aha/include/linux/page-flags.h

311 lines
9.4 KiB
C
Raw Normal View History

/*
* Macros for manipulating and testing page->flags
*/
#ifndef PAGE_FLAGS_H
#define PAGE_FLAGS_H
#include <linux/types.h>
#ifndef __GENERATING_BOUNDS_H
#include <linux/mm_types.h>
#include <linux/bounds.h>
#endif /* !__GENERATING_BOUNDS_H */
/*
* Various page->flags bits:
*
* PG_reserved is set for special pages, which can never be swapped out. Some
* of them might not even exist (eg empty_bad_page)...
*
* The PG_private bitflag is set on pagecache pages if they contain filesystem
* specific data (which is normally at page->private). It can be used by
* private allocations for its own usage.
*
* During initiation of disk I/O, PG_locked is set. This bit is set before I/O
* and cleared when writeback _starts_ or when read _completes_. PG_writeback
* is set before writeback starts and cleared when it finishes.
*
* PG_locked also pins a page in pagecache, and blocks truncation of the file
* while it is held.
*
* page_waitqueue(page) is a wait queue of all tasks waiting for the page
* to become unlocked.
*
* PG_uptodate tells whether the page's contents is valid. When a read
* completes, the page becomes uptodate, unless a disk I/O error happened.
*
* PG_referenced, PG_reclaim are used for page reclaim for anonymous and
* file-backed pagecache (see mm/vmscan.c).
*
* PG_error is set to indicate that an I/O error occurred on this page.
*
* PG_arch_1 is an architecture specific page state bit. The generic code
* guarantees that this bit is cleared for a page when it first is entered into
* the page cache.
*
* PG_highmem pages are not permanently mapped into the kernel virtual address
* space, they need to be kmapped separately for doing IO on the pages. The
* struct page (these bits with information) are always mapped into kernel
* address space...
*
* PG_buddy is set to indicate that the page is free and in the buddy system
* (see mm/page_alloc.c).
*
*/
/*
* Don't use the *_dontuse flags. Use the macros. Otherwise you'll break
* locked- and dirty-page accounting.
*
* The page flags field is split into two parts, the main flags area
* which extends from the low bits upwards, and the fields area which
* extends from the high bits downwards.
*
* | FIELD | ... | FLAGS |
* N-1 ^ 0
* (NR_PAGEFLAGS)
*
* The fields area is reserved for fields mapping zone, node (for NUMA) and
* SPARSEMEM section (for variants of SPARSEMEM that require section ids like
* SPARSEMEM_EXTREME with !SPARSEMEM_VMEMMAP).
*/
enum pageflags {
PG_locked, /* Page is locked. Don't touch. */
PG_error,
PG_referenced,
PG_uptodate,
PG_dirty,
PG_lru,
PG_active,
PG_slab,
PG_owner_priv_1, /* Owner use. If pagecache, fs may use*/
PG_arch_1,
PG_reserved,
PG_private, /* If pagecache, has fs-private data */
PG_writeback, /* Page is under writeback */
PAGEFLAGS_EXTENDED and separate page flags for Head and Tail Having separate page flags for the head and the tail of a compound page allows the compiler to use bitops instead of operations on a word to check for a tail page. That is f.e. important for virt_to_head_page() which is used in various critical code paths (kfree for example): Code for PageTail(page) Before: mov (%rdi),%rdx page->flags mov %rdx,%rax 3 bytes and $0x12000,%eax 5 bytes cmp $0x12000,%rax 6 bytes je 897 <kfree+0xa7> After: mov (%rdi),%rax test $0x40,%ah (3 bytes) jne 887 <kfree+0x97> So we go from 14 bytes to 3 bytes and from 3 instructions to one. From the use of 2 registers we go to none. We can only use page flags for this if we have page flags available. This patch introduces CONFIG_PAGEFLAGS_EXTENDED that is set if pageflags are not scarce due to SPARSEMEM using page flags for its sectionid on 32 bit NUMA platforms. Additional page flag definitions can be added to the CONFIG_PAGEFLAGS_EXTENDED section in page-flags.h if the functionality depends on PAGEFLAGS_EXTENDED or if more page flag overlapping tricks are used for the !PAGEFLAGS_EXTENDED fallback (the upcoming virtual compound patch may hook in here and Rik's/Lee's additional page flags to solve the reclaim issues could also be added there [hint... hint... where are these patchsets?]). Avoiding the overlaying of Pg_reclaim also clears the way for possible use of compound pages for the pagecache or on the LRU. Signed-off-by: Christoph Lameter <clameter@sgi.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 09:12:55 +00:00
