kernel-fxtec-pro1x/include/linux/gfp.h

346 lines
12 KiB
C
Raw Normal View History

#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 them 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)
#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
*
* __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. This modifier is deprecated and no new
* users should be added.
*
* __GFP_NORETRY: The VM implementation must not retry indefinitely.
Add __GFP_MOVABLE for callers to flag allocations from high memory that may be migrated It is often known at allocation time whether a page may be migrated or not. This patch adds a flag called __GFP_MOVABLE and a new mask called GFP_HIGH_MOVABLE. Allocations using the __GFP_MOVABLE can be either migrated using the page migration mechanism or reclaimed by syncing with backing storage and discarding. An API function very similar to alloc_zeroed_user_highpage() is added for __GFP_MOVABLE allocations called alloc_zeroed_user_highpage_movable(). The flags used by alloc_zeroed_user_highpage() are not changed because it would change the semantics of an existing API. After this patch is applied there are no in-kernel users of alloc_zeroed_user_highpage() so it probably should be marked deprecated if this patch is merged. Note that this patch includes a minor cleanup to the use of __GFP_ZERO in shmem.c to keep all flag modifications to inode->mapping in the shmem_dir_alloc() helper function. This clean-up suggestion is courtesy of Hugh Dickens. Additional credit goes to Christoph Lameter and Linus Torvalds for shaping the concept. Credit to Hugh Dickens for catching issues with shmem swap vector and ramfs allocations. [akpm@linux-foundation.org: build fix] [hugh@veritas.com: __GFP_ZERO cleanup] Signed-off-by: Mel Gorman <mel@csn.ul.ie> Cc: Andy Whitcroft <apw@shadowen.org> Cc: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-17 05:03:05 -06:00
*
* __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 */
#ifdef CONFIG_KMEMCHECK
2008-05-31 07:56:17 -06:00
#define __GFP_NOTRACK ((__force gfp_t)0x200000u) /* Don't track with kmemcheck */
#else
#define __GFP_NOTRACK ((__force gfp_t)0)
#endif
2008-05-31 07:56:17 -06:00
/*
* 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)
#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)
Add __GFP_MOVABLE for callers to flag allocations from high memory that may be migrated It is often known at allocation time whether a page may be migrated or not. This patch adds a flag called __GFP_MOVABLE and a new mask called GFP_HIGH_MOVABLE. Allocations using the __GFP_MOVABLE can be either migrated using the page migration mechanism or reclaimed by syncing with backing storage and discarding. An API function very similar to alloc_zeroed_user_highpage() is added for __GFP_MOVABLE allocations called alloc_zeroed_user_highpage_movable(). The flags used by alloc_zeroed_user_highpage() are not changed because it would change the semantics of an existing API. After this patch is applied there are no in-kernel users of alloc_zeroed_user_highpage() so it probably should be marked deprecated if this patch is merged. Note that this patch includes a minor cleanup to the use of __GFP_ZERO in shmem.c to keep all flag modifications to inode->mapping in the shmem_dir_alloc() helper function. This clean-up suggestion is courtesy of Hugh Dickens. Additional credit goes to Christoph Lameter and Linus Torvalds for shaping the concept. Credit to Hugh Dickens for catching issues with shmem swap vector and ramfs allocations. [akpm@linux-foundation.org: build fix] [hugh@veritas.com: __GFP_ZERO cleanup] Signed-off-by: Mel Gorman <mel@csn.ul.ie> Cc: Andy Whitcroft <apw@shadowen.org> Cc: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-17 05:03:05 -06:00
#define GFP_HIGHUSER_MOVABLE (__GFP_WAIT | __GFP_IO | __GFP_FS | \
__GFP_HARDWALL | __GFP_HIGHMEM | \
__GFP_MOVABLE)
#define GFP_IOFS (__GFP_IO | __GFP_FS)
#ifdef CONFIG_NUMA
#define GFP_THISNODE (__GFP_THISNODE | __GFP_NOWARN | __GFP_NORETRY)
#else
#define GFP_THISNODE ((__force gfp_t)0)
#endif
Categorize GFP flags The function of GFP_LEVEL_MASK seems to be unclear. In order to clear up the mystery we get rid of it and replace GFP_LEVEL_MASK with 3 sets of GFP flags: GFP_RECLAIM_MASK Flags used to control page allocator reclaim behavior. GFP_CONSTRAINT_MASK Flags used to limit where allocations can occur. GFP_SLAB_BUG_MASK Flags that the slab allocator BUG()s on. These replace the uses of GFP_LEVEL mask in the slab allocators and in vmalloc.c. The use of the flags not included in these sets may occur as a result of a slab allocation standing in for a page allocation when constructing scatter gather lists. Extraneous flags are cleared and not passed through to the page allocator. __GFP_MOVABLE/RECLAIMABLE, __GFP_COLD and __GFP_COMP will now be ignored if passed to a slab allocator. Change the allocation of allocator meta data in SLAB and vmalloc to not pass through flags listed in GFP_CONSTRAINT_MASK. SLAB already removes the __GFP_THISNODE flag for such allocations. Generalize that to also cover vmalloc. The use of GFP_CONSTRAINT_MASK also includes __GFP_HARDWALL. The impact of allocator metadata placement on access latency to the cachelines of the object itself is minimal since metadata is only referenced on alloc and free. The attempt is still made to place the meta data optimally but we consistently allow fallback both in SLAB and vmalloc (SLUB does not need to allocate metadata like that). Allocator metadata may serve multiple in kernel users and thus should not be subject to the limitations arising from a single allocation context. [akpm@linux-foundation.org: fix fallback_alloc()] Signed-off-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 02:25:41 -06:00
/* This mask makes up all the page movable related flags */
#define GFP_MOVABLE_MASK (__GFP_RECLAIMABLE|__GFP_MOVABLE)
Categorize GFP flags The function of GFP_LEVEL_MASK seems to be unclear. In order to clear up the mystery we get rid of it and replace GFP_LEVEL_MASK with 3 sets of GFP flags: GFP_RECLAIM_MASK Flags used to control page allocator reclaim behavior. GFP_CONSTRAINT_MASK Flags used to limit where allocations can occur. GFP_SLAB_BUG_MASK Flags that the slab allocator BUG()s on. These replace the uses of GFP_LEVEL mask in the slab allocators and in vmalloc.c. The use of the flags not included in these sets may occur as a result of a slab allocation standing in for a page allocation when constructing scatter gather lists. Extraneous flags are cleared and not passed through to the page allocator. __GFP_MOVABLE/RECLAIMABLE, __GFP_COLD and __GFP_COMP will now be ignored if passed to a slab allocator. Change the allocation of allocator meta data in SLAB and vmalloc to not pass through flags listed in GFP_CONSTRAINT_MASK. SLAB already removes the __GFP_THISNODE flag for such allocations. Generalize that to also cover vmalloc. The use of GFP_CONSTRAINT_MASK also includes __GFP_HARDWALL. The impact of allocator metadata placement on access latency to the cachelines of the object itself is minimal since metadata is only referenced on alloc and free. The attempt is still made to place the meta data optimally but we consistently allow fallback both in SLAB and vmalloc (SLUB does not need to allocate metadata like that). Allocator metadata may serve multiple in kernel users and thus should not be subject to the limitations arising from a single allocation context. [akpm@linux-foundation.org: fix fallback_alloc()] Signed-off-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 02:25:41 -06:00
/* 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))
Categorize GFP flags The function of GFP_LEVEL_MASK seems to be unclear. In order to clear up the mystery we get rid of it and replace GFP_LEVEL_MASK with 3 sets of GFP flags: GFP_RECLAIM_MASK Flags used to control page allocator reclaim behavior. GFP_CONSTRAINT_MASK Flags used to limit where allocations can occur. GFP_SLAB_BUG_MASK Flags that the slab allocator BUG()s on. These replace the uses of GFP_LEVEL mask in the slab allocators and in vmalloc.c. The use of the flags not included in these sets may occur as a result of a slab allocation standing in for a page allocation when constructing scatter gather lists. Extraneous flags are cleared and not passed through to the page allocator. __GFP_MOVABLE/RECLAIMABLE, __GFP_COLD and __GFP_COMP will now be ignored if passed to a slab allocator. Change the allocation of allocator meta data in SLAB and vmalloc to not pass through flags listed in GFP_CONSTRAINT_MASK. SLAB already removes the __GFP_THISNODE flag for such allocations. Generalize that to also cover vmalloc. The use of GFP_CONSTRAINT_MASK also includes __GFP_HARDWALL. The impact of allocator metadata placement on access latency to the cachelines of the object itself is minimal since metadata is only referenced on alloc and free. The attempt is still made to place the meta data optimally but we consistently allow fallback both in SLAB and vmalloc (SLUB does not need to allocate metadata like that). Allocator metadata may serve multiple in kernel users and thus should not be subject to the limitations arising from a single allocation context. [akpm@linux-foundation.org: fix fallback_alloc()] Signed-off-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 02:25:41 -06:00
/* 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
[PATCH] x86_64: Add 4GB DMA32 zone Add a new 4GB GFP_DMA32 zone between the GFP_DMA and GFP_NORMAL zones. As a bit of historical background: when the x86-64 port was originally designed we had some discussion if we should use a 16MB DMA zone like i386 or a 4GB DMA zone like IA64 or both. Both was ruled out at this point because it was in early 2.4 when VM is still quite shakey and had bad troubles even dealing with one DMA zone. We settled on the 16MB DMA zone mainly because we worried about older soundcards and the floppy. But this has always caused problems since then because device drivers had trouble getting enough DMA able memory. These days the VM works much better and the wide use of NUMA has proven it can deal with many zones successfully. So this patch adds both zones. This helps drivers who need a lot of memory below 4GB because their hardware is not accessing more (graphic drivers - proprietary and free ones, video frame buffer drivers, sound drivers etc.). Previously they could only use IOMMU+16MB GFP_DMA, which was not enough memory. Another common problem is that hardware who has full memory addressing for >4GB misses it for some control structures in memory (like transmit rings or other metadata). They tended to allocate memory in the 16MB GFP_DMA or the IOMMU/swiotlb then using pci_alloc_consistent, but that can tie up a lot of precious 16MB GFPDMA/IOMMU/swiotlb memory (even on AMD systems the IOMMU tends to be quite small) especially if you have many devices. With the new zone pci_alloc_consistent can just put this stuff into memory below 4GB which works better. One argument was still if the zone should be 4GB or 2GB. The main motivation for 2GB would be an unnamed not so unpopular hardware raid controller (mostly found in older machines from a particular four letter company) who has a strange 2GB restriction in firmware. But that one works ok with swiotlb/IOMMU anyways, so it doesn't really need GFP_DMA32. I chose 4GB to be compatible with IA64 and because it seems to be the most common restriction. The new zone is so far added only for x86-64. For other architectures who don't set up this new zone nothing changes. Architectures can set a compatibility define in Kconfig CONFIG_DMA_IS_DMA32 that will define GFP_DMA32 as GFP_DMA. Otherwise it's a nop because on 32bit architectures it's normally not needed because GFP_NORMAL (=0) is DMA able enough. One problem is still that GFP_DMA means different things on different architectures. e.g. some drivers used to have #ifdef ia64 use GFP_DMA (trusting it to be 4GB) #elif __x86_64__ (use other hacks like the swiotlb because 16MB is not enough) ... . This was quite ugly and is now obsolete. These should be now converted to use GFP_DMA32 unconditionally. I haven't done this yet. Or best only use pci_alloc_consistent/dma_alloc_coherent which will use GFP_DMA32 transparently. Signed-off-by: Andi Kleen <ak@suse.de> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-11-05 09:25:53 -07:00
/* 4GB DMA on some platforms */
#define GFP_DMA32 __GFP_DMA32
Print out statistics in relation to fragmentation avoidance to /proc/pagetypeinfo This patch provides fragmentation avoidance statistics via /proc/pagetypeinfo. The information is collected only on request so there is no runtime overhead. The statistics are in three parts: The first part prints information on the size of blocks that pages are being grouped on and looks like Page block order: 10 Pages per block: 1024 The second part is a more detailed version of /proc/buddyinfo and looks like Free pages count per migrate type at order 0 1 2 3 4 5 6 7 8 9 10 Node 0, zone DMA, type Unmovable 0 0 0 0 0 0 0 0 0 0 0 Node 0, zone DMA, type Reclaimable 1 0 0 0 0 0 0 0 0 0 0 Node 0, zone DMA, type Movable 0 0 0 0 0 0 0 0 0 0 0 Node 0, zone DMA, type Reserve 0 4 4 0 0 0 0 1 0 1 0 Node 0, zone Normal, type Unmovable 111 8 4 4 2 3 1 0 0 0 0 Node 0, zone Normal, type Reclaimable 293 89 8 0 0 0 0 0 0 0 0 Node 0, zone Normal, type Movable 1 6 13 9 7 6 3 0 0 0 0 Node 0, zone Normal, type Reserve 0 0 0 0 0 0 0 0 0 0 4 The third part looks like Number of blocks type Unmovable Reclaimable Movable Reserve Node 0, zone DMA 0 1 2 1 Node 0, zone Normal 3 17 94 4 To walk the zones within a node with interrupts disabled, walk_zones_in_node() is introduced and shared between /proc/buddyinfo, /proc/zoneinfo and /proc/pagetypeinfo to reduce code duplication. It seems specific to what vmstat.c requires but could be broken out as a general utility function in mmzone.c if there were other other potential users. Signed-off-by: Mel Gorman <mel@csn.ul.ie> Acked-by: Andy Whitcroft <apw@shadowen.org> Acked-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 02:26:02 -06:00
/* 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);
}
[PATCH] x86_64: Add 4GB DMA32 zone Add a new 4GB GFP_DMA32 zone between the GFP_DMA and GFP_NORMAL zones. As a bit of historical background: when the x86-64 port was originally designed we had some discussion if we should use a 16MB DMA zone like i386 or a 4GB DMA zone like IA64 or both. Both was ruled out at this point because it was in early 2.4 when VM is still quite shakey and had bad troubles even dealing with one DMA zone. We settled on the 16MB DMA zone mainly because we worried about older soundcards and the floppy. But this has always caused problems since then because device drivers had trouble getting enough DMA able memory. These days the VM works much better and the wide use of NUMA has proven it can deal with many zones successfully. So this patch adds both zones. This helps drivers who need a lot of memory below 4GB because their hardware is not accessing more (graphic drivers - proprietary and free ones, video frame buffer drivers, sound drivers etc.). Previously they could only use IOMMU+16MB GFP_DMA, which was not enough memory. Another common problem is that hardware who has full memory addressing for >4GB misses it for some control structures in memory (like transmit rings or other metadata). They tended to allocate memory in the 16MB GFP_DMA or the IOMMU/swiotlb then using pci_alloc_consistent, but that can tie up a lot of precious 16MB GFPDMA/IOMMU/swiotlb memory (even on AMD systems the IOMMU tends to be quite small) especially if you have many devices. With the new zone pci_alloc_consistent can just put this stuff into memory below 4GB which works better. One argument was still if the zone should be 4GB or 2GB. The main motivation for 2GB would be an unnamed not so unpopular hardware raid controller (mostly found in older machines from a particular four letter company) who has a strange 2GB restriction in firmware. But that one works ok with swiotlb/IOMMU anyways, so it doesn't really need GFP_DMA32. I chose 4GB to be compatible with IA64 and because it seems to be the most common restriction. The new zone is so far added only for x86-64. For other architectures who don't set up this new zone nothing changes. Architectures can set a compatibility define in Kconfig CONFIG_DMA_IS_DMA32 that will define GFP_DMA32 as GFP_DMA. Otherwise it's a nop because on 32bit architectures it's normally not needed because GFP_NORMAL (=0) is DMA able enough. One problem is still that GFP_DMA means different things on different architectures. e.g. some drivers used to have #ifdef ia64 use GFP_DMA (trusting it to be 4GB) #elif __x86_64__ (use other hacks like the swiotlb because 16MB is not enough) ... . This was quite ugly and is now obsolete. These should be now converted to use GFP_DMA32 unconditionally. I haven't done this yet. Or best only use pci_alloc_consistent/dma_alloc_coherent which will use GFP_DMA32 transparently. Signed-off-by: Andi Kleen <ak@suse.de> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-11-05 09:25:53 -07:00
#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
[PATCH] mempolicies: fix policy_zone check There is a check in zonelist_policy that compares pieces of the bitmap obtained from a gfp mask via GFP_ZONETYPES with a zone number in function zonelist_policy(). The bitmap is an ORed mask of __GFP_DMA, __GFP_DMA32 and __GFP_HIGHMEM. The policy_zone is a zone number with the possible values of ZONE_DMA, ZONE_DMA32, ZONE_HIGHMEM and ZONE_NORMAL. These are two different domains of values. For some reason seemed to work before the zone reduction patchset (It definitely works on SGI boxes since we just have one zone and the check cannot fail). With the zone reduction patchset this check definitely fails on systems with two zones if the system actually has memory in both zones. This is because