ get_mm_rss(mm), (int)task_cpu(p), p->oomkilladj,
+ p->comm);
task_unlock(p);
} while_each_thread(g, p);
}
@@ -325,8 +323,11 @@ static void __oom_kill_task(struct task_struct *p, int verbose)
return;
}
- if (!p->mm)
+ if (!p->mm) {
+ WARN_ON(1);
+ printk(KERN_WARNING "tried to kill an mm-less task!\n");
return;
+ }
if (verbose)
printk(KERN_ERR "Killed process %d (%s)\n",
@@ -348,13 +349,28 @@ static int oom_kill_task(struct task_struct *p)
struct mm_struct *mm;
struct task_struct *g, *q;
- task_lock(p);
mm = p->mm;
- if (!mm || mm->oom_adj == OOM_DISABLE) {
- task_unlock(p);
+
+ /* 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)
return 1;
- }
- task_unlock(p);
+
+ /*
+ * 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);
+
__oom_kill_task(p, 1);
/*
@@ -377,11 +393,10 @@ static int oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
struct task_struct *c;
if (printk_ratelimit()) {
- 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);
+ "gfp_mask=0x%x, order=%d, oomkilladj=%d\n",
+ current->comm, gfp_mask, order, current->oomkilladj);
+ task_lock(current);
cpuset_print_task_mems_allowed(current);
task_unlock(current);
dump_stack();
@@ -394,9 +409,8 @@ 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->mm && (p->flags & PF_EXITING)) {
+ if (p->flags & PF_EXITING) {
__oom_kill_task(p, 0);
return 0;
}
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 7b0dcea4935..81627ebcd31 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -541,8 +541,11 @@ static void balance_dirty_pages(struct address_space *mapping)
* filesystems (i.e. NFS) in which data may have been
* written to the server's write cache, but has not yet
* been flushed to permanent storage.
+ * Only move pages to writeback if this bdi is over its
+ * threshold otherwise wait until the disk writes catch
+ * up.
*/
- if (bdi_nr_reclaimable) {
+ if (bdi_nr_reclaimable > bdi_thresh) {
writeback_inodes(&wbc);
pages_written += write_chunk - wbc.nr_to_write;
get_dirty_limits(&background_thresh, &dirty_thresh,
@@ -572,7 +575,7 @@ static void balance_dirty_pages(struct address_space *mapping)
if (pages_written >= write_chunk)
break; /* We've done our duty */
- congestion_wait(WRITE, HZ/10);
+ congestion_wait(BLK_RW_ASYNC, HZ/10);
}
if (bdi_nr_reclaimable + bdi_nr_writeback < bdi_thresh &&
@@ -666,7 +669,7 @@ void throttle_vm_writeout(gfp_t gfp_mask)
if (global_page_state(NR_UNSTABLE_NFS) +
global_page_state(NR_WRITEBACK) <= dirty_thresh)
break;
- congestion_wait(WRITE, HZ/10);
+ congestion_wait(BLK_RW_ASYNC, HZ/10);
/*
* The caller might hold locks which can prevent IO completion
@@ -712,7 +715,7 @@ static void background_writeout(unsigned long _min_pages)
if (wbc.nr_to_write > 0 || wbc.pages_skipped > 0) {
/* Wrote less than expected */
if (wbc.encountered_congestion || wbc.more_io)
- congestion_wait(WRITE, HZ/10);
+ congestion_wait(BLK_RW_ASYNC, HZ/10);
else
break;
}
@@ -784,7 +787,7 @@ static void wb_kupdate(unsigned long arg)
writeback_inodes(&wbc);
if (wbc.nr_to_write > 0) {
if (wbc.encountered_congestion || wbc.more_io)
- congestion_wait(WRITE, HZ/10);
+ congestion_wait(BLK_RW_ASYNC, HZ/10);
else
break; /* All the old data is written */
}
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index a5f3c278c57..a0de15f4698 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -73,6 +73,7 @@ unsigned long totalram_pages __read_mostly;
unsigned long totalreserve_pages __read_mostly;
unsigned long highest_memmap_pfn __read_mostly;
int percpu_pagelist_fraction;
+gfp_t gfp_allowed_mask __read_mostly = GFP_BOOT_MASK;
#ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE
int pageblock_order __read_mostly;
@@ -487,7 +488,6 @@ static inline void __free_one_page(struct page *page,
*/
static inline void free_page_mlock(struct page *page)
{
- __ClearPageMlocked(page);
__dec_zone_page_state(page, NR_MLOCK);
__count_vm_event(UNEVICTABLE_MLOCKFREED);
}
@@ -557,7 +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);
+ int wasMlocked = TestClearPageMlocked(page);
kmemcheck_free_shadow(page, order);
@@ -575,7 +575,7 @@ 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))
+ if (unlikely(wasMlocked))
free_page_mlock(page);
__count_vm_events(PGFREE, 1 << order);
free_one_page(page_zone(page), page, order,
@@ -817,13 +817,15 @@ __rmqueue_fallback(struct zone *zone, int order, int start_migratetype)
* agressive about taking ownership of free pages
*/
if (unlikely(current_order >= (pageblock_order >> 1)) ||
- start_migratetype == MIGRATE_RECLAIMABLE) {
+ start_migratetype == MIGRATE_RECLAIMABLE ||
+ page_group_by_mobility_disabled) {
unsigned long pages;
pages = move_freepages_block(zone, page,
start_migratetype);
/* Claim the whole block if over half of it is free */
- if (pages >= (1 << (pageblock_order-1)))
+ if (pages >= (1 << (pageblock_order-1)) ||
+ page_group_by_mobility_disabled)
set_pageblock_migratetype(page,
start_migratetype);
@@ -882,7 +884,7 @@ retry_reserve:
*/
static int rmqueue_bulk(struct zone *zone, unsigned int order,
unsigned long count, struct list_head *list,
- int migratetype)
+ int migratetype, int cold)
{
int i;
@@ -901,7 +903,10 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order,
* merge IO requests if the physical pages are ordered
* properly.
*/
- list_add(&page->lru, list);
+ if (likely(cold == 0))
+ list_add(&page->lru, list);
+ else
+ list_add_tail(&page->lru, list);
set_page_private(page, migratetype);
list = &page->lru;
}
@@ -1021,7 +1026,7 @@ 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);
+ int wasMlocked = TestClearPageMlocked(page);
kmemcheck_free_shadow(page, 0);
@@ -1040,7 +1045,7 @@ static void free_hot_cold_page(struct page *page, int cold)
pcp = &zone_pcp(zone, get_cpu())->pcp;
set_page_private(page, get_pageblock_migratetype(page));
local_irq_save(flags);
- if (unlikely(clearMlocked))
+ if (unlikely(wasMlocked))
free_page_mlock(page);
__count_vm_event(PGFREE);
@@ -1119,7 +1124,8 @@ again:
local_irq_save(flags);
if (!pcp->count) {
pcp->count = rmqueue_bulk(zone, 0,
- pcp->batch, &pcp->list, migratetype);
+ pcp->batch, &pcp->list,
+ migratetype, cold);
if (unlikely(!pcp->count))
goto failed;
}
@@ -1138,7 +1144,8 @@ again:
/* Allocate more to the pcp list if necessary */
if (unlikely(&page->lru == &pcp->list)) {
pcp->count += rmqueue_bulk(zone, 0,
- pcp->batch, &pcp->list, migratetype);
+ pcp->batch, &pcp->list,
+ migratetype, cold);
page = list_entry(pcp->list.next, struct page, lru);
}
@@ -1153,10 +1160,10 @@ again:
* properly detect and handle allocation failures.
*
* We most definitely don't want callers attempting to
- * allocate greater than single-page units with
+ * allocate greater than order-1 page units with
* __GFP_NOFAIL.
*/
- WARN_ON_ONCE(order > 0);
+ WARN_ON_ONCE(order > 1);
}
spin_lock_irqsave(&zone->lock, flags);
page = __rmqueue(zone, order, migratetype);
@@ -1666,7 +1673,7 @@ __alloc_pages_high_priority(gfp_t gfp_mask, unsigned int order,
preferred_zone, migratetype);
if (!page && gfp_mask & __GFP_NOFAIL)
- congestion_wait(WRITE, HZ/50);
+ congestion_wait(BLK_RW_ASYNC, HZ/50);
} while (!page && (gfp_mask & __GFP_NOFAIL));
return page;
@@ -1740,8 +1747,10 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
* be using allocators in order of preference for an area that is
* too large.
*/
- if (WARN_ON_ONCE(order >= MAX_ORDER))
+ if (order >= MAX_ORDER) {
+ WARN_ON_ONCE(!(gfp_mask & __GFP_NOWARN));
return NULL;
+ }
/*
* GFP_THISNODE (meaning __GFP_THISNODE, __GFP_NORETRY and
@@ -1789,6 +1798,10 @@ rebalance:
if (p->flags & PF_MEMALLOC)
goto nopage;
+ /* Avoid allocations with no watermarks from looping endlessly */
+ if (test_thread_flag(TIF_MEMDIE) && !(gfp_mask & __GFP_NOFAIL))
+ goto nopage;
+
/* Try direct reclaim and then allocating */
page = __alloc_pages_direct_reclaim(gfp_mask, order,
zonelist, high_zoneidx,
@@ -1831,7 +1844,7 @@ rebalance:
pages_reclaimed += did_some_progress;
if (should_alloc_retry(gfp_mask, order, pages_reclaimed)) {
/* Wait for some write requests to complete then retry */
- congestion_wait(WRITE, HZ/50);
+ congestion_wait(BLK_RW_ASYNC, HZ/50);
goto rebalance;
}
@@ -1863,6 +1876,8 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
struct page *page;
int migratetype = allocflags_to_migratetype(gfp_mask);
+ gfp_mask &= gfp_allowed_mask;
+
lockdep_trace_alloc(gfp_mask);
might_sleep_if(gfp_mask & __GFP_WAIT);
@@ -1981,7 +1996,7 @@ void *alloc_pages_exact(size_t size, gfp_t gfp_mask)
unsigned long alloc_end = addr + (PAGE_SIZE << order);
unsigned long used = addr + PAGE_ALIGN(size);
- split_page(virt_to_page(addr), order);
+ split_page(virt_to_page((void *)addr), order);
while (used < alloc_end) {
free_page(used);
used += PAGE_SIZE;
@@ -2531,7 +2546,6 @@ static void build_zonelists(pg_data_t *pgdat)
prev_node = local_node;
nodes_clear(used_mask);
- memset(node_load, 0, sizeof(node_load));
memset(node_order, 0, sizeof(node_order));
j = 0;
@@ -2640,6 +2654,9 @@ static int __build_all_zonelists(void *dummy)
{
int nid;
+#ifdef CONFIG_NUMA
+ memset(node_load, 0, sizeof(node_load));
+#endif
for_each_online_node(nid) {
pg_data_t *pgdat = NODE_DATA(nid);
@@ -3024,7 +3041,7 @@ bad:
if (dzone == zone)
break;
kfree(zone_pcp(dzone, cpu));
- zone_pcp(dzone, cpu) = NULL;
+ zone_pcp(dzone, cpu) = &boot_pageset[cpu];
}
return -ENOMEM;
}
@@ -3039,7 +3056,7 @@ static inline void free_zone_pagesets(int cpu)
/* Free per_cpu_pageset if it is slab allocated */
if (pset != &boot_pageset[cpu])
kfree(pset);
- zone_pcp(zone, cpu) = NULL;
+ zone_pcp(zone, cpu) = &boot_pageset[cpu];
}
}
@@ -4030,6 +4047,8 @@ static void __init find_zone_movable_pfns_for_nodes(unsigned long *movable_pfn)
int i, nid;
unsigned long usable_startpfn;
unsigned long kernelcore_node, kernelcore_remaining;
+ /* save the state before borrow the nodemask */
+ nodemask_t saved_node_state = node_states[N_HIGH_MEMORY];
unsigned long totalpages = early_calculate_totalpages();
int usable_nodes = nodes_weight(node_states[N_HIGH_MEMORY]);
@@ -4057,7 +4076,7 @@ static void __init find_zone_movable_pfns_for_nodes(unsigned long *movable_pfn)
/* If kernelcore was not specified, there is no ZONE_MOVABLE */
if (!required_kernelcore)
- return;
+ goto out;
/* usable_startpfn is the lowest possible pfn ZONE_MOVABLE can be at */
find_usable_zone_for_movable();
@@ -4156,6 +4175,10 @@ restart:
for (nid = 0; nid < MAX_NUMNODES; nid++)
zone_movable_pfn[nid] =
roundup(zone_movable_pfn[nid], MAX_ORDER_NR_PAGES);
+
+out:
+ /* restore the node_state */
+ node_states[N_HIGH_MEMORY] = saved_node_state;
}
/* Any regular memory on that node ? */
@@ -4240,11 +4263,6 @@ 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();
@@ -4657,7 +4675,7 @@ int percpu_pagelist_fraction_sysctl_handler(ctl_table *table, int write,
ret = proc_dointvec_minmax(table, write, file, buffer, length, ppos);
if (!write || (ret == -EINVAL))
return ret;
- for_each_zone(zone) {
+ for_each_populated_zone(zone) {
for_each_online_cpu(cpu) {
unsigned long high;
high = zone->present_pages / percpu_pagelist_fraction;
@@ -4742,8 +4760,10 @@ void *__init alloc_large_system_hash(const char *tablename,
* some pages at the end of hash table which
* alloc_pages_exact() automatically does
*/
- if (get_order(size) < MAX_ORDER)
+ if (get_order(size) < MAX_ORDER) {
table = alloc_pages_exact(size, GFP_ATOMIC);
+ kmemleak_alloc(table, size, 1, GFP_ATOMIC);
+ }
}
} while (!table && size > PAGE_SIZE && --log2qty);
@@ -4761,16 +4781,6 @@ void *__init alloc_large_system_hash(const char *tablename,
if (_hash_mask)
*_hash_mask = (1 << log2qty) - 1;
- /*
- * If hashdist is set, the table allocation is done with __vmalloc()
- * which invokes the kmemleak_alloc() callback. This function may also
- * be called before the slab and kmemleak are initialised when
- * kmemleak simply buffers the request to be executed later
- * (GFP_ATOMIC flag ignored in this case).
