linux/mm/filemap.c

2630 lines
69 KiB
C
Raw Normal View History

/*
* linux/mm/filemap.c
*
* Copyright (C) 1994-1999 Linus Torvalds
*/
/*
* This file handles the generic file mmap semantics used by
* most "normal" filesystems (but you don't /have/ to use this:
* the NFS filesystem used to do this differently, for example)
*/
#include <linux/module.h>
#include <linux/compiler.h>
#include <linux/fs.h>
[PATCH] x86: cache pollution aware __copy_from_user_ll() Use the x86 cache-bypassing copy instructions for copy_from_user(). Some performance data are Total of GLOBAL_POWER_EVENTS (CPU cycle samples) 2.6.12.4.orig 1921587 2.6.12.4.nt 1599424 1599424/1921587=83.23% (16.77% reduction) BSQ_CACHE_REFERENCE (L3 cache miss) 2.6.12.4.orig 57427 2.6.12.4.nt 20858 20858/57427=36.32% (63.7% reduction) L3 cache miss reduction of __copy_from_user_ll samples % 37408 65.1412 vmlinux __copy_from_user_ll 23 0.1103 vmlinux __copy_user_zeroing_intel_nocache 23/37408=0.061% (99.94% reduction) Top 5 of 2.6.12.4.nt Counted GLOBAL_POWER_EVENTS events (time during which processor is not stopped) with a unit mask of 0x01 (mandatory) count 100000 samples % app name symbol name 128392 8.0274 vmlinux __copy_user_zeroing_intel_nocache 64206 4.0143 vmlinux journal_add_journal_head 59746 3.7355 vmlinux do_get_write_access 47674 2.9807 vmlinux journal_put_journal_head 46021 2.8774 vmlinux journal_dirty_metadata pattern9-0-cpu4-0-09011728/summary.out Counted BSQ_CACHE_REFERENCE events (cache references seen by the bus unit) with a unit mask of 0x3f (multiple flags) count 3000 samples % app name symbol name 69755 4.2861 vmlinux __copy_user_zeroing_intel_nocache 55685 3.4215 vmlinux journal_add_journal_head 52371 3.2179 vmlinux __find_get_block 45504 2.7960 vmlinux journal_put_journal_head 36005 2.2123 vmlinux journal_stop pattern9-0-cpu4-0-09011744/summary.out Counted BSQ_CACHE_REFERENCE events (cache references seen by the bus unit) with a unit mask of 0x200 (read 3rd level cache miss) count 3000 samples % app name symbol name 1147 5.4994 vmlinux journal_add_journal_head 881 4.2240 vmlinux journal_dirty_data 872 4.1809 vmlinux blk_rq_map_sg 734 3.5192 vmlinux journal_commit_transaction 617 2.9582 vmlinux radix_tree_delete pattern9-0-cpu4-0-09011731/summary.out iozone results are original 2.6.12.4 CPU time = 207.768 sec cache aware CPU time = 184.783 sec (three times run) 184.783/207.768=88.94% (11.06% reduction) original: pattern9-0-cpu4-0-08191720/iozone.out: CPU Utilization: Wall time 45.997 CPU time 64.527 CPU utilization 140.28 % pattern9-0-cpu4-0-08191741/iozone.out: CPU Utilization: Wall time 46.878 CPU time 71.933 CPU utilization 153.45 % pattern9-0-cpu4-0-08191743/iozone.out: CPU Utilization: Wall time 45.152 CPU time 71.308 CPU utilization 157.93 % cache awre: pattern9-0-cpu4-0-09011728/iozone.out: CPU Utilization: Wall time 44.842 CPU time 62.465 CPU utilization 139.30 % pattern9-0-cpu4-0-09011731/iozone.out: CPU Utilization: Wall time 44.718 CPU time 59.273 CPU utilization 132.55 % pattern9-0-cpu4-0-09011744/iozone.out: CPU Utilization: Wall time 44.367 CPU time 63.045 CPU utilization 142.10 % Signed-off-by: Hiro Yoshioka <hyoshiok@miraclelinux.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 17:04:16 +08:00
#include <linux/uaccess.h>
#include <linux/aio.h>
#include <linux/capability.h>
#include <linux/kernel_stat.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#include <linux/gfp.h>
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/mman.h>
#include <linux/pagemap.h>
#include <linux/file.h>
#include <linux/uio.h>
#include <linux/hash.h>
#include <linux/writeback.h>
#include <linux/backing-dev.h>
#include <linux/pagevec.h>
#include <linux/blkdev.h>
#include <linux/security.h>
#include <linux/syscalls.h>
#include <linux/cpuset.h>
#include <linux/hardirq.h> /* for BUG_ON(!in_atomic()) only */
Memory controller: memory accounting Add the accounting hooks. The accounting is carried out for RSS and Page Cache (unmapped) pages. There is now a common limit and accounting for both. The RSS accounting is accounted at page_add_*_rmap() and page_remove_rmap() time. Page cache is accounted at add_to_page_cache(), __delete_from_page_cache(). Swap cache is also accounted for. Each page's page_cgroup is protected with the last bit of the page_cgroup pointer, this makes handling of race conditions involving simultaneous mappings of a page easier. A reference count is kept in the page_cgroup to deal with cases where a page might be unmapped from the RSS of all tasks, but still lives in the page cache. Credits go to Vaidyanathan Srinivasan for helping with reference counting work of the page cgroup. Almost all of the page cache accounting code has help from Vaidyanathan Srinivasan. [hugh@veritas.com: fix swapoff breakage] [akpm@linux-foundation.org: fix locking] Signed-off-by: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Paul Menage <menage@google.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Kirill Korotaev <dev@sw.ru> Cc: Herbert Poetzl <herbert@13thfloor.at> Cc: David Rientjes <rientjes@google.com> Cc: <Valdis.Kletnieks@vt.edu> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-07 16:13:53 +08:00
#include <linux/memcontrol.h>
vmscan: split LRU lists into anon & file sets Split the LRU lists in two, one set for pages that are backed by real file systems ("file") and one for pages that are backed by memory and swap ("anon"). The latter includes tmpfs. The advantage of doing this is that the VM will not have to scan over lots of anonymous pages (which we generally do not want to swap out), just to find the page cache pages that it should evict. This patch has the infrastructure and a basic policy to balance how much we scan the anon lists and how much we scan the file lists. The big policy changes are in separate patches. [lee.schermerhorn@hp.com: collect lru meminfo statistics from correct offset] [kosaki.motohiro@jp.fujitsu.com: prevent incorrect oom under split_lru] [kosaki.motohiro@jp.fujitsu.com: fix pagevec_move_tail() doesn't treat unevictable page] [hugh@veritas.com: memcg swapbacked pages active] [hugh@veritas.com: splitlru: BDI_CAP_SWAP_BACKED] [akpm@linux-foundation.org: fix /proc/vmstat units] [nishimura@mxp.nes.nec.co.jp: memcg: fix handling of shmem migration] [kosaki.motohiro@jp.fujitsu.com: adjust Quicklists field of /proc/meminfo] [kosaki.motohiro@jp.fujitsu.com: fix style issue of get_scan_ratio()] Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <Lee.Schermerhorn@hp.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:32 +08:00
#include <linux/mm_inline.h> /* for page_is_file_cache() */
#include "internal.h"
/*
* FIXME: remove all knowledge of the buffer layer from the core VM
*/
#include <linux/buffer_head.h> /* for try_to_free_buffers */
#include <asm/mman.h>
/*
* Shared mappings implemented 30.11.1994. It's not fully working yet,
* though.
*
* Shared mappings now work. 15.8.1995 Bruno.
*
* finished 'unifying' the page and buffer cache and SMP-threaded the
* page-cache, 21.05.1999, Ingo Molnar <mingo@redhat.com>
*
* SMP-threaded pagemap-LRU 1999, Andrea Arcangeli <andrea@suse.de>
*/
/*
* Lock ordering:
*
* ->i_mmap_mutex (truncate_pagecache)
* ->private_lock (__free_pte->__set_page_dirty_buffers)
* ->swap_lock (exclusive_swap_page, others)
* ->mapping->tree_lock
*
* ->i_mutex
* ->i_mmap_mutex (truncate->unmap_mapping_range)
*
* ->mmap_sem
* ->i_mmap_mutex
* ->page_table_lock or pte_lock (various, mainly in memory.c)
* ->mapping->tree_lock (arch-dependent flush_dcache_mmap_lock)
*
* ->mmap_sem
* ->lock_page (access_process_vm)
*
* ->i_mutex (generic_file_buffered_write)
* ->mmap_sem (fault_in_pages_readable->do_page_fault)
*
* ->i_mutex
* ->i_alloc_sem (various)
*
* inode_wb_list_lock
* sb_lock (fs/fs-writeback.c)
* ->mapping->tree_lock (__sync_single_inode)
*
* ->i_mmap_mutex
* ->anon_vma.lock (vma_adjust)
*
* ->anon_vma.lock
* ->page_table_lock or pte_lock (anon_vma_prepare and various)
*
* ->page_table_lock or pte_lock
* ->swap_lock (try_to_unmap_one)
* ->private_lock (try_to_unmap_one)
* ->tree_lock (try_to_unmap_one)
* ->zone.lru_lock (follow_page->mark_page_accessed)
* ->zone.lru_lock (check_pte_range->isolate_lru_page)
* ->private_lock (page_remove_rmap->set_page_dirty)
* ->tree_lock (page_remove_rmap->set_page_dirty)
* inode_wb_list_lock (page_remove_rmap->set_page_dirty)
* ->inode->i_lock (page_remove_rmap->set_page_dirty)
* inode_wb_list_lock (zap_pte_range->set_page_dirty)
* ->inode->i_lock (zap_pte_range->set_page_dirty)
* ->private_lock (zap_pte_range->__set_page_dirty_buffers)
*
HWPOISON: The high level memory error handler in the VM v7 Add the high level memory handler that poisons pages that got corrupted by hardware (typically by a two bit flip in a DIMM or a cache) on the Linux level. The goal is to prevent everyone from accessing these pages in the future. This done at the VM level by marking a page hwpoisoned and doing the appropriate action based on the type of page it is. The code that does this is portable and lives in mm/memory-failure.c To quote the overview comment: High level machine check handler. Handles pages reported by the hardware as being corrupted usually due to a 2bit ECC memory or cache failure. This focuses on pages detected as corrupted in the background. When the current CPU tries to consume corruption the currently running process can just be killed directly instead. This implies that if the error cannot be handled for some reason it's safe to just ignore it because no corruption has been consumed yet. Instead when that happens another machine check will happen. Handles page cache pages in various states. The tricky part here is that we can access any page asynchronous to other VM users, because memory failures could happen anytime and anywhere, possibly violating some of their assumptions. This is why this code has to be extremely careful. Generally it tries to use normal locking rules, as in get the standard locks, even if that means the error handling takes potentially a long time. Some of the operations here are somewhat inefficient and have non linear algorithmic complexity, because the data structures have not been optimized for this case. This is in particular the case for the mapping from a vma to a process. Since this case is expected to be rare we hope we can get away with this. There are in principle two strategies to kill processes on poison: - just unmap the data and wait for an actual reference before killing - kill as soon as corruption is detected. Both have advantages and disadvantages and should be used in different situations. Right now both are implemented and can be switched with a new sysctl vm.memory_failure_early_kill The default is early kill. The patch does some rmap data structure walking on its own to collect processes to kill. This is unusual because normally all rmap data structure knowledge is in rmap.c only. I put it here for now to keep everything together and rmap knowledge has been seeping out anyways Includes contributions from Johannes Weiner, Chris Mason, Fengguang Wu, Nick Piggin (who did a lot of great work) and others. Cc: npiggin@suse.de Cc: riel@redhat.com Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Rik van Riel <riel@redhat.com> Reviewed-by: Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com>
2009-09-16 17:50:15 +08:00
* (code doesn't rely on that order, so you could switch it around)
* ->tasklist_lock (memory_failure, collect_procs_ao)
* ->i_mmap_mutex
*/
/*
* Delete a page from the page cache and free it. Caller has to make
* sure the page is locked and that nobody else uses it - or that usage
* is safe. The caller must hold the mapping's tree_lock.
*/
void __delete_from_page_cache(struct page *page)
{
struct address_space *mapping = page->mapping;
radix_tree_delete(&mapping->page_tree, page->index);
page->mapping = NULL;
mapping->nrpages--;
__dec_zone_page_state(page, NR_FILE_PAGES);
if (PageSwapBacked(page))
__dec_zone_page_state(page, NR_SHMEM);
BUG_ON(page_mapped(page));
/*
* Some filesystems seem to re-dirty the page even after
* the VM has canceled the dirty bit (eg ext3 journaling).
*
* Fix it up by doing a final dirty accounting check after
* having removed the page entirely.
*/
if (PageDirty(page) && mapping_cap_account_dirty(mapping)) {
dec_zone_page_state(page, NR_FILE_DIRTY);
dec_bdi_stat(mapping->backing_dev_info, BDI_RECLAIMABLE);
}
}
/**
* delete_from_page_cache - delete page from page cache
* @page: the page which the kernel is trying to remove from page cache
*
* This must be called only on pages that have been verified to be in the page
* cache and locked. It will never put the page into the free list, the caller
* has a reference on the page.
*/
void delete_from_page_cache(struct page *page)
{
struct address_space *mapping = page->mapping;
void (*freepage)(struct page *);
BUG_ON(!PageLocked(page));
freepage = mapping->a_ops->freepage;
spin_lock_irq(&mapping->tree_lock);
__delete_from_page_cache(page);
spin_unlock_irq(&mapping->tree_lock);
mem_cgroup_uncharge_cache_page(page);
if (freepage)
freepage(page);
mm: introduce delete_from_page_cache() Presently we increase the page refcount in add_to_page_cache() but don't decrease it in remove_from_page_cache(). Such asymmetry adds confusion, requiring that callers notice it and a comment explaining why they release a page reference. It's not a good API. A long time ago, Hugh tried it (http://lkml.org/lkml/2004/10/24/140) but gave up because reiser4's drop_page() had to unlock the page between removing it from page cache and doing the page_cache_release(). But now the situation is changed. I think at least things in current mainline don't have any obstacles. The problem is for out-of-mainline filesystems - if they have done such things as reiser4, this patch could be a problem but they will discover this at compile time since we remove remove_from_page_cache(). This patch: This function works as just wrapper remove_from_page_cache(). The difference is that it decreases page references in itself. So caller have to make sure it has a page reference before calling. This patch is ready for removing remove_from_page_cache(). Signed-off-by: Minchan Kim <minchan.kim@gmail.com> Cc: Christoph Hellwig <hch@infradead.org> Acked-by: Hugh Dickins <hughd@google.com> Acked-by: Mel Gorman <mel@csn.ul.ie> Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Reviewed-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Edward Shishkin <edward.shishkin@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-03-23 07:30:53 +08:00
page_cache_release(page);
}
EXPORT_SYMBOL(delete_from_page_cache);
static int sleep_on_page(void *word)
{
io_schedule();
return 0;
}
static int sleep_on_page_killable(void *word)
{
sleep_on_page(word);
return fatal_signal_pending(current) ? -EINTR : 0;
}
/**
* __filemap_fdatawrite_range - start writeback on mapping dirty pages in range
* @mapping: address space structure to write
* @start: offset in bytes where the range starts
* @end: offset in bytes where the range ends (inclusive)
* @sync_mode: enable synchronous operation
*
* Start writeback against all of a mapping's dirty pages that lie
* within the byte offsets <start, end> inclusive.
*
* If sync_mode is WB_SYNC_ALL then this is a "data integrity" operation, as
* opposed to a regular memory cleansing writeback. The difference between
* these two operations is that if a dirty page/buffer is encountered, it must
* be waited upon, and not just skipped over.
*/
[PATCH] fadvise(): write commands Add two new linux-specific fadvise extensions(): LINUX_FADV_ASYNC_WRITE: start async writeout of any dirty pages between file offsets `offset' and `offset+len'. Any pages which are currently under writeout are skipped, whether or not they are dirty. LINUX_FADV_WRITE_WAIT: wait upon writeout of any dirty pages between file offsets `offset' and `offset+len'. By combining these two operations the application may do several things: LINUX_FADV_ASYNC_WRITE: push some or all of the dirty pages at the disk. LINUX_FADV_WRITE_WAIT, LINUX_FADV_ASYNC_WRITE: push all of the currently dirty pages at the disk. LINUX_FADV_WRITE_WAIT, LINUX_FADV_ASYNC_WRITE, LINUX_FADV_WRITE_WAIT: push all of the currently dirty pages at the disk, wait until they have been written. It should be noted that none of these operations write out the file's metadata. So unless the application is strictly performing overwrites of already-instantiated disk blocks, there are no guarantees here that the data will be available after a crash. To complete this suite of operations I guess we should have a "sync file metadata only" operation. This gives applications access to all the building blocks needed for all sorts of sync operations. But sync-metadata doesn't fit well with the fadvise() interface. Probably it should be a new syscall: sys_fmetadatasync(). The patch also diddles with the meaning of `endbyte' in sys_fadvise64_64(). It is made to represent that last affected byte in the file (ie: it is inclusive). Generally, all these byterange and pagerange functions are inclusive so we can easily represent EOF with -1. As Ulrich notes, these two functions are somewhat abusive of the fadvise() concept, which appears to be "set the future policy for this fd". But these commands are a perfect fit with the fadvise() impementation, and several of the existing fadvise() commands are synchronous and don't affect future policy either. I think we can live with the slight incongruity. Cc: Michael Kerrisk <mtk-manpages@gmx.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-24 19:18:04 +08:00
int __filemap_fdatawrite_range(struct address_space *mapping, loff_t start,
loff_t end, int sync_mode)
{
int ret;
struct writeback_control wbc = {
.sync_mode = sync_mode,
mm: write_cache_pages integrity fix In write_cache_pages, nr_to_write is heeded even for data-integrity syncs, so the function will return success after writing out nr_to_write pages, even if that was not sufficient to guarantee data integrity. The callers tend to set it to values that could break data interity semantics easily in practice. For example, nr_to_write can be set to mapping->nr_pages * 2, however if a file has a single, dirty page, then fsync is called, subsequent pages might be concurrently added and dirtied, then write_cache_pages might writeout two of these newly dirty pages, while not writing out the old page that should have been written out. Fix this by ignoring nr_to_write if it is a data integrity sync. This is a data integrity bug. The reason this has been done in the past is to avoid stalling sync operations behind page dirtiers. "If a file has one dirty page at offset 1000000000000000 then someone does an fsync() and someone else gets in first and starts madly writing pages at offset 0, we want to write that page at 1000000000000000. Somehow." What we do today is return success after an arbitrary amount of pages are written, whether or not we have provided the data-integrity semantics that the caller has asked for. Even this doesn't actually fix all stall cases completely: in the above situation, if the file has a huge number of pages in pagecache (but not dirty), then mapping->nrpages is going to be huge, even if pages are being dirtied. This change does indeed make the possibility of long stalls lager, and that's not a good thing, but lying about data integrity is even worse. We have to either perform the sync, or return -ELINUXISLAME so at least the caller knows what has happened. There are subsequent competing approaches in the works to solve the stall problems properly, without compromising data integrity. Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Chris Mason <chris.mason@oracle.com> Cc: Dave Chinner <david@fromorbit.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-07 06:39:08 +08:00
.nr_to_write = LONG_MAX,
[PATCH] writeback: fix range handling When a writeback_control's `start' and `end' fields are used to indicate a one-byte-range starting at file offset zero, the required values of .start=0,.end=0 mean that the ->writepages() implementation has no way of telling that it is being asked to perform a range request. Because we're currently overloading (start == 0 && end == 0) to mean "this is not a write-a-range request". To make all this sane, the patch changes range of writeback_control. So caller does: If it is calling ->writepages() to write pages, it sets range (range_start/end or range_cyclic) always. And if range_cyclic is true, ->writepages() thinks the range is cyclic, otherwise it just uses range_start and range_end. This patch does, - Add LLONG_MAX, LLONG_MIN, ULLONG_MAX to include/linux/kernel.h -1 is usually ok for range_end (type is long long). But, if someone did, range_end += val; range_end is "val - 1" u64val = range_end >> bits; u64val is "~(0ULL)" or something, they are wrong. So, this adds LLONG_MAX to avoid nasty things, and uses LLONG_MAX for range_end. - All callers of ->writepages() sets range_start/end or range_cyclic. - Fix updates of ->writeback_index. It seems already bit strange. If it starts at 0 and ended by check of nr_to_write, this last index may reduce chance to scan end of file. So, this updates ->writeback_index only if range_cyclic is true or whole-file is scanned. Signed-off-by: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp> Cc: Nathan Scott <nathans@sgi.com> Cc: Anton Altaparmakov <aia21@cantab.net> Cc: Steven French <sfrench@us.ibm.com> Cc: "Vladimir V. Saveliev" <vs@namesys.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 17:03:26 +08:00
.range_start = start,
.range_end = end,
};
if (!mapping_cap_writeback_dirty(mapping))
return 0;
ret = do_writepages(mapping, &wbc);
return ret;
}
static inline int __filemap_fdatawrite(struct address_space *mapping,
int sync_mode)
{
[PATCH] writeback: fix range handling When a writeback_control's `start' and `end' fields are used to indicate a one-byte-range starting at file offset zero, the required values of .start=0,.end=0 mean that the ->writepages() implementation has no way of telling that it is being asked to perform a range request. Because we're currently overloading (start == 0 && end == 0) to mean "this is not a write-a-range request". To make all this sane, the patch changes range of writeback_control. So caller does: If it is calling ->writepages() to write pages, it sets range (range_start/end or range_cyclic) always. And if range_cyclic is true, ->writepages() thinks the range is cyclic, otherwise it just uses range_start and range_end. This patch does, - Add LLONG_MAX, LLONG_MIN, ULLONG_MAX to include/linux/kernel.h -1 is usually ok for range_end (type is long long). But, if someone did, range_end += val; range_end is "val - 1" u64val = range_end >> bits; u64val is "~(0ULL)" or something, they are wrong. So, this adds LLONG_MAX to avoid nasty things, and uses LLONG_MAX for range_end. - All callers of ->writepages() sets range_start/end or range_cyclic. - Fix updates of ->writeback_index. It seems already bit strange. If it starts at 0 and ended by check of nr_to_write, this last index may reduce chance to scan end of file. So, this updates ->writeback_index only if range_cyclic is true or whole-file is scanned. Signed-off-by: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp> Cc: Nathan Scott <nathans@sgi.com> Cc: Anton Altaparmakov <aia21@cantab.net> Cc: Steven French <sfrench@us.ibm.com> Cc: "Vladimir V. Saveliev" <vs@namesys.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 17:03:26 +08:00
return __filemap_fdatawrite_range(mapping, 0, LLONG_MAX, sync_mode);
}
int filemap_fdatawrite(struct address_space *mapping)
{
return __filemap_fdatawrite(mapping, WB_SYNC_ALL);
}
EXPORT_SYMBOL(filemap_fdatawrite);
int filemap_fdatawrite_range(struct address_space *mapping, loff_t start,
[PATCH] fadvise(): write commands Add two new linux-specific fadvise extensions(): LINUX_FADV_ASYNC_WRITE: start async writeout of any dirty pages between file offsets `offset' and `offset+len'. Any pages which are currently under writeout are skipped, whether or not they are dirty. LINUX_FADV_WRITE_WAIT: wait upon writeout of any dirty pages between file offsets `offset' and `offset+len'. By combining these two operations the application may do several things: LINUX_FADV_ASYNC_WRITE: push some or all of the dirty pages at the disk. LINUX_FADV_WRITE_WAIT, LINUX_FADV_ASYNC_WRITE: push all of the currently dirty pages at the disk. LINUX_FADV_WRITE_WAIT, LINUX_FADV_ASYNC_WRITE, LINUX_FADV_WRITE_WAIT: push all of the currently dirty pages at the disk, wait until they have been written. It should be noted that none of these operations write out the file's metadata. So unless the application is strictly performing overwrites of already-instantiated disk blocks, there are no guarantees here that the data will be available after a crash. To complete this suite of operations I guess we should have a "sync file metadata only" operation. This gives applications access to all the building blocks needed for all sorts of sync operations. But sync-metadata doesn't fit well with the fadvise() interface. Probably it should be a new syscall: sys_fmetadatasync(). The patch also diddles with the meaning of `endbyte' in sys_fadvise64_64(). It is made to represent that last affected byte in the file (ie: it is inclusive). Generally, all these byterange and pagerange functions are inclusive so we can easily represent EOF with -1. As Ulrich notes, these two functions are somewhat abusive of the fadvise() concept, which appears to be "set the future policy for this fd". But these commands are a perfect fit with the fadvise() impementation, and several of the existing fadvise() commands are synchronous and don't affect future policy either. I think we can live with the slight incongruity. Cc: Michael Kerrisk <mtk-manpages@gmx.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-24 19:18:04 +08:00
loff_t end)
{
return __filemap_fdatawrite_range(mapping, start, end, WB_SYNC_ALL);
}
EXPORT_SYMBOL(filemap_fdatawrite_range);
/**
* filemap_flush - mostly a non-blocking flush
* @mapping: target address_space
*
* This is a mostly non-blocking flush. Not suitable for data-integrity
* purposes - I/O may not be started against all dirty pages.
*/
int filemap_flush(struct address_space *mapping)
{
return __filemap_fdatawrite(mapping, WB_SYNC_NONE);
}
EXPORT_SYMBOL(filemap_flush);
/**
* filemap_fdatawait_range - wait for writeback to complete
* @mapping: address space structure to wait for
* @start_byte: offset in bytes where the range starts
* @end_byte: offset in bytes where the range ends (inclusive)
*
* Walk the list of under-writeback pages of the given address space
* in the given range and wait for all of them.
*/
int filemap_fdatawait_range(struct address_space *mapping, loff_t start_byte,
loff_t end_byte)
{
pgoff_t index = start_byte >> PAGE_CACHE_SHIFT;
pgoff_t end = end_byte >> PAGE_CACHE_SHIFT;
struct pagevec pvec;
int nr_pages;
int ret = 0;
if (end_byte < start_byte)
return 0;
pagevec_init(&pvec, 0);
while ((index <= end) &&
(nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
PAGECACHE_TAG_WRITEBACK,
min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1)) != 0) {
unsigned i;
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
/* until radix tree lookup accepts end_index */
if (page->index > end)
continue;
wait_on_page_writeback(page);
if (TestClearPageError(page))
ret = -EIO;
}
pagevec_release(&pvec);
cond_resched();
}
/* Check for outstanding write errors */
if (test_and_clear_bit(AS_ENOSPC, &mapping->flags))
ret = -ENOSPC;
if (test_and_clear_bit(AS_EIO, &mapping->flags))
ret = -EIO;
return ret;
}
EXPORT_SYMBOL(filemap_fdatawait_range);
/**
* filemap_fdatawait - wait for all under-writeback pages to complete
* @mapping: address space structure to wait for
*
* Walk the list of under-writeback pages of the given address space
* and wait for all of them.
*/
int filemap_fdatawait(struct address_space *mapping)
{
loff_t i_size = i_size_read(mapping->host);
if (i_size == 0)
return 0;
return filemap_fdatawait_range(mapping, 0, i_size - 1);
}
EXPORT_SYMBOL(filemap_fdatawait);
int filemap_write_and_wait(struct address_space *mapping)
{
int err = 0;
if (mapping->nrpages) {
err = filemap_fdatawrite(mapping);
/*
* Even if the above returned error, the pages may be
* written partially (e.g. -ENOSPC), so we wait for it.
* But the -EIO is special case, it may indicate the worst
* thing (e.g. bug) happened, so we avoid waiting for it.
*/
if (err != -EIO) {
int err2 = filemap_fdatawait(mapping);
if (!err)
err = err2;
}
}
return err;
}
EXPORT_SYMBOL(filemap_write_and_wait);
/**
* filemap_write_and_wait_range - write out & wait on a file range
* @mapping: the address_space for the pages
* @lstart: offset in bytes where the range starts
* @lend: offset in bytes where the range ends (inclusive)
*
* Write out and wait upon file offsets lstart->lend, inclusive.
*
* Note that `lend' is inclusive (describes the last byte to be written) so
* that this function can be used to write to the very end-of-file (end = -1).
*/
int filemap_write_and_wait_range(struct address_space *mapping,
loff_t lstart, loff_t lend)
{
int err = 0;
if (mapping->nrpages) {
err = __filemap_fdatawrite_range(mapping, lstart, lend,
WB_SYNC_ALL);
/* See comment of filemap_write_and_wait() */
if (err != -EIO) {
int err2 = filemap_fdatawait_range(mapping,
lstart, lend);
if (!err)
err = err2;
}
}
return err;
}
EXPORT_SYMBOL(filemap_write_and_wait_range);
/**
* replace_page_cache_page - replace a pagecache page with a new one
* @old: page to be replaced
* @new: page to replace with
* @gfp_mask: allocation mode
*
* This function replaces a page in the pagecache with a new one. On
* success it acquires the pagecache reference for the new page and
* drops it for the old page. Both the old and new pages must be
* locked. This function does not add the new page to the LRU, the
* caller must do that.
*
* The remove + add is atomic. The only way this function can fail is
* memory allocation failure.
*/
int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask)
{
int error;
struct mem_cgroup *memcg = NULL;
VM_BUG_ON(!PageLocked(old));
VM_BUG_ON(!PageLocked(new));
VM_BUG_ON(new->mapping);
/*
* This is not page migration, but prepare_migration and
* end_migration does enough work for charge replacement.
*
* In the longer term we probably want a specialized function
* for moving the charge from old to new in a more efficient
* manner.
*/
error = mem_cgroup_prepare_migration(old, new, &memcg, gfp_mask);
if (error)
return error;
error = radix_tree_preload(gfp_mask & ~__GFP_HIGHMEM);
if (!error) {
struct address_space *mapping = old->mapping;
void (*freepage)(struct page *);
pgoff_t offset = old->index;
freepage = mapping->a_ops->freepage;
page_cache_get(new);
new->mapping = mapping;
new->index = offset;
spin_lock_irq(&mapping->tree_lock);
__delete_from_page_cache(old);
error = radix_tree_insert(&mapping->page_tree, offset, new);
BUG_ON(error);
mapping->nrpages++;
__inc_zone_page_state(new, NR_FILE_PAGES);
if (PageSwapBacked(new))
__inc_zone_page_state(new, NR_SHMEM);
spin_unlock_irq(&mapping->tree_lock);
radix_tree_preload_end();
if (freepage)
freepage(old);
page_cache_release(old);
mem_cgroup_end_migration(memcg, old, new, true);
} else {
mem_cgroup_end_migration(memcg, old, new, false);
}
return error;
}
EXPORT_SYMBOL_GPL(replace_page_cache_page);
/**
mm: speculative page references If we can be sure that elevating the page_count on a pagecache page will pin it, we can speculatively run this operation, and subsequently check to see if we hit the right page rather than relying on holding a lock or otherwise pinning a reference to the page. This can be done if get_page/put_page behaves consistently throughout the whole tree (ie. if we "get" the page after it has been used for something else, we must be able to free it with a put_page). Actually, there is a period where the count behaves differently: when the page is free or if it is a constituent page of a compound page. We need an atomic_inc_not_zero operation to ensure we don't try to grab the page in either case. This patch introduces the core locking protocol to the pagecache (ie. adds page_cache_get_speculative, and tweaks some update-side code to make it work). Thanks to Hugh for pointing out an improvement to the algorithm setting page_count to zero when we have control of all references, in order to hold off speculative getters. [kamezawa.hiroyu@jp.fujitsu.com: fix migration_entry_wait()] [hugh@veritas.com: fix add_to_page_cache] [akpm@linux-foundation.org: repair a comment] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeff Garzik <jeff@garzik.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Hugh Dickins <hugh@veritas.com> Cc: "Paul E. McKenney" <paulmck@us.ibm.com> Reviewed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Acked-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-26 10:45:30 +08:00
* add_to_page_cache_locked - add a locked page to the pagecache
* @page: page to add
* @mapping: the page's address_space
* @offset: page index
* @gfp_mask: page allocation mode
*
mm: speculative page references If we can be sure that elevating the page_count on a pagecache page will pin it, we can speculatively run this operation, and subsequently check to see if we hit the right page rather than relying on holding a lock or otherwise pinning a reference to the page. This can be done if get_page/put_page behaves consistently throughout the whole tree (ie. if we "get" the page after it has been used for something else, we must be able to free it with a put_page). Actually, there is a period where the count behaves differently: when the page is free or if it is a constituent page of a compound page. We need an atomic_inc_not_zero operation to ensure we don't try to grab the page in either case. This patch introduces the core locking protocol to the pagecache (ie. adds page_cache_get_speculative, and tweaks some update-side code to make it work). Thanks to Hugh for pointing out an improvement to the algorithm setting page_count to zero when we have control of all references, in order to hold off speculative getters. [kamezawa.hiroyu@jp.fujitsu.com: fix migration_entry_wait()] [hugh@veritas.com: fix add_to_page_cache] [akpm@linux-foundation.org: repair a comment] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeff Garzik <jeff@garzik.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Hugh Dickins <hugh@veritas.com> Cc: "Paul E. McKenney" <paulmck@us.ibm.com> Reviewed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Acked-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-26 10:45:30 +08:00
* This function is used to add a page to the pagecache. It must be locked.
* This function does not add the page to the LRU. The caller must do that.
*/
mm: speculative page references If we can be sure that elevating the page_count on a pagecache page will pin it, we can speculatively run this operation, and subsequently check to see if we hit the right page rather than relying on holding a lock or otherwise pinning a reference to the page. This can be done if get_page/put_page behaves consistently throughout the whole tree (ie. if we "get" the page after it has been used for something else, we must be able to free it with a put_page). Actually, there is a period where the count behaves differently: when the page is free or if it is a constituent page of a compound page. We need an atomic_inc_not_zero operation to ensure we don't try to grab the page in either case. This patch introduces the core locking protocol to the pagecache (ie. adds page_cache_get_speculative, and tweaks some update-side code to make it work). Thanks to Hugh for pointing out an improvement to the algorithm setting page_count to zero when we have control of all references, in order to hold off speculative getters. [kamezawa.hiroyu@jp.fujitsu.com: fix migration_entry_wait()] [hugh@veritas.com: fix add_to_page_cache] [akpm@linux-foundation.org: repair a comment] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeff Garzik <jeff@garzik.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Hugh Dickins <hugh@veritas.com> Cc: "Paul E. McKenney" <paulmck@us.ibm.com> Reviewed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Acked-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-26 10:45:30 +08:00
int add_to_page_cache_locked(struct page *page, struct address_space *mapping,
pgoff_t offset, gfp_t gfp_mask)
{
mm: speculative page references If we can be sure that elevating the page_count on a pagecache page will pin it, we can speculatively run this operation, and subsequently check to see if we hit the right page rather than relying on holding a lock or otherwise pinning a reference to the page. This can be done if get_page/put_page behaves consistently throughout the whole tree (ie. if we "get" the page after it has been used for something else, we must be able to free it with a put_page). Actually, there is a period where the count behaves differently: when the page is free or if it is a constituent page of a compound page. We need an atomic_inc_not_zero operation to ensure we don't try to grab the page in either case. This patch introduces the core locking protocol to the pagecache (ie. adds page_cache_get_speculative, and tweaks some update-side code to make it work). Thanks to Hugh for pointing out an improvement to the algorithm setting page_count to zero when we have control of all references, in order to hold off speculative getters. [kamezawa.hiroyu@jp.fujitsu.com: fix migration_entry_wait()] [hugh@veritas.com: fix add_to_page_cache] [akpm@linux-foundation.org: repair a comment] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeff Garzik <jeff@garzik.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Hugh Dickins <hugh@veritas.com> Cc: "Paul E. McKenney" <paulmck@us.ibm.com> Reviewed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Acked-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-26 10:45:30 +08:00
int error;
VM_BUG_ON(!PageLocked(page));
error = mem_cgroup_cache_charge(page, current->mm,
gfp_mask & GFP_RECLAIM_MASK);
if (error)
goto out;
error = radix_tree_preload(gfp_mask & ~__GFP_HIGHMEM);
if (error == 0) {
mm: speculative page references If we can be sure that elevating the page_count on a pagecache page will pin it, we can speculatively run this operation, and subsequently check to see if we hit the right page rather than relying on holding a lock or otherwise pinning a reference to the page. This can be done if get_page/put_page behaves consistently throughout the whole tree (ie. if we "get" the page after it has been used for something else, we must be able to free it with a put_page). Actually, there is a period where the count behaves differently: when the page is free or if it is a constituent page of a compound page. We need an atomic_inc_not_zero operation to ensure we don't try to grab the page in either case. This patch introduces the core locking protocol to the pagecache (ie. adds page_cache_get_speculative, and tweaks some update-side code to make it work). Thanks to Hugh for pointing out an improvement to the algorithm setting page_count to zero when we have control of all references, in order to hold off speculative getters. [kamezawa.hiroyu@jp.fujitsu.com: fix migration_entry_wait()] [hugh@veritas.com: fix add_to_page_cache] [akpm@linux-foundation.org: repair a comment] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeff Garzik <jeff@garzik.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Hugh Dickins <hugh@veritas.com> Cc: "Paul E. McKenney" <paulmck@us.ibm.com> Reviewed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Acked-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-26 10:45:30 +08:00
page_cache_get(page);
page->mapping = mapping;
page->index = offset;
spin_lock_irq(&mapping->tree_lock);
error = radix_tree_insert(&mapping->page_tree, offset, page);
mm: speculative page references If we can be sure that elevating the page_count on a pagecache page will pin it, we can speculatively run this operation, and subsequently check to see if we hit the right page rather than relying on holding a lock or otherwise pinning a reference to the page. This can be done if get_page/put_page behaves consistently throughout the whole tree (ie. if we "get" the page after it has been used for something else, we must be able to free it with a put_page). Actually, there is a period where the count behaves differently: when the page is free or if it is a constituent page of a compound page. We need an atomic_inc_not_zero operation to ensure we don't try to grab the page in either case. This patch introduces the core locking protocol to the pagecache (ie. adds page_cache_get_speculative, and tweaks some update-side code to make it work). Thanks to Hugh for pointing out an improvement to the algorithm setting page_count to zero when we have control of all references, in order to hold off speculative getters. [kamezawa.hiroyu@jp.fujitsu.com: fix migration_entry_wait()] [hugh@veritas.com: fix add_to_page_cache] [akpm@linux-foundation.org: repair a comment] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeff Garzik <jeff@garzik.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Hugh Dickins <hugh@veritas.com> Cc: "Paul E. McKenney" <paulmck@us.ibm.com> Reviewed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Acked-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-26 10:45:30 +08:00
if (likely(!error)) {
mapping->nrpages++;
__inc_zone_page_state(page, NR_FILE_PAGES);
if (PageSwapBacked(page))
__inc_zone_page_state(page, NR_SHMEM);
spin_unlock_irq(&mapping->tree_lock);
mm: speculative page references If we can be sure that elevating the page_count on a pagecache page will pin it, we can speculatively run this operation, and subsequently check to see if we hit the right page rather than relying on holding a lock or otherwise pinning a reference to the page. This can be done if get_page/put_page behaves consistently throughout the whole tree (ie. if we "get" the page after it has been used for something else, we must be able to free it with a put_page). Actually, there is a period where the count behaves differently: when the page is free or if it is a constituent page of a compound page. We need an atomic_inc_not_zero operation to ensure we don't try to grab the page in either case. This patch introduces the core locking protocol to the pagecache (ie. adds page_cache_get_speculative, and tweaks some update-side code to make it work). Thanks to Hugh for pointing out an improvement to the algorithm setting page_count to zero when we have control of all references, in order to hold off speculative getters. [kamezawa.hiroyu@jp.fujitsu.com: fix migration_entry_wait()] [hugh@veritas.com: fix add_to_page_cache] [akpm@linux-foundation.org: repair a comment] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeff Garzik <jeff@garzik.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Hugh Dickins <hugh@veritas.com> Cc: "Paul E. McKenney" <paulmck@us.ibm.com> Reviewed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Acked-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-26 10:45:30 +08:00
} else {
page->mapping = NULL;
spin_unlock_irq(&mapping->tree_lock);
memcg: remove refcnt from page_cgroup memcg: performance improvements Patch Description 1/5 ... remove refcnt fron page_cgroup patch (shmem handling is fixed) 2/5 ... swapcache handling patch 3/5 ... add helper function for shmem's memory reclaim patch 4/5 ... optimize by likely/unlikely ppatch 5/5 ... remove redundunt check patch (shmem handling is fixed.) Unix bench result. == 2.6.26-rc2-mm1 + memory resource controller Execl Throughput 2915.4 lps (29.6 secs, 3 samples) C Compiler Throughput 1019.3 lpm (60.0 secs, 3 samples) Shell Scripts (1 concurrent) 5796.0 lpm (60.0 secs, 3 samples) Shell Scripts (8 concurrent) 1097.7 lpm (60.0 secs, 3 samples) Shell Scripts (16 concurrent) 565.3 lpm (60.0 secs, 3 samples) File Read 1024 bufsize 2000 maxblocks 1022128.0 KBps (30.0 secs, 3 samples) File Write 1024 bufsize 2000 maxblocks 544057.0 KBps (30.0 secs, 3 samples) File Copy 1024 bufsize 2000 maxblocks 346481.0 KBps (30.0 secs, 3 samples) File Read 256 bufsize 500 maxblocks 319325.0 KBps (30.0 secs, 3 samples) File Write 256 bufsize 500 maxblocks 148788.0 KBps (30.0 secs, 3 samples) File Copy 256 bufsize 500 maxblocks 99051.0 KBps (30.0 secs, 3 samples) File Read 4096 bufsize 8000 maxblocks 2058917.0 KBps (30.0 secs, 3 samples) File Write 4096 bufsize 8000 maxblocks 1606109.0 KBps (30.0 secs, 3 samples) File Copy 4096 bufsize 8000 maxblocks 854789.0 KBps (30.0 secs, 3 samples) Dc: sqrt(2) to 99 decimal places 126145.2 lpm (30.0 secs, 3 samples) INDEX VALUES TEST BASELINE RESULT INDEX Execl Throughput 43.0 2915.4 678.0 File Copy 1024 bufsize 2000 maxblocks 3960.0 346481.0 875.0 File Copy 256 bufsize 500 maxblocks 1655.0 99051.0 598.5 File Copy 4096 bufsize 8000 maxblocks 5800.0 854789.0 1473.8 Shell Scripts (8 concurrent) 6.0 1097.7 1829.5 ========= FINAL SCORE 991.3 == 2.6.26-rc2-mm1 + this set == Execl Throughput 3012.9 lps (29.9 secs, 3 samples) C Compiler Throughput 981.0 lpm (60.0 secs, 3 samples) Shell Scripts (1 concurrent) 5872.0 lpm (60.0 secs, 3 samples) Shell Scripts (8 concurrent) 1120.3 lpm (60.0 secs, 3 samples) Shell Scripts (16 concurrent) 578.0 lpm (60.0 secs, 3 samples) File Read 1024 bufsize 2000 maxblocks 1003993.0 KBps (30.0 secs, 3 samples) File Write 1024 bufsize 2000 maxblocks 550452.0 KBps (30.0 secs, 3 samples) File Copy 1024 bufsize 2000 maxblocks 347159.0 KBps (30.0 secs, 3 samples) File Read 256 bufsize 500 maxblocks 314644.0 KBps (30.0 secs, 3 samples) File Write 256 bufsize 500 maxblocks 151852.0 KBps (30.0 secs, 3 samples) File Copy 256 bufsize 500 maxblocks 101000.0 KBps (30.0 secs, 3 samples) File Read 4096 bufsize 8000 maxblocks 2033256.0 KBps (30.0 secs, 3 samples) File Write 4096 bufsize 8000 maxblocks 1611814.0 KBps (30.0 secs, 3 samples) File Copy 4096 bufsize 8000 maxblocks 847979.0 KBps (30.0 secs, 3 samples) Dc: sqrt(2) to 99 decimal places 128148.7 lpm (30.0 secs, 3 samples) INDEX VALUES TEST BASELINE RESULT INDEX Execl Throughput 43.0 3012.9 700.7 File Copy 1024 bufsize 2000 maxblocks 3960.0 347159.0 876.7 File Copy 256 bufsize 500 maxblocks 1655.0 101000.0 610.3 File Copy 4096 bufsize 8000 maxblocks 5800.0 847979.0 1462.0 Shell Scripts (8 concurrent) 6.0 1120.3 1867.2 ========= FINAL SCORE 1004.6 This patch: Remove refcnt from page_cgroup(). After this, * A page is charged only when !page_mapped() && no page_cgroup is assigned. * Anon page is newly mapped. * File page is added to mapping->tree. * A page is uncharged only when * Anon page is fully unmapped. * File page is removed from LRU. There is no change in behavior from user's view. This patch also removes unnecessary calls in rmap.c which was used only for refcnt mangement. [akpm@linux-foundation.org: fix warning] [hugh@veritas.com: fix shmem_unuse_inode charging] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Balbir Singh <balbir@in.ibm.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Pavel Emelyanov <xemul@openvz.org> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Hugh Dickins <hugh@veritas.com> Cc: YAMAMOTO Takashi <yamamoto@valinux.co.jp> Cc: Paul Menage <menage@google.com> Cc: David Rientjes <rientjes@google.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-25 16:47:14 +08:00
mem_cgroup_uncharge_cache_page(page);
mm: speculative page references If we can be sure that elevating the page_count on a pagecache page will pin it, we can speculatively run this operation, and subsequently check to see if we hit the right page rather than relying on holding a lock or otherwise pinning a reference to the page. This can be done if get_page/put_page behaves consistently throughout the whole tree (ie. if we "get" the page after it has been used for something else, we must be able to free it with a put_page). Actually, there is a period where the count behaves differently: when the page is free or if it is a constituent page of a compound page. We need an atomic_inc_not_zero operation to ensure we don't try to grab the page in either case. This patch introduces the core locking protocol to the pagecache (ie. adds page_cache_get_speculative, and tweaks some update-side code to make it work). Thanks to Hugh for pointing out an improvement to the algorithm setting page_count to zero when we have control of all references, in order to hold off speculative getters. [kamezawa.hiroyu@jp.fujitsu.com: fix migration_entry_wait()] [hugh@veritas.com: fix add_to_page_cache] [akpm@linux-foundation.org: repair a comment] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeff Garzik <jeff@garzik.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Hugh Dickins <hugh@veritas.com> Cc: "Paul E. McKenney" <paulmck@us.ibm.com> Reviewed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Acked-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-26 10:45:30 +08:00
page_cache_release(page);
}
radix_tree_preload_end();
} else
memcg: remove refcnt from page_cgroup memcg: performance improvements Patch Description 1/5 ... remove refcnt fron page_cgroup patch (shmem handling is fixed) 2/5 ... swapcache handling patch 3/5 ... add helper function for shmem's memory reclaim patch 4/5 ... optimize by likely/unlikely ppatch 5/5 ... remove redundunt check patch (shmem handling is fixed.) Unix bench result. == 2.6.26-rc2-mm1 + memory resource controller Execl Throughput 2915.4 lps (29.6 secs, 3 samples) C Compiler Throughput 1019.3 lpm (60.0 secs, 3 samples) Shell Scripts (1 concurrent) 5796.0 lpm (60.0 secs, 3 samples) Shell Scripts (8 concurrent) 1097.7 lpm (60.0 secs, 3 samples) Shell Scripts (16 concurrent) 565.3 lpm (60.0 secs, 3 samples) File Read 1024 bufsize 2000 maxblocks 1022128.0 KBps (30.0 secs, 3 samples) File Write 1024 bufsize 2000 maxblocks 544057.0 KBps (30.0 secs, 3 samples) File Copy 1024 bufsize 2000 maxblocks 346481.0 KBps (30.0 secs, 3 samples) File Read 256 bufsize 500 maxblocks 319325.0 KBps (30.0 secs, 3 samples) File Write 256 bufsize 500 maxblocks 148788.0 KBps (30.0 secs, 3 samples) File Copy 256 bufsize 500 maxblocks 99051.0 KBps (30.0 secs, 3 samples) File Read 4096 bufsize 8000 maxblocks 2058917.0 KBps (30.0 secs, 3 samples) File Write 4096 bufsize 8000 maxblocks 1606109.0 KBps (30.0 secs, 3 samples) File Copy 4096 bufsize 8000 maxblocks 854789.0 KBps (30.0 secs, 3 samples) Dc: sqrt(2) to 99 decimal places 126145.2 lpm (30.0 secs, 3 samples) INDEX VALUES TEST BASELINE RESULT INDEX Execl Throughput 43.0 2915.4 678.0 File Copy 1024 bufsize 2000 maxblocks 3960.0 346481.0 875.0 File Copy 256 bufsize 500 maxblocks 1655.0 99051.0 598.5 File Copy 4096 bufsize 8000 maxblocks 5800.0 854789.0 1473.8 Shell Scripts (8 concurrent) 6.0 1097.7 1829.5 ========= FINAL SCORE 991.3 == 2.6.26-rc2-mm1 + this set == Execl Throughput 3012.9 lps (29.9 secs, 3 samples) C Compiler Throughput 981.0 lpm (60.0 secs, 3 samples) Shell Scripts (1 concurrent) 5872.0 lpm (60.0 secs, 3 samples) Shell Scripts (8 concurrent) 1120.3 lpm (60.0 secs, 3 samples) Shell Scripts (16 concurrent) 578.0 lpm (60.0 secs, 3 samples) File Read 1024 bufsize 2000 maxblocks 1003993.0 KBps (30.0 secs, 3 samples) File Write 1024 bufsize 2000 maxblocks 550452.0 KBps (30.0 secs, 3 samples) File Copy 1024 bufsize 2000 maxblocks 347159.0 KBps (30.0 secs, 3 samples) File Read 256 bufsize 500 maxblocks 314644.0 KBps (30.0 secs, 3 samples) File Write 256 bufsize 500 maxblocks 151852.0 KBps (30.0 secs, 3 samples) File Copy 256 bufsize 500 maxblocks 101000.0 KBps (30.0 secs, 3 samples) File Read 4096 bufsize 8000 maxblocks 2033256.0 KBps (30.0 secs, 3 samples) File Write 4096 bufsize 8000 maxblocks 1611814.0 KBps (30.0 secs, 3 samples) File Copy 4096 bufsize 8000 maxblocks 847979.0 KBps (30.0 secs, 3 samples) Dc: sqrt(2) to 99 decimal places 128148.7 lpm (30.0 secs, 3 samples) INDEX VALUES TEST BASELINE RESULT INDEX Execl Throughput 43.0 3012.9 700.7 File Copy 1024 bufsize 2000 maxblocks 3960.0 347159.0 876.7 File Copy 256 bufsize 500 maxblocks 1655.0 101000.0 610.3 File Copy 4096 bufsize 8000 maxblocks 5800.0 847979.0 1462.0 Shell Scripts (8 concurrent) 6.0 1120.3 1867.2 ========= FINAL SCORE 1004.6 This patch: Remove refcnt from page_cgroup(). After this, * A page is charged only when !page_mapped() && no page_cgroup is assigned. * Anon page is newly mapped. * File page is added to mapping->tree. * A page is uncharged only when * Anon page is fully unmapped. * File page is removed from LRU. There is no change in behavior from user's view. This patch also removes unnecessary calls in rmap.c which was used only for refcnt mangement. [akpm@linux-foundation.org: fix warning] [hugh@veritas.com: fix shmem_unuse_inode charging] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Balbir Singh <balbir@in.ibm.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Pavel Emelyanov <xemul@openvz.org> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Hugh Dickins <hugh@veritas.com> Cc: YAMAMOTO Takashi <yamamoto@valinux.co.jp> Cc: Paul Menage <menage@google.com> Cc: David Rientjes <rientjes@google.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-25 16:47:14 +08:00
mem_cgroup_uncharge_cache_page(page);
Memory controller: memory accounting Add the accounting hooks. The accounting is carried out for RSS and Page Cache (unmapped) pages. There is now a common limit and accounting for both. The RSS accounting is accounted at page_add_*_rmap() and page_remove_rmap() time. Page cache is accounted at add_to_page_cache(), __delete_from_page_cache(). Swap cache is also accounted for. Each page's page_cgroup is protected with the last bit of the page_cgroup pointer, this makes handling of race conditions involving simultaneous mappings of a page easier. A reference count is kept in the page_cgroup to deal with cases where a page might be unmapped from the RSS of all tasks, but still lives in the page cache. Credits go to Vaidyanathan Srinivasan for helping with reference counting work of the page cgroup. Almost all of the page cache accounting code has help from Vaidyanathan Srinivasan. [hugh@veritas.com: fix swapoff breakage] [akpm@linux-foundation.org: fix locking] Signed-off-by: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Paul Menage <menage@google.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Kirill Korotaev <dev@sw.ru> Cc: Herbert Poetzl <herbert@13thfloor.at> Cc: David Rientjes <rientjes@google.com> Cc: <Valdis.Kletnieks@vt.edu> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-07 16:13:53 +08:00
out:
return error;
}
mm: speculative page references If we can be sure that elevating the page_count on a pagecache page will pin it, we can speculatively run this operation, and subsequently check to see if we hit the right page rather than relying on holding a lock or otherwise pinning a reference to the page. This can be done if get_page/put_page behaves consistently throughout the whole tree (ie. if we "get" the page after it has been used for something else, we must be able to free it with a put_page). Actually, there is a period where the count behaves differently: when the page is free or if it is a constituent page of a compound page. We need an atomic_inc_not_zero operation to ensure we don't try to grab the page in either case. This patch introduces the core locking protocol to the pagecache (ie. adds page_cache_get_speculative, and tweaks some update-side code to make it work). Thanks to Hugh for pointing out an improvement to the algorithm setting page_count to zero when we have control of all references, in order to hold off speculative getters. [kamezawa.hiroyu@jp.fujitsu.com: fix migration_entry_wait()] [hugh@veritas.com: fix add_to_page_cache] [akpm@linux-foundation.org: repair a comment] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeff Garzik <jeff@garzik.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Hugh Dickins <hugh@veritas.com> Cc: "Paul E. McKenney" <paulmck@us.ibm.com> Reviewed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Acked-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-26 10:45:30 +08:00
EXPORT_SYMBOL(add_to_page_cache_locked);
int add_to_page_cache_lru(struct page *page, struct address_space *mapping,
pgoff_t offset, gfp_t gfp_mask)
{
vmscan: split LRU lists into anon & file sets Split the LRU lists in two, one set for pages that are backed by real file systems ("file") and one for pages that are backed by memory and swap ("anon"). The latter includes tmpfs. The advantage of doing this is that the VM will not have to scan over lots of anonymous pages (which we generally do not want to swap out), just to find the page cache pages that it should evict. This patch has the infrastructure and a basic policy to balance how much we scan the anon lists and how much we scan the file lists. The big policy changes are in separate patches. [lee.schermerhorn@hp.com: collect lru meminfo statistics from correct offset] [kosaki.motohiro@jp.fujitsu.com: prevent incorrect oom under split_lru] [kosaki.motohiro@jp.fujitsu.com: fix pagevec_move_tail() doesn't treat unevictable page] [hugh@veritas.com: memcg swapbacked pages active] [hugh@veritas.com: splitlru: BDI_CAP_SWAP_BACKED] [akpm@linux-foundation.org: fix /proc/vmstat units] [nishimura@mxp.nes.nec.co.jp: memcg: fix handling of shmem migration] [kosaki.motohiro@jp.fujitsu.com: adjust Quicklists field of /proc/meminfo] [kosaki.motohiro@jp.fujitsu.com: fix style issue of get_scan_ratio()] Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <Lee.Schermerhorn@hp.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:32 +08:00
int ret;
/*
* Splice_read and readahead add shmem/tmpfs pages into the page cache
* before shmem_readpage has a chance to mark them as SwapBacked: they
tmpfs: insert tmpfs cache pages to inactive list at first Shaohua Li reported parallel file copy on tmpfs can lead to OOM killer. This is regression of caused by commit 9ff473b9a7 ("vmscan: evict streaming IO first"). Wow, It is 2 years old patch! Currently, tmpfs file cache is inserted active list at first. This means that the insertion doesn't only increase numbers of pages in anon LRU, but it also reduces anon scanning ratio. Therefore, vmscan will get totally confused. It scans almost only file LRU even though the system has plenty unused tmpfs pages. Historically, lru_cache_add_active_anon() was used for two reasons. 1) Intend to priotize shmem page rather than regular file cache. 2) Intend to avoid reclaim priority inversion of used once pages. But we've lost both motivation because (1) Now we have separate anon and file LRU list. then, to insert active list doesn't help such priotize. (2) In past, one pte access bit will cause page activation. then to insert inactive list with pte access bit mean higher priority than to insert active list. Its priority inversion may lead to uninteded lru chun. but it was already solved by commit 645747462 (vmscan: detect mapped file pages used only once). (Thanks Hannes, you are great!) Thus, now we can use lru_cache_add_anon() instead. Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Reported-by: Shaohua Li <shaohua.li@intel.com> Reviewed-by: Wu Fengguang <fengguang.wu@intel.com> Reviewed-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Rik van Riel <riel@redhat.com> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Acked-by: Hugh Dickins <hughd@google.com> Cc: Henrique de Moraes Holschuh <hmh@hmh.eng.br> Cc: <stable@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-05-25 05:31:48 +08:00
* need to go on the anon lru below, and mem_cgroup_cache_charge
vmscan: split LRU lists into anon & file sets Split the LRU lists in two, one set for pages that are backed by real file systems ("file") and one for pages that are backed by memory and swap ("anon"). The latter includes tmpfs. The advantage of doing this is that the VM will not have to scan over lots of anonymous pages (which we generally do not want to swap out), just to find the page cache pages that it should evict. This patch has the infrastructure and a basic policy to balance how much we scan the anon lists and how much we scan the file lists. The big policy changes are in separate patches. [lee.schermerhorn@hp.com: collect lru meminfo statistics from correct offset] [kosaki.motohiro@jp.fujitsu.com: prevent incorrect oom under split_lru] [kosaki.motohiro@jp.fujitsu.com: fix pagevec_move_tail() doesn't treat unevictable page] [hugh@veritas.com: memcg swapbacked pages active] [hugh@veritas.com: splitlru: BDI_CAP_SWAP_BACKED] [akpm@linux-foundation.org: fix /proc/vmstat units] [nishimura@mxp.nes.nec.co.jp: memcg: fix handling of shmem migration] [kosaki.motohiro@jp.fujitsu.com: adjust Quicklists field of /proc/meminfo] [kosaki.motohiro@jp.fujitsu.com: fix style issue of get_scan_ratio()] Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <Lee.Schermerhorn@hp.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:32 +08:00
* (called in add_to_page_cache) needs to know where they're going too.
*/
if (mapping_cap_swap_backed(mapping))
SetPageSwapBacked(page);
ret = add_to_page_cache(page, mapping, offset, gfp_mask);
if (ret == 0) {
if (page_is_file_cache(page))
lru_cache_add_file(page);
else
tmpfs: insert tmpfs cache pages to inactive list at first Shaohua Li reported parallel file copy on tmpfs can lead to OOM killer. This is regression of caused by commit 9ff473b9a7 ("vmscan: evict streaming IO first"). Wow, It is 2 years old patch! Currently, tmpfs file cache is inserted active list at first. This means that the insertion doesn't only increase numbers of pages in anon LRU, but it also reduces anon scanning ratio. Therefore, vmscan will get totally confused. It scans almost only file LRU even though the system has plenty unused tmpfs pages. Historically, lru_cache_add_active_anon() was used for two reasons. 1) Intend to priotize shmem page rather than regular file cache. 2) Intend to avoid reclaim priority inversion of used once pages. But we've lost both motivation because (1) Now we have separate anon and file LRU list. then, to insert active list doesn't help such priotize. (2) In past, one pte access bit will cause page activation. then to insert inactive list with pte access bit mean higher priority than to insert active list. Its priority inversion may lead to uninteded lru chun. but it was already solved by commit 645747462 (vmscan: detect mapped file pages used only once). (Thanks Hannes, you are great!) Thus, now we can use lru_cache_add_anon() instead. Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Reported-by: Shaohua Li <shaohua.li@intel.com> Reviewed-by: Wu Fengguang <fengguang.wu@intel.com> Reviewed-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Rik van Riel <riel@redhat.com> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Acked-by: Hugh Dickins <hughd@google.com> Cc: Henrique de Moraes Holschuh <hmh@hmh.eng.br> Cc: <stable@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-05-25 05:31:48 +08:00
lru_cache_add_anon(page);
vmscan: split LRU lists into anon & file sets Split the LRU lists in two, one set for pages that are backed by real file systems ("file") and one for pages that are backed by memory and swap ("anon"). The latter includes tmpfs. The advantage of doing this is that the VM will not have to scan over lots of anonymous pages (which we generally do not want to swap out), just to find the page cache pages that it should evict. This patch has the infrastructure and a basic policy to balance how much we scan the anon lists and how much we scan the file lists. The big policy changes are in separate patches. [lee.schermerhorn@hp.com: collect lru meminfo statistics from correct offset] [kosaki.motohiro@jp.fujitsu.com: prevent incorrect oom under split_lru] [kosaki.motohiro@jp.fujitsu.com: fix pagevec_move_tail() doesn't treat unevictable page] [hugh@veritas.com: memcg swapbacked pages active] [hugh@veritas.com: splitlru: BDI_CAP_SWAP_BACKED] [akpm@linux-foundation.org: fix /proc/vmstat units] [nishimura@mxp.nes.nec.co.jp: memcg: fix handling of shmem migration] [kosaki.motohiro@jp.fujitsu.com: adjust Quicklists field of /proc/meminfo] [kosaki.motohiro@jp.fujitsu.com: fix style issue of get_scan_ratio()] Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <Lee.Schermerhorn@hp.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:32 +08:00
}
return ret;
}
EXPORT_SYMBOL_GPL(add_to_page_cache_lru);
#ifdef CONFIG_NUMA
struct page *__page_cache_alloc(gfp_t gfp)
{
cpuset,mm: fix no node to alloc memory when changing cpuset's mems Before applying this patch, cpuset updates task->mems_allowed and mempolicy by setting all new bits in the nodemask first, and clearing all old unallowed bits later. But in the way, the allocator may find that there is no node to alloc memory. The reason is that cpuset rebinds the task's mempolicy, it cleans the nodes which the allocater can alloc pages on, for example: (mpol: mempolicy) task1 task1's mpol task2 alloc page 1 alloc on node0? NO 1 1 change mems from 1 to 0 1 rebind task1's mpol 0-1 set new bits 0 clear disallowed bits alloc on node1? NO 0 ... can't alloc page goto oom This patch fixes this problem by expanding the nodes range first(set newly allowed bits) and shrink it lazily(clear newly disallowed bits). So we use a variable to tell the write-side task that read-side task is reading nodemask, and the write-side task clears newly disallowed nodes after read-side task ends the current memory allocation. [akpm@linux-foundation.org: fix spello] Signed-off-by: Miao Xie <miaox@cn.fujitsu.com> Cc: David Rientjes <rientjes@google.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Paul Menage <menage@google.com> Cc: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Hugh Dickins <hugh.dickins@tiscali.co.uk> Cc: Ravikiran Thirumalai <kiran@scalex86.org> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Christoph Lameter <cl@linux-foundation.org> Cc: Andi Kleen <andi@firstfloor.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-05-25 05:32:08 +08:00
int n;
struct page *page;
if (cpuset_do_page_mem_spread()) {
cpuset,mm: fix no node to alloc memory when changing cpuset's mems Before applying this patch, cpuset updates task->mems_allowed and mempolicy by setting all new bits in the nodemask first, and clearing all old unallowed bits later. But in the way, the allocator may find that there is no node to alloc memory. The reason is that cpuset rebinds the task's mempolicy, it cleans the nodes which the allocater can alloc pages on, for example: (mpol: mempolicy) task1 task1's mpol task2 alloc page 1 alloc on node0? NO 1 1 change mems from 1 to 0 1 rebind task1's mpol 0-1 set new bits 0 clear disallowed bits alloc on node1? NO 0 ... can't alloc page goto oom This patch fixes this problem by expanding the nodes range first(set newly allowed bits) and shrink it lazily(clear newly disallowed bits). So we use a variable to tell the write-side task that read-side task is reading nodemask, and the write-side task clears newly disallowed nodes after read-side task ends the current memory allocation. [akpm@linux-foundation.org: fix spello] Signed-off-by: Miao Xie <miaox@cn.fujitsu.com> Cc: David Rientjes <rientjes@google.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Paul Menage <menage@google.com> Cc: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Hugh Dickins <hugh.dickins@tiscali.co.uk> Cc: Ravikiran Thirumalai <kiran@scalex86.org> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Christoph Lameter <cl@linux-foundation.org> Cc: Andi Kleen <andi@firstfloor.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-05-25 05:32:08 +08:00
get_mems_allowed();
n = cpuset_mem_spread_node();
page = alloc_pages_exact_node(n, gfp, 0);
put_mems_allowed();
return page;
}
return alloc_pages(gfp, 0);
}
EXPORT_SYMBOL(__page_cache_alloc);
#endif
/*
* In order to wait for pages to become available there must be
* waitqueues associated with pages. By using a hash table of
* waitqueues where the bucket discipline is to maintain all
* waiters on the same queue and wake all when any of the pages
* become available, and for the woken contexts to check to be
* sure the appropriate page became available, this saves space
* at a cost of "thundering herd" phenomena during rare hash
* collisions.
*/
static wait_queue_head_t *page_waitqueue(struct page *page)
{
const struct zone *zone = page_zone(page);
return &zone->wait_table[hash_ptr(page, zone->wait_table_bits)];
}
static inline void wake_up_page(struct page *page, int bit)
{
__wake_up_bit(page_waitqueue(page), &page->flags, bit);
}
void wait_on_page_bit(struct page *page, int bit_nr)
{
DEFINE_WAIT_BIT(wait, &page->flags, bit_nr);
if (test_bit(bit_nr, &page->flags))
__wait_on_bit(page_waitqueue(page), &wait, sleep_on_page,
TASK_UNINTERRUPTIBLE);
}
EXPORT_SYMBOL(wait_on_page_bit);
int wait_on_page_bit_killable(struct page *page, int bit_nr)
{
DEFINE_WAIT_BIT(wait, &page->flags, bit_nr);
if (!test_bit(bit_nr, &page->flags))
return 0;
return __wait_on_bit(page_waitqueue(page), &wait,
sleep_on_page_killable, TASK_KILLABLE);
}
/**
* add_page_wait_queue - Add an arbitrary waiter to a page's wait queue
* @page: Page defining the wait queue of interest
* @waiter: Waiter to add to the queue
*
* Add an arbitrary @waiter to the wait queue for the nominated @page.
*/
void add_page_wait_queue(struct page *page, wait_queue_t *waiter)
{
wait_queue_head_t *q = page_waitqueue(page);
unsigned long flags;
spin_lock_irqsave(&q->lock, flags);
__add_wait_queue(q, waiter);
spin_unlock_irqrestore(&q->lock, flags);
}
EXPORT_SYMBOL_GPL(add_page_wait_queue);
/**
* unlock_page - unlock a locked page
* @page: the page
*
* Unlocks the page and wakes up sleepers in ___wait_on_page_locked().
* Also wakes sleepers in wait_on_page_writeback() because the wakeup
* mechananism between PageLocked pages and PageWriteback pages is shared.
* But that's OK - sleepers in wait_on_page_writeback() just go back to sleep.
*
* The mb is necessary to enforce ordering between the clear_bit and the read
* of the waitqueue (to avoid SMP races with a parallel wait_on_page_locked()).
*/
void unlock_page(struct page *page)
{
VM_BUG_ON(!PageLocked(page));
clear_bit_unlock(PG_locked, &page->flags);
smp_mb__after_clear_bit();
wake_up_page(page, PG_locked);
}
EXPORT_SYMBOL(unlock_page);
/**
* end_page_writeback - end writeback against a page
* @page: the page
*/
void end_page_writeback(struct page *page)
{
if (TestClearPageReclaim(page))
rotate_reclaimable_page(page);
if (!test_clear_page_writeback(page))
BUG();
smp_mb__after_clear_bit();
wake_up_page(page, PG_writeback);
}
EXPORT_SYMBOL(end_page_writeback);
/**
* __lock_page - get a lock on the page, assuming we need to sleep to get it
* @page: the page to lock
*/
void __lock_page(struct page *page)
{
DEFINE_WAIT_BIT(wait, &page->flags, PG_locked);
__wait_on_bit_lock(page_waitqueue(page), &wait, sleep_on_page,
TASK_UNINTERRUPTIBLE);
}
EXPORT_SYMBOL(__lock_page);
int __lock_page_killable(struct page *page)
{
DEFINE_WAIT_BIT(wait, &page->flags, PG_locked);
return __wait_on_bit_lock(page_waitqueue(page), &wait,
sleep_on_page_killable, TASK_KILLABLE);
}
EXPORT_SYMBOL_GPL(__lock_page_killable);
mm: retry page fault when blocking on disk transfer This change reduces mmap_sem hold times that are caused by waiting for disk transfers when accessing file mapped VMAs. It introduces the VM_FAULT_ALLOW_RETRY flag, which indicates that the call site wants mmap_sem to be released if blocking on a pending disk transfer. In that case, filemap_fault() returns the VM_FAULT_RETRY status bit and do_page_fault() will then re-acquire mmap_sem and retry the page fault. It is expected that the retry will hit the same page which will now be cached, and thus it will complete with a low mmap_sem hold time. Tests: - microbenchmark: thread A mmaps a large file and does random read accesses to the mmaped area - achieves about 55 iterations/s. Thread B does mmap/munmap in a loop at a separate location - achieves 55 iterations/s before, 15000 iterations/s after. - We are seeing related effects in some applications in house, which show significant performance regressions when running without this change. [akpm@linux-foundation.org: fix warning & crash] Signed-off-by: Michel Lespinasse <walken@google.com> Acked-by: Rik van Riel <riel@redhat.com> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Reviewed-by: Wu Fengguang <fengguang.wu@intel.com> Cc: Ying Han <yinghan@google.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Acked-by: "H. Peter Anvin" <hpa@zytor.com> Cc: <linux-arch@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-10-27 05:21:57 +08:00
int __lock_page_or_retry(struct page *page, struct mm_struct *mm,
unsigned int flags)
{
if (flags & FAULT_FLAG_ALLOW_RETRY) {
/*
* CAUTION! In this case, mmap_sem is not released
* even though return 0.
*/
if (flags & FAULT_FLAG_RETRY_NOWAIT)
return 0;
up_read(&mm->mmap_sem);
if (flags & FAULT_FLAG_KILLABLE)
wait_on_page_locked_killable(page);
else
wait_on_page_locked(page);
mm: retry page fault when blocking on disk transfer This change reduces mmap_sem hold times that are caused by waiting for disk transfers when accessing file mapped VMAs. It introduces the VM_FAULT_ALLOW_RETRY flag, which indicates that the call site wants mmap_sem to be released if blocking on a pending disk transfer. In that case, filemap_fault() returns the VM_FAULT_RETRY status bit and do_page_fault() will then re-acquire mmap_sem and retry the page fault. It is expected that the retry will hit the same page which will now be cached, and thus it will complete with a low mmap_sem hold time. Tests: - microbenchmark: thread A mmaps a large file and does random read accesses to the mmaped area - achieves about 55 iterations/s. Thread B does mmap/munmap in a loop at a separate location - achieves 55 iterations/s before, 15000 iterations/s after. - We are seeing related effects in some applications in house, which show significant performance regressions when running without this change. [akpm@linux-foundation.org: fix warning & crash] Signed-off-by: Michel Lespinasse <walken@google.com> Acked-by: Rik van Riel <riel@redhat.com> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Reviewed-by: Wu Fengguang <fengguang.wu@intel.com> Cc: Ying Han <yinghan@google.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Acked-by: "H. Peter Anvin" <hpa@zytor.com> Cc: <linux-arch@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-10-27 05:21:57 +08:00
return 0;
} else {
if (flags & FAULT_FLAG_KILLABLE) {
int ret;
ret = __lock_page_killable(page);
if (ret) {
up_read(&mm->mmap_sem);
return 0;
}
} else
__lock_page(page);
return 1;
mm: retry page fault when blocking on disk transfer This change reduces mmap_sem hold times that are caused by waiting for disk transfers when accessing file mapped VMAs. It introduces the VM_FAULT_ALLOW_RETRY flag, which indicates that the call site wants mmap_sem to be released if blocking on a pending disk transfer. In that case, filemap_fault() returns the VM_FAULT_RETRY status bit and do_page_fault() will then re-acquire mmap_sem and retry the page fault. It is expected that the retry will hit the same page which will now be cached, and thus it will complete with a low mmap_sem hold time. Tests: - microbenchmark: thread A mmaps a large file and does random read accesses to the mmaped area - achieves about 55 iterations/s. Thread B does mmap/munmap in a loop at a separate location - achieves 55 iterations/s before, 15000 iterations/s after. - We are seeing related effects in some applications in house, which show significant performance regressions when running without this change. [akpm@linux-foundation.org: fix warning & crash] Signed-off-by: Michel Lespinasse <walken@google.com> Acked-by: Rik van Riel <riel@redhat.com> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Reviewed-by: Wu Fengguang <fengguang.wu@intel.com> Cc: Ying Han <yinghan@google.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Acked-by: "H. Peter Anvin" <hpa@zytor.com> Cc: <linux-arch@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-10-27 05:21:57 +08:00
}
}
/**
* find_get_page - find and get a page reference
* @mapping: the address_space to search
* @offset: the page index
*
* Is there a pagecache struct page at the given (mapping, offset) tuple?
* If yes, increment its refcount and return it; if no, return NULL.
*/
struct page *find_get_page(struct address_space *mapping, pgoff_t offset)
{
void **pagep;
struct page *page;
rcu_read_lock();
repeat:
page = NULL;
pagep = radix_tree_lookup_slot(&mapping->page_tree, offset);
if (pagep) {
page = radix_tree_deref_slot(pagep);
if (unlikely(!page))
goto out;
if (radix_tree_deref_retry(page))
goto repeat;
if (!page_cache_get_speculative(page))
goto repeat;
/*
* Has the page moved?
* This is part of the lockless pagecache protocol. See
* include/linux/pagemap.h for details.
*/
if (unlikely(page != *pagep)) {
page_cache_release(page);
goto repeat;
}
}
out:
rcu_read_unlock();
return page;
}
EXPORT_SYMBOL(find_get_page);
/**
* find_lock_page - locate, pin and lock a pagecache page
* @mapping: the address_space to search
* @offset: the page index
*
* Locates the desired pagecache page, locks it, increments its reference
* count and returns its address.
*
* Returns zero if the page was not present. find_lock_page() may sleep.
*/
struct page *find_lock_page(struct address_space *mapping, pgoff_t offset)
{
struct page *page;
repeat:
page = find_get_page(mapping, offset);
if (page) {
lock_page(page);
/* Has the page been truncated? */
if (unlikely(page->mapping != mapping)) {
unlock_page(page);
page_cache_release(page);
goto repeat;
}
VM_BUG_ON(page->index != offset);
}
return page;
}
EXPORT_SYMBOL(find_lock_page);
/**
* find_or_create_page - locate or add a pagecache page
* @mapping: the page's address_space
* @index: the page's index into the mapping
* @gfp_mask: page allocation mode
*
* Locates a page in the pagecache. If the page is not present, a new page
* is allocated using @gfp_mask and is added to the pagecache and to the VM's
* LRU list. The returned page is locked and has its reference count
* incremented.
*
* find_or_create_page() may sleep, even if @gfp_flags specifies an atomic
* allocation!
*
* find_or_create_page() returns the desired page's address, or zero on
* memory exhaustion.
*/
struct page *find_or_create_page(struct address_space *mapping,
pgoff_t index, gfp_t gfp_mask)
{
struct page *page;
int err;
repeat:
page = find_lock_page(mapping, index);
if (!page) {
page = __page_cache_alloc(gfp_mask);
if (!page)
return NULL;
mm: pagecache gfp flags fix Frustratingly, gfp_t is really divided into two classes of flags. One are the context dependent ones (can we sleep? can we enter filesystem? block subsystem? should we use some extra reserves, etc.). The other ones are the type of memory required and depend on how the algorithm is implemented rather than the point at which the memory is allocated (highmem? dma memory? etc). Some of the functions which allocate a page and add it to page cache take a gfp_t, but sometimes those functions or their callers aren't really doing the right thing: when allocating pagecache page, the memory type should be mapping_gfp_mask(mapping). When allocating radix tree nodes, the memory type should be kernel mapped (not highmem) memory. The gfp_t argument should only really be needed for context dependent options. This patch doesn't really solve that tangle in a nice way, but it does attempt to fix a couple of bugs. - find_or_create_page changes its radix-tree allocation to only include the main context dependent flags in order so the pagecache page may be allocated from arbitrary types of memory without affecting the radix-tree. In practice, slab allocations don't come from highmem anyway, and radix-tree only uses slab allocations. So there isn't a practical change (unless some fs uses GFP_DMA for pages). - grab_cache_page_nowait() is changed to allocate radix-tree nodes with GFP_NOFS, because it is not supposed to reenter the filesystem. This bug could cause lock recursion if a filesystem is not expecting the function to reenter the fs (as-per documentation). Filesystems should be careful about exactly what semantics they want and what they get when fiddling with gfp_t masks to allocate pagecache. One should be as liberal as possible with the type of memory that can be used, and same for the the context specific flags. 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>
2009-01-07 06:40:28 +08:00
/*
* We want a regular kernel memory (not highmem or DMA etc)
* allocation for the radix tree nodes, but we need to honour
* the context-specific requirements the caller has asked for.
* GFP_RECLAIM_MASK collects those requirements.
*/
err = add_to_page_cache_lru(page, mapping, index,
(gfp_mask & GFP_RECLAIM_MASK));
if (unlikely(err)) {
page_cache_release(page);
page = NULL;
if (err == -EEXIST)
goto repeat;
}
}
return page;
}
EXPORT_SYMBOL(find_or_create_page);
/**
* find_get_pages - gang pagecache lookup
* @mapping: The address_space to search
* @start: The starting page index
* @nr_pages: The maximum number of pages
* @pages: Where the resulting pages are placed
*
* find_get_pages() will search for and return a group of up to
* @nr_pages pages in the mapping. The pages are placed at @pages.
* find_get_pages() takes a reference against the returned pages.
*
* The search returns a group of mapping-contiguous pages with ascending
* indexes. There may be holes in the indices due to not-present pages.
*
* find_get_pages() returns the number of pages which were found.
*/
unsigned find_get_pages(struct address_space *mapping, pgoff_t start,
unsigned int nr_pages, struct page **pages)
{
unsigned int i;
unsigned int ret;
unsigned int nr_found;
rcu_read_lock();
restart:
nr_found = radix_tree_gang_lookup_slot(&mapping->page_tree,
(void ***)pages, start, nr_pages);
ret = 0;
for (i = 0; i < nr_found; i++) {
struct page *page;
repeat:
page = radix_tree_deref_slot((void **)pages[i]);
if (unlikely(!page))
continue;
/*
* This can only trigger when the entry at index 0 moves out
* of or back to the root: none yet gotten, safe to restart.
