linux/mm/filemap.c

2694 lines
71 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/export.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 09:04:16 +00:00
#include <linux/uaccess.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 08:04:11 +00:00
#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/cpuset.h>
#include <linux/hardirq.h> /* for BUG_ON(!in_atomic()) only */
mm: memcontrol: rewrite charge API These patches rework memcg charge lifetime to integrate more naturally with the lifetime of user pages. This drastically simplifies the code and reduces charging and uncharging overhead. The most expensive part of charging and uncharging is the page_cgroup bit spinlock, which is removed entirely after this series. Here are the top-10 profile entries of a stress test that reads a 128G sparse file on a freshly booted box, without even a dedicated cgroup (i.e. executing in the root memcg). Before: 15.36% cat [kernel.kallsyms] [k] copy_user_generic_string 13.31% cat [kernel.kallsyms] [k] memset 11.48% cat [kernel.kallsyms] [k] do_mpage_readpage 4.23% cat [kernel.kallsyms] [k] get_page_from_freelist 2.38% cat [kernel.kallsyms] [k] put_page 2.32% cat [kernel.kallsyms] [k] __mem_cgroup_commit_charge 2.18% kswapd0 [kernel.kallsyms] [k] __mem_cgroup_uncharge_common 1.92% kswapd0 [kernel.kallsyms] [k] shrink_page_list 1.86% cat [kernel.kallsyms] [k] __radix_tree_lookup 1.62% cat [kernel.kallsyms] [k] __pagevec_lru_add_fn After: 15.67% cat [kernel.kallsyms] [k] copy_user_generic_string 13.48% cat [kernel.kallsyms] [k] memset 11.42% cat [kernel.kallsyms] [k] do_mpage_readpage 3.98% cat [kernel.kallsyms] [k] get_page_from_freelist 2.46% cat [kernel.kallsyms] [k] put_page 2.13% kswapd0 [kernel.kallsyms] [k] shrink_page_list 1.88% cat [kernel.kallsyms] [k] __radix_tree_lookup 1.67% cat [kernel.kallsyms] [k] __pagevec_lru_add_fn 1.39% kswapd0 [kernel.kallsyms] [k] free_pcppages_bulk 1.30% cat [kernel.kallsyms] [k] kfree As you can see, the memcg footprint has shrunk quite a bit. text data bss dec hex filename 37970 9892 400 48262 bc86 mm/memcontrol.o.old 35239 9892 400 45531 b1db mm/memcontrol.o This patch (of 4): The memcg charge API charges pages before they are rmapped - i.e. have an actual "type" - and so every callsite needs its own set of charge and uncharge functions to know what type is being operated on. Worse, uncharge has to happen from a context that is still type-specific, rather than at the end of the page's lifetime with exclusive access, and so requires a lot of synchronization. Rewrite the charge API to provide a generic set of try_charge(), commit_charge() and cancel_charge() transaction operations, much like what's currently done for swap-in: mem_cgroup_try_charge() attempts to reserve a charge, reclaiming pages from the memcg if necessary. mem_cgroup_commit_charge() commits the page to the charge once it has a valid page->mapping and PageAnon() reliably tells the type. mem_cgroup_cancel_charge() aborts the transaction. This reduces the charge API and enables subsequent patches to drastically simplify uncharging. As pages need to be committed after rmap is established but before they are added to the LRU, page_add_new_anon_rmap() must stop doing LRU additions again. Revive lru_cache_add_active_or_unevictable(). [hughd@google.com: fix shmem_unuse] [hughd@google.com: Add comments on the private use of -EAGAIN] Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: Michal Hocko <mhocko@suse.cz> Cc: Tejun Heo <tj@kernel.org> Cc: Vladimir Davydov <vdavydov@parallels.com> Signed-off-by: Hugh Dickins <hughd@google.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-08 21:19:20 +00:00
#include <linux/hugetlb.h>
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 08:13:53 +00:00
#include <linux/memcontrol.h>
#include <linux/cleancache.h>
#include <linux/rmap.h>
#include "internal.h"
#define CREATE_TRACE_POINTS
#include <trace/events/filemap.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_rwsem (truncate_pagecache)
* ->private_lock (__free_pte->__set_page_dirty_buffers)
* ->swap_lock (exclusive_swap_page, others)
* ->mapping->tree_lock
*
* ->i_mutex
* ->i_mmap_rwsem (truncate->unmap_mapping_range)
*
* ->mmap_sem
* ->i_mmap_rwsem
* ->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_perform_write)
* ->mmap_sem (fault_in_pages_readable->do_page_fault)
*
writeback: split inode_wb_list_lock into bdi_writeback.list_lock Split the global inode_wb_list_lock into a per-bdi_writeback list_lock, as it's currently the most contended lock in the system for metadata heavy workloads. It won't help for single-filesystem workloads for which we'll need the I/O-less balance_dirty_pages, but at least we can dedicate a cpu to spinning on each bdi now for larger systems. Based on earlier patches from Nick Piggin and Dave Chinner. It reduces lock contentions to 1/4 in this test case: 10 HDD JBOD, 100 dd on each disk, XFS, 6GB ram lock_stat version 0.3 ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- class name con-bounces contentions waittime-min waittime-max waittime-total acq-bounces acquisitions holdtime-min holdtime-max holdtime-total ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- vanilla 2.6.39-rc3: inode_wb_list_lock: 42590 44433 0.12 147.74 144127.35 252274 886792 0.08 121.34 917211.23 ------------------ inode_wb_list_lock 2 [<ffffffff81165da5>] bdev_inode_switch_bdi+0x29/0x85 inode_wb_list_lock 34 [<ffffffff8115bd0b>] inode_wb_list_del+0x22/0x49 inode_wb_list_lock 12893 [<ffffffff8115bb53>] __mark_inode_dirty+0x170/0x1d0 inode_wb_list_lock 10702 [<ffffffff8115afef>] writeback_single_inode+0x16d/0x20a ------------------ inode_wb_list_lock 2 [<ffffffff81165da5>] bdev_inode_switch_bdi+0x29/0x85 inode_wb_list_lock 19 [<ffffffff8115bd0b>] inode_wb_list_del+0x22/0x49 inode_wb_list_lock 5550 [<ffffffff8115bb53>] __mark_inode_dirty+0x170/0x1d0 inode_wb_list_lock 8511 [<ffffffff8115b4ad>] writeback_sb_inodes+0x10f/0x157 2.6.39-rc3 + patch: &(&wb->list_lock)->rlock: 11383 11657 0.14 151.69 40429.51 90825 527918 0.11 145.90 556843.37 ------------------------ &(&wb->list_lock)->rlock 10 [<ffffffff8115b189>] inode_wb_list_del+0x5f/0x86 &(&wb->list_lock)->rlock 1493 [<ffffffff8115b1ed>] writeback_inodes_wb+0x3d/0x150 &(&wb->list_lock)->rlock 3652 [<ffffffff8115a8e9>] writeback_sb_inodes+0x123/0x16f &(&wb->list_lock)->rlock 1412 [<ffffffff8115a38e>] writeback_single_inode+0x17f/0x223 ------------------------ &(&wb->list_lock)->rlock 3 [<ffffffff8110b5af>] bdi_lock_two+0x46/0x4b &(&wb->list_lock)->rlock 6 [<ffffffff8115b189>] inode_wb_list_del+0x5f/0x86 &(&wb->list_lock)->rlock 2061 [<ffffffff8115af97>] __mark_inode_dirty+0x173/0x1cf &(&wb->list_lock)->rlock 2629 [<ffffffff8115a8e9>] writeback_sb_inodes+0x123/0x16f hughd@google.com: fix recursive lock when bdi_lock_two() is called with new the same as old akpm@linux-foundation.org: cleanup bdev_inode_switch_bdi() comment Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
2011-04-22 00:19:44 +00:00
* bdi->wb.list_lock
* sb_lock (fs/fs-writeback.c)
* ->mapping->tree_lock (__sync_single_inode)
*
* ->i_mmap_rwsem
* ->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)
writeback: split inode_wb_list_lock into bdi_writeback.list_lock Split the global inode_wb_list_lock into a per-bdi_writeback list_lock, as it's currently the most contended lock in the system for metadata heavy workloads. It won't help for single-filesystem workloads for which we'll need the I/O-less balance_dirty_pages, but at least we can dedicate a cpu to spinning on each bdi now for larger systems. Based on earlier patches from Nick Piggin and Dave Chinner. It reduces lock contentions to 1/4 in this test case: 10 HDD JBOD, 100 dd on each disk, XFS, 6GB ram lock_stat version 0.3 ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- class name con-bounces contentions waittime-min waittime-max waittime-total acq-bounces acquisitions holdtime-min holdtime-max holdtime-total ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- vanilla 2.6.39-rc3: inode_wb_list_lock: 42590 44433 0.12 147.74 144127.35 252274 886792 0.08 121.34 917211.23 ------------------ inode_wb_list_lock 2 [<ffffffff81165da5>] bdev_inode_switch_bdi+0x29/0x85 inode_wb_list_lock 34 [<ffffffff8115bd0b>] inode_wb_list_del+0x22/0x49 inode_wb_list_lock 12893 [<ffffffff8115bb53>] __mark_inode_dirty+0x170/0x1d0 inode_wb_list_lock 10702 [<ffffffff8115afef>] writeback_single_inode+0x16d/0x20a ------------------ inode_wb_list_lock 2 [<ffffffff81165da5>] bdev_inode_switch_bdi+0x29/0x85 inode_wb_list_lock 19 [<ffffffff8115bd0b>] inode_wb_list_del+0x22/0x49 inode_wb_list_lock 5550 [<ffffffff8115bb53>] __mark_inode_dirty+0x170/0x1d0 inode_wb_list_lock 8511 [<ffffffff8115b4ad>] writeback_sb_inodes+0x10f/0x157 2.6.39-rc3 + patch: &(&wb->list_lock)->rlock: 11383 11657 0.14 151.69 40429.51 90825 527918 0.11 145.90 556843.37 ------------------------ &(&wb->list_lock)->rlock 10 [<ffffffff8115b189>] inode_wb_list_del+0x5f/0x86 &(&wb->list_lock)->rlock 1493 [<ffffffff8115b1ed>] writeback_inodes_wb+0x3d/0x150 &(&wb->list_lock)->rlock 3652 [<ffffffff8115a8e9>] writeback_sb_inodes+0x123/0x16f &(&wb->list_lock)->rlock 1412 [<ffffffff8115a38e>] writeback_single_inode+0x17f/0x223 ------------------------ &(&wb->list_lock)->rlock 3 [<ffffffff8110b5af>] bdi_lock_two+0x46/0x4b &(&wb->list_lock)->rlock 6 [<ffffffff8115b189>] inode_wb_list_del+0x5f/0x86 &(&wb->list_lock)->rlock 2061 [<ffffffff8115af97>] __mark_inode_dirty+0x173/0x1cf &(&wb->list_lock)->rlock 2629 [<ffffffff8115a8e9>] writeback_sb_inodes+0x123/0x16f hughd@google.com: fix recursive lock when bdi_lock_two() is called with new the same as old akpm@linux-foundation.org: cleanup bdev_inode_switch_bdi() comment Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
2011-04-22 00:19:44 +00:00
* bdi.wb->list_lock (page_remove_rmap->set_page_dirty)
* ->inode->i_lock (page_remove_rmap->set_page_dirty)
memcg: add per cgroup dirty page accounting When modifying PG_Dirty on cached file pages, update the new MEM_CGROUP_STAT_DIRTY counter. This is done in the same places where global NR_FILE_DIRTY is managed. The new memcg stat is visible in the per memcg memory.stat cgroupfs file. The most recent past attempt at this was http://thread.gmane.org/gmane.linux.kernel.cgroups/8632 The new accounting supports future efforts to add per cgroup dirty page throttling and writeback. It also helps an administrator break down a container's memory usage and provides evidence to understand memcg oom kills (the new dirty count is included in memcg oom kill messages). The ability to move page accounting between memcg (memory.move_charge_at_immigrate) makes this accounting more complicated than the global counter. The existing mem_cgroup_{begin,end}_page_stat() lock is used to serialize move accounting with stat updates. Typical update operation: memcg = mem_cgroup_begin_page_stat(page) if (TestSetPageDirty()) { [...] mem_cgroup_update_page_stat(memcg) } mem_cgroup_end_page_stat(memcg) Summary of mem_cgroup_end_page_stat() overhead: - Without CONFIG_MEMCG it's a no-op - With CONFIG_MEMCG and no inter memcg task movement, it's just rcu_read_lock() - With CONFIG_MEMCG and inter memcg task movement, it's rcu_read_lock() + spin_lock_irqsave() A memcg parameter is added to several routines because their callers now grab mem_cgroup_begin_page_stat() which returns the memcg later needed by for mem_cgroup_update_page_stat(). Because mem_cgroup_begin_page_stat() may disable interrupts, some adjustments are needed: - move __mark_inode_dirty() from __set_page_dirty() to its caller. __mark_inode_dirty() locking does not want interrupts disabled. - use spin_lock_irqsave(tree_lock) rather than spin_lock_irq() in __delete_from_page_cache(), replace_page_cache_page(), invalidate_complete_page2(), and __remove_mapping(). text data bss dec hex filename 8925147 1774832 1785856 12485835 be84cb vmlinux-!CONFIG_MEMCG-before 8925339 1774832 1785856 12486027 be858b vmlinux-!CONFIG_MEMCG-after +192 text bytes 8965977 1784992 1785856 12536825 bf4bf9 vmlinux-CONFIG_MEMCG-before 8966750 1784992 1785856 12537598 bf4efe vmlinux-CONFIG_MEMCG-after +773 text bytes Performance tests run on v4.0-rc1-36-g4f671fe2f952. Lower is better for all metrics, they're all wall clock or cycle counts. The read and write fault benchmarks just measure fault time, they do not include I/O time. * CONFIG_MEMCG not set: baseline patched kbuild 1m25.030000(+-0.088% 3 samples) 1m25.426667(+-0.120% 3 samples) dd write 100 MiB 0.859211561 +-15.10% 0.874162885 +-15.03% dd write 200 MiB 1.670653105 +-17.87% 1.669384764 +-11.99% dd write 1000 MiB 8.434691190 +-14.15% 8.474733215 +-14.77% read fault cycles 254.0(+-0.000% 10 samples) 253.0(+-0.000% 10 samples) write fault cycles 2021.2(+-3.070% 10 samples) 1984.5(+-1.036% 10 samples) * CONFIG_MEMCG=y root_memcg: baseline patched kbuild 1m25.716667(+-0.105% 3 samples) 1m25.686667(+-0.153% 3 samples) dd write 100 MiB 0.855650830 +-14.90% 0.887557919 +-14.90% dd write 200 MiB 1.688322953 +-12.72% 1.667682724 +-13.33% dd write 1000 MiB 8.418601605 +-14.30% 8.673532299 +-15.00% read fault cycles 266.0(+-0.000% 10 samples) 266.0(+-0.000% 10 samples) write fault cycles 2051.7(+-1.349% 10 samples) 2049.6(+-1.686% 10 samples) * CONFIG_MEMCG=y non-root_memcg: baseline patched kbuild 1m26.120000(+-0.273% 3 samples) 1m25.763333(+-0.127% 3 samples) dd write 100 MiB 0.861723964 +-15.25% 0.818129350 +-14.82% dd write 200 MiB 1.669887569 +-13.30% 1.698645885 +-13.27% dd write 1000 MiB 8.383191730 +-14.65% 8.351742280 +-14.52% read fault cycles 265.7(+-0.172% 10 samples) 267.0(+-0.000% 10 samples) write fault cycles 2070.6(+-1.512% 10 samples) 2084.4(+-2.148% 10 samples) As expected anon page faults are not affected by this patch. tj: Updated to apply on top of the recent cancel_dirty_page() changes. Signed-off-by: Sha Zhengju <handai.szj@gmail.com> Signed-off-by: Greg Thelen <gthelen@google.com> Signed-off-by: Tejun Heo <tj@kernel.org> Signed-off-by: Jens Axboe <axboe@fb.com>
2015-05-22 21:13:16 +00:00
* ->memcg->move_lock (page_remove_rmap->mem_cgroup_begin_page_stat)
writeback: split inode_wb_list_lock into bdi_writeback.list_lock Split the global inode_wb_list_lock into a per-bdi_writeback list_lock, as it's currently the most contended lock in the system for metadata heavy workloads. It won't help for single-filesystem workloads for which we'll need the I/O-less balance_dirty_pages, but at least we can dedicate a cpu to spinning on each bdi now for larger systems. Based on earlier patches from Nick Piggin and Dave Chinner. It reduces lock contentions to 1/4 in this test case: 10 HDD JBOD, 100 dd on each disk, XFS, 6GB ram lock_stat version 0.3 ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- class name con-bounces contentions waittime-min waittime-max waittime-total acq-bounces acquisitions holdtime-min holdtime-max holdtime-total ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- vanilla 2.6.39-rc3: inode_wb_list_lock: 42590 44433 0.12 147.74 144127.35 252274 886792 0.08 121.34 917211.23 ------------------ inode_wb_list_lock 2 [<ffffffff81165da5>] bdev_inode_switch_bdi+0x29/0x85 inode_wb_list_lock 34 [<ffffffff8115bd0b>] inode_wb_list_del+0x22/0x49 inode_wb_list_lock 12893 [<ffffffff8115bb53>] __mark_inode_dirty+0x170/0x1d0 inode_wb_list_lock 10702 [<ffffffff8115afef>] writeback_single_inode+0x16d/0x20a ------------------ inode_wb_list_lock 2 [<ffffffff81165da5>] bdev_inode_switch_bdi+0x29/0x85 inode_wb_list_lock 19 [<ffffffff8115bd0b>] inode_wb_list_del+0x22/0x49 inode_wb_list_lock 5550 [<ffffffff8115bb53>] __mark_inode_dirty+0x170/0x1d0 inode_wb_list_lock 8511 [<ffffffff8115b4ad>] writeback_sb_inodes+0x10f/0x157 2.6.39-rc3 + patch: &(&wb->list_lock)->rlock: 11383 11657 0.14 151.69 40429.51 90825 527918 0.11 145.90 556843.37 ------------------------ &(&wb->list_lock)->rlock 10 [<ffffffff8115b189>] inode_wb_list_del+0x5f/0x86 &(&wb->list_lock)->rlock 1493 [<ffffffff8115b1ed>] writeback_inodes_wb+0x3d/0x150 &(&wb->list_lock)->rlock 3652 [<ffffffff8115a8e9>] writeback_sb_inodes+0x123/0x16f &(&wb->list_lock)->rlock 1412 [<ffffffff8115a38e>] writeback_single_inode+0x17f/0x223 ------------------------ &(&wb->list_lock)->rlock 3 [<ffffffff8110b5af>] bdi_lock_two+0x46/0x4b &(&wb->list_lock)->rlock 6 [<ffffffff8115b189>] inode_wb_list_del+0x5f/0x86 &(&wb->list_lock)->rlock 2061 [<ffffffff8115af97>] __mark_inode_dirty+0x173/0x1cf &(&wb->list_lock)->rlock 2629 [<ffffffff8115a8e9>] writeback_sb_inodes+0x123/0x16f hughd@google.com: fix recursive lock when bdi_lock_two() is called with new the same as old akpm@linux-foundation.org: cleanup bdev_inode_switch_bdi() comment Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
2011-04-22 00:19:44 +00:00
* bdi.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)
*
* ->i_mmap_rwsem
* ->tasklist_lock (memory_failure, collect_procs_ao)
*/
mm + fs: store shadow entries in page cache Reclaim will be leaving shadow entries in the page cache radix tree upon evicting the real page. As those pages are found from the LRU, an iput() can lead to the inode being freed concurrently. At this point, reclaim must no longer install shadow pages because the inode freeing code needs to ensure the page tree is really empty. Add an address_space flag, AS_EXITING, that the inode freeing code sets under the tree lock before doing the final truncate. Reclaim will check for this flag before installing shadow pages. Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Rik van Riel <riel@redhat.com> Reviewed-by: Minchan Kim <minchan@kernel.org> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Bob Liu <bob.liu@oracle.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Dave Chinner <david@fromorbit.com> Cc: Greg Thelen <gthelen@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jan Kara <jack@suse.cz> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Luigi Semenzato <semenzato@google.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Metin Doslu <metin@citusdata.com> Cc: Michel Lespinasse <walken@google.com> Cc: Ozgun Erdogan <ozgun@citusdata.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Roman Gushchin <klamm@yandex-team.ru> Cc: Ryan Mallon <rmallon@gmail.com> Cc: Tejun Heo <tj@kernel.org> Cc: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-03 21:47:49 +00:00
static void page_cache_tree_delete(struct address_space *mapping,
struct page *page, void *shadow)
{
mm: keep page cache radix tree nodes in check Previously, page cache radix tree nodes were freed after reclaim emptied out their page pointers. But now reclaim stores shadow entries in their place, which are only reclaimed when the inodes themselves are reclaimed. This is problematic for bigger files that are still in use after they have a significant amount of their cache reclaimed, without any of those pages actually refaulting. The shadow entries will just sit there and waste memory. In the worst case, the shadow entries will accumulate until the machine runs out of memory. To get this under control, the VM will track radix tree nodes exclusively containing shadow entries on a per-NUMA node list. Per-NUMA rather than global because we expect the radix tree nodes themselves to be allocated node-locally and we want to reduce cross-node references of otherwise independent cache workloads. A simple shrinker will then reclaim these nodes on memory pressure. A few things need to be stored in the radix tree node to implement the shadow node LRU and allow tree deletions coming from the list: 1. There is no index available that would describe the reverse path from the node up to the tree root, which is needed to perform a deletion. To solve this, encode in each node its offset inside the parent. This can be stored in the unused upper bits of the same member that stores the node's height at no extra space cost. 2. The number of shadow entries needs to be counted in addition to the regular entries, to quickly detect when the node is ready to go to the shadow node LRU list. The current entry count is an unsigned int but the maximum number of entries is 64, so a shadow counter can easily be stored in the unused upper bits. 3. Tree modification needs tree lock and tree root, which are located in the address space, so store an address_space backpointer in the node. The parent pointer of the node is in a union with the 2-word rcu_head, so the backpointer comes at no extra cost as well. 4. The node needs to be linked to an LRU list, which requires a list head inside the node. This does increase the size of the node, but it does not change the number of objects that fit into a slab page. [akpm@linux-foundation.org: export the right function] Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Rik van Riel <riel@redhat.com> Reviewed-by: Minchan Kim <minchan@kernel.org> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Bob Liu <bob.liu@oracle.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Dave Chinner <david@fromorbit.com> Cc: Greg Thelen <gthelen@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jan Kara <jack@suse.cz> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Luigi Semenzato <semenzato@google.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Metin Doslu <metin@citusdata.com> Cc: Michel Lespinasse <walken@google.com> Cc: Ozgun Erdogan <ozgun@citusdata.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Roman Gushchin <klamm@yandex-team.ru> Cc: Ryan Mallon <rmallon@gmail.com> Cc: Tejun Heo <tj@kernel.org> Cc: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-03 21:47:56 +00:00
struct radix_tree_node *node;
unsigned long index;
unsigned int offset;
unsigned int tag;
void **slot;
mm + fs: store shadow entries in page cache Reclaim will be leaving shadow entries in the page cache radix tree upon evicting the real page. As those pages are found from the LRU, an iput() can lead to the inode being freed concurrently. At this point, reclaim must no longer install shadow pages because the inode freeing code needs to ensure the page tree is really empty. Add an address_space flag, AS_EXITING, that the inode freeing code sets under the tree lock before doing the final truncate. Reclaim will check for this flag before installing shadow pages. Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Rik van Riel <riel@redhat.com> Reviewed-by: Minchan Kim <minchan@kernel.org> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Bob Liu <bob.liu@oracle.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Dave Chinner <david@fromorbit.com> Cc: Greg Thelen <gthelen@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jan Kara <jack@suse.cz> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Luigi Semenzato <semenzato@google.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Metin Doslu <metin@citusdata.com> Cc: Michel Lespinasse <walken@google.com> Cc: Ozgun Erdogan <ozgun@citusdata.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Roman Gushchin <klamm@yandex-team.ru> Cc: Ryan Mallon <rmallon@gmail.com> Cc: Tejun Heo <tj@kernel.org> Cc: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-03 21:47:49 +00:00
mm: keep page cache radix tree nodes in check Previously, page cache radix tree nodes were freed after reclaim emptied out their page pointers. But now reclaim stores shadow entries in their place, which are only reclaimed when the inodes themselves are reclaimed. This is problematic for bigger files that are still in use after they have a significant amount of their cache reclaimed, without any of those pages actually refaulting. The shadow entries will just sit there and waste memory. In the worst case, the shadow entries will accumulate until the machine runs out of memory. To get this under control, the VM will track radix tree nodes exclusively containing shadow entries on a per-NUMA node list. Per-NUMA rather than global because we expect the radix tree nodes themselves to be allocated node-locally and we want to reduce cross-node references of otherwise independent cache workloads. A simple shrinker will then reclaim these nodes on memory pressure. A few things need to be stored in the radix tree node to implement the shadow node LRU and allow tree deletions coming from the list: 1. There is no index available that would describe the reverse path from the node up to the tree root, which is needed to perform a deletion. To solve this, encode in each node its offset inside the parent. This can be stored in the unused upper bits of the same member that stores the node's height at no extra space cost. 2. The number of shadow entries needs to be counted in addition to the regular entries, to quickly detect when the node is ready to go to the shadow node LRU list. The current entry count is an unsigned int but the maximum number of entries is 64, so a shadow counter can easily be stored in the unused upper bits. 3. Tree modification needs tree lock and tree root, which are located in the address space, so store an address_space backpointer in the node. The parent pointer of the node is in a union with the 2-word rcu_head, so the backpointer comes at no extra cost as well. 4. The node needs to be linked to an LRU list, which requires a list head inside the node. This does increase the size of the node, but it does not change the number of objects that fit into a slab page. [akpm@linux-foundation.org: export the right function] Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Rik van Riel <riel@redhat.com> Reviewed-by: Minchan Kim <minchan@kernel.org> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Bob Liu <bob.liu@oracle.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Dave Chinner <david@fromorbit.com> Cc: Greg Thelen <gthelen@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jan Kara <jack@suse.cz> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Luigi Semenzato <semenzato@google.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Metin Doslu <metin@citusdata.com> Cc: Michel Lespinasse <walken@google.com> Cc: Ozgun Erdogan <ozgun@citusdata.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Roman Gushchin <klamm@yandex-team.ru> Cc: Ryan Mallon <rmallon@gmail.com> Cc: Tejun Heo <tj@kernel.org> Cc: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-03 21:47:56 +00:00
VM_BUG_ON(!PageLocked(page));
__radix_tree_lookup(&mapping->page_tree, page->index, &node, &slot);
if (shadow) {
mm + fs: store shadow entries in page cache Reclaim will be leaving shadow entries in the page cache radix tree upon evicting the real page. As those pages are found from the LRU, an iput() can lead to the inode being freed concurrently. At this point, reclaim must no longer install shadow pages because the inode freeing code needs to ensure the page tree is really empty. Add an address_space flag, AS_EXITING, that the inode freeing code sets under the tree lock before doing the final truncate. Reclaim will check for this flag before installing shadow pages. Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Rik van Riel <riel@redhat.com> Reviewed-by: Minchan Kim <minchan@kernel.org> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Bob Liu <bob.liu@oracle.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Dave Chinner <david@fromorbit.com> Cc: Greg Thelen <gthelen@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jan Kara <jack@suse.cz> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Luigi Semenzato <semenzato@google.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Metin Doslu <metin@citusdata.com> Cc: Michel Lespinasse <walken@google.com> Cc: Ozgun Erdogan <ozgun@citusdata.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Roman Gushchin <klamm@yandex-team.ru> Cc: Ryan Mallon <rmallon@gmail.com> Cc: Tejun Heo <tj@kernel.org> Cc: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-03 21:47:49 +00:00
mapping->nrshadows++;
/*
* Make sure the nrshadows update is committed before
* the nrpages update so that final truncate racing
* with reclaim does not see both counters 0 at the
* same time and miss a shadow entry.
*/
smp_wmb();
mm: keep page cache radix tree nodes in check Previously, page cache radix tree nodes were freed after reclaim emptied out their page pointers. But now reclaim stores shadow entries in their place, which are only reclaimed when the inodes themselves are reclaimed. This is problematic for bigger files that are still in use after they have a significant amount of their cache reclaimed, without any of those pages actually refaulting. The shadow entries will just sit there and waste memory. In the worst case, the shadow entries will accumulate until the machine runs out of memory. To get this under control, the VM will track radix tree nodes exclusively containing shadow entries on a per-NUMA node list. Per-NUMA rather than global because we expect the radix tree nodes themselves to be allocated node-locally and we want to reduce cross-node references of otherwise independent cache workloads. A simple shrinker will then reclaim these nodes on memory pressure. A few things need to be stored in the radix tree node to implement the shadow node LRU and allow tree deletions coming from the list: 1. There is no index available that would describe the reverse path from the node up to the tree root, which is needed to perform a deletion. To solve this, encode in each node its offset inside the parent. This can be stored in the unused upper bits of the same member that stores the node's height at no extra space cost. 2. The number of shadow entries needs to be counted in addition to the regular entries, to quickly detect when the node is ready to go to the shadow node LRU list. The current entry count is an unsigned int but the maximum number of entries is 64, so a shadow counter can easily be stored in the unused upper bits. 3. Tree modification needs tree lock and tree root, which are located in the address space, so store an address_space backpointer in the node. The parent pointer of the node is in a union with the 2-word rcu_head, so the backpointer comes at no extra cost as well. 4. The node needs to be linked to an LRU list, which requires a list head inside the node. This does increase the size of the node, but it does not change the number of objects that fit into a slab page. [akpm@linux-foundation.org: export the right function] Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Rik van Riel <riel@redhat.com> Reviewed-by: Minchan Kim <minchan@kernel.org> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Bob Liu <bob.liu@oracle.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Dave Chinner <david@fromorbit.com> Cc: Greg Thelen <gthelen@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jan Kara <jack@suse.cz> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Luigi Semenzato <semenzato@google.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Metin Doslu <metin@citusdata.com> Cc: Michel Lespinasse <walken@google.com> Cc: Ozgun Erdogan <ozgun@citusdata.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Roman Gushchin <klamm@yandex-team.ru> Cc: Ryan Mallon <rmallon@gmail.com> Cc: Tejun Heo <tj@kernel.org> Cc: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-03 21:47:56 +00:00
}
mm + fs: store shadow entries in page cache Reclaim will be leaving shadow entries in the page cache radix tree upon evicting the real page. As those pages are found from the LRU, an iput() can lead to the inode being freed concurrently. At this point, reclaim must no longer install shadow pages because the inode freeing code needs to ensure the page tree is really empty. Add an address_space flag, AS_EXITING, that the inode freeing code sets under the tree lock before doing the final truncate. Reclaim will check for this flag before installing shadow pages. Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Rik van Riel <riel@redhat.com> Reviewed-by: Minchan Kim <minchan@kernel.org> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Bob Liu <bob.liu@oracle.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Dave Chinner <david@fromorbit.com> Cc: Greg Thelen <gthelen@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jan Kara <jack@suse.cz> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Luigi Semenzato <semenzato@google.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Metin Doslu <metin@citusdata.com> Cc: Michel Lespinasse <walken@google.com> Cc: Ozgun Erdogan <ozgun@citusdata.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Roman Gushchin <klamm@yandex-team.ru> Cc: Ryan Mallon <rmallon@gmail.com> Cc: Tejun Heo <tj@kernel.org> Cc: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-03 21:47:49 +00:00
mapping->nrpages--;
mm: keep page cache radix tree nodes in check Previously, page cache radix tree nodes were freed after reclaim emptied out their page pointers. But now reclaim stores shadow entries in their place, which are only reclaimed when the inodes themselves are reclaimed. This is problematic for bigger files that are still in use after they have a significant amount of their cache reclaimed, without any of those pages actually refaulting. The shadow entries will just sit there and waste memory. In the worst case, the shadow entries will accumulate until the machine runs out of memory. To get this under control, the VM will track radix tree nodes exclusively containing shadow entries on a per-NUMA node list. Per-NUMA rather than global because we expect the radix tree nodes themselves to be allocated node-locally and we want to reduce cross-node references of otherwise independent cache workloads. A simple shrinker will then reclaim these nodes on memory pressure. A few things need to be stored in the radix tree node to implement the shadow node LRU and allow tree deletions coming from the list: 1. There is no index available that would describe the reverse path from the node up to the tree root, which is needed to perform a deletion. To solve this, encode in each node its offset inside the parent. This can be stored in the unused upper bits of the same member that stores the node's height at no extra space cost. 2. The number of shadow entries needs to be counted in addition to the regular entries, to quickly detect when the node is ready to go to the shadow node LRU list. The current entry count is an unsigned int but the maximum number of entries is 64, so a shadow counter can easily be stored in the unused upper bits. 3. Tree modification needs tree lock and tree root, which are located in the address space, so store an address_space backpointer in the node. The parent pointer of the node is in a union with the 2-word rcu_head, so the backpointer comes at no extra cost as well. 4. The node needs to be linked to an LRU list, which requires a list head inside the node. This does increase the size of the node, but it does not change the number of objects that fit into a slab page. [akpm@linux-foundation.org: export the right function] Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Rik van Riel <riel@redhat.com> Reviewed-by: Minchan Kim <minchan@kernel.org> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Bob Liu <bob.liu@oracle.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Dave Chinner <david@fromorbit.com> Cc: Greg Thelen <gthelen@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jan Kara <jack@suse.cz> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Luigi Semenzato <semenzato@google.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Metin Doslu <metin@citusdata.com> Cc: Michel Lespinasse <walken@google.com> Cc: Ozgun Erdogan <ozgun@citusdata.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Roman Gushchin <klamm@yandex-team.ru> Cc: Ryan Mallon <rmallon@gmail.com> Cc: Tejun Heo <tj@kernel.org> Cc: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-03 21:47:56 +00:00
if (!node) {
/* Clear direct pointer tags in root node */
mapping->page_tree.gfp_mask &= __GFP_BITS_MASK;
radix_tree_replace_slot(slot, shadow);
return;
}
/* Clear tree tags for the removed page */
index = page->index;
offset = index & RADIX_TREE_MAP_MASK;
for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) {
if (test_bit(offset, node->tags[tag]))
radix_tree_tag_clear(&mapping->page_tree, index, tag);
}
/* Delete page, swap shadow entry */
radix_tree_replace_slot(slot, shadow);
workingset_node_pages_dec(node);
if (shadow)
workingset_node_shadows_inc(node);
else
if (__radix_tree_delete_node(&mapping->page_tree, node))
return;
/*
* Track node that only contains shadow entries.
*
* Avoid acquiring the list_lru lock if already tracked. The
* list_empty() test is safe as node->private_list is
* protected by mapping->tree_lock.
*/
if (!workingset_node_pages(node) &&
list_empty(&node->private_list)) {
node->private_data = mapping;
list_lru_add(&workingset_shadow_nodes, &node->private_list);
}
mm + fs: store shadow entries in page cache Reclaim will be leaving shadow entries in the page cache radix tree upon evicting the real page. As those pages are found from the LRU, an iput() can lead to the inode being freed concurrently. At this point, reclaim must no longer install shadow pages because the inode freeing code needs to ensure the page tree is really empty. Add an address_space flag, AS_EXITING, that the inode freeing code sets under the tree lock before doing the final truncate. Reclaim will check for this flag before installing shadow pages. Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Rik van Riel <riel@redhat.com> Reviewed-by: Minchan Kim <minchan@kernel.org> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Bob Liu <bob.liu@oracle.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Dave Chinner <david@fromorbit.com> Cc: Greg Thelen <gthelen@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jan Kara <jack@suse.cz> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Luigi Semenzato <semenzato@google.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Metin Doslu <metin@citusdata.com> Cc: Michel Lespinasse <walken@google.com> Cc: Ozgun Erdogan <ozgun@citusdata.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Roman Gushchin <klamm@yandex-team.ru> Cc: Ryan Mallon <rmallon@gmail.com> Cc: Tejun Heo <tj@kernel.org> Cc: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-03 21:47:49 +00:00
}
/*
* 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
memcg: add per cgroup dirty page accounting When modifying PG_Dirty on cached file pages, update the new MEM_CGROUP_STAT_DIRTY counter. This is done in the same places where global NR_FILE_DIRTY is managed. The new memcg stat is visible in the per memcg memory.stat cgroupfs file. The most recent past attempt at this was http://thread.gmane.org/gmane.linux.kernel.cgroups/8632 The new accounting supports future efforts to add per cgroup dirty page throttling and writeback. It also helps an administrator break down a container's memory usage and provides evidence to understand memcg oom kills (the new dirty count is included in memcg oom kill messages). The ability to move page accounting between memcg (memory.move_charge_at_immigrate) makes this accounting more complicated than the global counter. The existing mem_cgroup_{begin,end}_page_stat() lock is used to serialize move accounting with stat updates. Typical update operation: memcg = mem_cgroup_begin_page_stat(page) if (TestSetPageDirty()) { [...] mem_cgroup_update_page_stat(memcg) } mem_cgroup_end_page_stat(memcg) Summary of mem_cgroup_end_page_stat() overhead: - Without CONFIG_MEMCG it's a no-op - With CONFIG_MEMCG and no inter memcg task movement, it's just rcu_read_lock() - With CONFIG_MEMCG and inter memcg task movement, it's rcu_read_lock() + spin_lock_irqsave() A memcg parameter is added to several routines because their callers now grab mem_cgroup_begin_page_stat() which returns the memcg later needed by for mem_cgroup_update_page_stat(). Because mem_cgroup_begin_page_stat() may disable interrupts, some adjustments are needed: - move __mark_inode_dirty() from __set_page_dirty() to its caller. __mark_inode_dirty() locking does not want interrupts disabled. - use spin_lock_irqsave(tree_lock) rather than spin_lock_irq() in __delete_from_page_cache(), replace_page_cache_page(), invalidate_complete_page2(), and __remove_mapping(). text data bss dec hex filename 8925147 1774832 1785856 12485835 be84cb vmlinux-!CONFIG_MEMCG-before 8925339 1774832 1785856 12486027 be858b vmlinux-!CONFIG_MEMCG-after +192 text bytes 8965977 1784992 1785856 12536825 bf4bf9 vmlinux-CONFIG_MEMCG-before 8966750 1784992 1785856 12537598 bf4efe vmlinux-CONFIG_MEMCG-after +773 text bytes Performance tests run on v4.0-rc1-36-g4f671fe2f952. Lower is better for all metrics, they're all wall clock or cycle counts. The read and write fault benchmarks just measure fault time, they do not include I/O time. * CONFIG_MEMCG not set: baseline patched kbuild 1m25.030000(+-0.088% 3 samples) 1m25.426667(+-0.120% 3 samples) dd write 100 MiB 0.859211561 +-15.10% 0.874162885 +-15.03% dd write 200 MiB 1.670653105 +-17.87% 1.669384764 +-11.99% dd write 1000 MiB 8.434691190 +-14.15% 8.474733215 +-14.77% read fault cycles 254.0(+-0.000% 10 samples) 253.0(+-0.000% 10 samples) write fault cycles 2021.2(+-3.070% 10 samples) 1984.5(+-1.036% 10 samples) * CONFIG_MEMCG=y root_memcg: baseline patched kbuild 1m25.716667(+-0.105% 3 samples) 1m25.686667(+-0.153% 3 samples) dd write 100 MiB 0.855650830 +-14.90% 0.887557919 +-14.90% dd write 200 MiB 1.688322953 +-12.72% 1.667682724 +-13.33% dd write 1000 MiB 8.418601605 +-14.30% 8.673532299 +-15.00% read fault cycles 266.0(+-0.000% 10 samples) 266.0(+-0.000% 10 samples) write fault cycles 2051.7(+-1.349% 10 samples) 2049.6(+-1.686% 10 samples) * CONFIG_MEMCG=y non-root_memcg: baseline patched kbuild 1m26.120000(+-0.273% 3 samples) 1m25.763333(+-0.127% 3 samples) dd write 100 MiB 0.861723964 +-15.25% 0.818129350 +-14.82% dd write 200 MiB 1.669887569 +-13.30% 1.698645885 +-13.27% dd write 1000 MiB 8.383191730 +-14.65% 8.351742280 +-14.52% read fault cycles 265.7(+-0.172% 10 samples) 267.0(+-0.000% 10 samples) write fault cycles 2070.6(+-1.512% 10 samples) 2084.4(+-2.148% 10 samples) As expected anon page faults are not affected by this patch. tj: Updated to apply on top of the recent cancel_dirty_page() changes. Signed-off-by: Sha Zhengju <handai.szj@gmail.com> Signed-off-by: Greg Thelen <gthelen@google.com> Signed-off-by: Tejun Heo <tj@kernel.org> Signed-off-by: Jens Axboe <axboe@fb.com>
2015-05-22 21:13:16 +00:00
* is safe. The caller must hold the mapping's tree_lock and
* mem_cgroup_begin_page_stat().
*/
memcg: add per cgroup dirty page accounting When modifying PG_Dirty on cached file pages, update the new MEM_CGROUP_STAT_DIRTY counter. This is done in the same places where global NR_FILE_DIRTY is managed. The new memcg stat is visible in the per memcg memory.stat cgroupfs file. The most recent past attempt at this was http://thread.gmane.org/gmane.linux.kernel.cgroups/8632 The new accounting supports future efforts to add per cgroup dirty page throttling and writeback. It also helps an administrator break down a container's memory usage and provides evidence to understand memcg oom kills (the new dirty count is included in memcg oom kill messages). The ability to move page accounting between memcg (memory.move_charge_at_immigrate) makes this accounting more complicated than the global counter. The existing mem_cgroup_{begin,end}_page_stat() lock is used to serialize move accounting with stat updates. Typical update operation: memcg = mem_cgroup_begin_page_stat(page) if (TestSetPageDirty()) { [...] mem_cgroup_update_page_stat(memcg) } mem_cgroup_end_page_stat(memcg) Summary of mem_cgroup_end_page_stat() overhead: - Without CONFIG_MEMCG it's a no-op - With CONFIG_MEMCG and no inter memcg task movement, it's just rcu_read_lock() - With CONFIG_MEMCG and inter memcg task movement, it's rcu_read_lock() + spin_lock_irqsave() A memcg parameter is added to several routines because their callers now grab mem_cgroup_begin_page_stat() which returns the memcg later needed by for mem_cgroup_update_page_stat(). Because mem_cgroup_begin_page_stat() may disable interrupts, some adjustments are needed: - move __mark_inode_dirty() from __set_page_dirty() to its caller. __mark_inode_dirty() locking does not want interrupts disabled. - use spin_lock_irqsave(tree_lock) rather than spin_lock_irq() in __delete_from_page_cache(), replace_page_cache_page(), invalidate_complete_page2(), and __remove_mapping(). text data bss dec hex filename 8925147 1774832 1785856 12485835 be84cb vmlinux-!CONFIG_MEMCG-before 8925339 1774832 1785856 12486027 be858b vmlinux-!CONFIG_MEMCG-after +192 text bytes 8965977 1784992 1785856 12536825 bf4bf9 vmlinux-CONFIG_MEMCG-before 8966750 1784992 1785856 12537598 bf4efe vmlinux-CONFIG_MEMCG-after +773 text bytes Performance tests run on v4.0-rc1-36-g4f671fe2f952. Lower is better for all metrics, they're all wall clock or cycle counts. The read and write fault benchmarks just measure fault time, they do not include I/O time. * CONFIG_MEMCG not set: baseline patched kbuild 1m25.030000(+-0.088% 3 samples) 1m25.426667(+-0.120% 3 samples) dd write 100 MiB 0.859211561 +-15.10% 0.874162885 +-15.03% dd write 200 MiB 1.670653105 +-17.87% 1.669384764 +-11.99% dd write 1000 MiB 8.434691190 +-14.15% 8.474733215 +-14.77% read fault cycles 254.0(+-0.000% 10 samples) 253.0(+-0.000% 10 samples) write fault cycles 2021.2(+-3.070% 10 samples) 1984.5(+-1.036% 10 samples) * CONFIG_MEMCG=y root_memcg: baseline patched kbuild 1m25.716667(+-0.105% 3 samples) 1m25.686667(+-0.153% 3 samples) dd write 100 MiB 0.855650830 +-14.90% 0.887557919 +-14.90% dd write 200 MiB 1.688322953 +-12.72% 1.667682724 +-13.33% dd write 1000 MiB 8.418601605 +-14.30% 8.673532299 +-15.00% read fault cycles 266.0(+-0.000% 10 samples) 266.0(+-0.000% 10 samples) write fault cycles 2051.7(+-1.349% 10 samples) 2049.6(+-1.686% 10 samples) * CONFIG_MEMCG=y non-root_memcg: baseline patched kbuild 1m26.120000(+-0.273% 3 samples) 1m25.763333(+-0.127% 3 samples) dd write 100 MiB 0.861723964 +-15.25% 0.818129350 +-14.82% dd write 200 MiB 1.669887569 +-13.30% 1.698645885 +-13.27% dd write 1000 MiB 8.383191730 +-14.65% 8.351742280 +-14.52% read fault cycles 265.7(+-0.172% 10 samples) 267.0(+-0.000% 10 samples) write fault cycles 2070.6(+-1.512% 10 samples) 2084.4(+-2.148% 10 samples) As expected anon page faults are not affected by this patch. tj: Updated to apply on top of the recent cancel_dirty_page() changes. Signed-off-by: Sha Zhengju <handai.szj@gmail.com> Signed-off-by: Greg Thelen <gthelen@google.com> Signed-off-by: Tejun Heo <tj@kernel.org> Signed-off-by: Jens Axboe <axboe@fb.com>
2015-05-22 21:13:16 +00:00
void __delete_from_page_cache(struct page *page, void *shadow,
struct mem_cgroup *memcg)
{
struct address_space *mapping = page->mapping;
trace_mm_filemap_delete_from_page_cache(page);
/*
* if we're uptodate, flush out into the cleancache, otherwise
* invalidate any existing cleancache entries. We can't leave
* stale data around in the cleancache once our page is gone
*/
if (PageUptodate(page) && PageMappedToDisk(page))
cleancache_put_page(page);
else
cleancache_invalidate_page(mapping, page);
mm + fs: store shadow entries in page cache Reclaim will be leaving shadow entries in the page cache radix tree upon evicting the real page. As those pages are found from the LRU, an iput() can lead to the inode being freed concurrently. At this point, reclaim must no longer install shadow pages because the inode freeing code needs to ensure the page tree is really empty. Add an address_space flag, AS_EXITING, that the inode freeing code sets under the tree lock before doing the final truncate. Reclaim will check for this flag before installing shadow pages. Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Rik van Riel <riel@redhat.com> Reviewed-by: Minchan Kim <minchan@kernel.org> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Bob Liu <bob.liu@oracle.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Dave Chinner <david@fromorbit.com> Cc: Greg Thelen <gthelen@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jan Kara <jack@suse.cz> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Luigi Semenzato <semenzato@google.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Metin Doslu <metin@citusdata.com> Cc: Michel Lespinasse <walken@google.com> Cc: Ozgun Erdogan <ozgun@citusdata.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Roman Gushchin <klamm@yandex-team.ru> Cc: Ryan Mallon <rmallon@gmail.com> Cc: Tejun Heo <tj@kernel.org> Cc: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-03 21:47:49 +00:00
page_cache_tree_delete(mapping, page, shadow);
page->mapping = NULL;
/* Leave page->index set: truncation lookup relies upon it */
mm + fs: store shadow entries in page cache Reclaim will be leaving shadow entries in the page cache radix tree upon evicting the real page. As those pages are found from the LRU, an iput() can lead to the inode being freed concurrently. At this point, reclaim must no longer install shadow pages because the inode freeing code needs to ensure the page tree is really empty. Add an address_space flag, AS_EXITING, that the inode freeing code sets under the tree lock before doing the final truncate. Reclaim will check for this flag before installing shadow pages. Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Rik van Riel <riel@redhat.com> Reviewed-by: Minchan Kim <minchan@kernel.org> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Bob Liu <bob.liu@oracle.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Dave Chinner <david@fromorbit.com> Cc: Greg Thelen <gthelen@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jan Kara <jack@suse.cz> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Luigi Semenzato <semenzato@google.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Metin Doslu <metin@citusdata.com> Cc: Michel Lespinasse <walken@google.com> Cc: Ozgun Erdogan <ozgun@citusdata.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Roman Gushchin <klamm@yandex-team.ru> Cc: Ryan Mallon <rmallon@gmail.com> Cc: Tejun Heo <tj@kernel.org> Cc: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-03 21:47:49 +00:00
hugetlb: do not account hugetlb pages as NR_FILE_PAGES hugetlb pages uses add_to_page_cache to track shared mappings. This is OK from the data structure point of view but it is less so from the NR_FILE_PAGES accounting: - huge pages are accounted as 4k which is clearly wrong - this counter is used as the amount of the reclaimable page cache which is incorrect as well because hugetlb pages are special and not reclaimable - the counter is then exported to userspace via /proc/meminfo (in Cached:), /proc/vmstat and /proc/zoneinfo as nr_file_pages which is confusing at least: Cached: 8883504 kB HugePages_Free: 8348 ... Cached: 8916048 kB HugePages_Free: 156 ... thats 8192 huge pages allocated which is ~16G accounted as 32M There are usually not that many huge pages in the system for this to make any visible difference e.g. by fooling __vm_enough_memory or zone_pagecache_reclaimable. Fix this by special casing huge pages in both __delete_from_page_cache and __add_to_page_cache_locked. replace_page_cache_page is currently only used by fuse and that shouldn't touch hugetlb pages AFAICS but it is more robust to check for special casing there as well. Hugetlb pages shouldn't get to any other paths where we do accounting: - migration - we have a special handling via hugetlbfs_migrate_page - shmem - doesn't handle hugetlb pages directly even for SHM_HUGETLB resp. MAP_HUGETLB - swapcache - hugetlb is not swapable This has a user visible effect but I believe it is reasonable because the previously exported number is simply bogus. An alternative would be to account hugetlb pages with their real size and treat them similar to shmem. But this has some drawbacks. First we would have to special case in kernel users of NR_FILE_PAGES and considering how hugetlb is special we would have to do it everywhere. We do not want Cached exported by /proc/meminfo to include it because the value would be even more misleading. __vm_enough_memory and zone_pagecache_reclaimable would have to do the same thing because those pages are simply not reclaimable. The correction is even not trivial because we would have to consider all active hugetlb page sizes properly. Users of the counter outside of the kernel would have to do the same. So the question is why to account something that needs to be basically excluded for each reasonable usage. This doesn't make much sense to me. It seems that this has been broken since hugetlb was introduced but I haven't checked the whole history. [akpm@linux-foundation.org: tweak comments] Signed-off-by: Michal Hocko <mhocko@suse.cz> Acked-by: Mel Gorman <mgorman@suse.de> Tested-by: Mike Kravetz <mike.kravetz@oracle.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-06-24 23:57:24 +00:00
/* hugetlb pages do not participate in page cache accounting. */
if (!PageHuge(page))
__dec_zone_page_state(page, NR_FILE_PAGES);
if (PageSwapBacked(page))
__dec_zone_page_state(page, NR_SHMEM);
BUG_ON(page_mapped(page));
/*
page_writeback: clean up mess around cancel_dirty_page() This patch replaces cancel_dirty_page() with a helper function account_page_cleaned() which only updates counters. It's called from truncate_complete_page() and from try_to_free_buffers() (hack for ext3). Page is locked in both cases, page-lock protects against concurrent dirtiers: see commit 2d6d7f982846 ("mm: protect set_page_dirty() from ongoing truncation"). Delete_from_page_cache() shouldn't be called for dirty pages, they must be handled by caller (either written or truncated). This patch treats final dirty accounting fixup at the end of __delete_from_page_cache() as a debug check and adds WARN_ON_ONCE() around it. If something removes dirty pages without proper handling that might be a bug and unwritten data might be lost. Hugetlbfs has no dirty pages accounting, ClearPageDirty() is enough here. cancel_dirty_page() in nfs_wb_page_cancel() is redundant. This is helper for nfs_invalidate_page() and it's called only in case complete invalidation. The mess was started in v2.6.20 after commits 46d2277c796f ("Clean up and make try_to_free_buffers() not race with dirty pages") and 3e67c0987d75 ("truncate: clear page dirtiness before running try_to_free_buffers()") first was reverted right in v2.6.20 in commit ecdfc9787fe5 ("Resurrect 'try_to_free_buffers()' VM hackery"), second in v2.6.25 commit a2b345642f53 ("Fix dirty page accounting leak with ext3 data=journal"). Custom fixes were introduced between these points. NFS in v2.6.23, commit 1b3b4a1a2deb ("NFS: Fix a write request leak in nfs_invalidate_page()"). Kludge in __delete_from_page_cache() in v2.6.24, commit 3a6927906f1b ("Do dirty page accounting when removing a page from the page cache"). Since v2.6.25 all of them are redundant. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru> Cc: Tejun Heo <tj@kernel.org> Cc: Jan Kara <jack@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-04-14 22:45:27 +00:00
* At this point page must be either written or cleaned by truncate.