ZONE_NORMAL is selected using no __GFP flag at all and thus gfp_zone(gfpmask) == 0. ZONE_DMA is selected when __GFP_DMA is set. __GFP_DMA is 0x01. So gfp_zone(gfpmask) == 1. policy_zone is set to ZONE_NORMAL (==1) if ZONE_NORMAL and ZONE_DMA are populated. For ZONE_NORMAL gfp_zone(<no _GFP_DMA>) yields 0 which is < policy_zone(ZONE_NORMAL) and so policy is not applied to regular memory allocations! Instead gfp_zone(__GFP_DMA) == 1 which results in policy being applied to DMA allocations! What we realy want in that place is to establish the highest allowable zone for a given gfp_mask. If the highest zone is higher or equal to the policy_zone then memory policies need to be applied. We have such a highest_zone() function in page_alloc.c. So move the highest_zone() function from mm/page_alloc.c into include/linux/gfp.h. On the way we simplify the function and use the new zone_type that was also introduced with the zone reduction patchset plus we also specify the right type for the gfp flags parameter. Signed-off-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Lee Schermerhorn <Lee.Schermerhorn@hp.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-09-26 00:31:17 -06:00
#ifdef CONFIG_ZONE_DMA32
#define OPT_ZONE_DMA32 ZONE_DMA32
#else
#define OPT_ZONE_DMA32 ZONE_NORMAL
[PATCH] mempolicies: fix policy_zone check There is a check in zonelist_policy that compares pieces of the bitmap obtained from a gfp mask via GFP_ZONETYPES with a zone number in function zonelist_policy(). The bitmap is an ORed mask of __GFP_DMA, __GFP_DMA32 and __GFP_HIGHMEM. The policy_zone is a zone number with the possible values of ZONE_DMA, ZONE_DMA32, ZONE_HIGHMEM and ZONE_NORMAL. These are two different domains of values. For some reason seemed to work before the zone reduction patchset (It definitely works on SGI boxes since we just have one zone and the check cannot fail). With the zone reduction patchset this check definitely fails on systems with two zones if the system actually has memory in both zones. This is because ZONE_NORMAL is selected using no __GFP flag at all and thus gfp_zone(gfpmask) == 0. ZONE_DMA is selected when __GFP_DMA is set. __GFP_DMA is 0x01. So gfp_zone(gfpmask) == 1. policy_zone is set to ZONE_NORMAL (==1) if ZONE_NORMAL and ZONE_DMA are populated. For ZONE_NORMAL gfp_zone(<no _GFP_DMA>) yields 0 which is < policy_zone(ZONE_NORMAL) and so policy is not applied to regular memory allocations! Instead gfp_zone(__GFP_DMA) == 1 which results in policy being applied to DMA allocations! What we realy want in that place is to establish the highest allowable zone for a given gfp_mask. If the highest zone is higher or equal to the policy_zone then memory policies need to be applied. We have such a highest_zone() function in page_alloc.c. So move the highest_zone() function from mm/page_alloc.c into include/linux/gfp.h. On the way we simplify the function and use the new zone_type that was also introduced with the zone reduction patchset plus we also specify the right type for the gfp flags parameter. Signed-off-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Lee Schermerhorn <Lee.Schermerhorn@hp.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-09-26 00:31:17 -06:00
#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 1 bit of the lowest 3 bits (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 combinations 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);
[PATCH] mempolicies: fix policy_zone check There is a check in zonelist_policy that compares pieces of the bitmap obtained from a gfp mask via GFP_ZONETYPES with a zone number in function zonelist_policy(). The bitmap is an ORed mask of __GFP_DMA, __GFP_DMA32 and __GFP_HIGHMEM. The policy_zone is a zone number with the possible values of ZONE_DMA, ZONE_DMA32, ZONE_HIGHMEM and ZONE_NORMAL. These are two different domains of values. For some reason seemed to work before the zone reduction patchset (It definitely works on SGI boxes since we just have one zone and the check cannot fail). With the zone reduction patchset this check definitely fails on systems with two zones if the system actually has memory in both zones. This is because ZONE_NORMAL is selected using no __GFP flag at all and thus gfp_zone(gfpmask) == 0. ZONE_DMA is selected when __GFP_DMA is set. __GFP_DMA is 0x01. So gfp_zone(gfpmask) == 1. policy_zone is set to ZONE_NORMAL (==1) if ZONE_NORMAL and ZONE_DMA are populated. For ZONE_NORMAL gfp_zone(<no _GFP_DMA>) yields 0 which is < policy_zone(ZONE_NORMAL) and