#include <linux/mmzone.h>
#include <linux/stddef.h>
#include <linux/linkage.h>
-#include <linux/config.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.
*/
-/* Zone modifiers in GFP_ZONEMASK (see linux/mmzone.h - low two bits) */
#define __GFP_DMA ((__force gfp_t)0x01u)
#define __GFP_HIGHMEM ((__force gfp_t)0x02u)
-
+#define __GFP_DMA32 ((__force gfp_t)0x04u)
+#define __GFP_MOVABLE ((__force gfp_t)0x08u) /* Page is movable */
+#define GFP_ZONEMASK (__GFP_DMA|__GFP_HIGHMEM|__GFP_DMA32|__GFP_MOVABLE)
/*
* Action modifiers - doesn't change the zoning
*
* 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_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) /* Retry the allocation. Might fail */
-#define __GFP_NOFAIL ((__force gfp_t)0x800u) /* Retry for ever. Cannot fail */
-#define __GFP_NORETRY ((__force gfp_t)0x1000u)/* Do not retry. Might fail */
-#define __GFP_NO_GROW ((__force gfp_t)0x2000u)/* Slab internal usage */
+#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_NORECLAIM ((__force gfp_t)0x20000u) /* No realy zone reclaim during allocation */
-#define __GFP_HARDWALL ((__force gfp_t)0x40000u) /* Enforce hardwall cpuset memory allocs */
+#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_BITS_SHIFT 20 /* Room for 20 __GFP_FOO bits */
-#define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1))
+#ifdef CONFIG_KMEMCHECK
+#define __GFP_NOTRACK ((__force gfp_t)0x200000u) /* Don't track with kmemcheck */
+#else
+#define __GFP_NOTRACK ((__force gfp_t)0)
+#endif
+
+/*
+ * This may seem redundant, but it's a way of annotating false positives vs.
+ * allocations that simply cannot be supported (e.g. page tables).
+ */
+#define __GFP_NOTRACK_FALSE_POSITIVE (__GFP_NOTRACK)
-/* if you forget to add the bitmask here kernel will crash, period */
-#define GFP_LEVEL_MASK (__GFP_WAIT|__GFP_HIGH|__GFP_IO|__GFP_FS| \
- __GFP_COLD|__GFP_NOWARN|__GFP_REPEAT| \
- __GFP_NOFAIL|__GFP_NORETRY|__GFP_NO_GROW|__GFP_COMP| \
- __GFP_NOMEMALLOC|__GFP_NORECLAIM|__GFP_HARDWALL)
+#define __GFP_BITS_SHIFT 22 /* Room for 22 __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 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
-#define gfp_zone(mask) ((__force int)((mask) & (__force gfp_t)GFP_ZONEMASK))
+/* 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);
+}
+
+#ifdef CONFIG_HIGHMEM
+#define OPT_ZONE_HIGHMEM ZONE_HIGHMEM
+#else
+#define OPT_ZONE_HIGHMEM ZONE_NORMAL
+#endif
+
+#ifdef CONFIG_ZONE_DMA
+#define OPT_ZONE_DMA ZONE_DMA
+#else
+#define OPT_ZONE_DMA ZONE_NORMAL
+#endif
+
+#ifdef CONFIG_ZONE_DMA32
+#define OPT_ZONE_DMA32 ZONE_DMA32
+#else
+#define OPT_ZONE_DMA32 ZONE_NORMAL
+#endif
+
+/*
+ * GFP_ZONE_TABLE is a word size bitstring that is used for looking up the
+ * zone to use given the lowest 4 bits of gfp_t. Entries are ZONE_SHIFT long
+ * and there are 16 of them to cover all possible combinations of
+ * __GFP_DMA, __GFP_DMA32, __GFP_MOVABLE and __GFP_HIGHMEM
+ *
+ * The zone fallback order is MOVABLE=>HIGHMEM=>NORMAL=>DMA32=>DMA.
+ * But GFP_MOVABLE is not only a zone specifier but also an allocation
+ * policy. Therefore __GFP_MOVABLE plus another zone selector is valid.
+ * Only 1bit of the lowest 3 bit (DMA,DMA32,HIGHMEM) can be set to "1".
+ *
+ * bit result
+ * =================
+ * 0x0 => NORMAL
+ * 0x1 => DMA or NORMAL
+ * 0x2 => HIGHMEM or NORMAL
+ * 0x3 => BAD (DMA+HIGHMEM)
+ * 0x4 => DMA32 or DMA or NORMAL
+ * 0x5 => BAD (DMA+DMA32)
+ * 0x6 => BAD (HIGHMEM+DMA32)
+ * 0x7 => BAD (HIGHMEM+DMA32+DMA)
+ * 0x8 => NORMAL (MOVABLE+0)
+ * 0x9 => DMA or NORMAL (MOVABLE+DMA)
+ * 0xa => MOVABLE (Movable is valid only if HIGHMEM is set too)
+ * 0xb => BAD (MOVABLE+HIGHMEM+DMA)
+ * 0xc => DMA32 (MOVABLE+HIGHMEM+DMA32)
+ * 0xd => BAD (MOVABLE+DMA32+DMA)
+ * 0xe => BAD (MOVABLE+DMA32+HIGHMEM)
+ * 0xf => BAD (MOVABLE+DMA32+HIGHMEM+DMA)
+ *
+ * ZONES_SHIFT must be <= 2 on 32 bit platforms.