* Dirty page here signals a bug and loss of unwritten data.
*
page_writeback: clean up mess around cancel_dirty_page() This patch replaces cancel_dirty_page() with a helper function account_page_cleaned() which only updates counters. It's called from truncate_complete_page() and from try_to_free_buffers() (hack for ext3). Page is locked in both cases, page-lock protects against concurrent dirtiers: see commit 2d6d7f982846 ("mm: protect set_page_dirty() from ongoing truncation"). Delete_from_page_cache() shouldn't be called for dirty pages, they must be handled by caller (either written or truncated). This patch treats final dirty accounting fixup at the end of __delete_from_page_cache() as a debug check and adds WARN_ON_ONCE() around it. If something removes dirty pages without proper handling that might be a bug and unwritten data might be lost. Hugetlbfs has no dirty pages accounting, ClearPageDirty() is enough here. cancel_dirty_page() in nfs_wb_page_cancel() is redundant. This is helper for nfs_invalidate_page() and it's called only in case complete invalidation. The mess was started in v2.6.20 after commits 46d2277c796f ("Clean up and make try_to_free_buffers() not race with dirty pages") and 3e67c0987d75 ("truncate: clear page dirtiness before running try_to_free_buffers()") first was reverted right in v2.6.20 in commit ecdfc9787fe5 ("Resurrect 'try_to_free_buffers()' VM hackery"), second in v2.6.25 commit a2b345642f53 ("Fix dirty page accounting leak with ext3 data=journal"). Custom fixes were introduced between these points. NFS in v2.6.23, commit 1b3b4a1a2deb ("NFS: Fix a write request leak in nfs_invalidate_page()"). Kludge in __delete_from_page_cache() in v2.6.24, commit 3a6927906f1b ("Do dirty page accounting when removing a page from the page cache"). Since v2.6.25 all of them are redundant. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru> Cc: Tejun Heo <tj@kernel.org> Cc: Jan Kara <jack@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-04-14 22:45:27 +00:00
* This fixes dirty accounting after removing the page entirely but
* leaves PageDirty set: it has no effect for truncated page and
* anyway will be cleared before returning page into buddy allocator.
*/
page_writeback: clean up mess around cancel_dirty_page() This patch replaces cancel_dirty_page() with a helper function account_page_cleaned() which only updates counters. It's called from truncate_complete_page() and from try_to_free_buffers() (hack for ext3). Page is locked in both cases, page-lock protects against concurrent dirtiers: see commit 2d6d7f982846 ("mm: protect set_page_dirty() from ongoing truncation"). Delete_from_page_cache() shouldn't be called for dirty pages, they must be handled by caller (either written or truncated). This patch treats final dirty accounting fixup at the end of __delete_from_page_cache() as a debug check and adds WARN_ON_ONCE() around it. If something removes dirty pages without proper handling that might be a bug and unwritten data might be lost. Hugetlbfs has no dirty pages accounting, ClearPageDirty() is enough here. cancel_dirty_page() in nfs_wb_page_cancel() is redundant. This is helper for nfs_invalidate_page() and it's called only in case complete invalidation. The mess was started in v2.6.20 after commits 46d2277c796f ("Clean up and make try_to_free_buffers() not race with dirty pages") and 3e67c0987d75 ("truncate: clear page dirtiness before running try_to_free_buffers()") first was reverted right in v2.6.20 in commit ecdfc9787fe5 ("Resurrect 'try_to_free_buffers()' VM hackery"), second in v2.6.25 commit a2b345642f53 ("Fix dirty page accounting leak with ext3 data=journal"). Custom fixes were introduced between these points. NFS in v2.6.23, commit 1b3b4a1a2deb ("NFS: Fix a write request leak in nfs_invalidate_page()"). Kludge in __delete_from_page_cache() in v2.6.24, commit 3a6927906f1b ("Do dirty page accounting when removing a page from the page cache"). Since v2.6.25 all of them are redundant. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru> Cc: Tejun Heo <tj@kernel.org> Cc: Jan Kara <jack@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-04-14 22:45:27 +00:00
if (WARN_ON_ONCE(PageDirty(page)))
writeback: implement unlocked_inode_to_wb transaction and use it for stat updates The mechanism for detecting whether an inode should switch its wb (bdi_writeback) association is now in place. This patch build the framework for the actual switching. This patch adds a new inode flag I_WB_SWITCHING, which has two functions. First, the easy one, it ensures that there's only one switching in progress for a give inode. Second, it's used as a mechanism to synchronize wb stat updates. The two stats, WB_RECLAIMABLE and WB_WRITEBACK, aren't event counters but track the current number of dirty pages and pages under writeback respectively. As such, when an inode is moved from one wb to another, the inode's portion of those stats have to be transferred together; unfortunately, this is a bit tricky as those stat updates are percpu operations which are performed without holding any lock in some places. This patch solves the problem in a similar way as memcg. Each such lockless stat updates are wrapped in transaction surrounded by unlocked_inode_to_wb_begin/end(). During normal operation, they map to rcu_read_lock/unlock(); however, if I_WB_SWITCHING is asserted, mapping->tree_lock is grabbed across the transaction. In turn, the switching path sets I_WB_SWITCHING and waits for a RCU grace period to pass before actually starting to switch, which guarantees that all stat update paths are synchronizing against mapping->tree_lock. This patch still doesn't implement the actual switching. v3: Updated on top of the recent cancel_dirty_page() updates. unlocked_inode_to_wb_begin() now nests inside mem_cgroup_begin_page_stat() to match the locking order. v2: The i_wb access transaction will be used for !stat accesses too. Function names and comments updated accordingly. s/inode_wb_stat_unlocked_{begin|end}/unlocked_inode_to_wb_{begin|end}/ s/switch_wb/switch_wbs/ Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Jens Axboe <axboe@kernel.dk> Cc: Jan Kara <jack@suse.cz> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Greg Thelen <gthelen@google.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2015-05-28 18:50:53 +00:00
account_page_cleaned(page, mapping, memcg,
inode_to_wb(mapping->host));
}
/**
* 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;
memcg: add per cgroup dirty page accounting When modifying PG_Dirty on cached file pages, update the new MEM_CGROUP_STAT_DIRTY counter. This is done in the same places where global NR_FILE_DIRTY is managed. The new memcg stat is visible in the per memcg memory.stat cgroupfs file. The most recent past attempt at this was http://thread.gmane.org/gmane.linux.kernel.cgroups/8632 The new accounting supports future efforts to add per cgroup dirty page throttling and writeback. It also helps an administrator break down a container's memory usage and provides evidence to understand memcg oom kills (the new dirty count is included in memcg oom kill messages). The ability to move page accounting between memcg (memory.move_charge_at_immigrate) makes this accounting more complicated than the global counter. The existing mem_cgroup_{begin,end}_page_stat() lock is used to serialize move accounting with stat updates. Typical update operation: memcg = mem_cgroup_begin_page_stat(page) if (TestSetPageDirty()) { [...] mem_cgroup_update_page_stat(memcg) } mem_cgroup_end_page_stat(memcg) Summary of mem_cgroup_end_page_stat() overhead: - Without CONFIG_MEMCG it's a no-op - With CONFIG_MEMCG and no inter memcg task movement, it's just rcu_read_lock() - With CONFIG_MEMCG and inter memcg task movement, it's rcu_read_lock() + spin_lock_irqsave() A memcg parameter is added to several routines because their callers now grab mem_cgroup_begin_page_stat() which returns the memcg later needed by for mem_cgroup_update_page_stat(). Because mem_cgroup_begin_page_stat() may disable interrupts, some adjustments are needed: - move __mark_inode_dirty() from __set_page_dirty() to its caller. __mark_inode_dirty() locking does not want interrupts disabled. - use spin_lock_irqsave(tree_lock) rather than spin_lock_irq() in __delete_from_page_cache(), replace_page_cache_page(), invalidate_complete_page2(), and __remove_mapping(). text data bss dec hex filename 8925147 1774832 1785856 12485835 be84cb vmlinux-!CONFIG_MEMCG-before 8925339 1774832 1785856 12486027 be858b vmlinux-!CONFIG_MEMCG-after +192 text bytes 8965977 1784992 1785856 12536825 bf4bf9 vmlinux-CONFIG_MEMCG-before 8966750 1784992 1785856 12537598 bf4efe vmlinux-CONFIG_MEMCG-after +773 text bytes Performance tests run on v4.0-rc1-36-g4f671fe2f952. Lower is better for all metrics, they're all wall clock or cycle counts. The read and write fault benchmarks just measure fault time, they do not include I/O time. * CONFIG_MEMCG not set: baseline patched kbuild 1m25.030000(+-0.088% 3 samples) 1m25.426667(+-0.120% 3 samples) dd write 100 MiB 0.859211561 +-15.10% 0.874162885 +-15.03% dd write 200 MiB 1.670653105 +-17.87% 1.669384764 +-11.99% dd write 1000 MiB 8.434691190 +-14.15% 8.474733215 +-14.77% read fault cycles 254.0(+-0.000% 10 samples) 253.0(+-0.000% 10 samples) write fault cycles 2021.2(+-3.070% 10 samples) 1984.5(+-1.036% 10 samples) * CONFIG_MEMCG=y root_memcg: baseline patched kbuild 1m25.716667(+-0.105% 3 samples) 1m25.686667(+-0.153% 3 samples) dd write 100 MiB 0.855650830 +-14.90% 0.887557919 +-14.90% dd write 200 MiB 1.688322953 +-12.72% 1.667682724 +-13.33% dd write 1000 MiB 8.418601605 +-14.30% 8.673532299 +-15.00% read fault cycles 266.0(+-0.000% 10 samples) 266.0(+-0.000% 10 samples) write fault cycles 2051.7(+-1.349% 10 samples) 2049.6(+-1.686% 10 samples) * CONFIG_MEMCG=y non-root_memcg: baseline patched kbuild 1m26.120000(+-0.273% 3 samples) 1m25.763333(+-0.127% 3 samples) dd write 100 MiB 0.861723964 +-15.25% 0.818129350 +-14.82% dd write 200 MiB 1.669887569 +-13.30% 1.698645885 +-13.27% dd write 1000 MiB 8.383191730 +-14.65% 8.351742280 +-14.52% read fault cycles 265.7(+-0.172% 10 samples) 267.0(+-0.000% 10 samples) write fault cycles 2070.6(+-1.512% 10 samples) 2084.4(+-2.148% 10 samples) As expected anon page faults are not affected by this patch. tj: Updated to apply on top of the recent cancel_dirty_page() changes. Signed-off-by: Sha Zhengju <handai.szj@gmail.com> Signed-off-by: Greg Thelen <gthelen@google.com> Signed-off-by: Tejun Heo <tj@kernel.org> Signed-off-by: Jens Axboe <axboe@fb.com>
2015-05-22 21:13:16 +00:00
struct mem_cgroup *memcg;
unsigned long flags;
void (*freepage)(struct page *);
BUG_ON(!PageLocked(page));
freepage = mapping->a_ops->freepage;
memcg: add per cgroup dirty page accounting When modifying PG_Dirty on cached file pages, update the new MEM_CGROUP_STAT_DIRTY counter. This is done in the same places where global NR_FILE_DIRTY is managed. The new memcg stat is visible in the per memcg memory.stat cgroupfs file. The most recent past attempt at this was http://thread.gmane.org/gmane.linux.kernel.cgroups/8632 The new accounting supports future efforts to add per cgroup dirty page throttling and writeback. It also helps an administrator break down a container's memory usage and provides evidence to understand memcg oom kills (the new dirty count is included in memcg oom kill messages). The ability to move page accounting between memcg (memory.move_charge_at_immigrate) makes this accounting more complicated than the global counter. The existing mem_cgroup_{begin,end}_page_stat() lock is used to serialize move accounting with stat updates. Typical update operation: memcg = mem_cgroup_begin_page_stat(page) if (TestSetPageDirty()) { [...] mem_cgroup_update_page_stat(memcg) } mem_cgroup_end_page_stat(memcg) Summary of mem_cgroup_end_page_stat() overhead: - Without CONFIG_MEMCG it's a no-op - With CONFIG_MEMCG and no inter memcg task movement, it's just rcu_read_lock() - With CONFIG_MEMCG and inter memcg task movement, it's rcu_read_lock() + spin_lock_irqsave() A memcg parameter is added to several routines because their callers now grab mem_cgroup_begin_page_stat() which returns the memcg later needed by for mem_cgroup_update_page_stat(). Because mem_cgroup_begin_page_stat() may disable interrupts, some adjustments are needed: - move __mark_inode_dirty() from __set_page_dirty() to its caller. __mark_inode_dirty() locking does not want interrupts disabled. - use spin_lock_irqsave(tree_lock) rather than spin_lock_irq() in __delete_from_page_cache(), replace_page_cache_page(), invalidate_complete_page2(), and __remove_mapping(). text data bss dec hex filename 8925147 1774832 1785856 12485835 be84cb vmlinux-!CONFIG_MEMCG-before 8925339 1774832 1785856 12486027 be858b vmlinux-!CONFIG_MEMCG-after +192 text bytes 8965977 1784992 1785856 12536825 bf4bf9 vmlinux-CONFIG_MEMCG-before 8966750 1784992 1785856 12537598 bf4efe vmlinux-CONFIG_MEMCG-after +773 text bytes Performance tests run on v4.0-rc1-36-g4f671fe2f952. Lower is better for all metrics, they're all wall clock or cycle counts. The read and write fault benchmarks just measure fault time, they do not include I/O time. * CONFIG_MEMCG not set: baseline patched kbuild 1m25.030000(+-0.088% 3 samples) 1m25.426667(+-0.120% 3 samples) dd write 100 MiB 0.859211561 +-15.10% 0.874162885 +-15.03% dd write 200 MiB 1.670653105 +-17.87% 1.669384764 +-11.99% dd write 1000 MiB 8.434691190 +-14.15% 8.474733215 +-14.77% read fault cycles 254.0(+-0.000% 10 samples) 253.0(+-0.000% 10 samples) write fault cycles 2021.2(+-3.070% 10 samples) 1984.5(+-1.036% 10 samples) * CONFIG_MEMCG=y root_memcg: baseline patched kbuild 1m25.716667(+-0.105% 3 samples) 1m25.686667(+-0.153% 3 samples) dd write 100 MiB 0.855650830 +-14.90% 0.887557919 +-14.90% dd write 200 MiB 1.688322953 +-12.72% 1.667682724 +-13.33% dd write 1000 MiB 8.418601605 +-14.30% 8.673532299 +-15.00% read fault cycles 266.0(+-0.000% 10 samples) 266.0(+-0.000% 10 samples) write fault cycles 2051.7(+-1.349% 10 samples) 2049.6(+-1.686% 10 samples) * CONFIG_MEMCG=y non-root_memcg: baseline patched kbuild 1m26.120000(+-0.273% 3 samples) 1m25.763333(+-0.127% 3 samples) dd write 100 MiB 0.861723964 +-15.25% 0.818129350 +-14.82% dd write 200 MiB 1.669887569 +-13.30% 1.698645885 +-13.27% dd write 1000 MiB 8.383191730 +-14.65% 8.351742280 +-14.52% read fault cycles 265.7(+-0.172% 10 samples) 267.0(+-0.000% 10 samples) write fault cycles 2070.6(+-1.512% 10 samples) 2084.4(+-2.148% 10 samples) As expected anon page faults are not affected by this patch. tj: Updated to apply on top of the recent cancel_dirty_page() changes. Signed-off-by: Sha Zhengju <handai.szj@gmail.com> Signed-off-by: Greg Thelen <gthelen@google.com> Signed-off-by: Tejun Heo <tj@kernel.org> Signed-off-by: Jens Axboe <axboe@fb.com>
2015-05-22 21:13:16 +00:00
memcg = mem_cgroup_begin_page_stat(page);
spin_lock_irqsave(&mapping->tree_lock, flags);
__delete_from_page_cache(page, NULL, memcg);
spin_unlock_irqrestore(&mapping->tree_lock, flags);
mem_cgroup_end_page_stat(memcg);
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>
2011-03-22 23:30:53 +00:00
page_cache_release(page);
}
EXPORT_SYMBOL(delete_from_page_cache);
static int filemap_check_errors(struct address_space *mapping)
{
int ret = 0;
/* Check for outstanding write errors */
if (test_bit(AS_ENOSPC, &mapping->flags) &&
test_and_clear_bit(AS_ENOSPC, &mapping->flags))
ret = -ENOSPC;
if (test_bit(AS_EIO, &mapping->flags) &&
test_and_clear_bit(AS_EIO, &mapping->flags))
ret = -EIO;
return ret;
}
/**
* __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 11:18:04 +00:00
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>
2009-01-06 22:39:08 +00:00
.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 09:03:26 +00:00
.range_start = start,
.range_end = end,
};
if (!mapping_cap_writeback_dirty(mapping))
return 0;
writeback: make writeback_control track the inode being written back Currently, for cgroup writeback, the IO submission paths directly associate the bio's with the blkcg from inode_to_wb_blkcg_css(); however, it'd be necessary to keep more writeback context to implement foreign inode writeback detection. wbc (writeback_control) is the natural fit for the extra context - it persists throughout the writeback of each inode and is passed all the way down to IO submission paths. This patch adds wbc_attach_and_unlock_inode(), wbc_detach_inode(), and wbc_attach_fdatawrite_inode() which are used to associate wbc with the inode being written back. IO submission paths now use wbc_init_bio() instead of directly associating bio's with blkcg themselves. This leaves inode_to_wb_blkcg_css() w/o any user. The function is removed. wbc currently only tracks the associated wb (bdi_writeback). Future patches will add more for foreign inode detection. The association is established under i_lock which will be depended upon when migrating foreign inodes to other wb's. As currently, once established, inode to wb association never changes, going through wbc when initializing bio's doesn't cause any behavior changes. v2: submit_blk_blkcg() now checks whether the wbc is associated with a wb before dereferencing it. This can happen when pageout() is writing pages directly without going through the usual writeback path. As pageout() path is single-threaded, we don't want it to be blocked behind a slow cgroup and ultimately want it to delegate actual writing to the usual writeback path. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Jens Axboe <axboe@kernel.dk> Cc: Jan Kara <jack@suse.cz> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Greg Thelen <gthelen@google.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2015-06-02 14:39:48 +00:00
wbc_attach_fdatawrite_inode(&wbc, mapping->host);
ret = do_writepages(mapping, &wbc);
writeback: make writeback_control track the inode being written back Currently, for cgroup writeback, the IO submission paths directly associate the bio's with the blkcg from inode_to_wb_blkcg_css(); however, it'd be necessary to keep more writeback context to implement foreign inode writeback detection. wbc (writeback_control) is the natural fit for the extra context - it persists throughout the writeback of each inode and is passed all the way down to IO submission paths. This patch adds wbc_attach_and_unlock_inode(), wbc_detach_inode(), and wbc_attach_fdatawrite_inode() which are used to associate wbc with the inode being written back. IO submission paths now use wbc_init_bio() instead of directly associating bio's with blkcg themselves. This leaves inode_to_wb_blkcg_css() w/o any user. The function is removed. wbc currently only tracks the associated wb (bdi_writeback). Future patches will add more for foreign inode detection. The association is established under i_lock which will be depended upon when migrating foreign inodes to other wb's. As currently, once established, inode to wb association never changes, going through wbc when initializing bio's doesn't cause any behavior changes. v2: submit_blk_blkcg() now checks whether the wbc is associated with a wb before dereferencing it. This can happen when pageout() is writing pages directly without going through the usual writeback path. As pageout() path is single-threaded, we don't want it to be blocked behind a slow cgroup and ultimately want it to delegate actual writing to the usual writeback path. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Jens Axboe <axboe@kernel.dk> Cc: Jan Kara <jack@suse.cz> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Greg Thelen <gthelen@google.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2015-06-02 14:39:48 +00:00
wbc_detach_inode(&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 09:03:26 +00:00
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 11:18:04 +00:00
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 ret2, ret = 0;
if (end_byte < start_byte)
goto out;
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();
}
out:
ret2 = filemap_check_errors(mapping);
if (!ret)
ret = ret2;
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;
}
} else {
err = filemap_check_errors(mapping);
}
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;
}
} else {
err = filemap_check_errors(mapping);
}
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;
VM_BUG_ON_PAGE(!PageLocked(old), old);
VM_BUG_ON_PAGE(!PageLocked(new), new);
VM_BUG_ON_PAGE(new->mapping, new);
error = radix_tree_preload(gfp_mask & ~__GFP_HIGHMEM);
if (!error) {
struct address_space *mapping = old->mapping;
void (*freepage)(struct page *);
