2
0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-27 14:43:58 +08:00
linux-next/include/linux/page-flags.h

276 lines
10 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>
#include <linux/mm_types.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
* (N-FLAGS_RESERVED)
*
* The fields area is reserved for fields mapping zone, node and SPARSEMEM
* section. The boundry between these two areas is defined by
* FLAGS_RESERVED which defines the width of the fields section
* (see linux/mmzone.h). New flags must _not_ overlap with this area.
*/
#define PG_locked 0 /* Page is locked. Don't touch. */
#define PG_error 1
#define PG_referenced 2
#define PG_uptodate 3
#define PG_dirty 4
#define PG_lru 5
#define PG_active 6
#define PG_slab 7 /* slab debug (Suparna wants this) */
#define PG_owner_priv_1 8 /* Owner use. If pagecache, fs may use*/
#define PG_arch_1 9
#define PG_reserved 10
#define PG_private 11 /* If pagecache, has fs-private data */
#define PG_writeback 12 /* Page is under writeback */
#define PG_compound 14 /* Part of a compound page */
#define PG_swapcache 15 /* Swap page: swp_entry_t in private */
#define PG_mappedtodisk 16 /* Has blocks allocated on-disk */
#define PG_reclaim 17 /* To be reclaimed asap */
#define PG_buddy 19 /* Page is free, on buddy lists */
mm: share PG_readahead and PG_reclaim Share the same page flag bit for PG_readahead and PG_reclaim. One is used only on file reads, another is only for emergency writes. One is used mostly for fresh/young pages, another is for old pages. Combinations of possible interactions are: a) clear PG_reclaim => implicit clear of PG_readahead it will delay an asynchronous readahead into a synchronous one it actually does _good_ for readahead: the pages will be reclaimed soon, it's readahead thrashing! in this case, synchronous readahead makes more sense. b) clear PG_readahead => implicit clear of PG_reclaim one(and only one) page will not be reclaimed in time it can be avoided by checking PageWriteback(page) in readahead first c) set PG_reclaim => implicit set of PG_readahead will confuse readahead and make it restart the size rampup process it's a trivial problem, and can mostly be avoided by checking PageWriteback(page) first in readahead d) set PG_readahead => implicit set of PG_reclaim PG_readahead will never be set on already cached pages. PG_reclaim will always be cleared on dirtying a page. so not a problem. In summary, a) we get better behavior b,d) possible interactions can be avoided c) racy condition exists that might affect readahead, but the chance is _really_ low, and the hurt on readahead is trivial. Compound pages also use PG_reclaim, but for now they do not interact with reclaim/readahead code. Signed-off-by: Fengguang Wu <wfg@mail.ustc.edu.cn> Cc: Rusty Russell <rusty@rustcorp.com.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-19 16:48:07 +08:00
/* PG_readahead is only used for file reads; PG_reclaim is only for writes */
#define PG_readahead PG_reclaim /* Reminder to do async read-ahead */
/* PG_owner_priv_1 users should have descriptive aliases */
#define PG_checked PG_owner_priv_1 /* Used by some filesystems */
#define PG_pinned PG_owner_priv_1 /* Xen pinned pagetable */
#if (BITS_PER_LONG > 32)
/*
* 64-bit-only flags build down from bit 31
*
* 32 bit -------------------------------| FIELDS | FLAGS |
* 64 bit | FIELDS | ?????? FLAGS |
* 63 32 0
*/
#define PG_uncached 31 /* Page has been mapped as uncached */
#endif
/*
* Manipulation of page state flags
*/
#define PageLocked(page) \
test_bit(PG_locked, &(page)->flags)