*/
if (radix_tree_deref_retry(page)) {
WARN_ON(start | i);
goto restart;
}
if (!page_cache_get_speculative(page))
goto repeat;
/* Has the page moved? */
if (unlikely(page != *((void **)pages[i]))) {
page_cache_release(page);
goto repeat;
}
pages[ret] = page;
ret++;
}
/*
* If all entries were removed before we could secure them,
* try again, because callers stop trying once 0 is returned.
*/
if (unlikely(!ret && nr_found))
goto restart;
rcu_read_unlock();
return ret;
}
/**
* find_get_pages_contig - gang contiguous pagecache lookup
* @mapping: The address_space to search
* @index: The starting page index
* @nr_pages: The maximum number of pages
* @pages: Where the resulting pages are placed
*
* find_get_pages_contig() works exactly like find_get_pages(), except
* that the returned number of pages are guaranteed to be contiguous.
*
* find_get_pages_contig() returns the number of pages which were found.
*/
unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t index,
unsigned int nr_pages, struct page **pages)
{
unsigned int i;
unsigned int ret;
unsigned int nr_found;
rcu_read_lock();
restart:
nr_found = radix_tree_gang_lookup_slot(&mapping->page_tree,
(void ***)pages, index, nr_pages);
ret = 0;
for (i = 0; i < nr_found; i++) {
struct page *page;
repeat:
page = radix_tree_deref_slot((void **)pages[i]);
if (unlikely(!page))
continue;
/*
* This can only trigger when the entry at index 0 moves out
* of or back to the root: none yet gotten, safe to restart.
*/
if (radix_tree_deref_retry(page))
goto restart;
if (!page_cache_get_speculative(page))
goto repeat;
/* Has the page moved? */
if (unlikely(page != *((void **)pages[i]))) {
page_cache_release(page);
goto repeat;
}
/*
* must check mapping and index after taking the ref.
* otherwise we can get both false positives and false
* negatives, which is just confusing to the caller.
*/
if (page->mapping == NULL || page->index != index) {
page_cache_release(page);
break;
}
pages[ret] = page;
ret++;
index++;
}
rcu_read_unlock();
return ret;
}
EXPORT_SYMBOL(find_get_pages_contig);
/**
* find_get_pages_tag - find and return pages that match @tag
* @mapping: the address_space to search
* @index: the starting page index
* @tag: the tag index
* @nr_pages: the maximum number of pages
* @pages: where the resulting pages are placed
*
* Like find_get_pages, except we only return pages which are tagged with
* @tag. We update @index to index the next page for the traversal.
*/
unsigned find_get_pages_tag(struct address_space *mapping, pgoff_t *index,
int tag, unsigned int nr_pages, struct page **pages)
{
unsigned int i;
unsigned int ret;
unsigned int nr_found;
rcu_read_lock();
restart:
nr_found = radix_tree_gang_lookup_tag_slot(&mapping->page_tree,
(void ***)pages, *index, nr_pages, tag);
ret = 0;
for (i = 0; i < nr_found; i++) {
struct page *page;
repeat:
page = radix_tree_deref_slot((void **)pages[i]);
if (unlikely(!page))
continue;
/*
* This can only trigger when the entry at index 0 moves out
* of or back to the root: none yet gotten, safe to restart.
*/
if (radix_tree_deref_retry(page))
goto restart;
if (!page_cache_get_speculative(page))
goto repeat;
/* Has the page moved? */
if (unlikely(page != *((void **)pages[i]))) {
page_cache_release(page);
goto repeat;
}
pages[ret] = page;
ret++;
}
/*
* If all entries were removed before we could secure them,
* try again, because callers stop trying once 0 is returned.
*/
if (unlikely(!ret && nr_found))
goto restart;
rcu_read_unlock();
if (ret)
*index = pages[ret - 1]->index + 1;
return ret;
}
EXPORT_SYMBOL(find_get_pages_tag);
/**
* grab_cache_page_nowait - returns locked page at given index in given cache
* @mapping: target address_space
* @index: the page index
*
* Same as grab_cache_page(), but do not wait if the page is unavailable.
* This is intended for speculative data generators, where the data can
* be regenerated if the page couldn't be grabbed. This routine should
* be safe to call while holding the lock for another page.
*
* Clear __GFP_FS when allocating the page to avoid recursion into the fs
* and deadlock against the caller's locked page.
*/
struct page *
grab_cache_page_nowait(struct address_space *mapping, pgoff_t index)
{
struct page *page = find_get_page(mapping, index);
if (page) {
if (trylock_page(page))
return page;
page_cache_release(page);
return NULL;
}
page = __page_cache_alloc(mapping_gfp_mask(mapping) & ~__GFP_FS);
mm: pagecache gfp flags fix Frustratingly, gfp_t is really divided into two classes of flags. One are the context dependent ones (can we sleep? can we enter filesystem? block subsystem? should we use some extra reserves, etc.). The other ones are the type of memory required and depend on how the algorithm is implemented rather than the point at which the memory is allocated (highmem? dma memory? etc). Some of the functions which allocate a page and add it to page cache take a gfp_t, but sometimes those functions or their callers aren't really doing the right thing: when allocating pagecache page, the memory type should be mapping_gfp_mask(mapping). When allocating radix tree nodes, the memory type should be kernel mapped (not highmem) memory. The gfp_t argument should only really be needed for context dependent options. This patch doesn't really solve that tangle in a nice way, but it does attempt to fix a couple of bugs. - find_or_create_page changes its radix-tree allocation to only include the main context dependent flags in order so the pagecache page may be allocated from arbitrary types of memory without affecting the radix-tree. In practice, slab allocations don't come from highmem anyway, and radix-tree only uses slab allocations. So there isn't a practical change (unless some fs uses GFP_DMA for pages). - grab_cache_page_nowait() is changed to allocate radix-tree nodes with GFP_NOFS, because it is not supposed to reenter the filesystem. This bug could cause lock recursion if a filesystem is not expecting the function to reenter the fs (as-per documentation). Filesystems should be careful about exactly what semantics they want and what they get when fiddling with gfp_t masks to allocate pagecache. One should be as liberal as possible with the type of memory that can be used, and same for the the context specific flags. 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>
2009-01-07 06:40:28 +08:00
if (page && add_to_page_cache_lru(page, mapping, index, GFP_NOFS)) {
page_cache_release(page);
page = NULL;
}
return page;
}
EXPORT_SYMBOL(grab_cache_page_nowait);
[PATCH] readahead: backoff on I/O error Backoff readahead size exponentially on I/O error. Michael Tokarev <mjt@tls.msk.ru> described the problem as: [QUOTE] Suppose there's a CD-rom with a scratch/etc, one sector is unreadable. In order to "fix" it, one have to read it and write to another CD-rom, or something.. or just ignore the error (if it's just a skip in a video stream). Let's assume the unreadable block is number U. But current behavior is just insane. An application requests block number N, which is before U. Kernel tries to read-ahead blocks N..U. Cdrom drive tries to read it, re-read it.. for some time. Finally, when all the N..U-1 blocks are read, kernel returns block number N (as requested) to an application, successefully. Now an app requests block number N+1, and kernel tries to read blocks N+1..U+1. Retrying again as in previous step. And so on, up to when an app requests block number U-1. And when, finally, it requests block U, it receives read error. So, kernel currentry tries to re-read the same failing block as many times as the current readahead value (256 (times?) by default). This whole process already killed my cdrom drive (I posted about it to LKML several months ago) - literally, the drive has fried, and does not work anymore. Ofcourse that problem was a bug in firmware (or whatever) of the drive *too*, but.. main problem with that is current readahead logic as described above. [/QUOTE] Which was confirmed by Jens Axboe <axboe@suse.de>: [QUOTE] For ide-cd, it tends do only end the first part of the request on a medium error. So you may see a lot of repeats :/ [/QUOTE] With this patch, retries are expected to be reduced from, say, 256, to 5. [akpm@osdl.org: cleanups] Signed-off-by: Wu Fengguang <wfg@mail.ustc.edu.cn> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-25 20:48:43 +08:00
/*
* CD/DVDs are error prone. When a medium error occurs, the driver may fail
* a _large_ part of the i/o request. Imagine the worst scenario:
*
* ---R__________________________________________B__________
* ^ reading here ^ bad block(assume 4k)
*
* read(R) => miss => readahead(R...B) => media error => frustrating retries
* => failing the whole request => read(R) => read(R+1) =>
* readahead(R+1...B+1) => bang => read(R+2) => read(R+3) =>
* readahead(R+3...B+2) => bang => read(R+3) => read(R+4) =>
* readahead(R+4...B+3) => bang => read(R+4) => read(R+5) => ......
*
* It is going insane. Fix it by quickly scaling down the readahead size.
*/
static void shrink_readahead_size_eio(struct file *filp,
struct file_ra_state *ra)
{
ra->ra_pages /= 4;
}
/**
* do_generic_file_read - generic file read routine
* @filp: the file to read
* @ppos: current file position
* @desc: read_descriptor
* @actor: read method
*
* This is a generic file read routine, and uses the
* mapping->a_ops->readpage() function for the actual low-level stuff.
*
* This is really ugly. But the goto's actually try to clarify some
* of the logic when it comes to error handling etc.
*/
static void do_generic_file_read(struct file *filp, loff_t *ppos,
read_descriptor_t *desc, read_actor_t actor)
{
struct address_space *mapping = filp->f_mapping;
struct inode *inode = mapping->host;
struct file_ra_state *ra = &filp->f_ra;
pgoff_t index;
pgoff_t last_index;
pgoff_t prev_index;
unsigned long offset; /* offset into pagecache page */
unsigned int prev_offset;
int error;
index = *ppos >> PAGE_CACHE_SHIFT;
prev_index = ra->prev_pos >> PAGE_CACHE_SHIFT;
prev_offset = ra->prev_pos & (PAGE_CACHE_SIZE-1);
last_index = (*ppos + desc->count + PAGE_CACHE_SIZE-1) >> PAGE_CACHE_SHIFT;
offset = *ppos & ~PAGE_CACHE_MASK;
for (;;) {
struct page *page;
pgoff_t end_index;
Fix read/truncate race do_generic_mapping_read currently samples the i_size at the start and doesn't do so again unless it needs to call ->readpage to load a page. After ->readpage it has to re-sample i_size as a truncate may have caused that page to be filled with zeros, and the read() call should not see these. However there are other activities that might cause ->readpage to be called on a page between the time that do_generic_mapping_read samples i_size and when it finds that it has an uptodate page. These include at least read-ahead and possibly another thread performing a read. So do_generic_mapping_read must sample i_size *after* it has an uptodate page. Thus the current sampling at the start and after a read can be replaced with a sampling before the copy-out. The same change applied to __generic_file_splice_read. Note that this fixes any race with truncate_complete_page, but does not fix a possible race with truncate_partial_page. If a partial truncate happens after do_generic_mapping_read samples i_size and before the copy_out, the nuls that truncate_partial_page place in the page could be copied out incorrectly. I think the best fix for that is to *not* zero out parts of the page in truncate_partial_page, but rather to zero out the tail of a page when increasing i_size. Signed-off-by: Neil Brown <neilb@suse.de> Cc: Jens Axboe <jens.axboe@oracle.com> Acked-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-17 19:03:04 +08:00
loff_t isize;
unsigned long nr, ret;
cond_resched();
find_page:
page = find_get_page(mapping, index);
if (!page) {
page_cache_sync_readahead(mapping,
ra, filp,
index, last_index - index);
page = find_get_page(mapping, index);
if (unlikely(page == NULL))
goto no_cached_page;
}
if (PageReadahead(page)) {
page_cache_async_readahead(mapping,
ra, filp, page,
index, last_index - index);
}
vfs: pagecache usage optimization for pagesize!=blocksize When we read some part of a file through pagecache, if there is a pagecache of corresponding index but this page is not uptodate, read IO is issued and this page will be uptodate. I think this is good for pagesize == blocksize environment but there is room for improvement on pagesize != blocksize environment. Because in this case a page can have multiple buffers and even if a page is not uptodate, some buffers can be uptodate. So I suggest that when all buffers which correspond to a part of a file that we want to read are uptodate, use this pagecache and copy data from this pagecache to user buffer even if a page is not uptodate. This can reduce read IO and improve system throughput. I wrote a benchmark program and got result number with this program. This benchmark do: 1: mount and open a test file. 2: create a 512MB file. 3: close a file and umount. 4: mount and again open a test file. 5: pwrite randomly 300000 times on a test file. offset is aligned by IO size(1024bytes). 6: measure time of preading randomly 100000 times on a test file. The result was: 2.6.26 330 sec 2.6.26-patched 226 sec Arch:i386 Filesystem:ext3 Blocksize:1024 bytes Memory: 1GB On ext3/4, a file is written through buffer/block. So random read/write mixed workloads or random read after random write workloads are optimized with this patch under pagesize != blocksize environment. This test result showed this. The benchmark program is as follows: #include <stdio.h> #include <sys/types.h> #include <sys/stat.h> #include <fcntl.h> #include <unistd.h> #include <time.h> #include <stdlib.h> #include <string.h> #include <sys/mount.h> #define LEN 1024 #define LOOP 1024*512 /* 512MB */ main(void) { unsigned long i, offset, filesize; int fd; char buf[LEN]; time_t t1, t2; if (mount("/dev/sda1", "/root/test1/", "ext3", 0, 0) < 0) { perror("cannot mount\n"); exit(1); } memset(buf, 0, LEN); fd = open("/root/test1/testfile", O_CREAT|O_RDWR|O_TRUNC); if (fd < 0) { perror("cannot open file\n"); exit(1); } for (i = 0; i < LOOP; i++) write(fd, buf, LEN); close(fd); if (umount("/root/test1/") < 0) { perror("cannot umount\n"); exit(1); } if (mount("/dev/sda1", "/root/test1/", "ext3", 0, 0) < 0) { perror("cannot mount\n"); exit(1); } fd = open("/root/test1/testfile", O_RDWR); if (fd < 0) { perror("cannot open file\n"); exit(1); } filesize = LEN * LOOP; for (i = 0; i < 300000; i++){ offset = (random() % filesize) & (~(LEN - 1)); pwrite(fd, buf, LEN, offset); } printf("start test\n"); time(&t1); for (i = 0; i < 100000; i++){ offset = (random() % filesize) & (~(LEN - 1)); pread(fd, buf, LEN, offset); } time(&t2); printf("%ld sec\n", t2-t1); close(fd); if (umount("/root/test1/") < 0) { perror("cannot umount\n"); exit(1); } } Signed-off-by: Hisashi Hifumi <hifumi.hisashi@oss.ntt.co.jp> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Christoph Hellwig <hch@infradead.org> Cc: Jan Kara <jack@ucw.cz> Cc: <linux-ext4@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-29 06:46:36 +08:00
if (!PageUptodate(page)) {
if (inode->i_blkbits == PAGE_CACHE_SHIFT ||
!mapping->a_ops->is_partially_uptodate)
goto page_not_up_to_date;
if (!trylock_page(page))
vfs: pagecache usage optimization for pagesize!=blocksize When we read some part of a file through pagecache, if there is a pagecache of corresponding index but this page is not uptodate, read IO is issued and this page will be uptodate. I think this is good for pagesize == blocksize environment but there is room for improvement on pagesize != blocksize environment. Because in this case a page can have multiple buffers and even if a page is not uptodate, some buffers can be uptodate. So I suggest that when all buffers which correspond to a part of a file that we want to read are uptodate, use this pagecache and copy data from this pagecache to user buffer even if a page is not uptodate. This can reduce read IO and improve system throughput. I wrote a benchmark program and got result number with this program. This benchmark do: 1: mount and open a test file. 2: create a 512MB file. 3: close a file and umount. 4: mount and again open a test file. 5: pwrite randomly 300000 times on a test file. offset is aligned by IO size(1024bytes). 6: measure time of preading randomly 100000 times on a test file. The result was: 2.6.26 330 sec 2.6.26-patched 226 sec Arch:i386 Filesystem:ext3 Blocksize:1024 bytes Memory: 1GB On ext3/4, a file is written through buffer/block. So random read/write mixed workloads or random read after random write workloads are optimized with this patch under pagesize != blocksize environment. This test result showed this. The benchmark program is as follows: #include <stdio.h> #include <sys/types.h> #include <sys/stat.h> #include <fcntl.h> #include <unistd.h> #include <time.h> #include <stdlib.h> #include <string.h> #include <sys/mount.h> #define LEN 1024 #define LOOP 1024*512 /* 512MB */ main(void) { unsigned long i, offset, filesize; int fd; char buf[LEN]; time_t t1, t2; if (mount("/dev/sda1", "/root/test1/", "ext3", 0, 0) < 0) { perror("cannot mount\n"); exit(1); } memset(buf, 0, LEN); fd = open("/root/test1/testfile", O_CREAT|O_RDWR|O_TRUNC); if (fd < 0) { perror("cannot open file\n"); exit(1); } for (i = 0; i < LOOP; i++) write(fd, buf, LEN); close(fd); if (umount("/root/test1/") < 0) { perror("cannot umount\n"); exit(1); } if (mount("/dev/sda1", "/root/test1/", "ext3", 0, 0) < 0) { perror("cannot mount\n"); exit(1); } fd = open("/root/test1/testfile", O_RDWR); if (fd < 0) { perror("cannot open file\n"); exit(1); } filesize = LEN * LOOP; for (i = 0; i < 300000; i++){ offset = (random() % filesize) & (~(LEN - 1)); pwrite(fd, buf, LEN, offset); } printf("start test\n"); time(&t1); for (i = 0; i < 100000; i++){ offset = (random() % filesize) & (~(LEN - 1)); pread(fd, buf, LEN, offset); } time(&t2); printf("%ld sec\n", t2-t1); close(fd); if (umount("/root/test1/") < 0) { perror("cannot umount\n"); exit(1); } } Signed-off-by: Hisashi Hifumi <hifumi.hisashi@oss.ntt.co.jp> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Christoph Hellwig <hch@infradead.org> Cc: Jan Kara <jack@ucw.cz> Cc: <linux-ext4@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-29 06:46:36 +08:00
goto page_not_up_to_date;
mm/vfs: revalidate page->mapping in do_generic_file_read() 70 hours into some stress tests of a 2.6.32-based enterprise kernel, we ran into a NULL dereference in here: int block_is_partially_uptodate(struct page *page, read_descriptor_t *desc, unsigned long from) { ----> struct inode *inode = page->mapping->host; It looks like page->mapping was the culprit. (xmon trace is below). After closer examination, I realized that do_generic_file_read() does a find_get_page(), and eventually locks the page before calling block_is_partially_uptodate(). However, it doesn't revalidate the page->mapping after the page is locked. So, there's a small window between the find_get_page() and ->is_partially_uptodate() where the page could get truncated and page->mapping cleared. We _have_ a reference, so it can't get reclaimed, but it certainly can be truncated. I think the correct thing is to check page->mapping after the trylock_page(), and jump out if it got truncated. This patch has been running in the test environment for a month or so now, and we have not seen this bug pop up again. xmon info: 1f:mon> e cpu 0x1f: Vector: 300 (Data Access) at [c0000002ae36f770] pc: c0000000001e7a6c: .block_is_partially_uptodate+0xc/0x100 lr: c000000000142944: .generic_file_aio_read+0x1e4/0x770 sp: c0000002ae36f9f0 msr: 8000000000009032 dar: 0 dsisr: 40000000 current = 0xc000000378f99e30 paca = 0xc000000000f66300 pid = 21946, comm = bash 1f:mon> r R00 = 0025c0500000006d R16 = 0000000000000000 R01 = c0000002ae36f9f0 R17 = c000000362cd3af0 R02 = c000000000e8cd80 R18 = ffffffffffffffff R03 = c0000000031d0f88 R19 = 0000000000000001 R04 = c0000002ae36fa68 R20 = c0000003bb97b8a0 R05 = 0000000000000000 R21 = c0000002ae36fa68 R06 = 0000000000000000 R22 = 0000000000000000 R07 = 0000000000000001 R23 = c0000002ae36fbb0 R08 = 0000000000000002 R24 = 0000000000000000 R09 = 0000000000000000 R25 = c000000362cd3a80 R10 = 0000000000000000 R26 = 0000000000000002 R11 = c0000000001e7b60 R27 = 0000000000000000 R12 = 0000000042000484 R28 = 0000000000000001 R13 = c000000000f66300 R29 = c0000003bb97b9b8 R14 = 0000000000000001 R30 = c000000000e28a08 R15 = 000000000000ffff R31 = c0000000031d0f88 pc = c0000000001e7a6c .block_is_partially_uptodate+0xc/0x100 lr = c000000000142944 .generic_file_aio_read+0x1e4/0x770 msr = 8000000000009032 cr = 22000488 ctr = c0000000001e7a60 xer = 0000000020000000 trap = 300 dar = 0000000000000000 dsisr = 40000000 1f:mon> t [link register ] c000000000142944 .generic_file_aio_read+0x1e4/0x770 [c0000002ae36f9f0] c000000000142a14 .generic_file_aio_read+0x2b4/0x770 (unreliable) [c0000002ae36fb40] c0000000001b03e4 .do_sync_read+0xd4/0x160 [c0000002ae36fce0] c0000000001b153c .vfs_read+0xec/0x1f0 [c0000002ae36fd80] c0000000001b1768 .SyS_read+0x58/0xb0 [c0000002ae36fe30] c00000000000852c syscall_exit+0x0/0x40 --- Exception: c00 (System Call) at 00000080a840bc54 SP (fffca15df30) is in userspace 1f:mon> di c0000000001e7a6c c0000000001e7a6c e9290000 ld r9,0(r9) c0000000001e7a70 418200c0 beq c0000000001e7b30 # .block_is_partially_uptodate+0xd0/0x100 c0000000001e7a74 e9440008 ld r10,8(r4) c0000000001e7a78 78a80020 clrldi r8,r5,32 c0000000001e7a7c 3c000001 lis r0,1 c0000000001e7a80 812900a8 lwz r9,168(r9) c0000000001e7a84 39600001 li r11,1 c0000000001e7a88 7c080050 subf r0,r8,r0 c0000000001e7a8c 7f805040 cmplw cr7,r0,r10 c0000000001e7a90 7d6b4830 slw r11,r11,r9 c0000000001e7a94 796b0020 clrldi r11,r11,32 c0000000001e7a98 419d00a8 bgt cr7,c0000000001e7b40 # .block_is_partially_uptodate+0xe0/0x100 c0000000001e7a9c 7fa55840 cmpld cr7,r5,r11 c0000000001e7aa0 7d004214 add r8,r0,r8 c0000000001e7aa4 79080020 clrldi r8,r8,32 c0000000001e7aa8 419c0078 blt cr7,c0000000001e7b20 # .block_is_partially_uptodate+0xc0/0x100 Signed-off-by: Dave Hansen <dave@linux.vnet.ibm.com> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Reviewed-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: Rik van Riel <riel@redhat.com> Cc: <arunabal@in.ibm.com> Cc: <sbest@us.ibm.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: <stable@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-11-12 06:05:15 +08:00
/* Did it get truncated before we got the lock? */
if (!page->mapping)
goto page_not_up_to_date_locked;
vfs: pagecache usage optimization for pagesize!=blocksize When we read some part of a file through pagecache, if there is a pagecache of corresponding index but this page is not uptodate, read IO is issued and this page will be uptodate. I think this is good for pagesize == blocksize environment but there is room for improvement on pagesize != blocksize environment. Because in this case a page can have multiple buffers and even if a page is not uptodate, some buffers can be uptodate. So I suggest that when all buffers which correspond to a part of a file that we want to read are uptodate, use this pagecache and copy data from this pagecache to user buffer even if a page is not uptodate. This can reduce read IO and improve system throughput. I wrote a benchmark program and got result number with this program. This benchmark do: 1: mount and open a test file. 2: create a 512MB file. 3: close a file and umount. 4: mount and again open a test file. 5: pwrite randomly 300000 times on a test file. offset is aligned by IO size(1024bytes). 6: measure time of preading randomly 100000 times on a test file. The result was: 2.6.26 330 sec 2.6.26-patched 226 sec Arch:i386 Filesystem:ext3 Blocksize:1024 bytes Memory: 1GB On ext3/4, a file is written through buffer/block. So random read/write mixed workloads or random read after random write workloads are optimized with this patch under pagesize != blocksize environment. This test result showed this. The benchmark program is as follows: #include <stdio.h> #include <sys/types.h> #include <sys/stat.h> #include <fcntl.h> #include <unistd.h> #include <time.h> #include <stdlib.h> #include <string.h> #include <sys/mount.h> #define LEN 1024 #define LOOP 1024*512 /* 512MB */ main(void) { unsigned long i, offset, filesize; int fd; char buf[LEN]; time_t t1, t2; if (mount("/dev/sda1", "/root/test1/", "ext3", 0, 0) < 0) { perror("cannot mount\n"); exit(1); } memset(buf, 0, LEN); fd = open("/root/test1/testfile", O_CREAT|O_RDWR|O_TRUNC); if (fd < 0) { perror("cannot open file\n"); exit(1); } for (i = 0; i < LOOP; i++) write(fd, buf, LEN); close(fd); if (umount("/root/test1/") < 0) { perror("cannot umount\n"); exit(1); } if (mount("/dev/sda1", "/root/test1/", "ext3", 0, 0) < 0) { perror("cannot mount\n"); exit(1); } fd = open("/root/test1/testfile", O_RDWR); if (fd < 0) { perror("cannot open file\n"); exit(1); } filesize = LEN * LOOP; for (i = 0; i < 300000; i++){ offset = (random() % filesize) & (~(LEN - 1)); pwrite(fd, buf, LEN, offset); } printf("start test\n"); time(&t1); for (i = 0; i < 100000; i++){ offset = (random() % filesize) & (~(LEN - 1)); pread(fd, buf, LEN, offset); } time(&t2); printf("%ld sec\n", t2-t1); close(fd); if (umount("/root/test1/") < 0) { perror("cannot umount\n"); exit(1); } } Signed-off-by: Hisashi Hifumi <hifumi.hisashi@oss.ntt.co.jp> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Christoph Hellwig <hch@infradead.org> Cc: Jan Kara <jack@ucw.cz> Cc: <linux-ext4@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-29 06:46:36 +08:00
if (!mapping->a_ops->is_partially_uptodate(page,
desc, offset))
goto page_not_up_to_date_locked;
unlock_page(page);
}
page_ok:
Fix read/truncate race do_generic_mapping_read currently samples the i_size at the start and doesn't do so again unless it needs to call ->readpage to load a page. After ->readpage it has to re-sample i_size as a truncate may have caused that page to be filled with zeros, and the read() call should not see these. However there are other activities that might cause ->readpage to be called on a page between the time that do_generic_mapping_read samples i_size and when it finds that it has an uptodate page. These include at least read-ahead and possibly another thread performing a read. So do_generic_mapping_read must sample i_size *after* it has an uptodate page. Thus the current sampling at the start and after a read can be replaced with a sampling before the copy-out. The same change applied to __generic_file_splice_read. Note that this fixes any race with truncate_complete_page, but does not fix a possible race with truncate_partial_page. If a partial truncate happens after do_generic_mapping_read samples i_size and before the copy_out, the nuls that truncate_partial_page place in the page could be copied out incorrectly. I think the best fix for that is to *not* zero out parts of the page in truncate_partial_page, but rather to zero out the tail of a page when increasing i_size. Signed-off-by: Neil Brown <neilb@suse.de> Cc: Jens Axboe <jens.axboe@oracle.com> Acked-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-17 19:03:04 +08:00
/*
* i_size must be checked after we know the page is Uptodate.
*
* Checking i_size after the check allows us to calculate
* the correct value for "nr", which means the zero-filled
* part of the page is not copied back to userspace (unless
* another truncate extends the file - this is desired though).
*/
isize = i_size_read(inode);
end_index = (isize - 1) >> PAGE_CACHE_SHIFT;
if (unlikely(!isize || index > end_index)) {
page_cache_release(page);
goto out;
}
/* nr is the maximum number of bytes to copy from this page */
nr = PAGE_CACHE_SIZE;
if (index == end_index) {
nr = ((isize - 1) & ~PAGE_CACHE_MASK) + 1;
if (nr <= offset) {
page_cache_release(page);
goto out;
}
}
nr = nr - offset;
/* If users can be writing to this page using arbitrary
* virtual addresses, take care about potential aliasing
* before reading the page on the kernel side.
*/
if (mapping_writably_mapped(mapping))
flush_dcache_page(page);
/*
* When a sequential read accesses a page several times,
* only mark it as accessed the first time.
*/
if (prev_index != index || offset != prev_offset)
mark_page_accessed(page);
prev_index = index;
/*
* Ok, we have the page, and it's up-to-date, so
* now we can copy it to user space...
*
* The actor routine returns how many bytes were actually used..
* NOTE! This may not be the same as how much of a user buffer
* we filled up (we may be padding etc), so we can only update
* "pos" here (the actor routine has to update the user buffer
* pointers and the remaining count).
*/
ret = actor(desc, page, offset, nr);
offset += ret;
index += offset >> PAGE_CACHE_SHIFT;
offset &= ~PAGE_CACHE_MASK;
prev_offset = offset;
page_cache_release(page);
if (ret == nr && desc->count)
continue;
goto out;
page_not_up_to_date:
/* Get exclusive access to the page ... */
error = lock_page_killable(page);
if (unlikely(error))
goto readpage_error;
vfs: pagecache usage optimization for pagesize!=blocksize When we read some part of a file through pagecache, if there is a pagecache of corresponding index but this page is not uptodate, read IO is issued and this page will be uptodate. I think this is good for pagesize == blocksize environment but there is room for improvement on pagesize != blocksize environment. Because in this case a page can have multiple buffers and even if a page is not uptodate, some buffers can be uptodate. So I suggest that when all buffers which correspond to a part of a file that we want to read are uptodate, use this pagecache and copy data from this pagecache to user buffer even if a page is not uptodate. This can reduce read IO and improve system throughput. I wrote a benchmark program and got result number with this program. This benchmark do: 1: mount and open a test file. 2: create a 512MB file. 3: close a file and umount. 4: mount and again open a test file. 5: pwrite randomly 300000 times on a test file. offset is aligned by IO size(1024bytes). 6: measure time of preading randomly 100000 times on a test file. The result was: 2.6.26 330 sec 2.6.26-patched 226 sec Arch:i386 Filesystem:ext3 Blocksize:1024 bytes Memory: 1GB On ext3/4, a file is written through buffer/block. So random read/write mixed workloads or random read after random write workloads are optimized with this patch under pagesize != blocksize environment. This test result showed this. The benchmark program is as follows: #include <stdio.h> #include <sys/types.h> #include <sys/stat.h> #include <fcntl.h> #include <unistd.h> #include <time.h> #include <stdlib.h> #include <string.h> #include <sys/mount.h> #define LEN 1024 #define LOOP 1024*512 /* 512MB */ main(void) { unsigned long i, offset, filesize; int fd; char buf[LEN]; time_t t1, t2; if (mount("/dev/sda1", "/root/test1/", "ext3", 0, 0) < 0) { perror("cannot mount\n"); exit(1); } memset(buf, 0, LEN); fd = open("/root/test1/testfile", O_CREAT|O_RDWR|O_TRUNC); if (fd < 0) { perror("cannot open file\n"); exit(1); } for (i = 0; i < LOOP; i++) write(fd, buf, LEN); close(fd); if (umount("/root/test1/") < 0) { perror("cannot umount\n"); exit(1); } if (mount("/dev/sda1", "/root/test1/", "ext3", 0, 0) < 0) { perror("cannot mount\n"); exit(1); } fd = open("/root/test1/testfile", O_RDWR); if (fd < 0) { perror("cannot open file\n"); exit(1); } filesize = LEN * LOOP; for (i = 0; i < 300000; i++){ offset = (random() % filesize) & (~(LEN - 1)); pwrite(fd, buf, LEN, offset); } printf("start test\n"); time(&t1); for (i = 0; i < 100000; i++){ offset = (random() % filesize) & (~(LEN - 1)); pread(fd, buf, LEN, offset); } time(&t2); printf("%ld sec\n", t2-t1); close(fd); if (umount("/root/test1/") < 0) { perror("cannot umount\n"); exit(1); } } Signed-off-by: Hisashi Hifumi <hifumi.hisashi@oss.ntt.co.jp> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Christoph Hellwig <hch@infradead.org> Cc: Jan Kara <jack@ucw.cz> Cc: <linux-ext4@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-29 06:46:36 +08:00
page_not_up_to_date_locked:
/* Did it get truncated before we got the lock? */
if (!page->mapping) {
unlock_page(page);
page_cache_release(page);
continue;
}
/* Did somebody else fill it already? */
if (PageUptodate(page)) {
unlock_page(page);
goto page_ok;
}
readpage:
/*
* A previous I/O error may have been due to temporary
* failures, eg. multipath errors.
* PG_error will be set again if readpage fails.
*/
ClearPageError(page);
/* Start the actual read. The read will unlock the page. */
error = mapping->a_ops->readpage(filp, page);
if (unlikely(error)) {
if (error == AOP_TRUNCATED_PAGE) {
page_cache_release(page);
goto find_page;
}
goto readpage_error;
}
if (!PageUptodate(page)) {
error = lock_page_killable(page);
if (unlikely(error))
goto readpage_error;
if (!PageUptodate(page)) {
if (page->mapping == NULL) {
/*
* invalidate_mapping_pages got it
*/
unlock_page(page);
page_cache_release(page);
goto find_page;
}
unlock_page(page);
shrink_readahead_size_eio(filp, ra);
error = -EIO;
goto readpage_error;
}
unlock_page(page);
}
goto page_ok;
readpage_error:
/* UHHUH! A synchronous read error occurred. Report it */
desc->error = error;
page_cache_release(page);
goto out;
no_cached_page:
/*
* Ok, it wasn't cached, so we need to create a new
* page..
*/
page = page_cache_alloc_cold(mapping);
if (!page) {
desc->error = -ENOMEM;
goto out;
}
error = add_to_page_cache_lru(page, mapping,
index, GFP_KERNEL);
if (error) {
page_cache_release(page);
if (error == -EEXIST)
goto find_page;
desc->error = error;
goto out;
}
goto readpage;
}
out:
ra->prev_pos = prev_index;
ra->prev_pos <<= PAGE_CACHE_SHIFT;
ra->prev_pos |= prev_offset;
*ppos = ((loff_t)index << PAGE_CACHE_SHIFT) + offset;
file_accessed(filp);
}
int file_read_actor(read_descriptor_t *desc, struct page *page,
unsigned long offset, unsigned long size)
{
char *kaddr;
unsigned long left, count = desc->count;
if (size > count)
size = count;
/*
* Faults on the destination of a read are common, so do it before
* taking the kmap.
*/
if (!fault_in_pages_writeable(desc->arg.buf, size)) {
kaddr = kmap_atomic(page, KM_USER0);
left = __copy_to_user_inatomic(desc->arg.buf,
kaddr + offset, size);
kunmap_atomic(kaddr, KM_USER0);
if (left == 0)
goto success;
}
/* Do it the slow way */
kaddr = kmap(page);
left = __copy_to_user(desc->arg.buf, kaddr + offset, size);
kunmap(page);
if (left) {
size -= left;
desc->error = -EFAULT;
}
success:
desc->count = count - size;
desc->written += size;
desc->arg.buf += size;
return size;
}
/*
* Performs necessary checks before doing a write
* @iov: io vector request
* @nr_segs: number of segments in the iovec
* @count: number of bytes to write
* @access_flags: type of access: %VERIFY_READ or %VERIFY_WRITE
*
* Adjust number of segments and amount of bytes to write (nr_segs should be
* properly initialized first). Returns appropriate error code that caller
* should return or zero in case that write should be allowed.
*/
int generic_segment_checks(const struct iovec *iov,
unsigned long *nr_segs, size_t *count, int access_flags)
{
unsigned long seg;
size_t cnt = 0;
for (seg = 0; seg < *nr_segs; seg++) {
const struct iovec *iv = &iov[seg];
/*
* If any segment has a negative length, or the cumulative
* length ever wraps negative then return -EINVAL.
*/
cnt += iv->iov_len;
if (unlikely((ssize_t)(cnt|iv->iov_len) < 0))
return -EINVAL;
if (access_ok(access_flags, iv->iov_base, iv->iov_len))
continue;
if (seg == 0)
return -EFAULT;
*nr_segs = seg;
cnt -= iv->iov_len; /* This segment is no good */
break;
}
*count = cnt;
return 0;
}
EXPORT_SYMBOL(generic_segment_checks);
/**
* generic_file_aio_read - generic filesystem read routine
* @iocb: kernel I/O control block
* @iov: io vector request
* @nr_segs: number of segments in the iovec
* @pos: current file position
*
* This is the "read()" routine for all filesystems
* that can use the page cache directly.
*/
ssize_t
generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
unsigned long nr_segs, loff_t pos)
{
struct file *filp = iocb->ki_filp;
ssize_t retval;
unsigned long seg = 0;
size_t count;
loff_t *ppos = &iocb->ki_pos;
struct blk_plug plug;
count = 0;
retval = generic_segment_checks(iov, &nr_segs, &count, VERIFY_WRITE);
if (retval)
return retval;
blk_start_plug(&plug);
/* coalesce the iovecs and go direct-to-BIO for O_DIRECT */
if (filp->f_flags & O_DIRECT) {
loff_t size;
struct address_space *mapping;
struct inode *inode;
mapping = filp->f_mapping;
inode = mapping->host;
if (!count)
goto out; /* skip atime */
size = i_size_read(inode);
if (pos < size) {
retval = filemap_write_and_wait_range(mapping, pos,
pos + iov_length(iov, nr_segs) - 1);
if (!retval) {
retval = mapping->a_ops->direct_IO(READ, iocb,
iov, pos, nr_segs);
}
if (retval > 0) {
*ppos = pos + retval;
count -= retval;
}
/*
* Btrfs can have a short DIO read if we encounter
* compressed extents, so if there was an error, or if
* we've already read everything we wanted to, or if
* there was a short read because we hit EOF, go ahead
* and return. Otherwise fallthrough to buffered io for
* the rest of the read.
*/
if (retval < 0 || !count || *ppos >= size) {
file_accessed(filp);
goto out;
}
}
}
count = retval;
for (seg = 0; seg < nr_segs; seg++) {
read_descriptor_t desc;
loff_t offset = 0;
/*
* If we did a short DIO read we need to skip the section of the
* iov that we've already read data into.
*/
if (count) {
if (count > iov[seg].iov_len) {
count -= iov[seg].iov_len;
continue;
}
offset = count;
count = 0;
}
desc.written = 0;
desc.arg.buf = iov[seg].iov_base + offset;
desc.count = iov[seg].iov_len - offset;
if (desc.count == 0)
continue;
desc.error = 0;
do_generic_file_read(filp, ppos, &desc, file_read_actor);
retval += desc.written;
if (desc.error) {
retval = retval ?: desc.error;
break;
}
if (desc.count > 0)
break;
}
out:
blk_finish_plug(&plug);
return retval;
}
EXPORT_SYMBOL(generic_file_aio_read);
static ssize_t
do_readahead(struct address_space *mapping, struct file *filp,
pgoff_t index, unsigned long nr)
{
if (!mapping || !mapping->a_ops || !mapping->a_ops->readpage)
return -EINVAL;
force_page_cache_readahead(mapping, filp, index, nr);
return 0;
}
SYSCALL_DEFINE(readahead)(int fd, loff_t offset, size_t count)
{
ssize_t ret;
struct file *file;
ret = -EBADF;
file = fget(fd);
if (file) {
if (file->f_mode & FMODE_READ) {
struct address_space *mapping = file->f_mapping;
pgoff_t start = offset >> PAGE_CACHE_SHIFT;
pgoff_t end = (offset + count - 1) >> PAGE_CACHE_SHIFT;
unsigned long len = end - start + 1;
ret = do_readahead(mapping, file, start, len);
}
fput(file);
}
return ret;
}
#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS
asmlinkage long SyS_readahead(long fd, loff_t offset, long count)
{
return SYSC_readahead((int) fd, offset, (size_t) count);
}
SYSCALL_ALIAS(sys_readahead, SyS_readahead);
#endif
#ifdef CONFIG_MMU
/**
* page_cache_read - adds requested page to the page cache if not already there
* @file: file to read
* @offset: page index
*
* This adds the requested page to the page cache if it isn't already there,
* and schedules an I/O to read in its contents from disk.
*/
static int page_cache_read(struct file *file, pgoff_t offset)
{
struct address_space *mapping = file->f_mapping;
struct page *page;
int ret;
do {
page = page_cache_alloc_cold(mapping);
if (!page)
return -ENOMEM;
ret = add_to_page_cache_lru(page, mapping, offset, GFP_KERNEL);
if (ret == 0)
ret = mapping->a_ops->readpage(file, page);
else if (ret == -EEXIST)
ret = 0; /* losing race to add is OK */
page_cache_release(page);
} while (ret == AOP_TRUNCATED_PAGE);
return ret;
}
#define MMAP_LOTSAMISS (100)
/*
* Synchronous readahead happens when we don't even find
* a page in the page cache at all.
*/
static void do_sync_mmap_readahead(struct vm_area_struct *vma,
struct file_ra_state *ra,
struct file *file,
pgoff_t offset)
{
unsigned long ra_pages;
struct address_space *mapping = file->f_mapping;
/* If we don't want any read-ahead, don't bother */
if (VM_RandomReadHint(vma))
return;
if (!ra->ra_pages)
return;
if (VM_SequentialReadHint(vma)) {
readahead: enforce full sync mmap readahead size Now that we do readahead for sequential mmap reads, here is a simple evaluation of the impacts, and one further optimization. It's an NFS-root debian desktop system, readahead size = 60 pages. The numbers are grabbed after a fresh boot into console. approach pgmajfault RA miss ratio mmap IO count avg IO size(pages) A 383 31.6% 383 11 B 225 32.4% 390 11 C 224 32.6% 307 13 case A: mmap sync/async readahead disabled case B: mmap sync/async readahead enabled, with enforced full async readahead size case C: mmap sync/async readahead enabled, with enforced full sync/async readahead size or: A = vanilla 2.6.30-rc1 B = A plus mmap readahead C = B plus this patch The numbers show that - there are good possibilities for random mmap reads to trigger readahead - 'pgmajfault' is reduced by 1/3, due to the _async_ nature of readahead - case C can further reduce IO count by 1/4 - readahead miss ratios are not quite affected The theory is - readahead is _good_ for clustered random reads, and can perform _better_ than readaround because they could be _async_. - async readahead size is guaranteed to be larger than readaround size, and they are _async_, hence will mostly behave better However for B - sync readahead size could be smaller than readaround size, hence may make things worse by produce more smaller IOs which will be fixed by this patch. Final conclusion: - mmap readahead reduced major faults by 1/3 and no obvious overheads; - mmap io can be further reduced by 1/4 with this patch. Signed-off-by: Wu Fengguang <fengguang.wu@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-17 06:31:38 +08:00
page_cache_sync_readahead(mapping, ra, file, offset,
ra->ra_pages);
return;
}
/* Avoid banging the cache line if not needed */
if (ra->mmap_miss < MMAP_LOTSAMISS * 10)
ra->mmap_miss++;
/*
* Do we miss much more than hit in this file? If so,
* stop bothering with read-ahead. It will only hurt.
*/
if (ra->mmap_miss > MMAP_LOTSAMISS)
return;
/*
* mmap read-around
*/
ra_pages = max_sane_readahead(ra->ra_pages);
ra->start = max_t(long, 0, offset - ra_pages / 2);
ra->size = ra_pages;
ra->async_size = ra_pages / 4;
ra_submit(ra, mapping, file);
}
/*
* Asynchronous readahead happens when we find the page and PG_readahead,
* so we want to possibly extend the readahead further..
*/
static void do_async_mmap_readahead(struct vm_area_struct *vma,
struct file_ra_state *ra,
struct file *file,
struct page *page,
pgoff_t offset)
{
struct address_space *mapping = file->f_mapping;
/* If we don't want any read-ahead, don't bother */
if (VM_RandomReadHint(vma))
return;
if (ra->mmap_miss > 0)
ra->mmap_miss--;
if (PageReadahead(page))
readahead: enforce full readahead size on async mmap readahead We need this in one particular case and two more general ones. Now we do async readahead for sequential mmap reads, and do it with the help of PG_readahead. For normal reads, PG_readahead is the sufficient condition to do a sequential readahead. But unfortunately, for mmap reads, there is a tiny nuisance: [11736.998347] readahead-init0(process: sh/23926, file: sda1/w3m, offset=0:4503599627370495, ra=0+4-3) = 4 [11737.014985] readahead-around(process: w3m/23926, file: sda1/w3m, offset=0:0, ra=290+32-0) = 17 [11737.019488] readahead-around(process: w3m/23926, file: sda1/w3m, offset=0:0, ra=118+32-0) = 32 [11737.024921] readahead-interleaved(process: w3m/23926, file: sda1/w3m, offset=0:2, ra=4+6-6) = 6 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ~~~~~~~~~~~~~ An unfavorably small readahead. The original dumb read-around size could be more efficient. That happened because ld-linux.so does a read(832) in L1 before mmap(), which triggers a 4-page readahead, with the second page tagged PG_readahead. L0: open("/lib/libc.so.6", O_RDONLY) = 3 L1: read(3, "\177ELF\2\1\1\0\0\0\0\0\0\0\0\0\3\0>\0\1\0\0\0\340\342"..., 832) = 832 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ L2: fstat(3, {st_mode=S_IFREG|0755, st_size=1420624, ...}) = 0 L3: mmap(NULL, 3527256, PROT_READ|PROT_EXEC, MAP_PRIVATE|MAP_DENYWRITE, 3, 0) = 0x7fac6e51d000 L4: mprotect(0x7fac6e671000, 2097152, PROT_NONE) = 0 L5: mmap(0x7fac6e871000, 20480, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 0x154000) = 0x7fac6e871000 L6: mmap(0x7fac6e876000, 16984, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_ANONYMOUS, -1, 0) = 0x7fac6e876000 L7: close(3) = 0 In general, the PG_readahead flag will also be hit in cases - sequential reads - clustered random reads A full readahead size is desirable in both cases. Cc: Nick Piggin <npiggin@suse.de> Signed-off-by: Wu Fengguang <fengguang.wu@intel.com> Cc: Ying Han <yinghan@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-17 06:31:29 +08:00
page_cache_async_readahead(mapping, ra, file,
page, offset, ra->ra_pages);
}
/**
mm: merge populate and nopage into fault (fixes nonlinear) Nonlinear mappings are (AFAIKS) simply a virtual memory concept that encodes the virtual address -> file offset differently from linear mappings. ->populate is a layering violation because the filesystem/pagecache code should need to know anything about the virtual memory mapping. The hitch here is that the ->nopage handler didn't pass down enough information (ie. pgoff). But it is more logical to pass pgoff rather than have the ->nopage function calculate it itself anyway (because that's a similar layering violation). Having the populate handler install the pte itself is likewise a nasty thing to be doing. This patch introduces a new fault handler that replaces ->nopage and ->populate and (later) ->nopfn. Most of the old mechanism is still in place so there is a lot of duplication and nice cleanups that can be removed if everyone switches over. The rationale for doing this in the first place is that nonlinear mappings are subject to the pagefault vs invalidate/truncate race too, and it seemed stupid to duplicate the synchronisation logic rather than just consolidate the two. After this patch, MAP_NONBLOCK no longer sets up ptes for pages present in pagecache. Seems like a fringe functionality anyway. NOPAGE_REFAULT is removed. This should be implemented with ->fault, and no users have hit mainline yet. [akpm@linux-foundation.org: cleanup] [randy.dunlap@oracle.com: doc. fixes for readahead] [akpm@linux-foundation.org: build fix] Signed-off-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com> Cc: Mark Fasheh <mark.fasheh@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-19 16:46:59 +08:00
* filemap_fault - read in file data for page fault handling
* @vma: vma in which the fault was taken
* @vmf: struct vm_fault containing details of the fault
*
mm: merge populate and nopage into fault (fixes nonlinear) Nonlinear mappings are (AFAIKS) simply a virtual memory concept that encodes the virtual address -> file offset differently from linear mappings. ->populate is a layering violation because the filesystem/pagecache code should need to know anything about the virtual memory mapping. The hitch here is that the ->nopage handler didn't pass down enough information (ie. pgoff). But it is more logical to pass pgoff rather than have the ->nopage function calculate it itself anyway (because that's a similar layering violation). Having the populate handler install the pte itself is likewise a nasty thing to be doing. This patch introduces a new fault handler that replaces ->nopage and ->populate and (later) ->nopfn. Most of the old mechanism is still in place so there is a lot of duplication and nice cleanups that can be removed if everyone switches over. The rationale for doing this in the first place is that nonlinear mappings are subject to the pagefault vs invalidate/truncate race too, and it seemed stupid to duplicate the synchronisation logic rather than just consolidate the two. After this patch, MAP_NONBLOCK no longer sets up ptes for pages present in pagecache. Seems like a fringe functionality anyway. NOPAGE_REFAULT is removed. This should be implemented with ->fault, and no users have hit mainline yet. [akpm@linux-foundation.org: cleanup] [randy.dunlap@oracle.com: doc. fixes for readahead] [akpm@linux-foundation.org: build fix] Signed-off-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com> Cc: Mark Fasheh <mark.fasheh@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-19 16:46:59 +08:00
* filemap_fault() is invoked via the vma operations vector for a
* mapped memory region to read in file data during a page fault.
*
* The goto's are kind of ugly, but this streamlines the normal case of having
* it in the page cache, and handles the special cases reasonably without
* having a lot of duplicated code.
*/
int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
{
int error;
mm: merge populate and nopage into fault (fixes nonlinear) Nonlinear mappings are (AFAIKS) simply a virtual memory concept that encodes the virtual address -> file offset differently from linear mappings. ->populate is a layering violation because the filesystem/pagecache code should need to know anything about the virtual memory mapping. The hitch here is that the ->nopage handler didn't pass down enough information (ie. pgoff). But it is more logical to pass pgoff rather than have the ->nopage function calculate it itself anyway (because that's a similar layering violation). Having the populate handler install the pte itself is likewise a nasty thing to be doing. This patch introduces a new fault handler that replaces ->nopage and ->populate and (later) ->nopfn. Most of the old mechanism is still in place so there is a lot of duplication and nice cleanups that can be removed if everyone switches over. The rationale for doing this in the first place is that nonlinear mappings are subject to the pagefault vs invalidate/truncate race too, and it seemed stupid to duplicate the synchronisation logic rather than just consolidate the two. After this patch, MAP_NONBLOCK no longer sets up ptes for pages present in pagecache. Seems like a fringe functionality anyway. NOPAGE_REFAULT is removed. This should be implemented with ->fault, and no users have hit mainline yet. [akpm@linux-foundation.org: cleanup] [randy.dunlap@oracle.com: doc. fixes for readahead] [akpm@linux-foundation.org: build fix] Signed-off-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com> Cc: Mark Fasheh <mark.fasheh@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-19 16:46:59 +08:00
struct file *file = vma->vm_file;
struct address_space *mapping = file->f_mapping;
struct file_ra_state *ra = &file->f_ra;
struct inode *inode = mapping->host;
pgoff_t offset = vmf->pgoff;
struct page *page;
pgoff_t size;
mm: fault feedback #2 This patch completes Linus's wish that the fault return codes be made into bit flags, which I agree makes everything nicer. This requires requires all handle_mm_fault callers to be modified (possibly the modifications should go further and do things like fault accounting in handle_mm_fault -- however that would be for another patch). [akpm@linux-foundation.org: fix alpha build] [akpm@linux-foundation.org: fix s390 build] [akpm@linux-foundation.org: fix sparc build] [akpm@linux-foundation.org: fix sparc64 build] [akpm@linux-foundation.org: fix ia64 build] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Richard Henderson <rth@twiddle.net> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: Russell King <rmk@arm.linux.org.uk> Cc: Ian Molton <spyro@f2s.com> Cc: Bryan Wu <bryan.wu@analog.com> Cc: Mikael Starvik <starvik@axis.com> Cc: David Howells <dhowells@redhat.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Cc: "Luck, Tony" <tony.luck@intel.com> Cc: Hirokazu Takata <takata@linux-m32r.org> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Roman Zippel <zippel@linux-m68k.org> Cc: Greg Ungerer <gerg@uclinux.org> Cc: Matthew Wilcox <willy@debian.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Kazumoto Kojima <kkojima@rr.iij4u.or.jp> Cc: Richard Curnow <rc@rc0.org.uk> Cc: William Lee Irwin III <wli@holomorphy.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Jeff Dike <jdike@addtoit.com> Cc: Paolo 'Blaisorblade' Giarrusso <blaisorblade@yahoo.it> Cc: Miles Bader <uclinux-v850@lsi.nec.co.jp> Cc: Chris Zankel <chris@zankel.net> Acked-by: Kyle McMartin <kyle@mcmartin.ca> Acked-by: Haavard Skinnemoen <hskinnemoen@atmel.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Acked-by: Andi Kleen <ak@muc.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> [ Still apparently needs some ARM and PPC loving - Linus ] Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-19 16:47:05 +08:00
int ret = 0;
size = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
if (offset >= size)
return VM_FAULT_SIGBUS;
/*
* Do we have something in the page cache already?