so policy is not applied to regular memory allocations! Instead gfp_zone(__GFP_DMA) == 1 which results in policy being applied to DMA allocations! What we realy want in that place is to establish the highest allowable zone for a given gfp_mask. If the highest zone is higher or equal to the policy_zone then memory policies need to be applied. We have such a highest_zone() function in page_alloc.c. So move the highest_zone() function from mm/page_alloc.c into include/linux/gfp.h. On the way we simplify the function and use the new zone_type that was also introduced with the zone reduction patchset plus we also specify the right type for the gfp flags parameter. Signed-off-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Lee Schermerhorn <Lee.Schermerhorn@hp.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-09-26 00:31:17 -06:00
#endif
}
return z;
[PATCH] mempolicies: fix policy_zone check There is a check in zonelist_policy that compares pieces of the bitmap obtained from a gfp mask via GFP_ZONETYPES with a zone number in function zonelist_policy(). The bitmap is an ORed mask of __GFP_DMA, __GFP_DMA32 and __GFP_HIGHMEM. The policy_zone is a zone number with the possible values of ZONE_DMA, ZONE_DMA32, ZONE_HIGHMEM and ZONE_NORMAL. These are two different domains of values. For some reason seemed to work before the zone reduction patchset (It definitely works on SGI boxes since we just have one zone and the check cannot fail). With the zone reduction patchset this check definitely fails on systems with two zones if the system actually has memory in both zones. This is because ZONE_NORMAL is selected using no __GFP flag at all and thus gfp_zone(gfpmask) == 0. ZONE_DMA is selected when __GFP_DMA is set. __GFP_DMA is 0x01. So gfp_zone(gfpmask) == 1. policy_zone is set to ZONE_NORMAL (==1) if ZONE_NORMAL and ZONE_DMA are populated. For ZONE_NORMAL gfp_zone(<no _GFP_DMA>) yields 0 which is < policy_zone(ZONE_NORMAL) and so policy is not applied to regular memory allocations! Instead gfp_zone(__GFP_DMA) == 1 which results in policy being applied to DMA allocations! What we realy want in that place is to establish the highest allowable zone for a given gfp_mask. If the highest zone is higher or equal to the policy_zone then memory policies need to be applied. We have such a highest_zone() function in page_alloc.c. So move the highest_zone() function from mm/page_alloc.c into include/linux/gfp.h. On the way we simplify the function and use the new zone_type that was also introduced with the zone reduction patchset plus we also specify the right type for the gfp flags parameter. Signed-off-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Lee Schermerhorn <Lee.Schermerhorn@hp.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-09-26 00:31:17 -06:00
}
/*
* 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 *
page allocator: replace __alloc_pages_internal() with __alloc_pages_nodemask() The start of a large patch series to clean up and optimise the page allocator. The performance improvements are in a wide range depending on the exact machine but the results I've seen so fair are approximately; kernbench: 0 to 0.12% (elapsed time) 0.49% to 3.20% (sys time) aim9: -4% to 30% (for page_test and brk_test) tbench: -1% to 4% hackbench: -2.5% to 3.45% (mostly within the noise though) netperf-udp -1.34% to 4.06% (varies between machines a bit) netperf-tcp -0.44% to 5.22% (varies between machines a bit) I haven't sysbench figures at hand, but previously they were within the -0.5% to 2% range. On netperf, the client and server were bound to opposite number CPUs to maximise the problems with cache line bouncing of the struct pages so I expect different people to report different results for netperf depending on their exact machine and how they ran the test (different machines, same cpus client/server, shared cache but two threads client/server, different socket client/server etc). I also measured the vmlinux sizes for a single x86-based config with CONFIG_DEBUG_INFO enabled but not CONFIG_DEBUG_VM. The core of the .config is based on the Debian Lenny kernel config so I expect it to be reasonably typical. This patch: __alloc_pages_internal is the core page allocator function but essentially it is an alias of __alloc_pages_nodemask. Naming a publicly available and exported function "internal" is also a big ugly. This patch renames __alloc_pages_internal() to __alloc_pages_nodemask() and deletes the old nodemask function. Warning - This patch renames an exported symbol. No kernel driver is affected by external drivers calling __alloc_pages_internal() should change the call to __alloc_pages_nodemask() without any alteration of parameters. Signed-off-by: Mel Gorman <mel@csn.ul.ie> Reviewed-by: Christoph Lameter <cl@linux-foundation.org> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Reviewed-by: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-16 16:31:52 -06:00
__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)
{
page allocator: replace __alloc_pages_internal() with __alloc_pages_nodemask() The start of a large patch series to clean up and optimise the page allocator. The performance improvements are in a wide range depending on the exact machine but the results I've seen so fair are approximately; kernbench: 0 to 0.12% (elapsed time) 0.49% to 3.20% (sys time) aim9: -4% to 30% (for page_test and brk_test) tbench: -1% to 4% hackbench: -2.5% to 3.45% (mostly within the noise though) netperf-udp -1.34% to 4.06% (varies between machines a bit) netperf-tcp -0.44% to 5.22% (varies between machines a bit) I haven't sysbench figures at hand, but previously they were within the -0.5% to 2% range. On netperf, the client and server were bound to opposite number CPUs to maximise the problems with cache line bouncing of the struct pages so I expect different people to report different results for netperf depending on their exact machine and how they ran the test (different machines, same cpus client/server, shared cache but two threads client/server, different socket client/server etc). I also measured the vmlinux sizes for a single x86-based config with CONFIG_DEBUG_INFO enabled but not CONFIG_DEBUG_VM. The core of the .config is based on the Debian Lenny kernel config so I expect it to be reasonably typical. This patch: __alloc_pages_internal is the core page allocator function but essentially it is an alias of __alloc_pages_nodemask. Naming a publicly available and exported function "internal" is also a big ugly. This patch renames __alloc_pages_internal() to __alloc_pages_nodemask() and deletes the old nodemask function. Warning - This patch renames an exported symbol. No kernel driver is affected by external drivers calling __alloc_pages_internal() should change the call to __alloc_pages_nodemask() without any alteration of parameters. Signed-off-by: Mel Gorman <mel@csn.ul.ie> Reviewed-by: Christoph Lameter <cl@linux-foundation.org> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Reviewed-by: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-16 16:31:52 -06:00
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_cold_page(struct page *page, int cold);
#define __free_page(page) __free_pages((page), 0)
#define free_page(addr) free_pages((addr), 0)
void page_alloc_init(void);
Move remote node draining out of slab allocators Currently the slab allocators contain callbacks into the page allocator to perform the draining of pagesets on remote nodes. This requires SLUB to have a whole subsystem in order to be compatible with SLAB. Moving node draining out of the slab allocators avoids a section of code in SLUB. Move the node draining so that is is done when the vm statistics are updated. At that point we are already touching all the cachelines with the pagesets of a processor. Add a expire counter there. If we have to update per zone or global vm statistics then assume that the pageset will require subsequent draining. The expire counter will be decremented on each vm stats update pass until it reaches zero. Then we will drain one batch from the pageset. The draining will cause vm counter updates which will then cause another expiration until the pcp is empty. So we will drain a batch every 3 seconds. Note that remote node draining is a somewhat esoteric feature that is required on large NUMA systems because otherwise significant portions of system memory can become trapped in pcp queues. The number of pcp is determined by the number of processors and nodes in a system. A system with 4 processors and 2 nodes has 8 pcps which is okay. But a system with 1024 processors and 512 nodes has 512k pcps with a high potential for large amount of memory being caught in them. Signed-off-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-09 03:35:14 -06:00
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;
extern void set_gfp_allowed_mask(gfp_t mask);
extern gfp_t clear_gfp_allowed_mask(gfp_t mask);
#endif /* __LINUX_GFP_H */