- */
- if (!hashdist)
- kmemleak_alloc(table, size, 1, GFP_ATOMIC);
-
return table;
}
diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c
index 11a8a10a390..f22b4ebbd8d 100644
--- a/mm/page_cgroup.c
+++ b/mm/page_cgroup.c
@@ -83,12 +83,12 @@ void __init page_cgroup_init_flatmem(void)
goto fail;
}
printk(KERN_INFO "allocated %ld bytes of page_cgroup\n", total_usage);
- printk(KERN_INFO "please try cgroup_disable=memory option if you"
- " don't want\n");
+ printk(KERN_INFO "please try 'cgroup_disable=memory' option if you"
+ " don't want memory cgroups\n");
return;
fail:
- printk(KERN_CRIT "allocation of page_cgroup was failed.\n");
- printk(KERN_CRIT "please try cgroup_disable=memory boot option\n");
+ printk(KERN_CRIT "allocation of page_cgroup failed.\n");
+ printk(KERN_CRIT "please try 'cgroup_disable=memory' boot option\n");
panic("Out of memory");
}
@@ -99,6 +99,8 @@ struct page_cgroup *lookup_page_cgroup(struct page *page)
unsigned long pfn = page_to_pfn(page);
struct mem_section *section = __pfn_to_section(pfn);
+ if (!section->page_cgroup)
+ return NULL;
return section->page_cgroup + pfn;
}
@@ -252,14 +254,14 @@ void __init page_cgroup_init(void)
fail = init_section_page_cgroup(pfn);
}
if (fail) {
- printk(KERN_CRIT "try cgroup_disable=memory boot option\n");
+ printk(KERN_CRIT "try 'cgroup_disable=memory' boot option\n");
panic("Out of memory");
} else {
hotplug_memory_notifier(page_cgroup_callback, 0);
}
printk(KERN_INFO "allocated %ld bytes of page_cgroup\n", total_usage);
- printk(KERN_INFO "please try cgroup_disable=memory option if you don't"
- " want\n");
+ printk(KERN_INFO "please try 'cgroup_disable=memory' option if you don't"
+ " want memory cgroups\n");
}
void __meminit pgdat_page_cgroup_init(struct pglist_data *pgdat)
@@ -309,8 +311,6 @@ static int swap_cgroup_prepare(int type)
struct swap_cgroup_ctrl *ctrl;
unsigned long idx, max;
- if (!do_swap_account)
- return 0;
ctrl = &swap_cgroup_ctrl[type];
for (idx = 0; idx < ctrl->length; idx++) {
@@ -347,9 +347,6 @@ unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id)
struct swap_cgroup *sc;
unsigned short old;
- if (!do_swap_account)
- return 0;
-
ctrl = &swap_cgroup_ctrl[type];
mappage = ctrl->map[idx];
@@ -378,9 +375,6 @@ unsigned short lookup_swap_cgroup(swp_entry_t ent)
struct swap_cgroup *sc;
unsigned short ret;
- if (!do_swap_account)
- return 0;
-
ctrl = &swap_cgroup_ctrl[type];
mappage = ctrl->map[idx];
sc = page_address(mappage);
diff --git a/mm/percpu.c b/mm/percpu.c
index c0b2c1a76e8..3311c8919f3 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -8,12 +8,12 @@
*
* This is percpu allocator which can handle both static and dynamic
* areas. Percpu areas are allocated in chunks in vmalloc area. Each
- * chunk is consisted of num_possible_cpus() units and the first chunk
- * is used for static percpu variables in the kernel image (special
- * boot time alloc/init handling necessary as these areas need to be
- * brought up before allocation services are running). Unit grows as
- * necessary and all units grow or shrink in unison. When a chunk is
- * filled up, another chunk is allocated. ie. in vmalloc area
+ * chunk is consisted of nr_cpu_ids units and the first chunk is used
+ * for static percpu variables in the kernel image (special boot time
+ * alloc/init handling necessary as these areas need to be brought up
+ * before allocation services are running). Unit grows as necessary
+ * and all units grow or shrink in unison. When a chunk is filled up,
+ * another chunk is allocated. ie. in vmalloc area
*
* c0 c1 c2
* ------------------- ------------------- ------------
@@ -197,7 +197,12 @@ static unsigned long pcpu_chunk_addr(struct pcpu_chunk *chunk,
static bool pcpu_chunk_page_occupied(struct pcpu_chunk *chunk,
int page_idx)
{
- return *pcpu_chunk_pagep(chunk, 0, page_idx) != NULL;
+ /*
+ * Any possible cpu id can be used here, so there's no need to
+ * worry about preemption or cpu hotplug.