+ */
+
+#if 16 * ZONES_SHIFT > BITS_PER_LONG
+#error ZONES_SHIFT too large to create GFP_ZONE_TABLE integer
+#endif
+
+#define GFP_ZONE_TABLE ( \
+ (ZONE_NORMAL << 0 * ZONES_SHIFT) \
+ | (OPT_ZONE_DMA << __GFP_DMA * ZONES_SHIFT) \
+ | (OPT_ZONE_HIGHMEM << __GFP_HIGHMEM * ZONES_SHIFT) \
+ | (OPT_ZONE_DMA32 << __GFP_DMA32 * ZONES_SHIFT) \
+ | (ZONE_NORMAL << __GFP_MOVABLE * ZONES_SHIFT) \
+ | (OPT_ZONE_DMA << (__GFP_MOVABLE | __GFP_DMA) * ZONES_SHIFT) \
+ | (ZONE_MOVABLE << (__GFP_MOVABLE | __GFP_HIGHMEM) * ZONES_SHIFT)\
+ | (OPT_ZONE_DMA32 << (__GFP_MOVABLE | __GFP_DMA32) * ZONES_SHIFT)\
+)
+
+/*
+ * GFP_ZONE_BAD is a bitmap for all combination of __GFP_DMA, __GFP_DMA32
+ * __GFP_HIGHMEM and __GFP_MOVABLE that are not permitted. One flag per
+ * entry starting with bit 0. Bit is set if the combination is not
+ * allowed.
+ */
+#define GFP_ZONE_BAD ( \
+ 1 << (__GFP_DMA | __GFP_HIGHMEM) \
+ | 1 << (__GFP_DMA | __GFP_DMA32) \
+ | 1 << (__GFP_DMA32 | __GFP_HIGHMEM) \
+ | 1 << (__GFP_DMA | __GFP_DMA32 | __GFP_HIGHMEM) \
+ | 1 << (__GFP_MOVABLE | __GFP_HIGHMEM | __GFP_DMA) \
+ | 1 << (__GFP_MOVABLE | __GFP_DMA32 | __GFP_DMA) \
+ | 1 << (__GFP_MOVABLE | __GFP_DMA32 | __GFP_HIGHMEM) \
+ | 1 << (__GFP_MOVABLE | __GFP_DMA32 | __GFP_DMA | __GFP_HIGHMEM)\
+)
+
+static inline enum zone_type gfp_zone(gfp_t flags)
+{
+ enum zone_type z;
+ int bit = flags & GFP_ZONEMASK;
+
+ z = (GFP_ZONE_TABLE >> (bit * ZONES_SHIFT)) &
+ ((1 << ZONES_SHIFT) - 1);
+
+ if (__builtin_constant_p(bit))
+ MAYBE_BUILD_BUG_ON((GFP_ZONE_BAD >> bit) & 1);
+ else {
+#ifdef CONFIG_DEBUG_VM
+ BUG_ON((GFP_ZONE_BAD >> bit) & 1);
+#endif
+ }
+ return z;
+}
/*
* There is only one page-allocator function, and two main namespaces to
* 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);
-extern struct page *
-FASTCALL(__alloc_pages(gfp_t, unsigned int, struct zonelist *));
+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)
{
- if (unlikely(order >= MAX_ORDER))
- return NULL;
+ /* 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_DATA(nid)->node_zonelists + gfp_zone(gfp_mask));
+ return __alloc_pages(gfp_mask, order, node_zonelist(nid, gfp_mask));
}
#ifdef CONFIG_NUMA
static inline struct page *
alloc_pages(gfp_t gfp_mask, unsigned int order)
{
- if (unlikely(order >= MAX_ORDER))
- return NULL;
-
return alloc_pages_current(gfp_mask, order);
}
extern struct page *alloc_page_vma(gfp_t gfp_mask,
#endif
#define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0)
-extern unsigned long FASTCALL(__get_free_pages(gfp_t gfp_mask, unsigned int order));
-extern unsigned long FASTCALL(get_zeroed_page(gfp_t gfp_mask));
+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 FASTCALL(__free_pages(struct page *page, unsigned int order));
-extern void FASTCALL(free_pages(unsigned long addr, unsigned int order));
-extern void FASTCALL(free_hot_page(struct page *page));
-extern void FASTCALL(free_cold_page(struct page *page));
+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);
#define __free_page(page) __free_pages((page), 0)
#define free_page(addr) free_pages((addr),0)
void page_alloc_init(void);
-#ifdef CONFIG_NUMA
-void drain_remote_pages(void);
-#else
-static inline void drain_remote_pages(void) { };
-#endif
+void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp);
+void drain_all_pages(void);
+void drain_local_pages(void *dummy);
+
+extern gfp_t gfp_allowed_mask;
+
+static inline void set_gfp_allowed_mask(gfp_t mask)
+{
+ gfp_allowed_mask = mask;
+}
#endif /* __LINUX_GFP_H */
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff