#include <linux/pagevec.h>
#include <linux/blkdev.h>
#include <linux/slab.h>
+#include <linux/ratelimit.h>
#include <linux/oom.h>
#include <linux/notifier.h>
#include <linux/topology.h>
#include <linux/memory_hotplug.h>
#include <linux/nodemask.h>
#include <linux/vmalloc.h>
+#include <linux/vmstat.h>
#include <linux/mempolicy.h>
#include <linux/stop_machine.h>
#include <linux/sort.h>
#include <linux/compaction.h>
#include <trace/events/kmem.h>
#include <linux/ftrace_event.h>
+#include <linux/memcontrol.h>
+#include <linux/prefetch.h>
#include <asm/tlbflush.h>
#include <asm/div64.h>
if (unlikely(page_mapcount(page) |
(page->mapping != NULL) |
(atomic_read(&page->_count) != 0) |
- (page->flags & PAGE_FLAGS_CHECK_AT_FREE))) {
+ (page->flags & PAGE_FLAGS_CHECK_AT_FREE) |
+ (mem_cgroup_bad_page_check(page)))) {
bad_page(page);
return 1;
}
list = &pcp->lists[migratetype];
} while (list_empty(list));
+ /* This is the only non-empty list. Free them all. */
+ if (batch_free == MIGRATE_PCPTYPES)
+ batch_free = to_free;
+
do {
page = list_entry(list->prev, struct page, lru);
/* must delete as __free_one_page list manipulates */
if (unlikely(page_mapcount(page) |
(page->mapping != NULL) |
(atomic_read(&page->_count) != 0) |
- (page->flags & PAGE_FLAGS_CHECK_AT_PREP))) {
+ (page->flags & PAGE_FLAGS_CHECK_AT_PREP) |
+ (mem_cgroup_bad_page_check(page)))) {
bad_page(page);
return 1;
}
}
order = page_order(page);
- list_del(&page->lru);
- list_add(&page->lru,
- &zone->free_area[order].free_list[migratetype]);
+ list_move(&page->lru,
+ &zone->free_area[order].free_list[migratetype]);
page += 1 << order;
pages_moved += 1 << order;
}
* If breaking a large block of pages, move all free
* pages to the preferred allocation list. If falling
* back for a reclaimable kernel allocation, be more
- * agressive about taking ownership of free pages
+ * aggressive about taking ownership of free pages
*/
if (unlikely(current_order >= (pageblock_order >> 1)) ||
start_migratetype == MIGRATE_RECLAIMABLE ||
}
__count_zone_vm_events(PGALLOC, zone, 1 << order);
- zone_statistics(preferred_zone, zone);
+ zone_statistics(preferred_zone, zone, gfp_flags);
local_irq_restore(flags);
VM_BUG_ON(bad_range(zone, page));
#ifdef CONFIG_FAIL_PAGE_ALLOC
-static struct fail_page_alloc_attr {
+static struct {
struct fault_attr attr;
u32 ignore_gfp_highmem;
u32 ignore_gfp_wait;
u32 min_order;
-
-#ifdef CONFIG_FAULT_INJECTION_DEBUG_FS
-
- struct dentry *ignore_gfp_highmem_file;
- struct dentry *ignore_gfp_wait_file;
- struct dentry *min_order_file;
-
-#endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */
-
} fail_page_alloc = {
.attr = FAULT_ATTR_INITIALIZER,
.ignore_gfp_wait = 1,
{
mode_t mode = S_IFREG | S_IRUSR | S_IWUSR;
struct dentry *dir;
- int err;
-
- err = init_fault_attr_dentries(&fail_page_alloc.attr,
- "fail_page_alloc");
- if (err)
- return err;
- dir = fail_page_alloc.attr.dentries.dir;
-
- fail_page_alloc.ignore_gfp_wait_file =
- debugfs_create_bool("ignore-gfp-wait", mode, dir,
- &fail_page_alloc.ignore_gfp_wait);
-
- fail_page_alloc.ignore_gfp_highmem_file =
- debugfs_create_bool("ignore-gfp-highmem", mode, dir,
- &fail_page_alloc.ignore_gfp_highmem);
- fail_page_alloc.min_order_file =
- debugfs_create_u32("min-order", mode, dir,
- &fail_page_alloc.min_order);
-
- if (!fail_page_alloc.ignore_gfp_wait_file ||
- !fail_page_alloc.ignore_gfp_highmem_file ||
- !fail_page_alloc.min_order_file) {
- err = -ENOMEM;
- debugfs_remove(fail_page_alloc.ignore_gfp_wait_file);
- debugfs_remove(fail_page_alloc.ignore_gfp_highmem_file);
- debugfs_remove(fail_page_alloc.min_order_file);
- cleanup_fault_attr_dentries(&fail_page_alloc.attr);
- }
- return err;
+ dir = fault_create_debugfs_attr("fail_page_alloc", NULL,
+ &fail_page_alloc.attr);
+ if (IS_ERR(dir))
+ return PTR_ERR(dir);
+
+ if (!debugfs_create_bool("ignore-gfp-wait", mode, dir,
+ &fail_page_alloc.ignore_gfp_wait))
+ goto fail;
+ if (!debugfs_create_bool("ignore-gfp-highmem", mode, dir,
+ &fail_page_alloc.ignore_gfp_highmem))
+ goto fail;
+ if (!debugfs_create_u32("min-order", mode, dir,
+ &fail_page_alloc.min_order))
+ goto fail;
+
+ return 0;
+fail:
+ debugfs_remove_recursive(dir);
+
+ return -ENOMEM;
}
late_initcall(fail_page_alloc_debugfs);
set_bit(i, zlc->fullzones);
}
+/*
+ * clear all zones full, called after direct reclaim makes progress so that
+ * a zone that was recently full is not skipped over for up to a second
+ */
+static void zlc_clear_zones_full(struct zonelist *zonelist)
+{
+ struct zonelist_cache *zlc; /* cached zonelist speedup info */
+
+ zlc = zonelist->zlcache_ptr;
+ if (!zlc)
+ return;
+
+ bitmap_zero(zlc->fullzones, MAX_ZONES_PER_ZONELIST);
+}
+
#else /* CONFIG_NUMA */
static nodemask_t *zlc_setup(struct zonelist *zonelist, int alloc_flags)
static void zlc_mark_zone_full(struct zonelist *zonelist, struct zoneref *z)
{
}
+
+static void zlc_clear_zones_full(struct zonelist *zonelist)
+{
+}
#endif /* CONFIG_NUMA */
/*
continue;
if ((alloc_flags & ALLOC_CPUSET) &&
!cpuset_zone_allowed_softwall(zone, gfp_mask))
- goto try_next_zone;
+ continue;
BUILD_BUG_ON(ALLOC_NO_WATERMARKS < NR_WMARK);
if (!(alloc_flags & ALLOC_NO_WATERMARKS)) {
classzone_idx, alloc_flags))
goto try_this_zone;
+ if (NUMA_BUILD && !did_zlc_setup && nr_online_nodes > 1) {
+ /*
+ * we do zlc_setup if there are multiple nodes
+ * and before considering the first zone allowed
+ * by the cpuset.
+ */
+ allowednodes = zlc_setup(zonelist, alloc_flags);
+ zlc_active = 1;
+ did_zlc_setup = 1;
+ }
+
if (zone_reclaim_mode == 0)
goto this_zone_full;
+ /*
+ * As we may have just activated ZLC, check if the first
+ * eligible zone has failed zone_reclaim recently.
+ */
+ if (NUMA_BUILD && zlc_active &&
+ !zlc_zone_worth_trying(zonelist, z, allowednodes))
+ continue;
+
ret = zone_reclaim(zone, gfp_mask, order);
switch (ret) {
case ZONE_RECLAIM_NOSCAN:
/* did not scan */
- goto try_next_zone;
+ continue;
case ZONE_RECLAIM_FULL:
/* scanned but unreclaimable */
- goto this_zone_full;
+ continue;
default:
/* did we reclaim enough */
if (!zone_watermark_ok(zone, order, mark,
this_zone_full:
if (NUMA_BUILD)
zlc_mark_zone_full(zonelist, z);
-try_next_zone:
- if (NUMA_BUILD && !did_zlc_setup && nr_online_nodes > 1) {
- /*
- * we do zlc_setup after the first zone is tried but only
- * if there are multiple nodes make it worthwhile
- */
- allowednodes = zlc_setup(zonelist, alloc_flags);
- zlc_active = 1;
- did_zlc_setup = 1;
- }
}
if (unlikely(NUMA_BUILD && page == NULL && zlc_active)) {
return page;
}
+/*
+ * Large machines with many possible nodes should not always dump per-node
+ * meminfo in irq context.
+ */
+static inline bool should_suppress_show_mem(void)
+{
+ bool ret = false;
+
+#if NODES_SHIFT > 8
+ ret = in_interrupt();
+#endif
+ return ret;
+}
+
+static DEFINE_RATELIMIT_STATE(nopage_rs,
+ DEFAULT_RATELIMIT_INTERVAL,
+ DEFAULT_RATELIMIT_BURST);
+
+void warn_alloc_failed(gfp_t gfp_mask, int order, const char *fmt, ...)
+{
+ va_list args;
+ unsigned int filter = SHOW_MEM_FILTER_NODES;
+
+ if ((gfp_mask & __GFP_NOWARN) || !__ratelimit(&nopage_rs))
+ return;
+
+ /*
+ * This documents exceptions given to allocations in certain
+ * contexts that are allowed to allocate outside current's set
+ * of allowed nodes.
+ */
+ if (!(gfp_mask & __GFP_NOMEMALLOC))
+ if (test_thread_flag(TIF_MEMDIE) ||
+ (current->flags & (PF_MEMALLOC | PF_EXITING)))
+ filter &= ~SHOW_MEM_FILTER_NODES;
+ if (in_interrupt() || !(gfp_mask & __GFP_WAIT))
+ filter &= ~SHOW_MEM_FILTER_NODES;
+
+ if (fmt) {
+ printk(KERN_WARNING);
+ va_start(args, fmt);
+ vprintk(fmt, args);
+ va_end(args);
+ }
+
+ pr_warning("%s: page allocation failure: order:%d, mode:0x%x\n",
+ current->comm, order, gfp_mask);
+
+ dump_stack();
+ if (!should_suppress_show_mem())
+ show_mem(filter);
+}
+
static inline int
should_alloc_retry(gfp_t gfp_mask, unsigned int order,
unsigned long pages_reclaimed)
if (unlikely(!(*did_some_progress)))
return NULL;
+ /* After successful reclaim, reconsider all zones for allocation */
+ if (NUMA_BUILD)
+ zlc_clear_zones_full(zonelist);
+
retry:
page = get_page_from_freelist(gfp_mask, nodemask, order,
zonelist, high_zoneidx,
first_zones_zonelist(zonelist, high_zoneidx, NULL,
&preferred_zone);
+rebalance:
/* This is the last chance, in general, before the goto nopage. */
page = get_page_from_freelist(gfp_mask, nodemask, order, zonelist,
high_zoneidx, alloc_flags & ~ALLOC_NO_WATERMARKS,
if (page)
goto got_pg;
-rebalance:
/* Allocate without watermarks if the context allows */
if (alloc_flags & ALLOC_NO_WATERMARKS) {
page = __alloc_pages_high_priority(gfp_mask, order,
}
nopage:
- if (!(gfp_mask & __GFP_NOWARN) && printk_ratelimit()) {
- printk(KERN_WARNING "%s: page allocation failure."
- " order:%d, mode:0x%x\n",
- current->comm, order, gfp_mask);
- dump_stack();
- show_mem();
- }
+ warn_alloc_failed(gfp_mask, order, NULL);
return page;
got_pg:
if (kmemcheck_enabled)
EXPORT_SYMBOL(free_pages);
+static void *make_alloc_exact(unsigned long addr, unsigned order, size_t size)
+{
+ if (addr) {
+ unsigned long alloc_end = addr + (PAGE_SIZE << order);
+ unsigned long used = addr + PAGE_ALIGN(size);
+
+ split_page(virt_to_page((void *)addr), order);
+ while (used < alloc_end) {
+ free_page(used);
+ used += PAGE_SIZE;
+ }
+ }
+ return (void *)addr;
+}
+
/**
* alloc_pages_exact - allocate an exact number physically-contiguous pages.
* @size: the number of bytes to allocate
unsigned long addr;
addr = __get_free_pages(gfp_mask, order);
- if (addr) {
- unsigned long alloc_end = addr + (PAGE_SIZE << order);
- unsigned long used = addr + PAGE_ALIGN(size);
-
- split_page(virt_to_page((void *)addr), order);
- while (used < alloc_end) {
- free_page(used);
- used += PAGE_SIZE;
- }
- }
-
- return (void *)addr;
+ return make_alloc_exact(addr, order, size);
}
EXPORT_SYMBOL(alloc_pages_exact);
+/**
+ * alloc_pages_exact_nid - allocate an exact number of physically-contiguous
+ * pages on a node.
+ * @nid: the preferred node ID where memory should be allocated
+ * @size: the number of bytes to allocate
+ * @gfp_mask: GFP flags for the allocation
+ *
+ * Like alloc_pages_exact(), but try to allocate on node nid first before falling
+ * back.
+ * Note this is not alloc_pages_exact_node() which allocates on a specific node,
+ * but is not exact.
