Currently, the following scenario appears to be possible in theory: * Tasks are frozen for hibernation or suspend. * Free pages are almost exhausted. * Certain piece of code in the suspend code path attempts to allocate some memory using GFP_KERNEL and allocation order less than or equal to PAGE_ALLOC_COSTLY_ORDER. * __alloc_pages_internal() cannot find a free page so it invokes the OOM killer. * The OOM killer attempts to kill a task, but the task is frozen, so it doesn't die immediately. * __alloc_pages_internal() jumps to 'restart', unsuccessfully tries to find a free page and invokes the OOM killer. * No progress can be made. Although it is now hard to trigger during hibernation due to the memory shrinking carried out by the hibernation code, it is theoretically possible to trigger during suspend after the memory shrinking has been removed from that code path. Moreover, since memory allocations are going to be used for the hibernation memory shrinking, it will be even more likely to happen during hibernation. To prevent it from happening, introduce the oom_killer_disabled switch that will cause __alloc_pages_internal() to fail in the situations in which the OOM killer would have been called and make the freezer set this switch after tasks have been successfully frozen. [akpm@linux-foundation.org: be nicer to the namespace] Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl> Cc: Fengguang Wu <fengguang.wu@gmail.com> Cc: David Rientjes <rientjes@google.com> Acked-by: Pavel Machek <pavel@ucw.cz> Cc: Mel Gorman <mel@csn.ul.ie> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
259 lines
8.4 KiB
C
259 lines
8.4 KiB
C
#ifndef __LINUX_GFP_H
|
|
#define __LINUX_GFP_H
|
|
|
|
#include <linux/mmzone.h>
|
|
#include <linux/stddef.h>
|
|
#include <linux/linkage.h>
|
|
#include <linux/topology.h>
|
|
#include <linux/mmdebug.h>
|
|
|
|
struct vm_area_struct;
|
|
|
|
/*
|
|
* GFP bitmasks..
|
|
*
|
|
* Zone modifiers (see linux/mmzone.h - low three bits)
|
|
*
|
|
* Do not put any conditional on these. If necessary modify the definitions
|
|
* without the underscores and use the consistently. The definitions here may
|
|
* be used in bit comparisons.
|
|
*/
|
|
#define __GFP_DMA ((__force gfp_t)0x01u)
|
|
#define __GFP_HIGHMEM ((__force gfp_t)0x02u)
|
|
#define __GFP_DMA32 ((__force gfp_t)0x04u)
|
|
|
|
/*
|
|
* Action modifiers - doesn't change the zoning
|
|
*
|
|
* __GFP_REPEAT: Try hard to allocate the memory, but the allocation attempt
|
|
* _might_ fail. This depends upon the particular VM implementation.
|
|
*
|
|
* __GFP_NOFAIL: The VM implementation _must_ retry infinitely: the caller
|
|
* cannot handle allocation failures.
|
|
*
|
|
* __GFP_NORETRY: The VM implementation must not retry indefinitely.
|
|
*
|
|
* __GFP_MOVABLE: Flag that this page will be movable by the page migration
|
|
* mechanism or reclaimed
|
|
*/
|
|
#define __GFP_WAIT ((__force gfp_t)0x10u) /* Can wait and reschedule? */
|
|
#define __GFP_HIGH ((__force gfp_t)0x20u) /* Should access emergency pools? */
|
|
#define __GFP_IO ((__force gfp_t)0x40u) /* Can start physical IO? */
|
|
#define __GFP_FS ((__force gfp_t)0x80u) /* Can call down to low-level FS? */
|
|
#define __GFP_COLD ((__force gfp_t)0x100u) /* Cache-cold page required */
|
|
#define __GFP_NOWARN ((__force gfp_t)0x200u) /* Suppress page allocation failure warning */
|
|
#define __GFP_REPEAT ((__force gfp_t)0x400u) /* See above */
|
|
#define __GFP_NOFAIL ((__force gfp_t)0x800u) /* See above */
|
|
#define __GFP_NORETRY ((__force gfp_t)0x1000u)/* See above */
|
|
#define __GFP_COMP ((__force gfp_t)0x4000u)/* Add compound page metadata */
|
|