#ifdef CONFIG_PAGEFLAGS_EXTENDED
PG_head, /* A head page */
PG_tail, /* A tail page */
#else
PG_compound, /* A compound page */
PAGEFLAGS_EXTENDED and separate page flags for Head and Tail Having separate page flags for the head and the tail of a compound page allows the compiler to use bitops instead of operations on a word to check for a tail page. That is f.e. important for virt_to_head_page() which is used in various critical code paths (kfree for example): Code for PageTail(page) Before: mov (%rdi),%rdx page->flags mov %rdx,%rax 3 bytes and $0x12000,%eax 5 bytes cmp $0x12000,%rax 6 bytes je 897 <kfree+0xa7> After: mov (%rdi),%rax test $0x40,%ah (3 bytes) jne 887 <kfree+0x97> So we go from 14 bytes to 3 bytes and from 3 instructions to one. From the use of 2 registers we go to none. We can only use page flags for this if we have page flags available. This patch introduces CONFIG_PAGEFLAGS_EXTENDED that is set if pageflags are not scarce due to SPARSEMEM using page flags for its sectionid on 32 bit NUMA platforms. Additional page flag definitions can be added to the CONFIG_PAGEFLAGS_EXTENDED section in page-flags.h if the functionality depends on PAGEFLAGS_EXTENDED or if more page flag overlapping tricks are used for the !PAGEFLAGS_EXTENDED fallback (the upcoming virtual compound patch may hook in here and Rik's/Lee's additional page flags to solve the reclaim issues could also be added there [hint... hint... where are these patchsets?]). Avoiding the overlaying of Pg_reclaim also clears the way for possible use of compound pages for the pagecache or on the LRU. Signed-off-by: Christoph Lameter <clameter@sgi.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 09:12:55 +00:00
#endif
PG_swapcache, /* Swap page: swp_entry_t in private */
PG_mappedtodisk, /* Has blocks allocated on-disk */
PG_reclaim, /* To be reclaimed asap */
PG_buddy, /* Page is free, on buddy lists */
#ifdef CONFIG_IA64_UNCACHED_ALLOCATOR
PG_uncached, /* Page has been mapped as uncached */
#endif
__NR_PAGEFLAGS
};
#ifndef __GENERATING_BOUNDS_H
/*
* Macros to create function definitions for page flags
*/
#define TESTPAGEFLAG(uname, lname) \
static inline int Page##uname(struct page *page) \
{ return test_bit(PG_##lname, &page->flags); }
#define SETPAGEFLAG(uname, lname) \
static inline void SetPage##uname(struct page *page) \
{ set_bit(PG_##lname, &page->flags); }
#define CLEARPAGEFLAG(uname, lname) \
static inline void ClearPage##uname(struct page *page) \
{ clear_bit(PG_##lname, &page->flags); }
#define __SETPAGEFLAG(uname, lname) \
static inline void __SetPage##uname(struct page *page) \
{ __set_bit(PG_##lname, &page->flags); }
#define __CLEARPAGEFLAG(uname, lname) \
static inline void __ClearPage##uname(struct page *page) \
{ __clear_bit(PG_##lname, &page->flags); }
#define TESTSETFLAG(uname, lname) \
static inline int TestSetPage##uname(struct page *page) \
{ return test_and_set_bit(PG_##lname, &page->flags); }
#define TESTCLEARFLAG(uname, lname) \
static inline int TestClearPage##uname(struct page *page) \
{ return test_and_clear_bit(PG_##lname, &page->flags); }
#define PAGEFLAG(uname, lname) TESTPAGEFLAG(uname, lname) \
SETPAGEFLAG(uname, lname) CLEARPAGEFLAG(uname, lname)
#define __PAGEFLAG(uname, lname) TESTPAGEFLAG(uname, lname) \
__SETPAGEFLAG(uname, lname) __CLEARPAGEFLAG(uname, lname)
#define PAGEFLAG_FALSE(uname) \
static inline int Page##uname(struct page *page) \
{ return 0; }
#define TESTSCFLAG(uname, lname) \
TESTSETFLAG(uname, lname) TESTCLEARFLAG(uname, lname)
struct page; /* forward declaration */
PAGEFLAG(Locked, locked) TESTSCFLAG(Locked, locked)
PAGEFLAG(Error, error)
PAGEFLAG(Referenced, referenced) TESTCLEARFLAG(Referenced, referenced)
PAGEFLAG(Dirty, dirty) TESTSCFLAG(Dirty, dirty) __CLEARPAGEFLAG(Dirty, dirty)
PAGEFLAG(LRU, lru) __CLEARPAGEFLAG(LRU, lru)
PAGEFLAG(Active, active) __CLEARPAGEFLAG(Active, active)
__PAGEFLAG(Slab, slab)
PAGEFLAG(Checked, owner_priv_1) /* Used by some filesystems */
PAGEFLAG(Pinned, owner_priv_1) TESTSCFLAG(Pinned, owner_priv_1) /* Xen */
PAGEFLAG(Reserved, reserved) __CLEARPAGEFLAG(Reserved, reserved)
PAGEFLAG(Private, private) __CLEARPAGEFLAG(Private, private)
__SETPAGEFLAG(Private, private)
/*
* Only test-and-set exist for PG_writeback. The unconditional operators are
* risky: they bypass page accounting.
*/
TESTPAGEFLAG(Writeback, writeback) TESTSCFLAG(Writeback, writeback)
__PAGEFLAG(Buddy, buddy)
PAGEFLAG(MappedToDisk, mappedtodisk)
/* PG_readahead is only used for file reads; PG_reclaim is only for writes */
PAGEFLAG(Reclaim, reclaim) TESTCLEARFLAG(Reclaim, reclaim)
PAGEFLAG(Readahead, reclaim) /* Reminder to do async read-ahead */
#ifdef CONFIG_HIGHMEM
/*
* Must use a macro here due to header dependency issues. page_zone() is not
* available at this point.
*/
#define PageHighMem(__p) is_highmem(page_zone(__p))
#else
PAGEFLAG_FALSE(HighMem)
#endif
#ifdef CONFIG_SWAP
PAGEFLAG(SwapCache, swapcache)
#else
PAGEFLAG_FALSE(SwapCache)
#endif
#ifdef CONFIG_IA64_UNCACHED_ALLOCATOR
PAGEFLAG(Uncached, uncached)
#else
PAGEFLAG_FALSE(Uncached)
#endif
mm: fix PageUptodate data race After running SetPageUptodate, preceeding stores to the page contents to actually bring it uptodate may not be ordered with the store to set the page uptodate. Therefore, another CPU which checks PageUptodate is true, then reads the page contents can get stale data. Fix this by having an smp_wmb before SetPageUptodate, and smp_rmb after PageUptodate. Many places that test PageUptodate, do so with the page locked, and this would be enough to ensure memory ordering in those places if SetPageUptodate were only called while the page is locked. Unfortunately that is not always the case for some filesystems, but it could be an idea for the future. Also bring the handling of anonymous page uptodateness in line with that of file backed page management, by marking anon pages as uptodate when they _are_ uptodate, rather than when our implementation requires that they be marked as such. Doing allows us to get rid of the smp_wmb's in the page copying functions, which were especially added for anonymous pages for an analogous memory ordering problem. Both file and anonymous pages are handled with the same barriers. FAQ: Q. Why not do this in flush_dcache_page? A. Firstly, flush_dcache_page handles only one side (the smb side) of the ordering protocol; we'd still need smp_rmb somewhere. Secondly, hiding away memory barriers in a completely unrelated function is nasty; at least in the PageUptodate macros, they are located together with (half) the operations involved in the ordering. Thirdly, the smp_wmb is only required when first bringing the page uptodate, wheras flush_dcache_page should be called each time it is written to through the kernel mapping. It is logically the wrong place to put it. Q. Why does this increase my text size / reduce my performance / etc. A. Because it is adding the necessary instructions to eliminate the data-race. Q. Can it be improved? A. Yes, eg. if you were to create a rule that all SetPageUptodate operations run under the page lock, we could avoid the smp_rmb places where PageUptodate is queried under the page lock. Requires audit of all filesystems and at least some would need reworking. That's great you're interested, I'm eagerly awaiting your patches. Signed-off-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-05 06:29:34 +00:00
static inline int PageUptodate(struct page *page)
{
int ret = test_bit(PG_uptodate, &(page)->flags);
/*
* Must ensure that the data we read out of the page is loaded
* _after_ we've loaded page->flags to check for PageUptodate.
* We can skip the barrier if the page is not uptodate, because
* we wouldn't be reading anything from it.
*
* See SetPageUptodate() for the other side of the story.
*/
if (ret)
smp_rmb();
return ret;
}
static inline void __SetPageUptodate(struct page *page)
{
smp_wmb();
__set_bit(PG_uptodate, &(page)->flags);
[PATCH] zoned vm counters: create vmstat.c/.h from page_alloc.c/.h NOTE: ZVC are *not* the lightweight event counters. ZVCs are reliable whereas event counters do not need to be. Zone based VM statistics are necessary to be able to determine what the state of memory in one zone is. In a NUMA system this can be helpful for local reclaim and other memory optimizations that may be able to shift VM load in order to get more balanced memory use. It is also useful to know how the computing load affects the memory allocations on various zones. This patchset allows the retrieval of that data from userspace. The patchset introduces a framework for counters that is a cross between the existing page_stats --which are simply global counters split per cpu-- and the approach of deferred incremental updates implemented for nr_pagecache. Small per cpu 8 bit counters are added to struct zone. If the counter exceeds certain thresholds then the counters are accumulated in an array of atomic_long in the zone and in a global array that sums up all zone values. The small 8 bit counters are next to the per cpu page pointers and so they will be in high in the cpu cache when pages are allocated and freed. Access to VM counter information for a zone and for the whole machine is then possible by simply indexing an array (Thanks to Nick Piggin for pointing out that approach). The access to the total number of pages of various types does no longer require the summing up of all per cpu counters. Benefits of this patchset right now: - Ability for UP and SMP configuration to determine how memory is balanced between the DMA, NORMAL and HIGHMEM zones. - loops over all processors are avoided in writeback and reclaim paths. We can avoid caching the writeback information because the needed information is directly accessible. - Special handling for nr_pagecache removed. - zone_reclaim_interval vanishes since VM stats can now determine when it is worth to do local reclaim. - Fast inline per node page state determination. - Accurate counters in /sys/devices/system/node/node*/meminfo. Current counters are counting simply which processor allocated a page somewhere and guestimate based on that. So the counters were not useful to show the actual distribution of page use on a specific zone. - The swap_prefetch patch requires per node statistics in order to figure out when processors of a node can prefetch. This patch provides some of the needed numbers. - Detailed VM counters available in more /proc and /sys status files. References to earlier discussions: V1 http://marc.theaimsgroup.com/?l=linux-kernel&m=113511649910826&w=2 V2 http://marc.theaimsgroup.com/?l=linux-kernel&m=114980851924230&w=2 V3 http://marc.theaimsgroup.com/?l=linux-kernel&m=115014697910351&w=2 V4 http://marc.theaimsgroup.com/?l=linux-kernel&m=115024767318740&w=2 Performance tests with AIM7 did not show any regressions. Seems to be a tad faster even. Tested on ia64/NUMA. Builds fine on i386, SMP / UP. Includes fixes for s390/arm/uml arch code. This patch: Move counter code from page_alloc.c/page-flags.h to vmstat.c/h. Create vmstat.c/vmstat.h by separating the counter code and the proc functions. Move the vm_stat_text array before zoneinfo_show. [akpm@osdl.org: s390 build fix] [akpm@osdl.org: HOTPLUG_CPU build fix] Signed-off-by: Christoph Lameter <clameter@sgi.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Trond Myklebust <trond.myklebust@fys.uio.no> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-30 08:55:32 +00:00
#ifdef CONFIG_S390
mm: fix PageUptodate data race After running SetPageUptodate, preceeding stores to the page contents to actually bring it uptodate may not be ordered with the store to set the page uptodate. Therefore, another CPU which checks PageUptodate is true, then reads the page contents can get stale data. Fix this by having an smp_wmb before SetPageUptodate, and smp_rmb after PageUptodate. Many places that test PageUptodate, do so with the page locked, and this would be enough to ensure memory ordering in those places if SetPageUptodate were only called while the page is locked. Unfortunately that is not always the case for some filesystems, but it could be an idea for the future. Also bring the handling of anonymous page uptodateness in line with that of file backed page management, by marking anon pages as uptodate when they _are_ uptodate, rather than when our implementation requires that they be marked as such. Doing allows us to get rid of the smp_wmb's in the page copying functions, which were especially added for anonymous pages for an analogous memory ordering problem. Both file and anonymous pages are handled with the same barriers. FAQ: Q. Why not do this in flush_dcache_page? A. Firstly, flush_dcache_page handles only one side (the smb side) of the ordering protocol; we'd still need smp_rmb somewhere. Secondly, hiding away memory barriers in a completely unrelated function is nasty; at least in the PageUptodate macros, they are located together with (half) the operations involved in the ordering. Thirdly, the smp_wmb is only required when first bringing the page uptodate, wheras flush_dcache_page should be called each time it is written to through the kernel mapping. It is logically the wrong place to put it. Q. Why does this increase my text size / reduce my performance / etc. A. Because it is adding the necessary instructions to eliminate the data-race. Q. Can it be improved? A. Yes, eg. if you were to create a rule that all SetPageUptodate operations run under the page lock, we could avoid the smp_rmb places where PageUptodate is queried under the page lock. Requires audit of all filesystems and at least some would need reworking. That's great you're interested, I'm eagerly awaiting your patches. Signed-off-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-05 06:29:34 +00:00
page_clear_dirty(page);
#endif
}
static inline void SetPageUptodate(struct page *page)
{
mm: fix PageUptodate data race After running SetPageUptodate, preceeding stores to the page contents to actually bring it uptodate may not be ordered with the store to set the page uptodate. Therefore, another CPU which checks PageUptodate is true, then reads the page contents can get stale data. Fix this by having an smp_wmb before SetPageUptodate, and smp_rmb after PageUptodate. Many places that test PageUptodate, do so with the page locked, and this would be enough to ensure memory ordering in those places if SetPageUptodate were only called while the page is locked. Unfortunately that is not always the case for some filesystems, but it could be an idea for the future. Also bring the handling of anonymous page uptodateness in line with that of file backed page management, by marking anon pages as uptodate when they _are_ uptodate, rather than when our implementation requires that they be marked as such. Doing allows us to get rid of the smp_wmb's in the page copying functions, which were especially added for anonymous pages for an analogous memory ordering problem. Both file and anonymous pages are handled with the same barriers. FAQ: Q. Why not do this in flush_dcache_page? A. Firstly, flush_dcache_page handles only one side (the smb side) of the ordering protocol; we'd still need smp_rmb somewhere. Secondly, hiding away memory barriers in a completely unrelated function is nasty; at least in the PageUptodate macros, they are located together with (half) the operations involved in the ordering. Thirdly, the smp_wmb is only required when first bringing the page uptodate, wheras flush_dcache_page should be called each time it is written to through the kernel mapping. It is logically the wrong place to put it. Q. Why does this increase my text size / reduce my performance / etc. A. Because it is adding the necessary instructions to eliminate the data-race. Q. Can it be improved? A. Yes, eg. if you were to create a rule that all SetPageUptodate operations run under the page lock, we could avoid the smp_rmb places where PageUptodate is queried under the page lock. Requires audit of all filesystems and at least some would need reworking. That's great you're interested, I'm eagerly awaiting your patches. Signed-off-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-05 06:29:34 +00:00
#ifdef CONFIG_S390
if (!test_and_set_bit(PG_uptodate, &page->flags))
page_clear_dirty(page);
[PATCH] zoned vm counters: create vmstat.c/.h from page_alloc.c/.h NOTE: ZVC are *not* the lightweight event counters. ZVCs are reliable whereas event counters do not need to be. Zone based VM statistics are necessary to be able to determine what the state of memory in one zone is. In a NUMA system this can be helpful for local reclaim and other memory optimizations that may be able to shift VM load in order to get more balanced memory use. It is also useful to know how the computing load affects the memory allocations on various zones. This patchset allows the retrieval of that data from userspace. The patchset introduces a framework for counters that is a cross between the existing page_stats --which are simply global counters split per cpu-- and the approach of deferred incremental updates implemented for nr_pagecache. Small per cpu 8 bit counters are added to struct zone. If the counter exceeds certain thresholds then the counters are accumulated in an array of atomic_long in the zone and in a global array that sums up all zone values. The small 8 bit counters are next to the per cpu page pointers and so they will be