memcg: add per cgroup dirty page accounting When modifying PG_Dirty on cached file pages, update the new MEM_CGROUP_STAT_DIRTY counter. This is done in the same places where global NR_FILE_DIRTY is managed. The new memcg stat is visible in the per memcg memory.stat cgroupfs file. The most recent past attempt at this was http://thread.gmane.org/gmane.linux.kernel.cgroups/8632 The new accounting supports future efforts to add per cgroup dirty page throttling and writeback. It also helps an administrator break down a container's memory usage and provides evidence to understand memcg oom kills (the new dirty count is included in memcg oom kill messages). The ability to move page accounting between memcg (memory.move_charge_at_immigrate) makes this accounting more complicated than the global counter. The existing mem_cgroup_{begin,end}_page_stat() lock is used to serialize move accounting with stat updates. Typical update operation: memcg = mem_cgroup_begin_page_stat(page) if (TestSetPageDirty()) { [...] mem_cgroup_update_page_stat(memcg) } mem_cgroup_end_page_stat(memcg) Summary of mem_cgroup_end_page_stat() overhead: - Without CONFIG_MEMCG it's a no-op - With CONFIG_MEMCG and no inter memcg task movement, it's just rcu_read_lock() - With CONFIG_MEMCG and inter memcg task movement, it's rcu_read_lock() + spin_lock_irqsave() A memcg parameter is added to several routines because their callers now grab mem_cgroup_begin_page_stat() which returns the memcg later needed by for mem_cgroup_update_page_stat(). Because mem_cgroup_begin_page_stat() may disable interrupts, some adjustments are needed: - move __mark_inode_dirty() from __set_page_dirty() to its caller. __mark_inode_dirty() locking does not want interrupts disabled. - use spin_lock_irqsave(tree_lock) rather than spin_lock_irq() in __delete_from_page_cache(), replace_page_cache_page(), invalidate_complete_page2(), and __remove_mapping(). text data bss dec hex filename 8925147 1774832 1785856 12485835 be84cb vmlinux-!CONFIG_MEMCG-before 8925339 1774832 1785856 12486027 be858b vmlinux-!CONFIG_MEMCG-after +192 text bytes 8965977 1784992 1785856 12536825 bf4bf9 vmlinux-CONFIG_MEMCG-before 8966750 1784992 1785856 12537598 bf4efe vmlinux-CONFIG_MEMCG-after +773 text bytes Performance tests run on v4.0-rc1-36-g4f671fe2f952. Lower is better for all metrics, they're all wall clock or cycle counts. The read and write fault benchmarks just measure fault time, they do not include I/O time. * CONFIG_MEMCG not set: baseline patched kbuild 1m25.030000(+-0.088% 3 samples) 1m25.426667(+-0.120% 3 samples) dd write 100 MiB 0.859211561 +-15.10% 0.874162885 +-15.03% dd write 200 MiB 1.670653105 +-17.87% 1.669384764 +-11.99% dd write 1000 MiB 8.434691190 +-14.15% 8.474733215 +-14.77% read fault cycles 254.0(+-0.000% 10 samples) 253.0(+-0.000% 10 samples) write fault cycles 2021.2(+-3.070% 10 samples) 1984.5(+-1.036% 10 samples) * CONFIG_MEMCG=y root_memcg: baseline patched kbuild 1m25.716667(+-0.105% 3 samples) 1m25.686667(+-0.153% 3 samples) dd write 100 MiB 0.855650830 +-14.90% 0.887557919 +-14.90% dd write 200 MiB 1.688322953 +-12.72% 1.667682724 +-13.33% dd write 1000 MiB 8.418601605 +-14.30% 8.673532299 +-15.00% read fault cycles 266.0(+-0.000% 10 samples) 266.0(+-0.000% 10 samples) write fault cycles 2051.7(+-1.349% 10 samples) 2049.6(+-1.686% 10 samples) * CONFIG_MEMCG=y non-root_memcg: baseline patched kbuild 1m26.120000(+-0.273% 3 samples) 1m25.763333(+-0.127% 3 samples) dd write 100 MiB 0.861723964 +-15.25% 0.818129350 +-14.82% dd write 200 MiB 1.669887569 +-13.30% 1.698645885 +-13.27% dd write 1000 MiB 8.383191730 +-14.65% 8.351742280 +-14.52% read fault cycles 265.7(+-0.172% 10 samples) 267.0(+-0.000% 10 samples) write fault cycles 2070.6(+-1.512% 10 samples) 2084.4(+-2.148% 10 samples) As expected anon page faults are not affected by this patch. tj: Updated to apply on top of the recent cancel_dirty_page() changes. Signed-off-by: Sha Zhengju <handai.szj@gmail.com> Signed-off-by: Greg Thelen <gthelen@google.com> Signed-off-by: Tejun Heo <tj@kernel.org> Signed-off-by: Jens Axboe <axboe@fb.com>
2015-05-22 21:13:16 +00:00
struct mem_cgroup *memcg;
unsigned long flags;
pgoff_t offset = old->index;
freepage = mapping->a_ops->freepage;
page_cache_get(new);
new->mapping = mapping;
new->index = offset;
memcg: add per cgroup dirty page accounting When modifying PG_Dirty on cached file pages, update the new MEM_CGROUP_STAT_DIRTY counter. This is done in the same places where global NR_FILE_DIRTY is managed. The new memcg stat is visible in the per memcg memory.stat cgroupfs file. The most recent past attempt at this was http://thread.gmane.org/gmane.linux.kernel.cgroups/8632 The new accounting supports future efforts to add per cgroup dirty page throttling and writeback. It also helps an administrator break down a container's memory usage and provides evidence to understand memcg oom kills (the new dirty count is included in memcg oom kill messages). The ability to move page accounting between memcg (memory.move_charge_at_immigrate) makes this accounting more complicated than the global counter. The existing mem_cgroup_{begin,end}_page_stat() lock is used to serialize move accounting with stat updates. Typical update operation: memcg = mem_cgroup_begin_page_stat(page) if (TestSetPageDirty()) { [...] mem_cgroup_update_page_stat(memcg) } mem_cgroup_end_page_stat(memcg) Summary of mem_cgroup_end_page_stat() overhead: - Without CONFIG_MEMCG it's a no-op - With CONFIG_MEMCG and no inter memcg task movement, it's just rcu_read_lock() - With CONFIG_MEMCG and inter memcg task movement, it's rcu_read_lock() + spin_lock_irqsave() A memcg parameter is added to several routines because their callers now grab mem_cgroup_begin_page_stat() which returns the memcg later needed by for mem_cgroup_update_page_stat(). Because mem_cgroup_begin_page_stat() may disable interrupts, some adjustments are needed: - move __mark_inode_dirty() from __set_page_dirty() to its caller. __mark_inode_dirty() locking does not want interrupts disabled. - use spin_lock_irqsave(tree_lock) rather than spin_lock_irq() in __delete_from_page_cache(), replace_page_cache_page(), invalidate_complete_page2(), and __remove_mapping(). text data bss dec hex filename 8925147 1774832 1785856 12485835 be84cb vmlinux-!CONFIG_MEMCG-before 8925339 1774832 1785856 12486027 be858b vmlinux-!CONFIG_MEMCG-after +192 text bytes 8965977 1784992 1785856 12536825 bf4bf9 vmlinux-CONFIG_MEMCG-before 8966750 1784992 1785856 12537598 bf4efe vmlinux-CONFIG_MEMCG-after +773 text bytes Performance tests run on v4.0-rc1-36-g4f671fe2f952. Lower is better for all metrics, they're all wall clock or cycle counts. The read and write fault benchmarks just measure fault time, they do not include I/O time. * CONFIG_MEMCG not set: baseline patched kbuild 1m25.030000(+-0.088% 3 samples) 1m25.426667(+-0.120% 3 samples) dd write 100 MiB 0.859211561 +-15.10% 0.874162885 +-15.03% dd write 200 MiB 1.670653105 +-17.87% 1.669384764 +-11.99% dd write 1000 MiB 8.434691190 +-14.15% 8.474733215 +-14.77% read fault cycles 254.0(+-0.000% 10 samples) 253.0(+-0.000% 10 samples) write fault cycles 2021.2(+-3.070% 10 samples) 1984.5(+-1.036% 10 samples) * CONFIG_MEMCG=y root_memcg: baseline patched kbuild 1m25.716667(+-0.105% 3 samples) 1m25.686667(+-0.153% 3 samples) dd write 100 MiB 0.855650830 +-14.90% 0.887557919 +-14.90% dd write 200 MiB 1.688322953 +-12.72% 1.667682724 +-13.33% dd write 1000 MiB 8.418601605 +-14.30% 8.673532299 +-15.00% read fault cycles 266.0(+-0.000% 10 samples) 266.0(+-0.000% 10 samples) write fault cycles 2051.7(+-1.349% 10 samples) 2049.6(+-1.686% 10 samples) * CONFIG_MEMCG=y non-root_memcg: baseline patched kbuild 1m26.120000(+-0.273% 3 samples) 1m25.763333(+-0.127% 3 samples) dd write 100 MiB 0.861723964 +-15.25% 0.818129350 +-14.82% dd write 200 MiB 1.669887569 +-13.30% 1.698645885 +-13.27% dd write 1000 MiB 8.383191730 +-14.65% 8.351742280 +-14.52% read fault cycles 265.7(+-0.172% 10 samples) 267.0(+-0.000% 10 samples) write fault cycles 2070.6(+-1.512% 10 samples) 2084.4(+-2.148% 10 samples) As expected anon page faults are not affected by this patch. tj: Updated to apply on top of the recent cancel_dirty_page() changes. Signed-off-by: Sha Zhengju <handai.szj@gmail.com> Signed-off-by: Greg Thelen <gthelen@google.com> Signed-off-by: Tejun Heo <tj@kernel.org> Signed-off-by: Jens Axboe <axboe@fb.com>
2015-05-22 21:13:16 +00:00
memcg = mem_cgroup_begin_page_stat(old);
spin_lock_irqsave(&mapping->tree_lock, flags);
__delete_from_page_cache(old, NULL, memcg);
error = radix_tree_insert(&mapping->page_tree, offset, new);
BUG_ON(error);
mapping->nrpages++;
hugetlb: do not account hugetlb pages as NR_FILE_PAGES hugetlb pages uses add_to_page_cache to track shared mappings. This is OK from the data structure point of view but it is less so from the NR_FILE_PAGES accounting: - huge pages are accounted as 4k which is clearly wrong - this counter is used as the amount of the reclaimable page cache which is incorrect as well because hugetlb pages are special and not reclaimable - the counter is then exported to userspace via /proc/meminfo (in Cached:), /proc/vmstat and /proc/zoneinfo as nr_file_pages which is confusing at least: Cached: 8883504 kB HugePages_Free: 8348 ... Cached: 8916048 kB HugePages_Free: 156 ... thats 8192 huge pages allocated which is ~16G accounted as 32M There are usually not that many huge pages in the system for this to make any visible difference e.g. by fooling __vm_enough_memory or zone_pagecache_reclaimable. Fix this by special casing huge pages in both __delete_from_page_cache and __add_to_page_cache_locked. replace_page_cache_page is currently only used by fuse and that shouldn't touch hugetlb pages AFAICS but it is more robust to check for special casing there as well. Hugetlb pages shouldn't get to any other paths where we do accounting: - migration - we have a special handling via hugetlbfs_migrate_page - shmem - doesn't handle hugetlb pages directly even for SHM_HUGETLB resp. MAP_HUGETLB - swapcache - hugetlb is not swapable This has a user visible effect but I believe it is reasonable because the previously exported number is simply bogus. An alternative would be to account hugetlb pages with their real size and treat them similar to shmem. But this has some drawbacks. First we would have to special case in kernel users of NR_FILE_PAGES and considering how hugetlb is special we would have to do it everywhere. We do not want Cached exported by /proc/meminfo to include it because the value would be even more misleading. __vm_enough_memory and zone_pagecache_reclaimable would have to do the same thing because those pages are simply not reclaimable. The correction is even not trivial because we would have to consider all active hugetlb page sizes properly. Users of the counter outside of the kernel would have to do the same. So the question is why to account something that needs to be basically excluded for each reasonable usage. This doesn't make much sense to me. It seems that this has been broken since hugetlb was introduced but I haven't checked the whole history. [akpm@linux-foundation.org: tweak comments] Signed-off-by: Michal Hocko <mhocko@suse.cz> Acked-by: Mel Gorman <mgorman@suse.de> Tested-by: Mike Kravetz <mike.kravetz@oracle.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-06-24 23:57:24 +00:00
/*
* hugetlb pages do not participate in page cache accounting.