#define __GFP_ZERO ((__force gfp_t)0x8000u)/* Return zeroed page on success */
|
|
#define __GFP_NOMEMALLOC ((__force gfp_t)0x10000u) /* Don't use emergency reserves */
|
|
#define __GFP_HARDWALL ((__force gfp_t)0x20000u) /* Enforce hardwall cpuset memory allocs */
|
|
#define __GFP_THISNODE ((__force gfp_t)0x40000u)/* No fallback, no policies */
|
|
#define __GFP_RECLAIMABLE ((__force gfp_t)0x80000u) /* Page is reclaimable */
|
|
#define __GFP_MOVABLE ((__force gfp_t)0x100000u) /* Page is movable */
|
|
|
|
#define __GFP_BITS_SHIFT 21 /* Room for 21 __GFP_FOO bits */
|
|
#define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1))
|
|
|
|
/* This equals 0, but use constants in case they ever change */
|
|
#define GFP_NOWAIT (GFP_ATOMIC & ~__GFP_HIGH)
|
|
/* GFP_ATOMIC means both !wait (__GFP_WAIT not set) and use emergency pool */
|
|
#define GFP_ATOMIC (__GFP_HIGH)
|
|
#define GFP_NOIO (__GFP_WAIT)
|
|
#define GFP_NOFS (__GFP_WAIT | __GFP_IO)
|
|
#define GFP_KERNEL (__GFP_WAIT | __GFP_IO | __GFP_FS)
|
|
#define GFP_TEMPORARY (__GFP_WAIT | __GFP_IO | __GFP_FS | \
|
|
__GFP_RECLAIMABLE)
|
|
#define GFP_USER (__GFP_WAIT | __GFP_IO | __GFP_FS | __GFP_HARDWALL)
|
|
#define GFP_HIGHUSER (__GFP_WAIT | __GFP_IO | __GFP_FS | __GFP_HARDWALL | \
|
|
__GFP_HIGHMEM)
|
|
#define GFP_HIGHUSER_MOVABLE (__GFP_WAIT | __GFP_IO | __GFP_FS | \
|
|
__GFP_HARDWALL | __GFP_HIGHMEM | \
|
|
__GFP_MOVABLE)
|
|
|
|
#ifdef CONFIG_NUMA
|
|
#define GFP_THISNODE (__GFP_THISNODE | __GFP_NOWARN | __GFP_NORETRY)
|
|
#else
|
|
#define GFP_THISNODE ((__force gfp_t)0)
|
|
#endif
|
|
|
|
/* This mask makes up all the page movable related flags */
|
|
#define GFP_MOVABLE_MASK (__GFP_RECLAIMABLE|__GFP_MOVABLE)
|
|
|
|
/* Control page allocator reclaim behavior */
|
|
#define GFP_RECLAIM_MASK (__GFP_WAIT|__GFP_HIGH|__GFP_IO|__GFP_FS|\
|
|
__GFP_NOWARN|__GFP_REPEAT|__GFP_NOFAIL|\
|
|
__GFP_NORETRY|__GFP_NOMEMALLOC)
|
|
|
|
/* Control slab gfp mask during early boot */
|
|
#define SLAB_GFP_BOOT_MASK __GFP_BITS_MASK & ~(__GFP_WAIT|__GFP_IO|__GFP_FS)
|
|
|
|
/* Control allocation constraints */
|
|
#define GFP_CONSTRAINT_MASK (__GFP_HARDWALL|__GFP_THISNODE)
|
|
|
|
/* Do not use these with a slab allocator */
|
|
#define GFP_SLAB_BUG_MASK (__GFP_DMA32|__GFP_HIGHMEM|~__GFP_BITS_MASK)
|
|
|
|
/* Flag - indicates that the buffer will be suitable for DMA. Ignored on some
|
|
platforms, used as appropriate on others */
|
|
|
|
#define GFP_DMA __GFP_DMA
|
|
|
|
/* 4GB DMA on some platforms */
|
|
#define GFP_DMA32 __GFP_DMA32
|
|
|
|
/* Convert GFP flags to their corresponding migrate type */
|
|
static inline int allocflags_to_migratetype(gfp_t gfp_flags)
|
|
{
|
|
WARN_ON((gfp_flags & GFP_MOVABLE_MASK) == GFP_MOVABLE_MASK);
|
|
|
|
if (unlikely(page_group_by_mobility_disabled))
|
|
return MIGRATE_UNMOVABLE;
|
|
|
|
/* Group based on mobility */
|
|
return (((gfp_flags & __GFP_MOVABLE) != 0) << 1) |
|
|
((gfp_flags & __GFP_RECLAIMABLE) != 0);
|
|
}
|
|
|
|
static inline enum zone_type gfp_zone(gfp_t flags)
|
|
{
|
|
#ifdef CONFIG_ZONE_DMA
|
|
if (flags & __GFP_DMA)
|
|
return ZONE_DMA;
|
|
#endif
|
|
#ifdef CONFIG_ZONE_DMA32
|
|
if (flags & __GFP_DMA32)
|
|
return ZONE_DMA32;
|
|
#endif
|
|
if ((flags & (__GFP_HIGHMEM | __GFP_MOVABLE)) ==
|
|
(__GFP_HIGHMEM | __GFP_MOVABLE))
|
|
return ZONE_MOVABLE;
|
|
#ifdef CONFIG_HIGHMEM
|
|
if (flags & __GFP_HIGHMEM)
|
|
return ZONE_HIGHMEM;
|
|
#endif
|
|
return ZONE_NORMAL;
|
|
}
|
|
|
|
/*
|
|
* There is only one page-allocator function, and two main namespaces to
|
|
* it. The alloc_page*() variants return 'struct page *' and as such
|
|
* can allocate highmem pages, the *get*page*() variants return
|
|
* virtual kernel addresses to the allocated page(s).