#define SetPageLocked(page) \
set_bit(PG_locked, &(page)->flags)
#define TestSetPageLocked(page) \
test_and_set_bit(PG_locked, &(page)->flags)
#define ClearPageLocked(page) \
clear_bit(PG_locked, &(page)->flags)
#define TestClearPageLocked(page) \
test_and_clear_bit(PG_locked, &(page)->flags)
#define PageError(page) test_bit(PG_error, &(page)->flags)
#define SetPageError(page) set_bit(PG_error, &(page)->flags)
#define ClearPageError(page) clear_bit(PG_error, &(page)->flags)
#define PageReferenced(page) test_bit(PG_referenced, &(page)->flags)
#define SetPageReferenced(page) set_bit(PG_referenced, &(page)->flags)
#define ClearPageReferenced(page) clear_bit(PG_referenced, &(page)->flags)
#define TestClearPageReferenced(page) test_and_clear_bit(PG_referenced, &(page)->flags)
#define PageUptodate(page) test_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 16:55:32 +08:00
#ifdef CONFIG_S390
static inline void SetPageUptodate(struct page *page)
{
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 16:55:32 +08:00
#else
#define SetPageUptodate(page) set_bit(PG_uptodate, &(page)->flags)
#endif
#define ClearPageUptodate(page) clear_bit(PG_uptodate, &(page)->flags)
#define PageDirty(page) test_bit(PG_dirty, &(page)->flags)
#define SetPageDirty(page) set_bit(PG_dirty, &(page)->flags)
#define TestSetPageDirty(page) test_and_set_bit(PG_dirty, &(page)->flags)
#define ClearPageDirty(page) clear_bit(PG_dirty, &(page)->flags)
#define __ClearPageDirty(page) __clear_bit(PG_dirty, &(page)->flags)
#define TestClearPageDirty(page) test_and_clear_bit(PG_dirty, &(page)->flags)
#define PageLRU(page) test_bit(PG_lru, &(page)->flags)
#define SetPageLRU(page) set_bit(PG_lru, &(page)->flags)
#define ClearPageLRU(page) clear_bit(PG_lru, &(page)->flags)
#define __ClearPageLRU(page) __clear_bit(PG_lru, &(page)->flags)
#define PageActive(page) test_bit(PG_active, &(page)->flags)
#define SetPageActive(page) set_bit(PG_active, &(page)->flags)
#define ClearPageActive(page) clear_bit(PG_active, &(page)->flags)
#define __ClearPageActive(page) __clear_bit(PG_active, &(page)->flags)
#define PageSlab(page) test_bit(PG_slab, &(page)->flags)
#define __SetPageSlab(page) __set_bit(PG_slab, &(page)->flags)
#define __ClearPageSlab(page) __clear_bit(PG_slab, &(page)->flags)
#ifdef CONFIG_HIGHMEM
#define PageHighMem(page) is_highmem(page_zone(page))
#else
#define PageHighMem(page) 0 /* needed to optimize away at compile time */
#endif
#define PageChecked(page) test_bit(PG_checked, &(page)->flags)
#define SetPageChecked(page) set_bit(PG_checked, &(page)->flags)
#define ClearPageChecked(page) clear_bit(PG_checked, &(page)->flags)
#define PagePinned(page) test_bit(PG_pinned, &(page)->flags)
#define SetPagePinned(page) set_bit(PG_pinned, &(page)->flags)
#define ClearPagePinned(page) clear_bit(PG_pinned, &(page)->flags)
#define PageReserved(page) test_bit(PG_reserved, &(page)->flags)
#define SetPageReserved(page) set_bit(PG_reserved, &(page)->flags)
#define ClearPageReserved(page) clear_bit(PG_reserved, &(page)->flags)
#define __ClearPageReserved(page) __clear_bit(PG_reserved, &(page)->flags)
#define SetPagePrivate(page) set_bit(PG_private, &(page)->flags)
#define ClearPagePrivate(page) clear_bit(PG_private, &(page)->flags)
#define PagePrivate(page) test_bit(PG_private, &(page)->flags)
#define __SetPagePrivate(page) __set_bit(PG_private, &(page)->flags)
#define __ClearPagePrivate(page) __clear_bit(PG_private, &(page)->flags)
/*
* Only test-and-set exist for PG_writeback. The unconditional operators are
* risky: they bypass page accounting.