+ */
+ return *pcpu_chunk_pagep(chunk, raw_smp_processor_id(),
+ page_idx) != NULL;
}
/* set the pointer to a chunk in a page struct */
@@ -297,6 +302,14 @@ static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr)
return pcpu_first_chunk;
}
+ /*
+ * The address is relative to unit0 which might be unused and
+ * thus unmapped. Offset the address to the unit space of the
+ * current processor before looking it up in the vmalloc
+ * space. Note that any possible cpu id can be used here, so
+ * there's no need to worry about preemption or cpu hotplug.
+ */
+ addr += raw_smp_processor_id() * pcpu_unit_size;
return pcpu_get_page_chunk(vmalloc_to_page(addr));
}
@@ -549,16 +562,16 @@ static void pcpu_free_area(struct pcpu_chunk *chunk, int freeme)
* @chunk: chunk of interest
* @page_start: page index of the first page to unmap
* @page_end: page index of the last page to unmap + 1
- * @flush: whether to flush cache and tlb or not
+ * @flush_tlb: whether to flush tlb or not
*
* For each cpu, unmap pages [@page_start,@page_end) out of @chunk.
* If @flush is true, vcache is flushed before unmapping and tlb
* after.
*/
static void pcpu_unmap(struct pcpu_chunk *chunk, int page_start, int page_end,
- bool flush)
+ bool flush_tlb)
{
- unsigned int last = num_possible_cpus() - 1;
+ unsigned int last = nr_cpu_ids - 1;
unsigned int cpu;
/* unmap must not be done on immutable chunk */
@@ -569,9 +582,8 @@ static void pcpu_unmap(struct pcpu_chunk *chunk, int page_start, int page_end,
* the whole region at once rather than doing it for each cpu.
* This could be an overkill but is more scalable.
*/
- if (flush)
- flush_cache_vunmap(pcpu_chunk_addr(chunk, 0, page_start),
- pcpu_chunk_addr(chunk, last, page_end));
+ flush_cache_vunmap(pcpu_chunk_addr(chunk, 0, page_start),
+ pcpu_chunk_addr(chunk, last, page_end));
for_each_possible_cpu(cpu)
unmap_kernel_range_noflush(
@@ -579,7 +591,7 @@ static void pcpu_unmap(struct pcpu_chunk *chunk, int page_start, int page_end,
(page_end - page_start) << PAGE_SHIFT);
/* ditto as flush_cache_vunmap() */
- if (flush)
+ if (flush_tlb)
flush_tlb_kernel_range(pcpu_chunk_addr(chunk, 0, page_start),
pcpu_chunk_addr(chunk, last, page_end));
}
@@ -644,7 +656,7 @@ static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, int off, int size,
*/
static int pcpu_map(struct pcpu_chunk *chunk, int page_start, int page_end)
{
- unsigned int last = num_possible_cpus() - 1;
+ unsigned int last = nr_cpu_ids - 1;
unsigned int cpu;
int err;
@@ -750,7 +762,7 @@ static struct pcpu_chunk *alloc_pcpu_chunk(void)
chunk->map[chunk->map_used++] = pcpu_unit_size;
chunk->page = chunk->page_ar;
- chunk->vm = get_vm_area(pcpu_chunk_size, GFP_KERNEL);
+ chunk->vm = get_vm_area(pcpu_chunk_size, VM_ALLOC);
if (!chunk->vm) {
free_pcpu_chunk(chunk);
return NULL;
@@ -1068,9 +1080,9 @@ size_t __init pcpu_setup_first_chunk(pcpu_get_page_fn_t get_page_fn,
PFN_UP(size_sum));
pcpu_unit_size = pcpu_unit_pages << PAGE_SHIFT;
- pcpu_chunk_size = num_possible_cpus() * pcpu_unit_size;
+ pcpu_chunk_size = nr_cpu_ids * pcpu_unit_size;
pcpu_chunk_struct_size = sizeof(struct pcpu_chunk)
- + num_possible_cpus() * pcpu_unit_pages * sizeof(struct page *);
+ + nr_cpu_ids * pcpu_unit_pages * sizeof(struct page *);
if (dyn_size < 0)
dyn_size = pcpu_unit_size - static_size - reserved_size;
@@ -1234,6 +1246,7 @@ static struct page * __init pcpue_get_page(unsigned int cpu, int pageno)
ssize_t __init pcpu_embed_first_chunk(size_t static_size, size_t reserved_size,
ssize_t dyn_size, ssize_t unit_size)
{
+ size_t chunk_size;
unsigned int cpu;
/* determine parameters and allocate */
@@ -1248,19 +1261,26 @@ ssize_t __init pcpu_embed_first_chunk(size_t static_size, size_t reserved_size,
} else
pcpue_unit_size = max_t(size_t, pcpue_size, PCPU_MIN_UNIT_SIZE);
- pcpue_ptr = __alloc_bootmem_nopanic(
- num_possible_cpus() * pcpue_unit_size,
- PAGE_SIZE, __pa(MAX_DMA_ADDRESS));
- if (!pcpue_ptr)
+ chunk_size = pcpue_unit_size * nr_cpu_ids;
+
+ pcpue_ptr = __alloc_bootmem_nopanic(chunk_size, PAGE_SIZE,
+ __pa(MAX_DMA_ADDRESS));
+ if (!pcpue_ptr) {
+ pr_warning("PERCPU: failed to allocate %zu bytes for "
+ "embedding\n", chunk_size);
return -ENOMEM;
+ }
/* return the leftover and copy */
- for_each_possible_cpu(cpu) {
+ for (cpu = 0; cpu < nr_cpu_ids; cpu++) {
void *ptr = pcpue_ptr + cpu * pcpue_unit_size;
- free_bootmem(__pa(ptr + pcpue_size),
- pcpue_unit_size - pcpue_size);
- memcpy(ptr, __per_cpu_load, static_size);
+ if (cpu_possible(cpu)) {
+ free_bootmem(__pa(ptr + pcpue_size),
+ pcpue_unit_size - pcpue_size);
+ memcpy(ptr, __per_cpu_load, static_size);
+ } else
+ free_bootmem(__pa(ptr), pcpue_unit_size);
}
/* we're ready, commit */
diff --git a/mm/rmap.c b/mm/rmap.c
index c9ccc1a72dc..0895b5c7cbf 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -358,6 +358,7 @@ static int page_referenced_one(struct page *page,
*/
if (vma->vm_flags & VM_LOCKED) {
*mapcount = 1; /* break early from loop */