|
|
*/
|
|
|
|
static inline int gfp_zonelist(gfp_t flags)
|
|
{
|
|
if (NUMA_BUILD && unlikely(flags & __GFP_THISNODE))
|
|
return 1;
|
|
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* We get the zone list from the current node and the gfp_mask.
|
|
* This zone list contains a maximum of MAXNODES*MAX_NR_ZONES zones.
|
|
* There are two zonelists per node, one for all zones with memory and
|
|
* one containing just zones from the node the zonelist belongs to.
|
|
*
|
|
* For the normal case of non-DISCONTIGMEM systems the NODE_DATA() gets
|
|
* optimized to &contig_page_data at compile-time.
|
|
*/
|
|
static inline struct zonelist *node_zonelist(int nid, gfp_t flags)
|
|
{
|
|
return NODE_DATA(nid)->node_zonelists + gfp_zonelist(flags);
|
|
}
|
|
|
|
#ifndef HAVE_ARCH_FREE_PAGE
|
|
static inline void arch_free_page(struct page *page, int order) { }
|
|
#endif
|
|
#ifndef HAVE_ARCH_ALLOC_PAGE
|
|
static inline void arch_alloc_page(struct page *page, int order) { }
|
|
#endif
|
|
|
|
struct page *
|
|
__alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
|
|
struct zonelist *zonelist, nodemask_t *nodemask);
|
|
|
|
static inline struct page *
|
|
__alloc_pages(gfp_t gfp_mask, unsigned int order,
|
|
struct zonelist *zonelist)
|
|
{
|
|
return __alloc_pages_nodemask(gfp_mask, order, zonelist, NULL);
|
|
}
|
|
|
|
static inline struct page *alloc_pages_node(int nid, gfp_t gfp_mask,
|
|
unsigned int order)
|
|
{
|
|
/* Unknown node is current node */
|
|
if (nid < 0)
|
|
nid = numa_node_id();
|
|
|
|
return __alloc_pages(gfp_mask, order, node_zonelist(nid, gfp_mask));
|
|
}
|
|
|
|
static inline struct page *alloc_pages_exact_node(int nid, gfp_t gfp_mask,
|
|
unsigned int order)
|
|
{
|
|
VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES);
|
|
|
|
return __alloc_pages(gfp_mask, order, node_zonelist(nid, gfp_mask));
|
|
}
|
|
|
|
#ifdef CONFIG_NUMA
|
|
extern struct page *alloc_pages_current(gfp_t gfp_mask, unsigned order);
|
|
|
|
static inline struct page *
|
|
alloc_pages(gfp_t gfp_mask, unsigned int order)
|
|
{
|
|
return alloc_pages_current(gfp_mask, order);
|
|
}
|
|
extern struct page *alloc_page_vma(gfp_t gfp_mask,
|
|
struct vm_area_struct *vma, unsigned long addr);
|
|
#else
|
|
#define alloc_pages(gfp_mask, order) \
|
|
alloc_pages_node(numa_node_id(), gfp_mask, order)
|
|
#define alloc_page_vma(gfp_mask, vma, addr) alloc_pages(gfp_mask, 0)
|
|
#endif
|
|
#define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0)
|
|
|
|
extern unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order);
|
|
extern unsigned long get_zeroed_page(gfp_t gfp_mask);
|
|
|
|
void *alloc_pages_exact(size_t size, gfp_t gfp_mask);
|
|
void free_pages_exact(void *virt, size_t size);
|
|
|
|
#define __get_free_page(gfp_mask) \
|
|
__get_free_pages((gfp_mask),0)
|
|
|
|
#define __get_dma_pages(gfp_mask, order) \
|
|
__get_free_pages((gfp_mask) | GFP_DMA,(order))
|
|
|
|
extern void __free_pages(struct page *page, unsigned int order);
|
|
extern void free_pages(unsigned long addr, unsigned int order);
|
|
extern void free_hot_page(struct page *page);
|
|
extern void free_cold_page(struct page *page);
|
|
|
|
#define __free_page(page) __free_pages((page), 0)
|
|
#define free_page(addr) free_pages((addr),0)
|
|
|
|
void page_alloc_init(void);
|
|
void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp);
|
|
void drain_all_pages(void);
|
|
void drain_local_pages(void *dummy);
|
|
|
|
extern bool oom_killer_disabled;
|
|
|
|
static inline void oom_killer_disable(void)
|
|
{
|
|
oom_killer_disabled = true;
|
|
}
|
|
|
|
static inline void oom_killer_enable(void)
|
|
{
|
|
oom_killer_disabled = false;
|
|
}
|
|
|
|
#endif /* __LINUX_GFP_H */
|