in high in the cpu cache when pages are allocated and freed. Access to VM counter information for a zone and for the whole machine is then possible by simply indexing an array (Thanks to Nick Piggin for pointing out that approach). The access to the total number of pages of various types does no longer require the summing up of all per cpu counters. Benefits of this patchset right now: - Ability for UP and SMP configuration to determine how memory is balanced between the DMA, NORMAL and HIGHMEM zones. - loops over all processors are avoided in writeback and reclaim paths. We can avoid caching the writeback information because the needed information is directly accessible. - Special handling for nr_pagecache removed. - zone_reclaim_interval vanishes since VM stats can now determine when it is worth to do local reclaim. - Fast inline per node page state determination. - Accurate counters in /sys/devices/system/node/node*/meminfo. Current counters are counting simply which processor allocated a page somewhere and guestimate based on that. So the counters were not useful to show the actual distribution of page use on a specific zone. - The swap_prefetch patch requires per node statistics in order to figure out when processors of a node can prefetch. This patch provides some of the needed numbers. - Detailed VM counters available in more /proc and /sys status files. References to earlier discussions: V1 http://marc.theaimsgroup.com/?l=linux-kernel&m=113511649910826&w=2 V2 http://marc.theaimsgroup.com/?l=linux-kernel&m=114980851924230&w=2 V3 http://marc.theaimsgroup.com/?l=linux-kernel&m=115014697910351&w=2 V4 http://marc.theaimsgroup.com/?l=linux-kernel&m=115024767318740&w=2 Performance tests with AIM7 did not show any regressions. Seems to be a tad faster even. Tested on ia64/NUMA. Builds fine on i386, SMP / UP. Includes fixes for s390/arm/uml arch code. This patch: Move counter code from page_alloc.c/page-flags.h to vmstat.c/h. Create vmstat.c/vmstat.h by separating the counter code and the proc functions. Move the vm_stat_text array before zoneinfo_show. [akpm@osdl.org: s390 build fix] [akpm@osdl.org: HOTPLUG_CPU build fix] Signed-off-by: Christoph Lameter <clameter@sgi.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Trond Myklebust <trond.myklebust@fys.uio.no> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-30 08:55:32 +00:00
#else
mm: fix PageUptodate data race After running SetPageUptodate, preceeding stores to the page contents to actually bring it uptodate may not be ordered with the store to set the page uptodate. Therefore, another CPU which checks PageUptodate is true, then reads the page contents can get stale data. Fix this by having an smp_wmb before SetPageUptodate, and smp_rmb after PageUptodate. Many places that test PageUptodate, do so with the page locked, and this would be enough to ensure memory ordering in those places if SetPageUptodate were only called while the page is locked. Unfortunately that is not always the case for some filesystems, but it could be an idea for the future. Also bring the handling of anonymous page uptodateness in line with that of file backed page management, by marking anon pages as uptodate when they _are_ uptodate, rather than when our implementation requires that they be marked as such. Doing allows us to get rid of the smp_wmb's in the page copying functions, which were especially added for anonymous pages for an analogous memory ordering problem. Both file and anonymous pages are handled with the same barriers. FAQ: Q. Why not do this in flush_dcache_page? A. Firstly, flush_dcache_page handles only one side (the smb side) of the ordering protocol; we'd still need smp_rmb somewhere. Secondly, hiding away memory barriers in a completely unrelated function is nasty; at least in the PageUptodate macros, they are located together with (half) the operations involved in the ordering. Thirdly, the smp_wmb is only required when first bringing the page uptodate, wheras flush_dcache_page should be called each time it is written to through the kernel mapping. It is logically the wrong place to put it. Q. Why does this increase my text size / reduce my performance / etc. A. Because it is adding the necessary instructions to eliminate the data-race. Q. Can it be improved? A. Yes, eg. if you were to create a rule that all SetPageUptodate operations run under the page lock, we could avoid the smp_rmb places where PageUptodate is queried under the page lock. Requires audit of all filesystems and at least some would need reworking. That's great you're interested, I'm eagerly awaiting your patches. Signed-off-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-05 06:29:34 +00:00
/*
* Memory barrier must be issued before setting the PG_uptodate bit,
* so that all previous stores issued in order to bring the page
* uptodate are actually visible before PageUptodate becomes true.