*/
page = find_get_page(mapping, offset);
if (likely(page)) {
/*
* We found the page, so try async readahead before
* waiting for the lock.
*/
do_async_mmap_readahead(vma, ra, file, page, offset);
} else {
/* No page in the page cache at all */
do_sync_mmap_readahead(vma, ra, file, offset);
count_vm_event(PGMAJFAULT);
ret = VM_FAULT_MAJOR;
retry_find:
page = find_get_page(mapping, offset);
if (!page)
goto no_cached_page;
}
if (!lock_page_or_retry(page, vma->vm_mm, vmf->flags)) {
page_cache_release(page);
mm: retry page fault when blocking on disk transfer This change reduces mmap_sem hold times that are caused by waiting for disk transfers when accessing file mapped VMAs. It introduces the VM_FAULT_ALLOW_RETRY flag, which indicates that the call site wants mmap_sem to be released if blocking on a pending disk transfer. In that case, filemap_fault() returns the VM_FAULT_RETRY status bit and do_page_fault() will then re-acquire mmap_sem and retry the page fault. It is expected that the retry will hit the same page which will now be cached, and thus it will complete with a low mmap_sem hold time. Tests: - microbenchmark: thread A mmaps a large file and does random read accesses to the mmaped area - achieves about 55 iterations/s. Thread B does mmap/munmap in a loop at a separate location - achieves 55 iterations/s before, 15000 iterations/s after. - We are seeing related effects in some applications in house, which show significant performance regressions when running without this change. [akpm@linux-foundation.org: fix warning & crash] Signed-off-by: Michel Lespinasse <walken@google.com> Acked-by: Rik van Riel <riel@redhat.com> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Reviewed-by: Wu Fengguang <fengguang.wu@intel.com> Cc: Ying Han <yinghan@google.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Acked-by: "H. Peter Anvin" <hpa@zytor.com> Cc: <linux-arch@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-10-27 05:21:57 +08:00
return ret | VM_FAULT_RETRY;
}
/* Did it get truncated? */
if (unlikely(page->mapping != mapping)) {
unlock_page(page);
put_page(page);
goto retry_find;
}
VM_BUG_ON(page->index != offset);
/*
mm: fix fault vs invalidate race for linear mappings Fix the race between invalidate_inode_pages and do_no_page. Andrea Arcangeli identified a subtle race between invalidation of pages from pagecache with userspace mappings, and do_no_page. The issue is that invalidation has to shoot down all mappings to the page, before it can be discarded from the pagecache. Between shooting down ptes to a particular page, and actually dropping the struct page from the pagecache, do_no_page from any process might fault on that page and establish a new mapping to the page just before it gets discarded from the pagecache. The most common case where such invalidation is used is in file truncation. This case was catered for by doing a sort of open-coded seqlock between the file's i_size, and its truncate_count. Truncation will decrease i_size, then increment truncate_count before unmapping userspace pages; do_no_page will read truncate_count, then find the page if it is within i_size, and then check truncate_count under the page table lock and back out and retry if it had subsequently been changed (ptl will serialise against unmapping, and ensure a potentially updated truncate_count is actually visible). Complexity and documentation issues aside, the locking protocol fails in the case where we would like to invalidate pagecache inside i_size. do_no_page can come in anytime and filemap_nopage is not aware of the invalidation in progress (as it is when it is outside i_size). The end result is that dangling (->mapping == NULL) pages that appear to be from a particular file may be mapped into userspace with nonsense data. Valid mappings to the same place will see a different page. Andrea implemented two working fixes, one using a real seqlock, another using a page->flags bit. He also proposed using the page lock in do_no_page, but that was initially considered too heavyweight. However, it is not a global or per-file lock, and the page cacheline is modified in do_no_page to increment _count and _mapcount anyway, so a further modification should not be a large performance hit. Scalability is not an issue. This patch implements this latter approach. ->nopage implementations return with the page locked if it is possible for their underlying file to be invalidated (in that case, they must set a special vm_flags bit to indicate so). do_no_page only unlocks the page after setting up the mapping completely. invalidation is excluded because it holds the page lock during invalidation of each page (and ensures that the page is not mapped while holding the lock). This also allows significant simplifications in do_no_page, because we have the page locked in the right place in the pagecache from the start. 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>
2007-07-19 16:46:57 +08:00
* We have a locked page in the page cache, now we need to check
* that it's up-to-date. If not, it is going to be due to an error.
*/
mm: fix fault vs invalidate race for linear mappings Fix the race between invalidate_inode_pages and do_no_page. Andrea Arcangeli identified a subtle race between invalidation of pages from pagecache with userspace mappings, and do_no_page. The issue is that invalidation has to shoot down all mappings to the page, before it can be discarded from the pagecache. Between shooting down ptes to a particular page, and actually dropping the struct page from the pagecache, do_no_page from any process might fault on that page and establish a new mapping to the page just before it gets discarded from the pagecache. The most common case where such invalidation is used is in file truncation. This case was catered for by doing a sort of open-coded seqlock between the file's i_size, and its truncate_count. Truncation will decrease i_size, then increment truncate_count before unmapping userspace pages; do_no_page will read truncate_count, then find the page if it is within i_size, and then check truncate_count under the page table lock and back out and retry if it had subsequently been changed (ptl will serialise against unmapping, and ensure a potentially updated truncate_count is actually visible). Complexity and documentation issues aside, the locking protocol fails in the case where we would like to invalidate pagecache inside i_size. do_no_page can come in anytime and filemap_nopage is not aware of the invalidation in progress (as it is when it is outside i_size). The end result is that dangling (->mapping == NULL) pages that appear to be from a particular file may be mapped into userspace with nonsense data. Valid mappings to the same place will see a different page. Andrea implemented two working fixes, one using a real seqlock, another using a page->flags bit. He also proposed using the page lock in do_no_page, but that was initially considered too heavyweight. However, it is not a global or per-file lock, and the page cacheline is modified in do_no_page to increment _count and _mapcount anyway, so a further modification should not be a large performance hit. Scalability is not an issue. This patch implements this latter approach. ->nopage implementations return with the page locked if it is possible for their underlying file to be invalidated (in that case, they must set a special vm_flags bit to indicate so). do_no_page only unlocks the page after setting up the mapping completely. invalidation is excluded because it holds the page lock during invalidation of each page (and ensures that the page is not mapped while holding the lock). This also allows significant simplifications in do_no_page, because we have the page locked in the right place in the pagecache from the start. 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>
2007-07-19 16:46:57 +08:00
if (unlikely(!PageUptodate(page)))
goto page_not_uptodate;
/*
* Found the page and have a reference on it.
* We must recheck i_size under page lock.
*/
mm: fix fault vs invalidate race for linear mappings Fix the race between invalidate_inode_pages and do_no_page. Andrea Arcangeli identified a subtle race between invalidation of pages from pagecache with userspace mappings, and do_no_page. The issue is that invalidation has to shoot down all mappings to the page, before it can be discarded from the pagecache. Between shooting down ptes to a particular page, and actually dropping the struct page from the pagecache, do_no_page from any process might fault on that page and establish a new mapping to the page just before it gets discarded from the pagecache. The most common case where such invalidation is used is in file truncation. This case was catered for by doing a sort of open-coded seqlock between the file's i_size, and its truncate_count. Truncation will decrease i_size, then increment truncate_count before unmapping userspace pages; do_no_page will read truncate_count, then find the page if it is within i_size, and then check truncate_count under the page table lock and back out and retry if it had subsequently been changed (ptl will serialise against unmapping, and ensure a potentially updated truncate_count is actually visible). Complexity and documentation issues aside, the locking protocol fails in the case where we would like to invalidate pagecache inside i_size. do_no_page can come in anytime and filemap_nopage is not aware of the invalidation in progress (as it is when it is outside i_size). The end result is that dangling (->mapping == NULL) pages that appear to be from a particular file may be mapped into userspace with nonsense data. Valid mappings to the same place will see a different page. Andrea implemented two working fixes, one using a real seqlock, another using a page->flags bit. He also proposed using the page lock in do_no_page, but that was initially considered too heavyweight. However, it is not a global or per-file lock, and the page cacheline is modified in do_no_page to increment _count and _mapcount anyway, so a further modification should not be a large performance hit. Scalability is not an issue. This patch implements this latter approach. ->nopage implementations return with the page locked if it is possible for their underlying file to be invalidated (in that case, they must set a special vm_flags bit to indicate so). do_no_page only unlocks the page after setting up the mapping completely. invalidation is excluded because it holds the page lock during invalidation of each page (and ensures that the page is not mapped while holding the lock). This also allows significant simplifications in do_no_page, because we have the page locked in the right place in the pagecache from the start. 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>
2007-07-19 16:46:57 +08:00
size = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
if (unlikely(offset >= size)) {
mm: fix fault vs invalidate race for linear mappings Fix the race between invalidate_inode_pages and do_no_page. Andrea Arcangeli identified a subtle race between invalidation of pages from pagecache with userspace mappings, and do_no_page. The issue is that invalidation has to shoot down all mappings to the page, before it can be discarded from the pagecache. Between shooting down ptes to a particular page, and actually dropping the struct page from the pagecache, do_no_page from any process might fault on that page and establish a new mapping to the page just before it gets discarded from the pagecache. The most common case where such invalidation is used is in file truncation. This case was catered for by doing a sort of open-coded seqlock between the file's i_size, and its truncate_count. Truncation will decrease i_size, then increment truncate_count before unmapping userspace pages; do_no_page will read truncate_count, then find the page if it is within i_size, and then check truncate_count under the page table lock and back out and retry if it had subsequently been changed (ptl will serialise against unmapping, and ensure a potentially updated truncate_count is actually visible). Complexity and documentation issues aside, the locking protocol fails in the case where we would like to invalidate pagecache inside i_size. do_no_page can come in anytime and filemap_nopage is not aware of the invalidation in progress (as it is when it is outside i_size). The end result is that dangling (->mapping == NULL) pages that appear to be from a particular file may be mapped into userspace with nonsense data. Valid mappings to the same place will see a different page. Andrea implemented two working fixes, one using a real seqlock, another using a page->flags bit. He also proposed using the page lock in do_no_page, but that was initially considered too heavyweight. However, it is not a global or per-file lock, and the page cacheline is modified in do_no_page to increment _count and _mapcount anyway, so a further modification should not be a large performance hit. Scalability is not an issue. This patch implements this latter approach. ->nopage implementations return with the page locked if it is possible for their underlying file to be invalidated (in that case, they must set a special vm_flags bit to indicate so). do_no_page only unlocks the page after setting up the mapping completely. invalidation is excluded because it holds the page lock during invalidation of each page (and ensures that the page is not mapped while holding the lock). This also allows significant simplifications in do_no_page, because we have the page locked in the right place in the pagecache from the start. 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>
2007-07-19 16:46:57 +08:00
unlock_page(page);
page_cache_release(page);
return VM_FAULT_SIGBUS;
mm: fix fault vs invalidate race for linear mappings Fix the race between invalidate_inode_pages and do_no_page. Andrea Arcangeli identified a subtle race between invalidation of pages from pagecache with userspace mappings, and do_no_page. The issue is that invalidation has to shoot down all mappings to the page, before it can be discarded from the pagecache. Between shooting down ptes to a particular page, and actually dropping the struct page from the pagecache, do_no_page from any process might fault on that page and establish a new mapping to the page just before it gets discarded from the pagecache. The most common case where such invalidation is used is in file truncation. This case was catered for by doing a sort of open-coded seqlock between the file's i_size, and its truncate_count. Truncation will decrease i_size, then increment truncate_count before unmapping userspace pages; do_no_page will read truncate_count, then find the page if it is within i_size, and then check truncate_count under the page table lock and back out and retry if it had subsequently been changed (ptl will serialise against unmapping, and ensure a potentially updated truncate_count is actually visible). Complexity and documentation issues aside, the locking protocol fails in the case where we would like to invalidate pagecache inside i_size. do_no_page can come in anytime and filemap_nopage is not aware of the invalidation in progress (as it is when it is outside i_size). The end result is that dangling (->mapping == NULL) pages that appear to be from a particular file may be mapped into userspace with nonsense data. Valid mappings to the same place will see a different page. Andrea implemented two working fixes, one using a real seqlock, another using a page->flags bit. He also proposed using the page lock in do_no_page, but that was initially considered too heavyweight. However, it is not a global or per-file lock, and the page cacheline is modified in do_no_page to increment _count and _mapcount anyway, so a further modification should not be a large performance hit. Scalability is not an issue. This patch implements this latter approach. ->nopage implementations return with the page locked if it is possible for their underlying file to be invalidated (in that case, they must set a special vm_flags bit to indicate so). do_no_page only unlocks the page after setting up the mapping completely. invalidation is excluded because it holds the page lock during invalidation of each page (and ensures that the page is not mapped while holding the lock). This also allows significant simplifications in do_no_page, because we have the page locked in the right place in the pagecache from the start. 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>
2007-07-19 16:46:57 +08:00
}
vmf->page = page;
mm: fault feedback #2 This patch completes Linus's wish that the fault return codes be made into bit flags, which I agree makes everything nicer. This requires requires all handle_mm_fault callers to be modified (possibly the modifications should go further and do things like fault accounting in handle_mm_fault -- however that would be for another patch). [akpm@linux-foundation.org: fix alpha build] [akpm@linux-foundation.org: fix s390 build] [akpm@linux-foundation.org: fix sparc build] [akpm@linux-foundation.org: fix sparc64 build] [akpm@linux-foundation.org: fix ia64 build] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Richard Henderson <rth@twiddle.net> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: Russell King <rmk@arm.linux.org.uk> Cc: Ian Molton <spyro@f2s.com> Cc: Bryan Wu <bryan.wu@analog.com> Cc: Mikael Starvik <starvik@axis.com> Cc: David Howells <dhowells@redhat.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Cc: "Luck, Tony" <tony.luck@intel.com> Cc: Hirokazu Takata <takata@linux-m32r.org> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Roman Zippel <zippel@linux-m68k.org> Cc: Greg Ungerer <gerg@uclinux.org> Cc: Matthew Wilcox <willy@debian.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Kazumoto Kojima <kkojima@rr.iij4u.or.jp> Cc: Richard Curnow <rc@rc0.org.uk> Cc: William Lee Irwin III <wli@holomorphy.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Jeff Dike <jdike@addtoit.com> Cc: Paolo 'Blaisorblade' Giarrusso <blaisorblade@yahoo.it> Cc: Miles Bader <uclinux-v850@lsi.nec.co.jp> Cc: Chris Zankel <chris@zankel.net> Acked-by: Kyle McMartin <kyle@mcmartin.ca> Acked-by: Haavard Skinnemoen <hskinnemoen@atmel.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Acked-by: Andi Kleen <ak@muc.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> [ Still apparently needs some ARM and PPC loving - Linus ] Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-19 16:47:05 +08:00
return ret | VM_FAULT_LOCKED;
no_cached_page:
/*
* We're only likely to ever get here if MADV_RANDOM is in
* effect.
*/
error = page_cache_read(file, offset);
/*
* The page we want has now been added to the page cache.
* In the unlikely event that someone removed it in the
* meantime, we'll just come back here and read it again.
*/
if (error >= 0)
goto retry_find;
/*
* An error return from page_cache_read can result if the
* system is low on memory, or a problem occurs while trying
* to schedule I/O.
*/
if (error == -ENOMEM)
return VM_FAULT_OOM;
return VM_FAULT_SIGBUS;
page_not_uptodate:
/*
* Umm, take care of errors if the page isn't up-to-date.
* Try to re-read it _once_. We do this synchronously,
* because there really aren't any performance issues here
* and we need to check for errors.
*/
ClearPageError(page);
error = mapping->a_ops->readpage(file, page);
if (!error) {
wait_on_page_locked(page);
if (!PageUptodate(page))
error = -EIO;
}
mm: fix fault vs invalidate race for linear mappings Fix the race between invalidate_inode_pages and do_no_page. Andrea Arcangeli identified a subtle race between invalidation of pages from pagecache with userspace mappings, and do_no_page. The issue is that invalidation has to shoot down all mappings to the page, before it can be discarded from the pagecache. Between shooting down ptes to a particular page, and actually dropping the struct page from the pagecache, do_no_page from any process might fault on that page and establish a new mapping to the page just before it gets discarded from the pagecache. The most common case where such invalidation is used is in file truncation. This case was catered for by doing a sort of open-coded seqlock between the file's i_size, and its truncate_count. Truncation will decrease i_size, then increment truncate_count before unmapping userspace pages; do_no_page will read truncate_count, then find the page if it is within i_size, and then check truncate_count under the page table lock and back out and retry if it had subsequently been changed (ptl will serialise against unmapping, and ensure a potentially updated truncate_count is actually visible). Complexity and documentation issues aside, the locking protocol fails in the case where we would like to invalidate pagecache inside i_size. do_no_page can come in anytime and filemap_nopage is not aware of the invalidation in progress (as it is when it is outside i_size). The end result is that dangling (->mapping == NULL) pages that appear to be from a particular file may be mapped into userspace with nonsense data. Valid mappings to the same place will see a different page. Andrea implemented two working fixes, one using a real seqlock, another using a page->flags bit. He also proposed using the page lock in do_no_page, but that was initially considered too heavyweight. However, it is not a global or per-file lock, and the page cacheline is modified in do_no_page to increment _count and _mapcount anyway, so a further modification should not be a large performance hit. Scalability is not an issue. This patch implements this latter approach. ->nopage implementations return with the page locked if it is possible for their underlying file to be invalidated (in that case, they must set a special vm_flags bit to indicate so). do_no_page only unlocks the page after setting up the mapping completely. invalidation is excluded because it holds the page lock during invalidation of each page (and ensures that the page is not mapped while holding the lock). This also allows significant simplifications in do_no_page, because we have the page locked in the right place in the pagecache from the start. 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>
2007-07-19 16:46:57 +08:00
page_cache_release(page);
if (!error || error == AOP_TRUNCATED_PAGE)
goto retry_find;
mm: fix fault vs invalidate race for linear mappings Fix the race between invalidate_inode_pages and do_no_page. Andrea Arcangeli identified a subtle race between invalidation of pages from pagecache with userspace mappings, and do_no_page. The issue is that invalidation has to shoot down all mappings to the page, before it can be discarded from the pagecache. Between shooting down ptes to a particular page, and actually dropping the struct page from the pagecache, do_no_page from any process might fault on that page and establish a new mapping to the page just before it gets discarded from the pagecache. The most common case where such invalidation is used is in file truncation. This case was catered for by doing a sort of open-coded seqlock between the file's i_size, and its truncate_count. Truncation will decrease i_size, then increment truncate_count before unmapping userspace pages; do_no_page will read truncate_count, then find the page if it is within i_size, and then check truncate_count under the page table lock and back out and retry if it had subsequently been changed (ptl will serialise against unmapping, and ensure a potentially updated truncate_count is actually visible). Complexity and documentation issues aside, the locking protocol fails in the case where we would like to invalidate pagecache inside i_size. do_no_page can come in anytime and filemap_nopage is not aware of the invalidation in progress (as it is when it is outside i_size). The end result is that dangling (->mapping == NULL) pages that appear to be from a particular file may be mapped into userspace with nonsense data. Valid mappings to the same place will see a different page. Andrea implemented two working fixes, one using a real seqlock, another using a page->flags bit. He also proposed using the page lock in do_no_page, but that was initially considered too heavyweight. However, it is not a global or per-file lock, and the page cacheline is modified in do_no_page to increment _count and _mapcount anyway, so a further modification should not be a large performance hit. Scalability is not an issue. This patch implements this latter approach. ->nopage implementations return with the page locked if it is possible for their underlying file to be invalidated (in that case, they must set a special vm_flags bit to indicate so). do_no_page only unlocks the page after setting up the mapping completely. invalidation is excluded because it holds the page lock during invalidation of each page (and ensures that the page is not mapped while holding the lock). This also allows significant simplifications in do_no_page, because we have the page locked in the right place in the pagecache from the start. 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>
2007-07-19 16:46:57 +08:00
/* Things didn't work out. Return zero to tell the mm layer so. */
[PATCH] readahead: backoff on I/O error Backoff readahead size exponentially on I/O error. Michael Tokarev <mjt@tls.msk.ru> described the problem as: [QUOTE] Suppose there's a CD-rom with a scratch/etc, one sector is unreadable. In order to "fix" it, one have to read it and write to another CD-rom, or something.. or just ignore the error (if it's just a skip in a video stream). Let's assume the unreadable block is number U. But current behavior is just insane. An application requests block number N, which is before U. Kernel tries to read-ahead blocks N..U. Cdrom drive tries to read it, re-read it.. for some time. Finally, when all the N..U-1 blocks are read, kernel returns block number N (as requested) to an application, successefully. Now an app requests block number N+1, and kernel tries to read blocks N+1..U+1. Retrying again as in previous step. And so on, up to when an app requests block number U-1. And when, finally, it requests block U, it receives read error. So, kernel currentry tries to re-read the same failing block as many times as the current readahead value (256 (times?) by default). This whole process already killed my cdrom drive (I posted about it to LKML several months ago) - literally, the drive has fried, and does not work anymore. Ofcourse that problem was a bug in firmware (or whatever) of the drive *too*, but.. main problem with that is current readahead logic as described above. [/QUOTE] Which was confirmed by Jens Axboe <axboe@suse.de>: [QUOTE] For ide-cd, it tends do only end the first part of the request on a medium error. So you may see a lot of repeats :/ [/QUOTE] With this patch, retries are expected to be reduced from, say, 256, to 5. [akpm@osdl.org: cleanups] Signed-off-by: Wu Fengguang <wfg@mail.ustc.edu.cn> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-25 20:48:43 +08:00
shrink_readahead_size_eio(file, ra);
return VM_FAULT_SIGBUS;
mm: merge populate and nopage into fault (fixes nonlinear) Nonlinear mappings are (AFAIKS) simply a virtual memory concept that encodes the virtual address -> file offset differently from linear mappings. ->populate is a layering violation because the filesystem/pagecache code should need to know anything about the virtual memory mapping. The hitch here is that the ->nopage handler didn't pass down enough information (ie. pgoff). But it is more logical to pass pgoff rather than have the ->nopage function calculate it itself anyway (because that's a similar layering violation). Having the populate handler install the pte itself is likewise a nasty thing to be doing. This patch introduces a new fault handler that replaces ->nopage and ->populate and (later) ->nopfn. Most of the old mechanism is still in place so there is a lot of duplication and nice cleanups that can be removed if everyone switches over. The rationale for doing this in the first place is that nonlinear mappings are subject to the pagefault vs invalidate/truncate race too, and it seemed stupid to duplicate the synchronisation logic rather than just consolidate the two. After this patch, MAP_NONBLOCK no longer sets up ptes for pages present in pagecache. Seems like a fringe functionality anyway. NOPAGE_REFAULT is removed. This should be implemented with ->fault, and no users have hit mainline yet. [akpm@linux-foundation.org: cleanup] [randy.dunlap@oracle.com: doc. fixes for readahead] [akpm@linux-foundation.org: build fix] Signed-off-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com> Cc: Mark Fasheh <mark.fasheh@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-19 16:46:59 +08:00
}
EXPORT_SYMBOL(filemap_fault);
const struct vm_operations_struct generic_file_vm_ops = {
mm: merge populate and nopage into fault (fixes nonlinear) Nonlinear mappings are (AFAIKS) simply a virtual memory concept that encodes the virtual address -> file offset differently from linear mappings. ->populate is a layering violation because the filesystem/pagecache code should need to know anything about the virtual memory mapping. The hitch here is that the ->nopage handler didn't pass down enough information (ie. pgoff). But it is more logical to pass pgoff rather than have the ->nopage function calculate it itself anyway (because that's a similar layering violation). Having the populate handler install the pte itself is likewise a nasty thing to be doing. This patch introduces a new fault handler that replaces ->nopage and ->populate and (later) ->nopfn. Most of the old mechanism is still in place so there is a lot of duplication and nice cleanups that can be removed if everyone switches over. The rationale for doing this in the first place is that nonlinear mappings are subject to the pagefault vs invalidate/truncate race too, and it seemed stupid to duplicate the synchronisation logic rather than just consolidate the two. After this patch, MAP_NONBLOCK no longer sets up ptes for pages present in pagecache. Seems like a fringe functionality anyway. NOPAGE_REFAULT is removed. This should be implemented with ->fault, and no users have hit mainline yet. [akpm@linux-foundation.org: cleanup] [randy.dunlap@oracle.com: doc. fixes for readahead] [akpm@linux-foundation.org: build fix] Signed-off-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com> Cc: Mark Fasheh <mark.fasheh@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-19 16:46:59 +08:00
.fault = filemap_fault,
};
/* This is used for a general mmap of a disk file */
int generic_file_mmap(struct file * file, struct vm_area_struct * vma)
{
struct address_space *mapping = file->f_mapping;
if (!mapping->a_ops->readpage)
return -ENOEXEC;
file_accessed(file);
vma->vm_ops = &generic_file_vm_ops;
vma->vm_flags |= VM_CAN_NONLINEAR;
return 0;
}
/*
* This is for filesystems which do not implement ->writepage.
*/
int generic_file_readonly_mmap(struct file *file, struct vm_area_struct *vma)
{
if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_MAYWRITE))
return -EINVAL;
return generic_file_mmap(file, vma);
}
#else
int generic_file_mmap(struct file * file, struct vm_area_struct * vma)
{
return -ENOSYS;
}
int generic_file_readonly_mmap(struct file * file, struct vm_area_struct * vma)
{
return -ENOSYS;
}
#endif /* CONFIG_MMU */
EXPORT_SYMBOL(generic_file_mmap);
EXPORT_SYMBOL(generic_file_readonly_mmap);
static struct page *__read_cache_page(struct address_space *mapping,
pgoff_t index,
int (*filler)(void *,struct page*),
void *data,
gfp_t gfp)
{
struct page *page;
int err;
repeat:
page = find_get_page(mapping, index);
if (!page) {
page = __page_cache_alloc(gfp | __GFP_COLD);
if (!page)
return ERR_PTR(-ENOMEM);
err = add_to_page_cache_lru(page, mapping, index, GFP_KERNEL);
if (unlikely(err)) {
page_cache_release(page);
if (err == -EEXIST)
goto repeat;
/* Presumably ENOMEM for radix tree node */
return ERR_PTR(err);
}
err = filler(data, page);
if (err < 0) {
page_cache_release(page);
page = ERR_PTR(err);
}
}
return page;
}
static struct page *do_read_cache_page(struct address_space *mapping,
pgoff_t index,
int (*filler)(void *,struct page*),
void *data,
gfp_t gfp)
{
struct page *page;
int err;
retry:
page = __read_cache_page(mapping, index, filler, data, gfp);
if (IS_ERR(page))
return page;
if (PageUptodate(page))
goto out;
lock_page(page);
if (!page->mapping) {
unlock_page(page);
page_cache_release(page);
goto retry;
}
if (PageUptodate(page)) {
unlock_page(page);
goto out;
}
err = filler(data, page);
if (err < 0) {
page_cache_release(page);
return ERR_PTR(err);
}
out:
mark_page_accessed(page);
return page;
}
/**
* read_cache_page_async - read into page cache, fill it if needed
* @mapping: the page's address_space
* @index: the page index
* @filler: function to perform the read
* @data: destination for read data
*
* Same as read_cache_page, but don't wait for page to become unlocked
* after submitting it to the filler.
*
* Read into the page cache. If a page already exists, and PageUptodate() is
* not set, try to fill the page but don't wait for it to become unlocked.
*
* If the page does not get brought uptodate, return -EIO.
*/
struct page *read_cache_page_async(struct address_space *mapping,
pgoff_t index,
int (*filler)(void *,struct page*),
void *data)
{
return do_read_cache_page(mapping, index, filler, data, mapping_gfp_mask(mapping));
}
EXPORT_SYMBOL(read_cache_page_async);
static struct page *wait_on_page_read(struct page *page)
{
if (!IS_ERR(page)) {
wait_on_page_locked(page);
if (!PageUptodate(page)) {
page_cache_release(page);
page = ERR_PTR(-EIO);
}
}
return page;
}
/**
* read_cache_page_gfp - read into page cache, using specified page allocation flags.
* @mapping: the page's address_space
* @index: the page index
* @gfp: the page allocator flags to use if allocating
*
* This is the same as "read_mapping_page(mapping, index, NULL)", but with
* any new page allocations done using the specified allocation flags. Note
* that the Radix tree operations will still use GFP_KERNEL, so you can't
* expect to do this atomically or anything like that - but you can pass in
* other page requirements.
*
* If the page does not get brought uptodate, return -EIO.
*/
struct page *read_cache_page_gfp(struct address_space *mapping,
pgoff_t index,
gfp_t gfp)
{
filler_t *filler = (filler_t *)mapping->a_ops->readpage;
return wait_on_page_read(do_read_cache_page(mapping, index, filler, NULL, gfp));
}
EXPORT_SYMBOL(read_cache_page_gfp);
/**
* read_cache_page - read into page cache, fill it if needed
* @mapping: the page's address_space
* @index: the page index
* @filler: function to perform the read
* @data: destination for read data
*
* Read into the page cache. If a page already exists, and PageUptodate() is
* not set, try to fill the page then wait for it to become unlocked.
*
* If the page does not get brought uptodate, return -EIO.
*/
struct page *read_cache_page(struct address_space *mapping,
pgoff_t index,
int (*filler)(void *,struct page*),
void *data)
{
return wait_on_page_read(read_cache_page_async(mapping, index, filler, data));
}
EXPORT_SYMBOL(read_cache_page);
/*
* The logic we want is
*
* if suid or (sgid and xgrp)
* remove privs
*/
int should_remove_suid(struct dentry *dentry)
{
mode_t mode = dentry->d_inode->i_mode;
int kill = 0;
/* suid always must be killed */
if (unlikely(mode & S_ISUID))
kill = ATTR_KILL_SUID;
/*
* sgid without any exec bits is just a mandatory locking mark; leave
* it alone. If some exec bits are set, it's a real sgid; kill it.
*/
if (unlikely((mode & S_ISGID) && (mode & S_IXGRP)))
kill |= ATTR_KILL_SGID;
if (unlikely(kill && !capable(CAP_FSETID) && S_ISREG(mode)))
return kill;
return 0;
}
EXPORT_SYMBOL(should_remove_suid);
static int __remove_suid(struct dentry *dentry, int kill)
{
struct iattr newattrs;
newattrs.ia_valid = ATTR_FORCE | kill;
return notify_change(dentry, &newattrs);
}
int file_remove_suid(struct file *file)
{
struct dentry *dentry = file->f_path.dentry;
Implement file posix capabilities Implement file posix capabilities. This allows programs to be given a subset of root's powers regardless of who runs them, without having to use setuid and giving the binary all of root's powers. This version works with Kaigai Kohei's userspace tools, found at http://www.kaigai.gr.jp/index.php. For more information on how to use this patch, Chris Friedhoff has posted a nice page at http://www.friedhoff.org/fscaps.html. Changelog: Nov 27: Incorporate fixes from Andrew Morton (security-introduce-file-caps-tweaks and security-introduce-file-caps-warning-fix) Fix Kconfig dependency. Fix change signaling behavior when file caps are not compiled in. Nov 13: Integrate comments from Alexey: Remove CONFIG_ ifdef from capability.h, and use %zd for printing a size_t. Nov 13: Fix endianness warnings by sparse as suggested by Alexey Dobriyan. Nov 09: Address warnings of unused variables at cap_bprm_set_security when file capabilities are disabled, and simultaneously clean up the code a little, by pulling the new code into a helper function. Nov 08: For pointers to required userspace tools and how to use them, see http://www.friedhoff.org/fscaps.html. Nov 07: Fix the calculation of the highest bit checked in check_cap_sanity(). Nov 07: Allow file caps to be enabled without CONFIG_SECURITY, since capabilities are the default. Hook cap_task_setscheduler when !CONFIG_SECURITY. Move capable(TASK_KILL) to end of cap_task_kill to reduce audit messages. Nov 05: Add secondary calls in selinux/hooks.c to task_setioprio and task_setscheduler so that selinux and capabilities with file cap support can be stacked. Sep 05: As Seth Arnold points out, uid checks are out of place for capability code. Sep 01: Define task_setscheduler, task_setioprio, cap_task_kill, and task_setnice to make sure a user cannot affect a process in which they called a program with some fscaps. One remaining question is the note under task_setscheduler: are we ok with CAP_SYS_NICE being sufficient to confine a process to a cpuset? It is a semantic change, as without fsccaps, attach_task doesn't allow CAP_SYS_NICE to override the uid equivalence check. But since it uses security_task_setscheduler, which elsewhere is used where CAP_SYS_NICE can be used to override the uid equivalence check, fixing it might be tough. task_setscheduler note: this also controls cpuset:attach_task. Are we ok with CAP_SYS_NICE being used to confine to a cpuset? task_setioprio task_setnice sys_setpriority uses this (through set_one_prio) for another process. Need same checks as setrlimit Aug 21: Updated secureexec implementation to reflect the fact that euid and uid might be the same and nonzero, but the process might still have elevated caps. Aug 15: Handle endianness of xattrs. Enforce capability version match between kernel and disk. Enforce that no bits beyond the known max capability are set, else return -EPERM. With this extra processing, it may be worth reconsidering doing all the work at bprm_set_security rather than d_instantiate. Aug 10: Always call getxattr at bprm_set_security, rather than caching it at d_instantiate. [morgan@kernel.org: file-caps clean up for linux/capability.h] [bunk@kernel.org: unexport cap_inode_killpriv] Signed-off-by: Serge E. Hallyn <serue@us.ibm.com> Cc: Stephen Smalley <sds@tycho.nsa.gov> Cc: James Morris <jmorris@namei.org> Cc: Chris Wright <chrisw@sous-sol.org> Cc: Andrew Morgan <morgan@kernel.org> Signed-off-by: Andrew Morgan <morgan@kernel.org> Signed-off-by: Adrian Bunk <bunk@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17 14:31:36 +08:00
int killsuid = should_remove_suid(dentry);
int killpriv = security_inode_need_killpriv(dentry);
int error = 0;
Implement file posix capabilities Implement file posix capabilities. This allows programs to be given a subset of root's powers regardless of who runs them, without having to use setuid and giving the binary all of root's powers. This version works with Kaigai Kohei's userspace tools, found at http://www.kaigai.gr.jp/index.php. For more information on how to use this patch, Chris Friedhoff has posted a nice page at http://www.friedhoff.org/fscaps.html. Changelog: Nov 27: Incorporate fixes from Andrew Morton (security-introduce-file-caps-tweaks and security-introduce-file-caps-warning-fix) Fix Kconfig dependency. Fix change signaling behavior when file caps are not compiled in. Nov 13: Integrate comments from Alexey: Remove CONFIG_ ifdef from capability.h, and use %zd for printing a size_t. Nov 13: Fix endianness warnings by sparse as suggested by Alexey Dobriyan. Nov 09: Address warnings of unused variables at cap_bprm_set_security when file capabilities are disabled, and simultaneously clean up the code a little, by pulling the new code into a helper function. Nov 08: For pointers to required userspace tools and how to use them, see http://www.friedhoff.org/fscaps.html. Nov 07: Fix the calculation of the highest bit checked in check_cap_sanity(). Nov 07: Allow file caps to be enabled without CONFIG_SECURITY, since capabilities are the default. Hook cap_task_setscheduler when !CONFIG_SECURITY. Move capable(TASK_KILL) to end of cap_task_kill to reduce audit messages. Nov 05: Add secondary calls in selinux/hooks.c to task_setioprio and task_setscheduler so that selinux and capabilities with file cap support can be stacked. Sep 05: As Seth Arnold points out, uid checks are out of place for capability code. Sep 01: Define task_setscheduler, task_setioprio, cap_task_kill, and task_setnice to make sure a user cannot affect a process in which they called a program with some fscaps. One remaining question is the note under task_setscheduler: are we ok with CAP_SYS_NICE being sufficient to confine a process to a cpuset? It is a semantic change, as without fsccaps, attach_task doesn't allow CAP_SYS_NICE to override the uid equivalence check. But since it uses security_task_setscheduler, which elsewhere is used where CAP_SYS_NICE can be used to override the uid equivalence check, fixing it might be tough. task_setscheduler note: this also controls cpuset:attach_task. Are we ok with CAP_SYS_NICE being used to confine to a cpuset? task_setioprio task_setnice sys_setpriority uses this (through set_one_prio) for another process. Need same checks as setrlimit Aug 21: Updated secureexec implementation to reflect the fact that euid and uid might be the same and nonzero, but the process might still have elevated caps. Aug 15: Handle endianness of xattrs. Enforce capability version match between kernel and disk. Enforce that no bits beyond the known max capability are set, else return -EPERM. With this extra processing, it may be worth reconsidering doing all the work at bprm_set_security rather than d_instantiate. Aug 10: Always call getxattr at bprm_set_security, rather than caching it at d_instantiate. [morgan@kernel.org: file-caps clean up for linux/capability.h] [bunk@kernel.org: unexport cap_inode_killpriv] Signed-off-by: Serge E. Hallyn <serue@us.ibm.com> Cc: Stephen Smalley <sds@tycho.nsa.gov> Cc: James Morris <jmorris@namei.org> Cc: Chris Wright <chrisw@sous-sol.org> Cc: Andrew Morgan <morgan@kernel.org> Signed-off-by: Andrew Morgan <morgan@kernel.org> Signed-off-by: Adrian Bunk <bunk@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17 14:31:36 +08:00
if (killpriv < 0)
return killpriv;
if (killpriv)
error = security_inode_killpriv(dentry);
if (!error && killsuid)
error = __remove_suid(dentry, killsuid);
Implement file posix capabilities Implement file posix capabilities. This allows programs to be given a subset of root's powers regardless of who runs them, without having to use setuid and giving the binary all of root's powers. This version works with Kaigai Kohei's userspace tools, found at http://www.kaigai.gr.jp/index.php. For more information on how to use this patch, Chris Friedhoff has posted a nice page at http://www.friedhoff.org/fscaps.html. Changelog: Nov 27: Incorporate fixes from Andrew Morton (security-introduce-file-caps-tweaks and security-introduce-file-caps-warning-fix) Fix Kconfig dependency. Fix change signaling behavior when file caps are not compiled in. Nov 13: Integrate comments from Alexey: Remove CONFIG_ ifdef from capability.h, and use %zd for printing a size_t. Nov 13: Fix endianness warnings by sparse as suggested by Alexey Dobriyan. Nov 09: Address warnings of unused variables at cap_bprm_set_security when file capabilities are disabled, and simultaneously clean up the code a little, by pulling the new code into a helper function. Nov 08: For pointers to required userspace tools and how to use them, see http://www.friedhoff.org/fscaps.html. Nov 07: Fix the calculation of the highest bit checked in check_cap_sanity(). Nov 07: Allow file caps to be enabled without CONFIG_SECURITY, since capabilities are the default. Hook cap_task_setscheduler when !CONFIG_SECURITY. Move capable(TASK_KILL) to end of cap_task_kill to reduce audit messages. Nov 05: Add secondary calls in selinux/hooks.c to task_setioprio and task_setscheduler so that selinux and capabilities with file cap support can be stacked. Sep 05: As Seth Arnold points out, uid checks are out of place for capability code. Sep 01: Define task_setscheduler, task_setioprio, cap_task_kill, and task_setnice to make sure a user cannot affect a process in which they called a program with some fscaps. One remaining question is the note under task_setscheduler: are we ok with CAP_SYS_NICE being sufficient to confine a process to a cpuset? It is a semantic change, as without fsccaps, attach_task doesn't allow CAP_SYS_NICE to override the uid equivalence check. But since it uses security_task_setscheduler, which elsewhere is used where CAP_SYS_NICE can be used to override the uid equivalence check, fixing it might be tough. task_setscheduler note: this also controls cpuset:attach_task. Are we ok with CAP_SYS_NICE being used to confine to a cpuset? task_setioprio task_setnice sys_setpriority uses this (through set_one_prio) for another process. Need same checks as setrlimit Aug 21: Updated secureexec implementation to reflect the fact that euid and uid might be the same and nonzero, but the process might still have elevated caps. Aug 15: Handle endianness of xattrs. Enforce capability version match between kernel and disk. Enforce that no bits beyond the known max capability are set, else return -EPERM. With this extra processing, it may be worth reconsidering doing all the work at bprm_set_security rather than d_instantiate. Aug 10: Always call getxattr at bprm_set_security, rather than caching it at d_instantiate. [morgan@kernel.org: file-caps clean up for linux/capability.h] [bunk@kernel.org: unexport cap_inode_killpriv] Signed-off-by: Serge E. Hallyn <serue@us.ibm.com> Cc: Stephen Smalley <sds@tycho.nsa.gov> Cc: James Morris <jmorris@namei.org> Cc: Chris Wright <chrisw@sous-sol.org> Cc: Andrew Morgan <morgan@kernel.org> Signed-off-by: Andrew Morgan <morgan@kernel.org> Signed-off-by: Adrian Bunk <bunk@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17 14:31:36 +08:00
return error;
}
EXPORT_SYMBOL(file_remove_suid);
static size_t __iovec_copy_from_user_inatomic(char *vaddr,
const struct iovec *iov, size_t base, size_t bytes)
{
size_t copied = 0, left = 0;
while (bytes) {
char __user *buf = iov->iov_base + base;
int copy = min(bytes, iov->iov_len - base);
base = 0;
left = __copy_from_user_inatomic(vaddr, buf, copy);
copied += copy;
bytes -= copy;
vaddr += copy;
iov++;
[PATCH] Prepare for __copy_from_user_inatomic to not zero missed bytes The problem is that when we write to a file, the copy from userspace to pagecache is first done with preemption disabled, so if the source address is not immediately available the copy fails *and* *zeros* *the* *destination*. This is a problem because a concurrent read (which admittedly is an odd thing to do) might see zeros rather that was there before the write, or what was there after, or some mixture of the two (any of these being a reasonable thing to see). If the copy did fail, it will immediately be retried with preemption re-enabled so any transient problem with accessing the source won't cause an error. The first copying does not need to zero any uncopied bytes, and doing so causes the problem. It uses copy_from_user_atomic rather than copy_from_user so the simple expedient is to change copy_from_user_atomic to *not* zero out bytes on failure. The first of these two patches prepares for the change by fixing two places which assume copy_from_user_atomic does zero the tail. The two usages are very similar pieces of code which copy from a userspace iovec into one or more page-cache pages. These are changed to remove the assumption. The second patch changes __copy_from_user_inatomic* to not zero the tail. Once these are accepted, I will look at similar patches of other architectures where this is important (ppc, mips and sparc being the ones I can find). This patch: There is a problem with __copy_from_user_inatomic zeroing the tail of the buffer in the case of an error. As it is called in atomic context, the error may be transient, so it results in zeros being written where maybe they shouldn't be. In the usage in filemap, this opens a window for a well timed read to see data (zeros) which is not consistent with any ordering of reads and writes. Most cases where __copy_from_user_inatomic is called, a failure results in __copy_from_user being called immediately. As long as the latter zeros the tail, the former doesn't need to. However in *copy_from_user_iovec implementations (in both filemap and ntfs/file), it is assumed that copy_from_user_inatomic will zero the tail. This patch removes that assumption, so that after this patch it will be safe for copy_from_user_inatomic to not zero the tail. This patch also adds some commentary to filemap.h and asm-i386/uaccess.h. After this patch, all architectures that might disable preempt when kmap_atomic is called need to have their __copy_from_user_inatomic* "fixed". This includes - powerpc - i386 - mips - sparc Signed-off-by: Neil Brown <neilb@suse.de> Cc: David Howells <dhowells@redhat.com> Cc: Anton Altaparmakov <aia21@cantab.net> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: William Lee Irwin III <wli@holomorphy.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-25 20:47:58 +08:00
if (unlikely(left))
break;
}
return copied - left;
}
/*
* Copy as much as we can into the page and return the number of bytes which
* were successfully copied. If a fault is encountered then return the number of
* bytes which were copied.
*/
size_t iov_iter_copy_from_user_atomic(struct page *page,
struct iov_iter *i, unsigned long offset, size_t bytes)
{
char *kaddr;
size_t copied;
BUG_ON(!in_atomic());
kaddr = kmap_atomic(page, KM_USER0);
if (likely(i->nr_segs == 1)) {
int left;
char __user *buf = i->iov->iov_base + i->iov_offset;
left = __copy_from_user_inatomic(kaddr + offset, buf, bytes);
copied = bytes - left;
} else {
copied = __iovec_copy_from_user_inatomic(kaddr + offset,
i->iov, i->iov_offset, bytes);
}
kunmap_atomic(kaddr, KM_USER0);
return copied;
}
EXPORT_SYMBOL(iov_iter_copy_from_user_atomic);
/*
* This has the same sideeffects and return value as
* iov_iter_copy_from_user_atomic().
* The difference is that it attempts to resolve faults.
* Page must not be locked.
*/
size_t iov_iter_copy_from_user(struct page *page,
struct iov_iter *i, unsigned long offset, size_t bytes)
{
char *kaddr;
size_t copied;
kaddr = kmap(page);
if (likely(i->nr_segs == 1)) {
int left;
char __user *buf = i->iov->iov_base + i->iov_offset;
left = __copy_from_user(kaddr + offset, buf, bytes);
copied = bytes - left;
} else {
copied = __iovec_copy_from_user_inatomic(kaddr + offset,
i->iov, i->iov_offset, bytes);
}
kunmap(page);
return copied;
}
EXPORT_SYMBOL(iov_iter_copy_from_user);
void iov_iter_advance(struct iov_iter *i, size_t bytes)
{
BUG_ON(i->count < bytes);
if (likely(i->nr_segs == 1)) {
i->iov_offset += bytes;
i->count -= bytes;
} else {
const struct iovec *iov = i->iov;
size_t base = i->iov_offset;
/*
* The !iov->iov_len check ensures we skip over unlikely
* zero-length segments (without overruning the iovec).
*/
while (bytes || unlikely(i->count && !iov->iov_len)) {
int copy;
copy = min(bytes, iov->iov_len - base);
BUG_ON(!i->count || i->count < copy);
i->count -= copy;
bytes -= copy;
base += copy;
if (iov->iov_len == base) {
iov++;
base = 0;
}
}
i->iov = iov;
i->iov_offset = base;
}
}
EXPORT_SYMBOL(iov_iter_advance);
/*
* Fault in the first iovec of the given iov_iter, to a maximum length
* of bytes. Returns 0 on success, or non-zero if the memory could not be
* accessed (ie. because it is an invalid address).
*
* writev-intensive code may want this to prefault several iovecs -- that
* would be possible (callers must not rely on the fact that _only_ the
* first iovec will be faulted with the current implementation).
*/
int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes)
{
char __user *buf = i->iov->iov_base + i->iov_offset;
bytes = min(bytes, i->iov->iov_len - i->iov_offset);
return fault_in_pages_readable(buf, bytes);
}
EXPORT_SYMBOL(iov_iter_fault_in_readable);
/*
* Return the count of just the current iov_iter segment.
*/
size_t iov_iter_single_seg_count(struct iov_iter *i)
{
const struct iovec *iov = i->iov;
if (i->nr_segs == 1)
return i->count;
else
return min(i->count, iov->iov_len - i->iov_offset);
}
EXPORT_SYMBOL(iov_iter_single_seg_count);
/*
* Performs necessary checks before doing a write
*
* Can adjust writing position or amount of bytes to write.
* Returns appropriate error code that caller should return or
* zero in case that write should be allowed.
*/
inline int generic_write_checks(struct file *file, loff_t *pos, size_t *count, int isblk)
{
struct inode *inode = file->f_mapping->host;
unsigned long limit = rlimit(RLIMIT_FSIZE);
if (unlikely(*pos < 0))
return -EINVAL;
if (!isblk) {
/* FIXME: this is for backwards compatibility with 2.4 */
if (file->f_flags & O_APPEND)
*pos = i_size_read(inode);
if (limit != RLIM_INFINITY) {
if (*pos >= limit) {
send_sig(SIGXFSZ, current, 0);
return -EFBIG;
}
if (*count > limit - (typeof(limit))*pos) {
*count = limit - (typeof(limit))*pos;
}
}
}
/*
* LFS rule
*/
if (unlikely(*pos + *count > MAX_NON_LFS &&
!(file->f_flags & O_LARGEFILE))) {
if (*pos >= MAX_NON_LFS) {
return -EFBIG;
}
if (*count > MAX_NON_LFS - (unsigned long)*pos) {
*count = MAX_NON_LFS - (unsigned long)*pos;
}
}
/*
* Are we about to exceed the fs block limit ?
*
* If we have written data it becomes a short write. If we have
* exceeded without writing data we send a signal and return EFBIG.
* Linus frestrict idea will clean these up nicely..
*/
if (likely(!isblk)) {
if (unlikely(*pos >= inode->i_sb->s_maxbytes)) {
if (*count || *pos > inode->i_sb->s_maxbytes) {
return -EFBIG;
}
/* zero-length writes at ->s_maxbytes are OK */
}
if (unlikely(*pos + *count > inode->i_sb->s_maxbytes))
*count = inode->i_sb->s_maxbytes - *pos;
} else {
[PATCH] BLOCK: Make it possible to disable the block layer [try #6] Make it possible to disable the block layer. Not all embedded devices require it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require the block layer to be present. This patch does the following: (*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev support. (*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls an item that uses the block layer. This includes: (*) Block I/O tracing. (*) Disk partition code. (*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS. (*) The SCSI layer. As far as I can tell, even SCSI chardevs use the block layer to do scheduling. Some drivers that use SCSI facilities - such as USB storage - end up disabled indirectly from this. (*) Various block-based device drivers, such as IDE and the old CDROM drivers. (*) MTD blockdev handling and FTL. (*) JFFS - which uses set_bdev_super(), something it could avoid doing by taking a leaf out of JFFS2's book. (*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is, however, still used in places, and so is still available. (*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and parts of linux/fs.h. (*) Makes a number of files in fs/ contingent on CONFIG_BLOCK. (*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK. (*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK is not enabled. (*) fs/no-block.c is created to hold out-of-line stubs and things that are required when CONFIG_BLOCK is not set: (*) Default blockdev file operations (to give error ENODEV on opening). (*) Makes some /proc changes: (*) /proc/devices does not list any blockdevs. (*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK. (*) Makes some compat ioctl handling contingent on CONFIG_BLOCK. (*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if given command other than Q_SYNC or if a special device is specified. (*) In init/do_mounts.c, no reference is made to the blockdev routines if CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2. (*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return error ENOSYS by way of cond_syscall if so). (*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if CONFIG_BLOCK is not set, since they can't then happen. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2006-10-01 02:45:40 +08:00
#ifdef CONFIG_BLOCK
loff_t isize;
if (bdev_read_only(I_BDEV(inode)))
return -EPERM;
isize = i_size_read(inode);
if (*pos >= isize) {
if (*count || *pos > isize)
return -ENOSPC;
}
if (*pos + *count > isize)
*count = isize - *pos;
[PATCH] BLOCK: Make it possible to disable the block layer [try #6] Make it possible to disable the block layer. Not all embedded devices require it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require the block layer to be present. This patch does the following: (*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev support. (*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls an item that uses the block layer. This includes: (*) Block I/O tracing. (*) Disk partition code. (*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS. (*) The SCSI layer. As far as I can tell, even SCSI chardevs use the block layer to do scheduling. Some drivers that use SCSI facilities - such as USB storage - end up disabled indirectly from this. (*) Various block-based device drivers, such as IDE and the old CDROM drivers. (*) MTD blockdev handling and FTL. (*) JFFS - which uses set_bdev_super(), something it could avoid doing by taking a leaf out of JFFS2's book. (*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is, however, still used in places, and so is still available. (*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and parts of linux/fs.h. (*) Makes a number of files in fs/ contingent on CONFIG_BLOCK. (*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK. (*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK is not enabled. (*) fs/no-block.c is created to hold out-of-line stubs and things that are required when CONFIG_BLOCK is not set: (*) Default blockdev file operations (to give error ENODEV on opening). (*) Makes some /proc changes: (*) /proc/devices does not list any blockdevs. (*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK. (*) Makes some compat ioctl handling contingent on CONFIG_BLOCK. (*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if given command other than Q_SYNC or if a special device is specified. (*) In init/do_mounts.c, no reference is made to the blockdev routines if CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2. (*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return error ENOSYS by way of cond_syscall if so). (*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if CONFIG_BLOCK is not set, since they can't then happen. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2006-10-01 02:45:40 +08:00
#else
return -EPERM;
#endif
}
return 0;
}
EXPORT_SYMBOL(generic_write_checks);
int pagecache_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned flags,
struct page **pagep, void **fsdata)
{
const struct address_space_operations *aops = mapping->a_ops;
return aops->write_begin(file, mapping, pos, len, flags,
pagep, fsdata);
}
EXPORT_SYMBOL(pagecache_write_begin);
int pagecache_write_end(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned copied,
struct page *page, void *fsdata)
{
const struct address_space_operations *aops = mapping->a_ops;
mark_page_accessed(page);
return aops->write_end(file, mapping, pos, len, copied, page, fsdata);
}
EXPORT_SYMBOL(pagecache_write_end);
ssize_t
generic_file_direct_write(struct kiocb *iocb, const struct iovec *iov,
unsigned long *nr_segs, loff_t pos, loff_t *ppos,
size_t count, size_t ocount)
{
struct file *file = iocb->ki_filp;
struct address_space *mapping = file->f_mapping;
struct inode *inode = mapping->host;
ssize_t written;
size_t write_len;
pgoff_t end;
if (count != ocount)
*nr_segs = iov_shorten((struct iovec *)iov, *nr_segs, count);
write_len = iov_length(iov, *nr_segs);
end = (pos + write_len - 1) >> PAGE_CACHE_SHIFT;
written = filemap_write_and_wait_range(mapping, pos, pos + write_len - 1);
if (written)
goto out;
/*
* After a write we want buffered reads to be sure to go to disk to get
* the new data. We invalidate clean cached page from the region we're
* about to write. We do this *before* the write so that we can return
VFS: fix dio write returning EIO when try_to_release_page fails Dio write returns EIO when try_to_release_page fails because bh is still referenced. The patch commit 3f31fddfa26b7594b44ff2b34f9a04ba409e0f91 Author: Mingming Cao <cmm@us.ibm.com> Date: Fri Jul 25 01:46:22 2008 -0700 jbd: fix race between free buffer and commit transaction was merged into 2.6.27-rc1, but I noticed that this patch is not enough to fix the race. I did fsstress test heavily to 2.6.27-rc1, and found that dio write still sometimes got EIO through this test. The patch above fixed race between freeing buffer(dio) and committing transaction(jbd) but I discovered that there is another race, freeing buffer(dio) and ext3/4_ordered_writepage. : background_writeout() ->write_cache_pages() ->ext3_ordered_writepage() walk_page_buffers() -> take a bh ref block_write_full_page() -> unlock_page : <- end_page_writeback : <- race! (dio write->try_to_release_page fails) walk_page_buffers() ->release a bh ref ext3_ordered_writepage holds bh ref and does unlock_page remaining taking a bh ref, so this causes the race and failure of try_to_release_page. To fix this race, I used the approach of falling back to buffered writes if try_to_release_page() fails on a page. [akpm@linux-foundation.org: cleanups] Signed-off-by: Hisashi Hifumi <hifumi.hisashi@oss.ntt.co.jp> Cc: Chris Mason <chris.mason@oracle.com> Cc: Jan Kara <jack@suse.cz> Cc: Mingming Cao <cmm@us.ibm.com> Cc: Zach Brown <zach.brown@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-09-03 05:35:40 +08:00
* without clobbering -EIOCBQUEUED from ->direct_IO().
*/
if (mapping->nrpages) {
written = invalidate_inode_pages2_range(mapping,
pos >> PAGE_CACHE_SHIFT, end);
VFS: fix dio write returning EIO when try_to_release_page fails Dio write returns EIO when try_to_release_page fails because bh is still referenced. The patch commit 3f31fddfa26b7594b44ff2b34f9a04ba409e0f91 Author: Mingming Cao <cmm@us.ibm.com> Date: Fri Jul 25 01:46:22 2008 -0700 jbd: fix race between free buffer and commit transaction was merged into 2.6.27-rc1, but I noticed that this patch is not enough to fix the race. I did fsstress test heavily to 2.6.27-rc1, and found that dio write still sometimes got EIO through this test. The patch above fixed race between freeing buffer(dio) and committing transaction(jbd) but I discovered that there is another race, freeing buffer(dio) and ext3/4_ordered_writepage. : background_writeout() ->write_cache_pages() ->ext3_ordered_writepage() walk_page_buffers() -> take a bh ref block_write_full_page() -> unlock_page : <- end_page_writeback : <- race! (dio write->try_to_release_page fails) walk_page_buffers() ->release a bh ref ext3_ordered_writepage holds bh ref and does unlock_page remaining taking a bh ref, so this causes the race and failure of try_to_release_page. To fix this race, I used the approach of falling back to buffered writes if try_to_release_page() fails on a page. [akpm@linux-foundation.org: cleanups] Signed-off-by: Hisashi Hifumi <hifumi.hisashi@oss.ntt.co.jp> Cc: Chris Mason <chris.mason@oracle.com> Cc: Jan Kara <jack@suse.cz> Cc: Mingming Cao <cmm@us.ibm.com> Cc: Zach Brown <zach.brown@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-09-03 05:35:40 +08:00
/*
* If a page can not be invalidated, return 0 to fall back
* to buffered write.
*/
if (written) {
if (written == -EBUSY)
return 0;
goto out;
VFS: fix dio write returning EIO when try_to_release_page fails Dio write returns EIO when try_to_release_page fails because bh is still referenced. The patch commit 3f31fddfa26b7594b44ff2b34f9a04ba409e0f91 Author: Mingming Cao <cmm@us.ibm.com> Date: Fri Jul 25 01:46:22 2008 -0700 jbd: fix race between free buffer and commit transaction was merged into 2.6.27-rc1, but I noticed that this patch is not enough to fix the race. I did fsstress test heavily to 2.6.27-rc1, and found that dio write still sometimes got EIO through this test. The patch above fixed race between freeing buffer(dio) and committing transaction(jbd) but I discovered that there is another race, freeing buffer(dio) and ext3/4_ordered_writepage. : background_writeout() ->write_cache_pages() ->ext3_ordered_writepage() walk_page_buffers() -> take a bh ref block_write_full_page() -> unlock_page : <- end_page_writeback : <- race! (dio write->try_to_release_page fails) walk_page_buffers() ->release a bh ref ext3_ordered_writepage holds bh ref and does unlock_page remaining taking a bh ref, so this causes the race and failure of try_to_release_page. To fix this race, I used the approach of falling back to buffered writes if try_to_release_page() fails on a page. [akpm@linux-foundation.org: cleanups] Signed-off-by: Hisashi Hifumi <hifumi.hisashi@oss.ntt.co.jp> Cc: Chris Mason <chris.mason@oracle.com> Cc: Jan Kara <jack@suse.cz> Cc: Mingming Cao <cmm@us.ibm.com> Cc: Zach Brown <zach.brown@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-09-03 05:35:40 +08:00
}
}
written = mapping->a_ops->direct_IO(WRITE, iocb, iov, pos, *nr_segs);
/*
* Finally, try again to invalidate clean pages which might have been
* cached by non-direct readahead, or faulted in by get_user_pages()
* if the source of the write was an mmap'ed region of the file
* we're writing. Either one is a pretty crazy thing to do,
* so we don't support it 100%. If this invalidation
* fails, tough, the write still worked...
*/
if (mapping->nrpages) {
invalidate_inode_pages2_range(mapping,
pos >> PAGE_CACHE_SHIFT, end);
}
if (written > 0) {
pos += written;
if (pos > i_size_read(inode) && !S_ISBLK(inode->i_mode)) {
i_size_write(inode, pos);
mark_inode_dirty(inode);
}
*ppos = pos;
}
out:
return written;
}
EXPORT_SYMBOL(generic_file_direct_write);
/*
* Find or create a page at the given pagecache position. Return the locked
* page. This function is specifically for buffered writes.
*/
fs: symlink write_begin allocation context fix With the write_begin/write_end aops, page_symlink was broken because it could no longer pass a GFP_NOFS type mask into the point where the allocations happened. They are done in write_begin, which would always assume that the filesystem can be entered from reclaim. This bug could cause filesystem deadlocks. The funny thing with having a gfp_t mask there is that it doesn't really allow the caller to arbitrarily tinker with the context in which it can be called. It couldn't ever be GFP_ATOMIC, for example, because it needs to take the page lock. The only thing any callers care about is __GFP_FS anyway, so turn that into a single flag. Add a new flag for write_begin, AOP_FLAG_NOFS. Filesystems can now act on this flag in their write_begin function. Change __grab_cache_page to accept a nofs argument as well, to honour that flag (while we're there, change the name to grab_cache_page_write_begin which is more instructive and does away with random leading underscores). This is really a more flexible way to go in the end anyway -- if a filesystem happens to want any extra allocations aside from the pagecache ones in ints write_begin function, it may now use GFP_KERNEL (rather than GFP_NOFS) for common case allocations (eg. ocfs2_alloc_write_ctxt, for a random example). [kosaki.motohiro@jp.fujitsu.com: fix ubifs] [kosaki.motohiro@jp.fujitsu.com: fix fuse] Signed-off-by: Nick Piggin <npiggin@suse.de> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: <stable@kernel.org> [2.6.28.x] Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> [ Cleaned up the calling convention: just pass in the AOP flags untouched to the grab_cache_page_write_begin() function. That just simplifies everybody, and may even allow future expansion of the logic. - Linus ] Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-05 04:00:53 +08:00
struct page *grab_cache_page_write_begin(struct address_space *mapping,
pgoff_t index, unsigned flags)
{
int status;
struct page *page;
fs: symlink write_begin allocation context fix With the write_begin/write_end aops, page_symlink was broken because it could no longer pass a GFP_NOFS type mask into the point where the allocations happened. They are done in write_begin, which would always assume that the filesystem can be entered from reclaim. This bug could cause filesystem deadlocks. The funny thing with having a gfp_t mask there is that it doesn't really allow the caller to arbitrarily tinker with the context in which it can be called. It couldn't ever be GFP_ATOMIC, for example, because it needs to take the page lock. The only thing any callers care about is __GFP_FS anyway, so turn that into a single flag. Add a new flag for write_begin, AOP_FLAG_NOFS. Filesystems can now act on this flag in their write_begin function. Change __grab_cache_page to accept a nofs argument as well, to honour that flag (while we're there, change the name to grab_cache_page_write_begin which is more instructive and does away with random leading underscores). This is really a more flexible way to go in the end anyway -- if a filesystem happens to want any extra allocations aside from the pagecache ones in ints write_begin function, it may now use GFP_KERNEL (rather than GFP_NOFS) for common case allocations (eg. ocfs2_alloc_write_ctxt, for a random example). [kosaki.motohiro@jp.fujitsu.com: fix ubifs] [kosaki.motohiro@jp.fujitsu.com: fix fuse] Signed-off-by: Nick Piggin <npiggin@suse.de> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: <stable@kernel.org> [2.6.28.x] Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> [ Cleaned up the calling convention: just pass in the AOP flags untouched to the grab_cache_page_write_begin() function. That just simplifies everybody, and may even allow future expansion of the logic. - Linus ] Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-05 04:00:53 +08:00
gfp_t gfp_notmask = 0;
if (flags & AOP_FLAG_NOFS)
gfp_notmask = __GFP_FS;
repeat:
page = find_lock_page(mapping, index);
mm: remove likely() from grab_cache_page_write_begin() Running the annotated branch profiler on a box doing average work (firefox, evolution, xchat, distcc farm), the likely() used in grab_cache_page_write_begin() was incorrect most of the time: correct incorrect % Function File Line ------- --------- - -------- ---- ---- 1924262 71332401 97 grab_cache_page_write_begin filemap.c 2206 Adding a trace_printk() and running the function tracer limited to just this function I can see: gconfd-2-2696 [000] 4467.268935: grab_cache_page_write_begin: page= (null) mapping=ffff8800676a9460 index=7 gconfd-2-2696 [000] 4467.268946: grab_cache_page_write_begin <-ext3_write_begin gconfd-2-2696 [000] 4467.268947: grab_cache_page_write_begin: page= (null) mapping=ffff8800676a9460 index=8 gconfd-2-2696 [000] 4467.268959: grab_cache_page_write_begin <-ext3_write_begin gconfd-2-2696 [000] 4467.268960: grab_cache_page_write_begin: page= (null) mapping=ffff8800676a9460 index=9 gconfd-2-2696 [000] 4467.268972: grab_cache_page_write_begin <-ext3_write_begin gconfd-2-2696 [000] 4467.268973: grab_cache_page_write_begin: page= (null) mapping=ffff8800676a9460 index=10 gconfd-2-2696 [000] 4467.268991: grab_cache_page_write_begin <-ext3_write_begin gconfd-2-2696 [000] 4467.268992: grab_cache_page_write_begin: page= (null) mapping=ffff8800676a9460 index=11 gconfd-2-2696 [000] 4467.269005: grab_cache_page_write_begin <-ext3_write_begin Which shows that a lot of calls from ext3_write_begin will result in the page returned by "find_lock_page" will be NULL. Signed-off-by: Steven Rostedt <rostedt@goodmis.org> Acked-by: Nick Piggin <npiggin@kernel.dk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-01-14 07:46:18 +08:00
if (page)
return page;
fs: symlink write_begin allocation context fix With the write_begin/write_end aops, page_symlink was broken because it could no longer pass a GFP_NOFS type mask into the point where the allocations happened. They are done in write_begin, which would always assume that the filesystem can be entered from reclaim. This bug could cause filesystem deadlocks. The funny thing with having a gfp_t mask there is that it doesn't really allow the caller to arbitrarily tinker with the context in which it can be called. It couldn't ever be GFP_ATOMIC, for example, because it needs to take the page lock. The only thing any callers care about is __GFP_FS anyway, so turn that into a single flag. Add a new flag for write_begin, AOP_FLAG_NOFS. Filesystems can now act on this flag in their write_begin function. Change __grab_cache_page to accept a nofs argument as well, to honour that flag (while we're there, change the name to grab_cache_page_write_begin which is more instructive and does away with random leading underscores). This is really a more flexible way to go in the end anyway -- if a filesystem happens to want any extra allocations aside from the pagecache ones in ints write_begin function, it may now use GFP_KERNEL (rather than GFP_NOFS) for common case allocations (eg. ocfs2_alloc_write_ctxt, for a random example). [kosaki.motohiro@jp.fujitsu.com: fix ubifs] [kosaki.motohiro@jp.fujitsu.com: fix fuse] Signed-off-by: Nick Piggin <npiggin@suse.de> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: <stable@kernel.org> [2.6.28.x] Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> [ Cleaned up the calling convention: just pass in the AOP flags untouched to the grab_cache_page_write_begin() function. That just simplifies everybody, and may even allow future expansion of the logic. - Linus ] Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-05 04:00:53 +08:00
page = __page_cache_alloc(mapping_gfp_mask(mapping) & ~gfp_notmask);
if (!page)
return NULL;
fs: symlink write_begin allocation context fix With the write_begin/write_end aops, page_symlink was broken because it could no longer pass a GFP_NOFS type mask into the point where the allocations happened. They are done in write_begin, which would always assume that the filesystem can be entered from reclaim. This bug could cause filesystem deadlocks. The funny thing with having a gfp_t mask there is that it doesn't really allow the caller to arbitrarily tinker with the context in which it can be called. It couldn't ever be GFP_ATOMIC, for example, because it needs to take the page lock. The only thing any callers care about is __GFP_FS anyway, so turn that into a single flag. Add a new flag for write_begin, AOP_FLAG_NOFS. Filesystems can now act on this flag in their write_begin function. Change __grab_cache_page to accept a nofs argument as well, to honour that flag (while we're there, change the name to grab_cache_page_write_begin which is more instructive and does away with random leading underscores). This is really a more flexible way to go in the end anyway -- if a filesystem happens to want any extra allocations aside from the pagecache ones in ints write_begin function, it may now use GFP_KERNEL (rather than GFP_NOFS) for common case allocations (eg. ocfs2_alloc_write_ctxt, for a random example). [kosaki.motohiro@jp.fujitsu.com: fix ubifs] [kosaki.motohiro@jp.fujitsu.com: fix fuse] Signed-off-by: Nick Piggin <npiggin@suse.de> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: <stable@kernel.org> [2.6.28.x] Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> [ Cleaned up the calling convention: just pass in the AOP flags untouched to the grab_cache_page_write_begin() function. That just simplifies everybody, and may even allow future expansion of the logic. - Linus ] Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-05 04:00:53 +08:00
status = add_to_page_cache_lru(page, mapping, index,
GFP_KERNEL & ~gfp_notmask);
if (unlikely(status)) {
page_cache_release(page);
if (status == -EEXIST)
goto repeat;
return NULL;
}
return page;
}
fs: symlink write_begin allocation context fix With the write_begin/write_end aops, page_symlink was broken because it could no longer pass a GFP_NOFS type mask into the point where the allocations happened. They are done in write_begin, which would always assume that the filesystem can be entered from reclaim. This bug could cause filesystem deadlocks. The funny thing with having a gfp_t mask there is that it doesn't really allow the caller to arbitrarily tinker with the context in which it can be called. It couldn't ever be GFP_ATOMIC, for example, because it needs to take the page lock. The only thing any callers care about is __GFP_FS anyway, so turn that into a single flag. Add a new flag for write_begin, AOP_FLAG_NOFS. Filesystems can now act on this flag in their write_begin function. Change __grab_cache_page to accept a nofs argument as well, to honour that flag (while we're there, change the name to grab_cache_page_write_begin which is more instructive and does away with random leading underscores). This is really a more flexible way to go in the end anyway -- if a filesystem happens to want any extra allocations aside from the pagecache ones in ints write_begin function, it may now use GFP_KERNEL (rather than GFP_NOFS) for common case allocations (eg. ocfs2_alloc_write_ctxt, for a random example). [kosaki.motohiro@jp.fujitsu.com: fix ubifs] [kosaki.motohiro@jp.fujitsu.com: fix fuse] Signed-off-by: Nick Piggin <npiggin@suse.de> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: <stable@kernel.org> [2.6.28.x] Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> [ Cleaned up the calling convention: just pass in the AOP flags untouched to the grab_cache_page_write_begin() function. That just simplifies everybody, and may even allow future expansion of the logic. - Linus ] Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-05 04:00:53 +08:00
EXPORT_SYMBOL(grab_cache_page_write_begin);
static ssize_t generic_perform_write(struct file *file,
struct iov_iter *i, loff_t pos)
{
struct address_space *mapping = file->f_mapping;
const struct address_space_operations *a_ops = mapping->a_ops;
long status = 0;
ssize_t written = 0;
unsigned int flags = 0;
/*
* Copies from kernel address space cannot fail (NFSD is a big user).
*/
if (segment_eq(get_fs(), KERNEL_DS))
flags |= AOP_FLAG_UNINTERRUPTIBLE;
do {
struct page *page;
unsigned long offset; /* Offset into pagecache page */
unsigned long bytes; /* Bytes to write to page */
size_t copied; /* Bytes copied from user */
void *fsdata;
offset = (pos & (PAGE_CACHE_SIZE - 1));
bytes = min_t(unsigned long, PAGE_CACHE_SIZE - offset,
iov_iter_count(i));
again:
/*
* Bring in the user page that we will copy from _first_.
* Otherwise there's a nasty deadlock on copying from the
* same page as we're writing to, without it being marked
* up-to-date.
*
* Not only is this an optimisation, but it is also required
* to check that the address is actually valid, when atomic
* usercopies are used, below.
*/
if (unlikely(iov_iter_fault_in_readable(i, bytes))) {
status = -EFAULT;
break;
}
status = a_ops->write_begin(file, mapping, pos, bytes, flags,
&page, &fsdata);
if (unlikely(status))
break;
if (mapping_writably_mapped(mapping))
flush_dcache_page(page);
pagefault_disable();
copied = iov_iter_copy_from_user_atomic(page, i, offset, bytes);
pagefault_enable();
flush_dcache_page(page);
mark_page_accessed(page);
status = a_ops->write_end(file, mapping, pos, bytes, copied,
page, fsdata);
if (unlikely(status < 0))
break;
copied = status;
cond_resched();
iov_iter_advance(i, copied);
if (unlikely(copied == 0)) {
/*
* If we were unable to copy any data at all, we must
* fall back to a single segment length write.
*
* If we didn't fallback here, we could livelock
* because not all segments in the iov can be copied at
* once without a pagefault.
*/
bytes = min_t(unsigned long, PAGE_CACHE_SIZE - offset,
iov_iter_single_seg_count(i));
goto again;
}
pos += copied;
written += copied;
balance_dirty_pages_ratelimited(mapping);
} while (iov_iter_count(i));
return written ? written : status;
}
ssize_t
generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov,
unsigned long nr_segs, loff_t pos, loff_t *ppos,
size_t count, ssize_t written)
{
struct file *file = iocb->ki_filp;
ssize_t status;
struct iov_iter i;
iov_iter_init(&i, iov, nr_segs, count, written);
status = generic_perform_write(file, &i, pos);
if (likely(status >= 0)) {
written += status;
*ppos = pos + status;
}
return written ? written : status;
}
EXPORT_SYMBOL(generic_file_buffered_write);
/**
* __generic_file_aio_write - write data to a file
* @iocb: IO state structure (file, offset, etc.)
* @iov: vector with data to write
* @nr_segs: number of segments in the vector
* @ppos: position where to write
*
* This function does all the work needed for actually writing data to a
* file. It does all basic checks, removes SUID from the file, updates
* modification times and calls proper subroutines depending on whether we
* do direct IO or a standard buffered write.
*
* It expects i_mutex to be grabbed unless we work on a block device or similar
* object which does not need locking at all.
*
* This function does *not* take care of syncing data in case of O_SYNC write.
* A caller has to handle it. This is mainly due to the fact that we want to
* avoid syncing under i_mutex.
*/
ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
unsigned long nr_segs, loff_t *ppos)
{
struct file *file = iocb->ki_filp;
struct address_space * mapping = file->f_mapping;
size_t ocount; /* original count */
size_t count; /* after file limit checks */
struct inode *inode = mapping->host;
loff_t pos;
ssize_t written;
ssize_t err;
ocount = 0;
err = generic_segment_checks(iov, &nr_segs, &ocount, VERIFY_READ);
if (err)
return err;
count = ocount;
pos = *ppos;
vfs_check_frozen(inode->i_sb, SB_FREEZE_WRITE);
/* We can write back this queue in page reclaim */
current->backing_dev_info = mapping->backing_dev_info;
written = 0;
err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode));
if (err)
goto out;
if (count == 0)
goto out;
err = file_remove_suid(file);
if (err)
goto out;
file_update_time(file);
/* coalesce the iovecs and go direct-to-BIO for O_DIRECT */
if (unlikely(file->f_flags & O_DIRECT)) {
loff_t endbyte;
ssize_t written_buffered;
written = generic_file_direct_write(iocb, iov, &nr_segs, pos,
ppos, count, ocount);
if (written < 0 || written == count)
goto out;
/*
* direct-io write to a hole: fall through to buffered I/O
* for completing the rest of the request.
*/
pos += written;
count -= written;
written_buffered = generic_file_buffered_write(iocb, iov,
nr_segs, pos, ppos, count,
written);
/*
* If generic_file_buffered_write() retuned a synchronous error
* then we want to return the number of bytes which were
* direct-written, or the error code if that was zero. Note
* that this differs from normal direct-io semantics, which
* will return -EFOO even if some bytes were written.
*/
if (written_buffered < 0) {
err = written_buffered;
goto out;
}
/*
* We need to ensure that the page cache pages are written to
* disk and invalidated to preserve the expected O_DIRECT
* semantics.
*/
endbyte = pos + written_buffered - written - 1;
err = filemap_write_and_wait_range(file->f_mapping, pos, endbyte);
if (err == 0) {
written = written_buffered;
invalidate_mapping_pages(mapping,
pos >> PAGE_CACHE_SHIFT,
endbyte >> PAGE_CACHE_SHIFT);
} else {
/*
* We don't know how much we wrote, so just return
* the number of bytes which were direct-written
*/
}
} else {
written = generic_file_buffered_write(iocb, iov, nr_segs,
pos, ppos, count, written);
}
out:
current->backing_dev_info = NULL;
return written ? written : err;
}
EXPORT_SYMBOL(__generic_file_aio_write);
/**
* generic_file_aio_write - write data to a file
* @iocb: IO state structure
* @iov: vector with data to write
* @nr_segs: number of segments in the vector
* @pos: position in file where to write
*
* This is a wrapper around __generic_file_aio_write() to be used by most
* filesystems. It takes care of syncing the file in case of O_SYNC file
* and acquires i_mutex as needed.
*/
ssize_t generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
unsigned long nr_segs, loff_t pos)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
struct blk_plug plug;
ssize_t ret;
BUG_ON(iocb->ki_pos != pos);
mutex_lock(&inode->i_mutex);
blk_start_plug(&plug);
ret = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos);
mutex_unlock(&inode->i_mutex);
if (ret > 0 || ret == -EIOCBQUEUED) {
ssize_t err;
err = generic_write_sync(file, pos, ret);
if (err < 0 && ret > 0)
ret = err;
}
blk_finish_plug(&plug);
return ret;
}
EXPORT_SYMBOL(generic_file_aio_write);
/**
* try_to_release_page() - release old fs-specific metadata on a page
*
* @page: the page which the kernel is trying to free
* @gfp_mask: memory allocation flags (and I/O mode)
*
* The address_space is to try to release any data against the page
* (presumably at page->private). If the release was successful, return `1'.
* Otherwise return zero.
*
* This may also be called if PG_fscache is set on a page, indicating that the
* page is known to the local caching routines.
*
* The @gfp_mask argument specifies whether I/O may be performed to release
* this page (__GFP_IO), and whether the call may block (__GFP_WAIT & __GFP_FS).
*
*/
int try_to_release_page(struct page *page, gfp_t gfp_mask)
{
struct address_space * const mapping = page->mapping;
BUG_ON(!PageLocked(page));
if (PageWriteback(page))
return 0;
if (mapping && mapping->a_ops->releasepage)
return mapping->a_ops->releasepage(page, gfp_mask);
return try_to_free_buffers(page);
}
EXPORT_SYMBOL(try_to_release_page);