*/
#define PageWriteback(page) test_bit(PG_writeback, &(page)->flags)
#define TestSetPageWriteback(page) test_and_set_bit(PG_writeback, \
&(page)->flags)
#define TestClearPageWriteback(page) test_and_clear_bit(PG_writeback, \
&(page)->flags)
#define PageBuddy(page) test_bit(PG_buddy, &(page)->flags)
#define __SetPageBuddy(page) __set_bit(PG_buddy, &(page)->flags)
#define __ClearPageBuddy(page) __clear_bit(PG_buddy, &(page)->flags)
#define PageMappedToDisk(page) test_bit(PG_mappedtodisk, &(page)->flags)
#define SetPageMappedToDisk(page) set_bit(PG_mappedtodisk, &(page)->flags)
#define ClearPageMappedToDisk(page) clear_bit(PG_mappedtodisk, &(page)->flags)
#define PageReadahead(page) test_bit(PG_readahead, &(page)->flags)
#define SetPageReadahead(page) set_bit(PG_readahead, &(page)->flags)
#define ClearPageReadahead(page) clear_bit(PG_readahead, &(page)->flags)
#define PageReclaim(page) test_bit(PG_reclaim, &(page)->flags)
#define SetPageReclaim(page) set_bit(PG_reclaim, &(page)->flags)
#define ClearPageReclaim(page) clear_bit(PG_reclaim, &(page)->flags)
#define TestClearPageReclaim(page) test_and_clear_bit(PG_reclaim, &(page)->flags)
#define PageCompound(page) test_bit(PG_compound, &(page)->flags)
#define __SetPageCompound(page) __set_bit(PG_compound, &(page)->flags)
#define __ClearPageCompound(page) __clear_bit(PG_compound, &(page)->flags)
2007-05-07 05:49:39 +08:00
/*
* PG_reclaim is used in combination with PG_compound to mark the
* head and tail of a compound page
*
* PG_compound & PG_reclaim => Tail page
* PG_compound & ~PG_reclaim => Head page
2007-05-07 05:49:39 +08:00
*/
#define PG_head_tail_mask ((1L << PG_compound) | (1L << PG_reclaim))
#define PageTail(page) ((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;
}
#define PageHead(page) ((page->flags & PG_head_tail_mask) \
== (1L << PG_compound))
#define __SetPageHead(page) __SetPageCompound(page)
#define __ClearPageHead(page) __ClearPageCompound(page)
2007-05-07 05:49:39 +08:00
#ifdef CONFIG_SWAP
#define PageSwapCache(page) test_bit(PG_swapcache, &(page)->flags)
#define SetPageSwapCache(page) set_bit(PG_swapcache, &(page)->flags)
#define ClearPageSwapCache(page) clear_bit(PG_swapcache, &(page)->flags)
#else
#define PageSwapCache(page) 0
#endif
#define PageUncached(page) test_bit(PG_uncached, &(page)->flags)
#define SetPageUncached(page) set_bit(PG_uncached, &(page)->flags)
#define ClearPageUncached(page) clear_bit(PG_uncached, &(page)->flags)
struct page; /* forward declaration */
VM: Remove "clear_page_dirty()" and "test_clear_page_dirty()" functions They were horribly easy to mis-use because of their tempting naming, and they also did way more than any users of them generally wanted them to do. A dirty page can become clean under two circumstances: (a) when we write it out. We have "clear_page_dirty_for_io()" for this, and that function remains unchanged. In the "for IO" case it is not sufficient to just clear the dirty bit, you also have to mark the page as being under writeback etc. (b) when we actually remove a page due to it becoming inaccessible to users, notably because it was truncate()'d away or the file (or metadata) no longer exists, and we thus want to cancel any outstanding dirty state. For the (b) case, we now introduce "cancel_dirty_page()", which only touches the page state itself, and verifies that the page is not mapped (since cancelling writes on a mapped page would be actively wrong as it is still accessible to users). Some filesystems need to be fixed up for this: CIFS, FUSE, JFS, ReiserFS, XFS all use the old confusing functions, and will be fixed separately in subsequent commits (with some of them just removing the offending logic, and others using clear_page_dirty_for_io()). This was confirmed by Martin Michlmayr to fix the apt database corruption on ARM. Cc: Martin Michlmayr <tbm@cyrius.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Hugh Dickins <hugh@veritas.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Arjan van de Ven <arjan@infradead.org> Cc: Andrei Popa <andrei.popa@i-neo.ro> Cc: Andrew Morton <akpm@osdl.org> Cc: Dave Kleikamp <shaggy@linux.vnet.ibm.com> Cc: Gordon Farquharson <gordonfarquharson@gmail.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Trond Myklebust <trond.myklebust@fys.uio.no> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-21 05:46:42 +08:00
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);
}
#endif /* PAGE_FLAGS_H */