*
* s390 doesn't need an explicit smp_wmb here because the test and
* set bit already provides full barriers.
*/
smp_wmb();
set_bit(PG_uptodate, &(page)->flags);
#endif
mm: fix PageUptodate data race After running SetPageUptodate, preceeding stores to the page contents to actually bring it uptodate may not be ordered with the store to set the page uptodate. Therefore, another CPU which checks PageUptodate is true, then reads the page contents can get stale data. Fix this by having an smp_wmb before SetPageUptodate, and smp_rmb after PageUptodate. Many places that test PageUptodate, do so with the page locked, and this would be enough to ensure memory ordering in those places if SetPageUptodate were only called while the page is locked. Unfortunately that is not always the case for some filesystems, but it could be an idea for the future. Also bring the handling of anonymous page uptodateness in line with that of file backed page management, by marking anon pages as uptodate when they _are_ uptodate, rather than when our implementation requires that they be marked as such. Doing allows us to get rid of the smp_wmb's in the page copying functions, which were especially added for anonymous pages for an analogous memory ordering problem. Both file and anonymous pages are handled with the same barriers. FAQ: Q. Why not do this in flush_dcache_page? A. Firstly, flush_dcache_page handles only one side (the smb side) of the ordering protocol; we'd still need smp_rmb somewhere. Secondly, hiding away memory barriers in a completely unrelated function is nasty; at least in the PageUptodate macros, they are located together with (half) the operations involved in the ordering. Thirdly, the smp_wmb is only required when first bringing the page uptodate, wheras flush_dcache_page should be called each time it is written to through the kernel mapping. It is logically the wrong place to put it. Q. Why does this increase my text size / reduce my performance / etc. A. Because it is adding the necessary instructions to eliminate the data-race. Q. Can it be improved? A. Yes, eg. if you were to create a rule that all SetPageUptodate operations run under the page lock, we could avoid the smp_rmb places where PageUptodate is queried under the page lock. Requires audit of all filesystems and at least some would need reworking. That's great you're interested, I'm eagerly awaiting your patches. Signed-off-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-05 06:29:34 +00:00
}
CLEARPAGEFLAG(Uptodate, uptodate)
extern void cancel_dirty_page(struct page *page, unsigned int account_size);
int test_clear_page_writeback(struct page *page);
int test_set_page_writeback(struct page *page);
static inline void set_page_writeback(struct page *page)
{
test_set_page_writeback(page);
}
PAGEFLAGS_EXTENDED and separate page flags for Head and Tail Having separate page flags for the head and the tail of a compound page allows the compiler to use bitops instead of operations on a word to check for a tail page. That is f.e. important for virt_to_head_page() which is used in various critical code paths (kfree for example): Code for PageTail(page) Before: mov (%rdi),%rdx page->flags mov %rdx,%rax 3 bytes and $0x12000,%eax 5 bytes cmp $0x12000,%rax 6 bytes je 897 <kfree+0xa7> After: mov (%rdi),%rax test $0x40,%ah (3 bytes) jne 887 <kfree+0x97> So we go from 14 bytes to 3 bytes and from 3 instructions to one. From the use of 2 registers we go to none. We can only use page flags for this if we have page flags available. This patch introduces CONFIG_PAGEFLAGS_EXTENDED that is set if pageflags are not scarce due to SPARSEMEM using page flags for its sectionid on 32 bit NUMA platforms. Additional page flag definitions can be added to the CONFIG_PAGEFLAGS_EXTENDED section in page-flags.h if the functionality depends on PAGEFLAGS_EXTENDED or if more page flag overlapping tricks are used for the !PAGEFLAGS_EXTENDED fallback (the upcoming virtual compound patch may hook in here and Rik's/Lee's additional page flags to solve the reclaim issues could also be added there [hint... hint... where are these patchsets?]). Avoiding the overlaying of Pg_reclaim also clears the way for possible use of compound pages for the pagecache or on the LRU. Signed-off-by: Christoph Lameter <clameter@sgi.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 09:12:55 +00:00
#ifdef CONFIG_PAGEFLAGS_EXTENDED
/*
* System with lots of page flags available. This allows separate
* flags for PageHead() and PageTail() checks of compound pages so that bit
* tests can be used in performance sensitive paths. PageCompound is
* generally not used in hot code paths.