+ */
+void *alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask)
+{
+ unsigned order = get_order(size);
+ struct page *p = alloc_pages_node(nid, gfp_mask, order);
+ if (!p)
+ return NULL;
+ return make_alloc_exact((unsigned long)page_address(p), order, size);
+}
+EXPORT_SYMBOL(alloc_pages_exact_nid);
+
/**
* free_pages_exact - release memory allocated via alloc_pages_exact()
* @virt: the value returned by alloc_pages_exact.
}
#endif
+/*
+ * Determine whether the node should be displayed or not, depending on whether
+ * SHOW_MEM_FILTER_NODES was passed to show_free_areas().
+ */
+bool skip_free_areas_node(unsigned int flags, int nid)
+{
+ bool ret = false;
+
+ if (!(flags & SHOW_MEM_FILTER_NODES))
+ goto out;
+
+ get_mems_allowed();
+ ret = !node_isset(nid, cpuset_current_mems_allowed);
+ put_mems_allowed();
+out:
+ return ret;
+}
+
#define K(x) ((x) << (PAGE_SHIFT-10))
/*
* Show free area list (used inside shift_scroll-lock stuff)
* We also calculate the percentage fragmentation. We do this by counting the
* memory on each free list with the exception of the first item on the list.
+ * Suppresses nodes that are not allowed by current's cpuset if
+ * SHOW_MEM_FILTER_NODES is passed.
*/
-void show_free_areas(void)
+void show_free_areas(unsigned int filter)
{
int cpu;
struct zone *zone;
for_each_populated_zone(zone) {
+ if (skip_free_areas_node(filter, zone_to_nid(zone)))
+ continue;
show_node(zone);
printk("%s per-cpu:\n", zone->name);
for_each_populated_zone(zone) {
int i;
+ if (skip_free_areas_node(filter, zone_to_nid(zone)))
+ continue;
show_node(zone);
printk("%s"
" free:%lukB"
for_each_populated_zone(zone) {
unsigned long nr[MAX_ORDER], flags, order, total = 0;
+ if (skip_free_areas_node(filter, zone_to_nid(zone)))
+ continue;
show_node(zone);
printk("%s: ", zone->name);
* Called with zonelists_mutex held always
* unless system_state == SYSTEM_BOOTING.
*/
-void build_all_zonelists(void *data)
+void __ref build_all_zonelists(void *data)
{
set_zonelist_order();
#define LONG_ALIGN(x) (((x)+(sizeof(long))-1)&~((sizeof(long))-1))
+/*
+ * Check if a pageblock contains reserved pages
+ */
+static int pageblock_is_reserved(unsigned long start_pfn, unsigned long end_pfn)
+{
+ unsigned long pfn;
+
+ for (pfn = start_pfn; pfn < end_pfn; pfn++) {
+ if (!pfn_valid_within(pfn) || PageReserved(pfn_to_page(pfn)))
+ return 1;
+ }
+ return 0;
+}
+
/*
* Mark a number of pageblocks as MIGRATE_RESERVE. The number
* of blocks reserved is based on min_wmark_pages(zone). The memory within
*/
static void setup_zone_migrate_reserve(struct zone *zone)
{
- unsigned long start_pfn, pfn, end_pfn;
+ unsigned long start_pfn, pfn, end_pfn, block_end_pfn;
struct page *page;
unsigned long block_migratetype;
int reserve;
continue;
/* Blocks with reserved pages will never free, skip them. */
- if (PageReserved(page))
+ block_end_pfn = min(pfn + pageblock_nr_pages, end_pfn);
+ if (pageblock_is_reserved(pfn, block_end_pfn))
continue;
block_migratetype = get_pageblock_migratetype(page);
pcp->batch = PAGE_SHIFT * 8;
}
-static __meminit void setup_zone_pageset(struct zone *zone)
+static void setup_zone_pageset(struct zone *zone)
{
int cpu;
if (!slab_is_available()) {
zone->wait_table = (wait_queue_head_t *)
- alloc_bootmem_node(pgdat, alloc_size);
+ alloc_bootmem_node_nopanic(pgdat, alloc_size);
} else {
/*
* This case means that a zone whose size was 0 gets new memory
/*
* The zone ranges provided by the architecture do not include ZONE_MOVABLE
- * because it is sized independant of architecture. Unlike the other zones,
+ * because it is sized independent of architecture. Unlike the other zones,
* the starting point for ZONE_MOVABLE is not fixed. It may be different
* in each node depending on the size of each node and how evenly kernelcore
* is distributed. This helper function adjusts the zone ranges
unsigned long usemapsize = usemap_size(zonesize);
zone->pageblock_flags = NULL;
if (usemapsize)
- zone->pageblock_flags = alloc_bootmem_node(pgdat, usemapsize);
+ zone->pageblock_flags = alloc_bootmem_node_nopanic(pgdat,
+ usemapsize);
}
#else
static inline void setup_usemap(struct pglist_data *pgdat,
zone->zone_pgdat = pgdat;
zone_pcp_init(zone);
- for_each_lru(l) {
+ for_each_lru(l)
INIT_LIST_HEAD(&zone->lru[l].list);
- zone->reclaim_stat.nr_saved_scan[l] = 0;
- }
zone->reclaim_stat.recent_rotated[0] = 0;
zone->reclaim_stat.recent_rotated[1] = 0;
zone->reclaim_stat.recent_scanned[0] = 0;
size = (end - start) * sizeof(struct page);
map = alloc_remap(pgdat->node_id, size);
if (!map)
- map = alloc_bootmem_node(pgdat, size);
+ map = alloc_bootmem_node_nopanic(pgdat, size);
pgdat->node_mem_map = map + (pgdat->node_start_pfn - start);
}
#ifndef CONFIG_NEED_MULTIPLE_NODES
cmp_node_active_region, NULL);
}
+/**
+ * node_map_pfn_alignment - determine the maximum internode alignment
+ *
+ * This function should be called after node map is populated and sorted.
+ * It calculates the maximum power of two alignment which can distinguish
+ * all the nodes.
+ *
+ * For example, if all nodes are 1GiB and aligned to 1GiB, the return value
+ * would indicate 1GiB alignment with (1 << (30 - PAGE_SHIFT)). If the
+ * nodes are shifted by 256MiB, 256MiB. Note that if only the last node is
+ * shifted, 1GiB is enough and this function will indicate so.
+ *
+ * This is used to test whether pfn -> nid mapping of the chosen memory
+ * model has fine enough granularity to avoid incorrect mapping for the
+ * populated node map.
+ *
+ * Returns the determined alignment in pfn's. 0 if there is no alignment
+ * requirement (single node).
+ */
+unsigned long __init node_map_pfn_alignment(void)
+{
+ unsigned long accl_mask = 0, last_end = 0;
+ int last_nid = -1;
+ int i;
+
+ for_each_active_range_index_in_nid(i, MAX_NUMNODES) {
+ int nid = early_node_map[i].nid;
+ unsigned long start = early_node_map[i].start_pfn;
+ unsigned long end = early_node_map[i].end_pfn;
+ unsigned long mask;
+
+ if (!start || last_nid < 0 || last_nid == nid) {
+ last_nid = nid;
+ last_end = end;
+ continue;
+ }
+
+ /*
+ * Start with a mask granular enough to pin-point to the
+ * start pfn and tick off bits one-by-one until it becomes
+ * too coarse to separate the current node from the last.
+ */
+ mask = ~((1 << __ffs(start)) - 1);
+ while (mask && last_end <= (start & (mask << 1)))
+ mask <<= 1;
+
+ /* accumulate all internode masks */
+ accl_mask |= mask;
+ }
+
+ /* convert mask to number of pages */
+ return ~accl_mask + 1;
+}
+
/* Find the lowest pfn for a node */
static unsigned long __init find_min_pfn_for_node(int nid)
{
* 1TB 101 10GB
* 10TB 320 32GB
*/
-void calculate_zone_inactive_ratio(struct zone *zone)
+static void __meminit calculate_zone_inactive_ratio(struct zone *zone)
{
unsigned int gb, ratio;
zone->inactive_ratio = ratio;
}
-static void __init setup_per_zone_inactive_ratio(void)
+static void __meminit setup_per_zone_inactive_ratio(void)
{
struct zone *zone;
* 8192MB: 11584k
* 16384MB: 16384k
*/
-static int __init init_per_zone_wmark_min(void)
+int __meminit init_per_zone_wmark_min(void)
{
unsigned long lowmem_kbytes;
if (min_free_kbytes > 65536)
min_free_kbytes = 65536;
setup_per_zone_wmarks();
+ refresh_zone_stat_thresholds();
setup_per_zone_lowmem_reserve();
setup_per_zone_inactive_ratio();
return 0;
struct memory_isolate_notify arg;
int notifier_ret;
int ret = -EBUSY;
- int zone_idx;
zone = page_zone(page);
- zone_idx = zone_idx(zone);
spin_lock_irqsave(&zone->lock, flags);
page, atomic_read(&page->_count), page_mapcount(page),
page->mapping, page->index);
dump_page_flags(page->flags);
+ mem_cgroup_print_bad_page(page);
}
Code Review / linux-2.6.git / blobdiff