+ *vm_flags |= VM_LOCKED;
goto out_unmap;
}
@@ -703,8 +704,10 @@ void page_add_new_anon_rmap(struct page *page,
*/
void page_add_file_rmap(struct page *page)
{
- if (atomic_inc_and_test(&page->_mapcount))
+ if (atomic_inc_and_test(&page->_mapcount)) {
__inc_zone_page_state(page, NR_FILE_MAPPED);
+ mem_cgroup_update_mapped_file_stat(page, 1);
+ }
}
#ifdef CONFIG_DEBUG_VM
@@ -753,6 +756,7 @@ void page_remove_rmap(struct page *page)
mem_cgroup_uncharge_page(page);
__dec_zone_page_state(page,
PageAnon(page) ? NR_ANON_PAGES : NR_FILE_MAPPED);
+ mem_cgroup_update_mapped_file_stat(page, -1);
/*
* It would be tidy to reset the PageAnon mapping here,
* but that might overwrite a racing page_add_anon_rmap
diff --git a/mm/shmem.c b/mm/shmem.c
index e89d7ec18ed..d713239ce2c 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1558,6 +1558,7 @@ static struct inode *shmem_get_inode(struct super_block *sb, int mode,
spin_lock_init(&info->lock);
info->flags = flags & VM_NORESERVE;
INIT_LIST_HEAD(&info->swaplist);
+ cache_no_acl(inode);
switch (mode & S_IFMT) {
default:
@@ -2388,7 +2389,6 @@ static void shmem_destroy_inode(struct inode *inode)
/* only struct inode is valid if it's an inline symlink */
mpol_free_shared_policy(&SHMEM_I(inode)->policy);
}
- shmem_acl_destroy_inode(inode);
kmem_cache_free(shmem_inode_cachep, SHMEM_I(inode));
}
@@ -2397,10 +2397,6 @@ static void init_once(void *foo)
struct shmem_inode_info *p = (struct shmem_inode_info *) foo;
inode_init_once(&p->vfs_inode);
-#ifdef CONFIG_TMPFS_POSIX_ACL
- p->i_acl = NULL;
- p->i_default_acl = NULL;
-#endif
}
static int init_inodecache(void)
diff --git a/mm/shmem_acl.c b/mm/shmem_acl.c
index 8e5aadd7dcd..606a8e757a4 100644
--- a/mm/shmem_acl.c
+++ b/mm/shmem_acl.c
@@ -22,11 +22,11 @@ shmem_get_acl(struct inode *inode, int type)
spin_lock(&inode->i_lock);
switch(type) {
case ACL_TYPE_ACCESS:
- acl = posix_acl_dup(SHMEM_I(inode)->i_acl);
+ acl = posix_acl_dup(inode->i_acl);
break;
case ACL_TYPE_DEFAULT:
- acl = posix_acl_dup(SHMEM_I(inode)->i_default_acl);
+ acl = posix_acl_dup(inode->i_default_acl);
break;
}
spin_unlock(&inode->i_lock);
@@ -45,13 +45,13 @@ shmem_set_acl(struct inode *inode, int type, struct posix_acl *acl)
spin_lock(&inode->i_lock);
switch(type) {
case ACL_TYPE_ACCESS:
- free = SHMEM_I(inode)->i_acl;
- SHMEM_I(inode)->i_acl = posix_acl_dup(acl);
+ free = inode->i_acl;
+ inode->i_acl = posix_acl_dup(acl);
break;
case ACL_TYPE_DEFAULT:
- free = SHMEM_I(inode)->i_default_acl;
- SHMEM_I(inode)->i_default_acl = posix_acl_dup(acl);
+ free = inode->i_default_acl;
+ inode->i_default_acl = posix_acl_dup(acl);
break;
}
spin_unlock(&inode->i_lock);
@@ -155,23 +155,6 @@ shmem_acl_init(struct inode *inode, struct inode *dir)
}
/**
- * shmem_acl_destroy_inode - destroy acls hanging off the in-memory inode
- *
- * This is done before destroying the actual inode.
- */
-
-void
-shmem_acl_destroy_inode(struct inode *inode)
-{
- if (SHMEM_I(inode)->i_acl)
- posix_acl_release(SHMEM_I(inode)->i_acl);
- SHMEM_I(inode)->i_acl = NULL;
- if (SHMEM_I(inode)->i_default_acl)
- posix_acl_release(SHMEM_I(inode)->i_default_acl);
- SHMEM_I(inode)->i_default_acl = NULL;
-}
-
-/**
* shmem_check_acl - check_acl() callback for generic_permission()
*/
static int
diff --git a/mm/slab.c b/mm/slab.c
index f257d4dd474..7b5d4deacfc 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -305,12 +305,6 @@ struct kmem_list3 {
};
/*
- * The slab allocator is initialized with interrupts disabled. Therefore, make
- * sure early boot allocations don't accidentally enable interrupts.
- */
-static gfp_t slab_gfp_mask __read_mostly = SLAB_GFP_BOOT_MASK;
-
-/*
* Need this for bootstrapping a per node allocator.
*/
#define NUM_INIT_LISTS (3 * MAX_NUMNODES)
@@ -1550,20 +1544,12 @@ void __init kmem_cache_init(void)
}
g_cpucache_up = EARLY;
-
- /* Annotate slab for lockdep -- annotate the malloc caches */
- init_lock_keys();
}
void __init kmem_cache_init_late(void)
{
struct kmem_cache *cachep;
- /*
- * Interrupts are enabled now so all GFP allocations are safe.
- */
- slab_gfp_mask = __GFP_BITS_MASK;
-
/* 6) resize the head arrays to their final sizes */
mutex_lock(&cache_chain_mutex);
list_for_each_entry(cachep, &cache_chain, next)
@@ -1574,6 +1560,9 @@ void __init kmem_cache_init_late(void)
/* Done! */
g_cpucache_up = FULL;
+ /* Annotate slab for lockdep -- annotate the malloc caches */
+ init_lock_keys();
+
/*
* Register a cpu startup notifier callback that initializes
* cpu_cache_get for all new cpus
@@ -2308,6 +2297,15 @@ kmem_cache_create (const char *name, size_t size, size_t align,
/* really off slab. No need for manual alignment */
slab_size =
cachep->num * sizeof(kmem_bufctl_t) + sizeof(struct slab);
+
+#ifdef CONFIG_PAGE_POISONING
+ /* If we're going to use the generic kernel_map_pages()
+ * poisoning, then it's going to smash the contents of
+ * the redzone and userword anyhow, so switch them off.