*/
__PAGEFLAG(Head, head)
__PAGEFLAG(Tail, tail)
static inline int PageCompound(struct page *page)
{
return page->flags & ((1L << PG_head) | (1L << PG_tail));
}
#else
/*
* Reduce page flag use as much as possible by overlapping
* compound page flags with the flags used for page cache pages. Possible
* because PageCompound is always set for compound pages and not for
* pages on the LRU and/or pagecache.
*/
TESTPAGEFLAG(Compound, compound)
__PAGEFLAG(Head, compound)
2007-05-06 21:49:39 +00:00
/*
* PG_reclaim is used in combination with PG_compound to mark the
* head and tail of a compound page. This saves one page flag
* but makes it impossible to use compound pages for the page cache.
* The PG_reclaim bit would have to be used for reclaim or readahead
* if compound pages enter the page cache.
*
* PG_compound & PG_reclaim => Tail page
* PG_compound & ~PG_reclaim => Head page
2007-05-06 21:49:39 +00:00
*/
#define PG_head_tail_mask ((1L << PG_compound) | (1L << PG_reclaim))
static inline int PageTail(struct page *page)
{
return ((page->flags & PG_head_tail_mask) == PG_head_tail_mask);
}
static inline void __SetPageTail(struct page *page)
{
page->flags |= PG_head_tail_mask;
}
static inline void __ClearPageTail(struct page *page)
{
page->flags &= ~PG_head_tail_mask;
}
PAGEFLAGS_EXTENDED and separate page flags for Head and Tail Having separate page flags for the head and the tail of a compound page allows the compiler to use bitops instead of operations on a word to check for a tail page. That is f.e. important for virt_to_head_page() which is used in various critical code paths (kfree for example): Code for PageTail(page) Before: mov (%rdi),%rdx page->flags mov %rdx,%rax 3 bytes and $0x12000,%eax 5 bytes cmp $0x12000,%rax 6 bytes je 897 <kfree+0xa7> After: mov (%rdi),%rax test $0x40,%ah (3 bytes) jne 887 <kfree+0x97> So we go from 14 bytes to 3 bytes and from 3 instructions to one. From the use of 2 registers we go to none. We can only use page flags for this if we have page flags available. This patch introduces CONFIG_PAGEFLAGS_EXTENDED that is set if pageflags are not scarce due to SPARSEMEM using page flags for its sectionid on 32 bit NUMA platforms. Additional page flag definitions can be added to the CONFIG_PAGEFLAGS_EXTENDED section in page-flags.h if the functionality depends on PAGEFLAGS_EXTENDED or if more page flag overlapping tricks are used for the !PAGEFLAGS_EXTENDED fallback (the upcoming virtual compound patch may hook in here and Rik's/Lee's additional page flags to solve the reclaim issues could also be added there [hint... hint... where are these patchsets?]). Avoiding the overlaying of Pg_reclaim also clears the way for possible use of compound pages for the pagecache or on the LRU. Signed-off-by: Christoph Lameter <clameter@sgi.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 09:12:55 +00:00
#endif /* !PAGEFLAGS_EXTENDED */
#endif /* !__GENERATING_BOUNDS_H */
#endif /* PAGE_FLAGS_H */