+ */
+ if (size % PAGE_SIZE == 0 && flags & SLAB_POISON)
+ flags &= ~(SLAB_RED_ZONE | SLAB_STORE_USER);
+#endif
}
cachep->colour_off = cache_line_size();
@@ -2549,7 +2547,7 @@ void kmem_cache_destroy(struct kmem_cache *cachep)
}
if (unlikely(cachep->flags & SLAB_DESTROY_BY_RCU))
- synchronize_rcu();
+ rcu_barrier();
__kmem_cache_destroy(cachep);
mutex_unlock(&cache_chain_mutex);
@@ -3298,7 +3296,7 @@ __cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid,
unsigned long save_flags;
void *ptr;
- flags &= slab_gfp_mask;
+ flags &= gfp_allowed_mask;
lockdep_trace_alloc(flags);
@@ -3383,7 +3381,7 @@ __cache_alloc(struct kmem_cache *cachep, gfp_t flags, void *caller)
unsigned long save_flags;
void *objp;
- flags &= slab_gfp_mask;
+ flags &= gfp_allowed_mask;
lockdep_trace_alloc(flags);
diff --git a/mm/slob.c b/mm/slob.c
index 64f6db1943b..9641da3d5e5 100644
--- a/mm/slob.c
+++ b/mm/slob.c
@@ -133,17 +133,17 @@ static LIST_HEAD(free_slob_large);
*/
static inline int is_slob_page(struct slob_page *sp)
{
- return PageSlobPage((struct page *)sp);
+ return PageSlab((struct page *)sp);
}
static inline void set_slob_page(struct slob_page *sp)
{
- __SetPageSlobPage((struct page *)sp);
+ __SetPageSlab((struct page *)sp);
}
static inline void clear_slob_page(struct slob_page *sp)
{
- __ClearPageSlobPage((struct page *)sp);
+ __ClearPageSlab((struct page *)sp);
}
static inline struct slob_page *slob_page(const void *addr)
@@ -595,6 +595,8 @@ EXPORT_SYMBOL(kmem_cache_create);
void kmem_cache_destroy(struct kmem_cache *c)
{
kmemleak_free(c);
+ if (c->flags & SLAB_DESTROY_BY_RCU)
+ rcu_barrier();
slob_free(c, sizeof(struct kmem_cache));
}
EXPORT_SYMBOL(kmem_cache_destroy);
diff --git a/mm/slub.c b/mm/slub.c
index 2701419b0ad..b6276753626 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -21,7 +21,6 @@
#include <linux/kmemcheck.h>
#include <linux/cpu.h>
#include <linux/cpuset.h>
-#include <linux/kmemleak.h>
#include <linux/mempolicy.h>
#include <linux/ctype.h>
#include <linux/debugobjects.h>
@@ -179,12 +178,6 @@ static enum {
SYSFS /* Sysfs up */
} slab_state = DOWN;
-/*
- * The slab allocator is initialized with interrupts disabled. Therefore, make
- * sure early boot allocations don't accidentally enable interrupts.
- */
-static gfp_t slab_gfp_mask __read_mostly = SLAB_GFP_BOOT_MASK;
-
/* A list of all slab caches on the system */
static DECLARE_RWSEM(slub_lock);
static LIST_HEAD(slab_caches);
@@ -840,6 +833,11 @@ static inline unsigned long slabs_node(struct kmem_cache *s, int node)
return atomic_long_read(&n->nr_slabs);
}
+static inline unsigned long node_nr_slabs(struct kmem_cache_node *n)
+{
+ return atomic_long_read(&n->nr_slabs);
+}
+
static inline void inc_slabs_node(struct kmem_cache *s, int node, int objects)
{
struct kmem_cache_node *n = get_node(s, node);
@@ -1058,6 +1056,8 @@ static inline unsigned long kmem_cache_flags(unsigned long objsize,
static inline unsigned long slabs_node(struct kmem_cache *s, int node)
{ return 0; }
+static inline unsigned long node_nr_slabs(struct kmem_cache_node *n)
+ { return 0; }
static inline void inc_slabs_node(struct kmem_cache *s, int node,
int objects) {}
static inline void dec_slabs_node(struct kmem_cache *s, int node,
@@ -1084,11 +1084,17 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node)
{
struct page *page;
struct kmem_cache_order_objects oo = s->oo;
+ gfp_t alloc_gfp;
flags |= s->allocflags;
- page = alloc_slab_page(flags | __GFP_NOWARN | __GFP_NORETRY, node,
- oo);
+ /*
+ * Let the initial higher-order allocation fail under memory pressure
+ * so we fall-back to the minimum order allocation.
+ */
+ alloc_gfp = (flags | __GFP_NOWARN | __GFP_NORETRY) & ~__GFP_NOFAIL;
+
+ page = alloc_slab_page(alloc_gfp, node, oo);
if (unlikely(!page)) {
oo = s->min;
/*
@@ -1514,6 +1520,65 @@ static inline int node_match(struct kmem_cache_cpu *c, int node)
return 1;
}
+static int count_free(struct page *page)
+{
+ return page->objects - page->inuse;
+}
+
+static unsigned long count_partial(struct kmem_cache_node *n,
+ int (*get_count)(struct page *))
+{
+ unsigned long flags;
+ unsigned long x = 0;
+ struct page *page;
+
+ spin_lock_irqsave(&n->list_lock, flags);
+ list_for_each_entry(page, &n->partial, lru)
+ x += get_count(page);
+ spin_unlock_irqrestore(&n->list_lock, flags);
+ return x;
+}
+
+static inline unsigned long node_nr_objs(struct kmem_cache_node *n)
+{
+#ifdef CONFIG_SLUB_DEBUG
+ return atomic_long_read(&n->total_objects);
+#else
+ return 0;
+#endif
+}
+
+static noinline void
+slab_out_of_memory(struct kmem_cache *s, gfp_t gfpflags, int nid)
+{
+ int node;
+
+ printk(KERN_WARNING
+ "SLUB: Unable to allocate memory on node %d (gfp=0x%x)\n",
+ nid, gfpflags);
+ printk(KERN_WARNING " cache: %s, object size: %d, buffer size: %d, "
+ "default order: %d, min order: %d\n", s->name, s->objsize,
+ s->size, oo_order(s->oo), oo_order(s->min));
+
+ for_each_online_node(node) {
+ struct kmem_cache_node *n = get_node(s, node);
+ unsigned long nr_slabs;
+ unsigned long nr_objs;
+ unsigned long nr_free;
+
+ if (!n)
+ continue;
+
+ nr_free = count_partial(n, count_free);
+ nr_slabs = node_nr_slabs(n);
+ nr_objs = node_nr_objs(n);
+
+ printk(KERN_WARNING
+ " node %d: slabs: %ld, objs: %ld, free: %ld\n",
+ node, nr_slabs, nr_objs, nr_free);
+ }
+}
+
/*
* Slow path. The lockless freelist is empty or we need to perform
* debugging duties.
@@ -1595,6 +1660,8 @@ new_slab:
c->page = new;
goto load_freelist;
}
+ if (!(gfpflags & __GFP_NOWARN) && printk_ratelimit())
+ slab_out_of_memory(s, gfpflags, node);
return NULL;
debug:
if (!alloc_debug_processing(s, c->page, object, addr))
@@ -1624,7 +1691,7 @@ static __always_inline void *slab_alloc(struct kmem_cache *s,
unsigned long flags;
unsigned int objsize;
- gfpflags &= slab_gfp_mask;
+ gfpflags &= gfp_allowed_mask;
lockdep_trace_alloc(gfpflags);
might_sleep_if(gfpflags & __GFP_WAIT);
@@ -2537,6 +2604,8 @@ void kmem_cache_destroy(struct kmem_cache *s)
"still has objects.\n", s->name, __func__);
dump_stack();
}
+ if (s->flags & SLAB_DESTROY_BY_RCU)
+ rcu_barrier();
sysfs_slab_remove(s);
} else
up_write(&slub_lock);
@@ -2636,6 +2705,7 @@ static noinline struct kmem_cache *dma_kmalloc_cache(int index, gfp_t flags)
struct kmem_cache *s;
char *text;
size_t realsize;
+ unsigned long slabflags;
s = kmalloc_caches_dma[index];
if (s)
@@ -2657,10 +2727,18 @@ static noinline struct kmem_cache *dma_kmalloc_cache(int index, gfp_t flags)
(unsigned int)realsize);
s = kmalloc(kmem_size, flags & ~SLUB_DMA);
+ /*
+ * Must defer sysfs creation to a workqueue because we don't know
+ * what context we are called from. Before sysfs comes up, we don't
+ * need to do anything because our sysfs initcall will start by
+ * adding all existing slabs to sysfs.
+ */
+ slabflags = SLAB_CACHE_DMA|SLAB_NOTRACK;
+ if (slab_state >= SYSFS)
+ slabflags |= __SYSFS_ADD_DEFERRED;
+
if (!s || !text || !kmem_cache_open(s, flags, text,
- realsize, ARCH_KMALLOC_MINALIGN,
- SLAB_CACHE_DMA|SLAB_NOTRACK|__SYSFS_ADD_DEFERRED,
- NULL)) {
+ realsize, ARCH_KMALLOC_MINALIGN, slabflags, NULL)) {
kfree(s);
kfree(text);
goto unlock_out;
@@ -2669,7 +2747,8 @@ static noinline struct kmem_cache *dma_kmalloc_cache(int index, gfp_t flags)
list_add(&s->list, &slab_caches);
kmalloc_caches_dma[index] = s;
- schedule_work(&sysfs_add_work);
+ if (slab_state >= SYSFS)
+ schedule_work(&sysfs_add_work);
unlock_out:
up_write(&slub_lock);
@@ -2755,13 +2834,15 @@ EXPORT_SYMBOL(__kmalloc);
static void *kmalloc_large_node(size_t size, gfp_t flags, int node)
{
struct page *page;
+ void *ptr = NULL;
flags |= __GFP_COMP | __GFP_NOTRACK;
page = alloc_pages_node(node, flags, get_order(size));
if (page)
- return page_address(page);
- else
- return NULL;
+ ptr = page_address(page);
+
+ kmemleak_alloc(ptr, size, 1, flags);
+ return ptr;
}
#ifdef CONFIG_NUMA
@@ -2846,6 +2927,7 @@ void kfree(const void *x)
page = virt_to_head_page(x);
if (unlikely(!PageSlab(page))) {
BUG_ON(!PageCompound(page));
+ kmemleak_free(x);
put_page(page);
return;
}
@@ -3142,10 +3224,6 @@ void __init kmem_cache_init(void)
void __init kmem_cache_init_late(void)
{
- /*
- * Interrupts are enabled now so all GFP allocations are safe.
- */
- slab_gfp_mask = __GFP_BITS_MASK;
}
/*
@@ -3368,20 +3446,6 @@ void *__kmalloc_node_track_caller(size_t size, gfp_t gfpflags,
}
#ifdef CONFIG_SLUB_DEBUG
-static unsigned long count_partial(struct kmem_cache_node *n,
- int (*get_count)(struct page *))
-{
- unsigned long flags;
- unsigned long x = 0;
- struct page *page;
-
- spin_lock_irqsave(&n->list_lock, flags);
- list_for_each_entry(page, &n->partial, lru)
- x += get_count(page);
- spin_unlock_irqrestore(&n->list_lock, flags);
- return x;
-}
-
static int count_inuse(struct page *page)
{
return page->inuse;
@@ -3392,11 +3456,6 @@ static int count_total(struct page *page)
return page->objects;
}
-static int count_free(struct page *page)
-{
- return page->objects - page->inuse;
-}
-
static int validate_slab(struct kmem_cache *s, struct page *page,
unsigned long *map)
{
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 28faa01cf57..8ffdc0d23c5 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -583,8 +583,9 @@ static int swap_entry_free(struct swap_info_struct *p,
swap_list.next = p - swap_info;
nr_swap_pages++;
p->inuse_pages--;
- mem_cgroup_uncharge_swap(ent);
}
+ if (!swap_count(count))
+ mem_cgroup_uncharge_swap(ent);
return count;
}
@@ -609,12 +610,19 @@ void swap_free(swp_entry_t entry)
void swapcache_free(swp_entry_t entry, struct page *page)
{
struct swap_info_struct *p;
+ int ret;
- if (page)
- mem_cgroup_uncharge_swapcache(page, entry);
p = swap_info_get(entry);
if (p) {
- swap_entry_free(p, entry, SWAP_CACHE);
+ ret = swap_entry_free(p, entry, SWAP_CACHE);
+ if (page) {
+ bool swapout;
+ if (ret)
+ swapout = true; /* the end of swap out */
+ else
+ swapout = false; /* no more swap users! */
+ mem_cgroup_uncharge_swapcache(page, entry, swapout);
+ }
spin_unlock(&swap_lock);
}
return;
@@ -745,7 +753,7 @@ int swap_type_of(dev_t device, sector_t offset, struct block_device **bdev_p)
if (!bdev) {
if (bdev_p)
- *bdev_p = bdget(sis->bdev->bd_dev);
+ *bdev_p = bdgrab(sis->bdev);
spin_unlock(&swap_lock);
return i;
@@ -757,7 +765,7 @@ int swap_type_of(dev_t device, sector_t offset, struct block_device **bdev_p)
struct swap_extent, list);
if (se->start_block == offset) {
if (bdev_p)
- *bdev_p = bdget(sis->bdev->bd_dev);
+ *bdev_p = bdgrab(sis->bdev);
spin_unlock(&swap_lock);
bdput(bdev);
diff --git a/mm/thrash.c b/mm/thrash.c
index c4c5205a9c3..2372d4ed5dd 100644
--- a/mm/thrash.c
+++ b/mm/thrash.c
@@ -26,47 +26,45 @@ static DEFINE_SPINLOCK(swap_token_lock);
struct mm_struct *swap_token_mm;
static unsigned int global_faults;
-void grab_swap_token(void)
+void grab_swap_token(struct mm_struct *mm)
{
int current_interval;
global_faults++;
- current_interval = global_faults - current->mm->faultstamp;
+ current_interval = global_faults - mm->faultstamp;
if (!spin_trylock(&swap_token_lock))
return;
/* First come first served */
if (swap_token_mm == NULL) {
- current->mm->token_priority = current->mm->token_priority + 2;
- swap_token_mm = current->mm;
+ mm->token_priority = mm->token_priority + 2;
+ swap_token_mm = mm;
goto out;
}
- if (current->mm != swap_token_mm) {
- if (current_interval < current->mm->last_interval)
- current->mm->token_priority++;
+ if (mm != swap_token_mm) {
+ if (current_interval < mm->last_interval)
+ mm->token_priority++;
else {
- if (likely(current->mm->token_priority > 0))
- current->mm->token_priority--;
+ if (likely(mm->token_priority > 0))
+ mm->token_priority--;
}
/* Check if we deserve the token */
- if (current->mm->token_priority >
- swap_token_mm->token_priority) {
- current->mm->token_priority += 2;
- swap_token_mm = current->mm;
+ if (mm->token_priority > swap_token_mm->token_priority) {
+ mm->token_priority += 2;
+ swap_token_mm = mm;
}
} else {
/* Token holder came in again! */
- current->mm->token_priority += 2;
+ mm->token_priority += 2;
}
out:
- current->mm->faultstamp = global_faults;
- current->mm->last_interval = current_interval;
+ mm->faultstamp = global_faults;
+ mm->last_interval = current_interval;
spin_unlock(&swap_token_lock);
-return;
}
/* Called on process exit. */
diff --git a/mm/util.c b/mm/util.c
index d5d2213728c..7c35ad95f92 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -168,6 +168,10 @@ EXPORT_SYMBOL(krealloc);
*
* The memory of the object @p points to is zeroed before freed.
* If @p is %NULL, kzfree() does nothing.
+ *
+ * Note: this function zeroes the whole allocated buffer which can be a good
+ * deal bigger than the requested buffer size passed to kmalloc(). So be
+ * careful when using this function in performance sensitive code.
*/
void kzfree(const void *p)
{
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 4139aa52b94..94e86dd6954 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -630,9 +630,14 @@ static unsigned long shrink_page_list(struct list_head *page_list,
referenced = page_referenced(page, 1,
sc->mem_cgroup, &vm_flags);
- /* In active use or really unfreeable? Activate it. */
+ /*
+ * In active use or really unfreeable? Activate it.
+ * If page which have PG_mlocked lost isoltation race,
+ * try_to_unmap moves it to unevictable list
+ */
if (sc->order <= PAGE_ALLOC_COSTLY_ORDER &&
- referenced && page_mapping_inuse(page))
+ referenced && page_mapping_inuse(page)
+ && !(vm_flags & VM_LOCKED))
goto activate_locked;
/*
@@ -837,7 +842,6 @@ int __isolate_lru_page(struct page *page, int mode, int file)
*/
ClearPageLRU(page);
ret = 0;
- mem_cgroup_del_lru(page);
}
return ret;
@@ -885,12 +889,14 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
switch (__isolate_lru_page(page, mode, file)) {
case 0:
list_move(&page->lru, dst);
+ mem_cgroup_del_lru(page);
nr_taken++;
break;
case -EBUSY:
/* else it is being freed elsewhere */
list_move(&page->lru, src);
+ mem_cgroup_rotate_lru_list(page, page_lru(page));
continue;
default:
@@ -931,6 +937,7 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
continue;
if (__isolate_lru_page(cursor_page, mode, file) == 0) {
list_move(&cursor_page->lru, dst);
+ mem_cgroup_del_lru(cursor_page);
nr_taken++;
scan++;
}
@@ -1102,7 +1109,7 @@ static unsigned long shrink_inactive_list(unsigned long max_scan,
*/
if (nr_freed < nr_taken && !current_is_kswapd() &&
lumpy_reclaim) {
- congestion_wait(WRITE, HZ/10);
+ congestion_wait(BLK_RW_ASYNC, HZ/10);
/*
* The attempt at page out may have made some
@@ -1719,7 +1726,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
/* Take a nap, wait for some writeback to complete */
if (sc->nr_scanned && priority < DEF_PRIORITY - 2)
- congestion_wait(WRITE, HZ/10);
+ congestion_wait(BLK_RW_ASYNC, HZ/10);
}
/* top priority shrink_zones still had more to do? don't OOM, then */
if (!sc->all_unreclaimable && scanning_global_lru(sc))
@@ -1958,7 +1965,7 @@ loop_again:
* another pass across the zones.
*/
if (total_scanned && priority < DEF_PRIORITY - 2)
- congestion_wait(WRITE, HZ/10);
+ congestion_wait(BLK_RW_ASYNC, HZ/10);
/*
* We do this so kswapd doesn't build up large priorities for
@@ -2231,7 +2238,7 @@ unsigned long shrink_all_memory(unsigned long nr_pages)
goto out;
if (sc.nr_scanned && prio < DEF_PRIORITY - 2)
- congestion_wait(WRITE, HZ / 10);
+ congestion_wait(BLK_RW_ASYNC, HZ / 10);
}
}
generated by cgit v1.2.3 (git 2.25.1) at 2024-05-01 15:00:42 +0000