*/
if (!PageHuge(new))
__inc_zone_page_state(new, NR_FILE_PAGES);
if (PageSwapBacked(new))
__inc_zone_page_state(new, NR_SHMEM);
memcg: add per cgroup dirty page accounting When modifying PG_Dirty on cached file pages, update the new MEM_CGROUP_STAT_DIRTY counter. This is done in the same places where global NR_FILE_DIRTY is managed. The new memcg stat is visible in the per memcg memory.stat cgroupfs file. The most recent past attempt at this was http://thread.gmane.org/gmane.linux.kernel.cgroups/8632 The new accounting supports future efforts to add per cgroup dirty page throttling and writeback. It also helps an administrator break down a container's memory usage and provides evidence to understand memcg oom kills (the new dirty count is included in memcg oom kill messages). The ability to move page accounting between memcg (memory.move_charge_at_immigrate) makes this accounting more complicated than the global counter. The existing mem_cgroup_{begin,end}_page_stat() lock is used to serialize move accounting with stat updates. Typical update operation: memcg = mem_cgroup_begin_page_stat(page) if (TestSetPageDirty()) { [...] mem_cgroup_update_page_stat(memcg) } mem_cgroup_end_page_stat(memcg) Summary of mem_cgroup_end_page_stat() overhead: - Without CONFIG_MEMCG it's a no-op - With CONFIG_MEMCG and no inter memcg task movement, it's just rcu_read_lock() - With CONFIG_MEMCG and inter memcg task movement, it's rcu_read_lock() + spin_lock_irqsave() A memcg parameter is added to several routines because their callers now grab mem_cgroup_begin_page_stat() which returns the memcg later needed by for mem_cgroup_update_page_stat(). Because mem_cgroup_begin_page_stat() may disable interrupts, some adjustments are needed: - move __mark_inode_dirty() from __set_page_dirty() to its caller. __mark_inode_dirty() locking does not want interrupts disabled. - use spin_lock_irqsave(tree_lock) rather than spin_lock_irq() in __delete_from_page_cache(), replace_page_cache_page(), invalidate_complete_page2(), and __remove_mapping(). text data bss dec hex filename 8925147 1774832 1785856 12485835 be84cb vmlinux-!CONFIG_MEMCG-before 8925339 1774832 1785856 12486027 be858b vmlinux-!CONFIG_MEMCG-after +192 text bytes 8965977 1784992 1785856 12536825 bf4bf9 vmlinux-CONFIG_MEMCG-before 8966750 1784992 1785856 12537598 bf4efe vmlinux-CONFIG_MEMCG-after +773 text bytes Performance tests run on v4.0-rc1-36-g4f671fe2f952. Lower is better for all metrics, they're all wall clock or cycle counts. The read and write fault benchmarks just measure fault time, they do not include I/O time. * CONFIG_MEMCG not set: baseline patched kbuild 1m25.030000(+-0.088% 3 samples) 1m25.426667(+-0.120% 3 samples) dd write 100 MiB 0.859211561 +-15.10% 0.874162885 +-15.03% dd write 200 MiB 1.670653105 +-17.87% 1.669384764 +-11.99% dd write 1000 MiB 8.434691190 +-14.15% 8.474733215 +-14.77% read fault cycles 254.0(+-0.000% 10 samples) 253.0(+-0.000% 10 samples) write fault cycles 2021.2(+-3.070% 10 samples) 1984.5(+-1.036% 10 samples) * CONFIG_MEMCG=y root_memcg: baseline patched kbuild 1m25.716667(+-0.105% 3 samples) 1m25.686667(+-0.153% 3 samples) dd write 100 MiB 0.855650830 +-14.90% 0.887557919 +-14.90% dd write 200 MiB 1.688322953 +-12.72% 1.667682724 +-13.33% dd write 1000 MiB 8.418601605 +-14.30% 8.673532299 +-15.00% read fault cycles 266.0(+-0.000% 10 samples) 266.0(+-0.000% 10 samples) write fault cycles 2051.7(+-1.349% 10 samples) 2049.6(+-1.686% 10 samples) * CONFIG_MEMCG=y non-root_memcg: baseline patched kbuild 1m26.120000(+-0.273% 3 samples) 1m25.763333(+-0.127% 3 samples) dd write 100 MiB 0.861723964 +-15.25% 0.818129350 +-14.82% dd write 200 MiB 1.669887569 +-13.30% 1.698645885 +-13.27% dd write 1000 MiB 8.383191730 +-14.65% 8.351742280 +-14.52% read fault cycles 265.7(+-0.172% 10 samples) 267.0(+-0.000% 10 samples) write fault cycles 2070.6(+-1.512% 10 samples) 2084.4(+-2.148% 10 samples) As expected anon page faults are not affected by this patch. tj: Updated to apply on top of the recent cancel_dirty_page() changes. Signed-off-by: Sha Zhengju <handai.szj@gmail.com> Signed-off-by: Greg Thelen <gthelen@google.com> Signed-off-by: Tejun Heo <tj@kernel.org> Signed-off-by: Jens Axboe <axboe@fb.com>
2015-05-22 21:13:16 +00:00
spin_unlock_irqrestore(&mapping->tree_lock, flags);
mem_cgroup_end_page_stat(memcg);
mm: memcontrol: rewrite uncharge API The memcg uncharging code that is involved towards the end of a page's lifetime - truncation, reclaim, swapout, migration - is impressively complicated and fragile. Because anonymous and file pages were always charged before they had their page->mapping established, uncharges had to happen when the page type could still be known from the context; as in unmap for anonymous, page cache removal for file and shmem pages, and swap cache truncation for swap pages. However, these operations happen well before the page is actually freed, and so a lot of synchronization is necessary: - Charging, uncharging, page migration, and charge migration all need to take a per-page bit spinlock as they could race with uncharging. - Swap cache truncation happens during both swap-in and swap-out, and possibly repeatedly before the page is actually freed. This means that the memcg swapout code is called from many contexts that make no sense and it has to figure out the direction from page state to make sure memory and memory+swap are always correctly charged. - On page migration, the old page might be unmapped but then reused, so memcg code has to prevent untimely uncharging in that case. Because this code - which should be a simple charge transfer - is so special-cased, it is not reusable for replace_page_cache(). But now that charged pages always have a page->mapping, introduce mem_cgroup_uncharge(), which is called after the final put_page(), when we know for sure that nobody is looking at the page anymore. For page migration, introduce mem_cgroup_migrate(), which is called after the migration is successful and the new page is fully rmapped. Because the old page is no longer uncharged after migration, prevent double charges by decoupling the page's memcg association (PCG_USED and pc->mem_cgroup) from the page holding an actual charge. The new bits PCG_MEM and PCG_MEMSW represent the respective charges and are transferred to the new page during migration. mem_cgroup_migrate() is suitable for replace_page_cache() as well, which gets rid of mem_cgroup_replace_page_cache(). However, care needs to be taken because both the source and the target page can already be charged and on the LRU when fuse is splicing: grab the page lock on the charge moving side to prevent changing pc->mem_cgroup of a page under migration. Also, the lruvecs of both pages change as we uncharge the old and charge the new during migration, and putback may race with us, so grab the lru lock and isolate the pages iff on LRU to prevent races and ensure the pages are on the right lruvec afterward. Swap accounting is massively simplified: because the page is no longer uncharged as early as swap cache deletion, a new mem_cgroup_swapout() can transfer the page's memory+swap charge (PCG_MEMSW) to the swap entry before the final put_page() in page reclaim. Finally, page_cgroup changes are now protected by whatever protection the page itself offers: anonymous pages are charged under the page table lock, whereas page cache insertions, swapin, and migration hold the page lock. Uncharging happens under full exclusion with no outstanding references. Charging and uncharging also ensure that the page is off-LRU, which serializes against charge migration. Remove the very costly page_cgroup lock and set pc->flags non-atomically. [mhocko@suse.cz: mem_cgroup_charge_statistics needs preempt_disable] [vdavydov@parallels.com: fix flags definition] Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Hugh Dickins <hughd@google.com> Cc: Tejun Heo <tj@kernel.org> Cc: Vladimir Davydov <vdavydov@parallels.com> Tested-by: Jet Chen <jet.chen@intel.com> Acked-by: Michal Hocko <mhocko@suse.cz> Tested-by: Felipe Balbi <balbi@ti.com> Signed-off-by: Vladimir Davydov <vdavydov@parallels.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-08 21:19:22 +00:00
mem_cgroup_migrate(old, new, true);
radix_tree_preload_end();
if (freepage)
freepage(old);
page_cache_release(old);
}
return error;
}
EXPORT_SYMBOL_GPL(replace_page_cache_page);
2014-04-03 21:47:46 +00:00
static int page_cache_tree_insert(struct address_space *mapping,
mm: thrash detection-based file cache sizing The VM maintains cached filesystem pages on two types of lists. One list holds the pages recently faulted into the cache, the other list holds pages that have been referenced repeatedly on that first list. The idea is to prefer reclaiming young pages over those that have shown to benefit from caching in the past. We call the recently usedbut ultimately was not significantly better than a FIFO policy and still thrashed cache based on eviction speed, rather than actual demand for cache. This patch solves one half of the problem by decoupling the ability to detect working set changes from the inactive list size. By maintaining a history of recently evicted file pages it can detect frequently used pages with an arbitrarily small inactive list size, and subsequently apply pressure on the active list based on actual demand for cache, not just overall eviction speed. Every zone maintains a counter that tracks inactive list aging speed. When a page is evicted, a snapshot of this counter is stored in the now-empty page cache radix tree slot. On refault, the minimum access distance of the page can be assessed, to evaluate whether the page should be part of the active list or not. This fixes the VM's blindness towards working set changes in excess of the inactive list. And it's the foundation to further improve the protection ability and reduce the minimum inactive list size of 50%. Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Rik van Riel <riel@redhat.com> Reviewed-by: Minchan Kim <minchan@kernel.org> Reviewed-by: Bob Liu <bob.liu@oracle.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Dave Chinner <david@fromorbit.com> Cc: Greg Thelen <gthelen@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jan Kara <jack@suse.cz> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Luigi Semenzato <semenzato@google.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Metin Doslu <metin@citusdata.com> Cc: Michel Lespinasse <walken@google.com> Cc: Ozgun Erdogan <ozgun@citusdata.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Roman Gushchin <klamm@yandex-team.ru> Cc: Ryan Mallon <rmallon@gmail.com> Cc: Tejun Heo <tj@kernel.org> Cc: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-03 21:47:51 +00:00
struct page *page, void **shadowp)
2014-04-03 21:47:46 +00:00
{
mm: keep page cache radix tree nodes in check Previously, page cache radix tree nodes were freed after reclaim emptied out their page pointers. But now reclaim stores shadow entries in their place, which are only reclaimed when the inodes themselves are reclaimed. This is problematic for bigger files that are still in use after they have a significant amount of their cache reclaimed, without any of those pages actually refaulting. The shadow entries will just sit there and waste memory. In the worst case, the shadow entries will accumulate until the machine runs out of memory. To get this under control, the VM will track radix tree nodes exclusively containing shadow entries on a per-NUMA node list. Per-NUMA rather than global because we expect the radix tree nodes themselves to be allocated node-locally and we want to reduce cross-node references of otherwise independent cache workloads. A simple shrinker will then reclaim these nodes on memory pressure. A few things need to be stored in the radix tree node to implement the shadow node LRU and allow tree deletions coming from the list: 1. There is no index available that would describe the reverse path from the node up to the tree root, which is needed to perform a deletion. To solve this, encode in each node its offset inside the parent. This can be stored in the unused upper bits of the same member that stores the node's height at no extra space cost. 2. The number of shadow entries needs to be counted in addition to the regular entries, to quickly detect when the node is ready to go to the shadow node LRU list. The current entry count is an unsigned int but the maximum number of entries is 64, so a shadow counter can easily be stored in the unused upper bits. 3. Tree modification needs tree lock and tree root, which are located in the address space, so store an address_space backpointer in the node. The parent pointer of the node is in a union with the 2-word rcu_head, so the backpointer comes at no extra cost as well. 4. The node needs to be linked to an LRU list, which requires a list head inside the node. This does increase the size of the node, but it does not change the number of objects that fit into a slab page. [akpm@linux-foundation.org: export the right function] Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Rik van Riel <riel@redhat.com> Reviewed-by: Minchan Kim <minchan@kernel.org> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Bob Liu <bob.liu@oracle.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Dave Chinner <david@fromorbit.com> Cc: Greg Thelen <gthelen@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jan Kara <jack@suse.cz> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Luigi Semenzato <semenzato@google.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Metin Doslu <metin@citusdata.com> Cc: Michel Lespinasse <walken@google.com> Cc: Ozgun Erdogan <ozgun@citusdata.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Roman Gushchin <klamm@yandex-team.ru> Cc: Ryan Mallon <rmallon@gmail.com> Cc: Tejun Heo <tj@kernel.org> Cc: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-03 21:47:56 +00:00
struct radix_tree_node *node;
2014-04-03 21:47:46 +00:00
void **slot;
int error;
mm: keep page cache radix tree nodes in check Previously, page cache radix tree nodes were freed after reclaim emptied out their page pointers. But now reclaim stores shadow entries in their place, which are only reclaimed when the inodes themselves are reclaimed. This is problematic for bigger files that are still in use after they have a significant amount of their cache reclaimed, without any of those pages actually refaulting. The shadow entries will just sit there and waste memory. In the worst case, the shadow entries will accumulate until the machine runs out of memory. To get this under control, the VM will track radix tree nodes exclusively containing shadow entries on a per-NUMA node list. Per-NUMA rather than global because we expect the radix tree nodes themselves to be allocated node-locally and we want to reduce cross-node references of otherwise independent cache workloads. A simple shrinker will then reclaim these nodes on memory pressure. A few things need to be stored in the radix tree node to implement the shadow node LRU and allow tree deletions coming from the list: 1. There is no index available that would describe the reverse path from the node up to the tree root, which is needed to perform a deletion. To solve this, encode in each node its offset inside the parent. This can be stored in the unused upper bits of the same member that stores the node's height at no extra space cost. 2. The number of shadow entries needs to be counted in addition to the regular entries, to quickly detect when the node is ready to go to the shadow node LRU list. The current entry count is an unsigned int but the maximum number of entries is 64, so a shadow counter can easily be stored in the unused upper bits. 3. Tree modification needs tree lock and tree root, which are located in the address space, so store an address_space backpointer in the node. The parent pointer of the node is in a union with the 2-word rcu_head, so the backpointer comes at no extra cost as well. 4. The node needs to be linked to an LRU list, which requires a list head inside the node. This does increase the size of the node, but it does not change the number of objects that fit into a slab page. [akpm@linux-foundation.org: export the right function] Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Rik van Riel <riel@redhat.com> Reviewed-by: Minchan Kim <minchan@kernel.org> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Bob Liu <bob.liu@oracle.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Dave Chinner <david@fromorbit.com> Cc: Greg Thelen <gthelen@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jan Kara <jack@suse.cz> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Luigi Semenzato <semenzato@google.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Metin Doslu <metin@citusdata.com> Cc: Michel Lespinasse <walken@google.com> Cc: Ozgun Erdogan <ozgun@citusdata.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Roman Gushchin <klamm@yandex-team.ru> Cc: Ryan Mallon <rmallon@gmail.com> Cc: Tejun Heo <tj@kernel.org> Cc: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-03 21:47:56 +00:00
error = __radix_tree_create(&mapping->page_tree, page->index,
&node, &slot);
if (error)
return error;
if (*slot) {
2014-04-03 21:47:46 +00:00
void *p;
p = radix_tree_deref_slot_protected(slot, &mapping->tree_lock);
if (!radix_tree_exceptional_entry(p))
return -EEXIST;
mm: thrash detection-based file cache sizing The VM maintains cached filesystem pages on two types of lists. One list holds the pages recently faulted into the cache, the other list holds pages that have been referenced repeatedly on that first list. The idea is to prefer reclaiming young pages over those that have shown to benefit from caching in the past. We call the recently usedbut ultimately was not significantly better than a FIFO policy and still thrashed cache based on eviction speed, rather than actual demand for cache. This patch solves one half of the problem by decoupling the ability to detect working set changes from the inactive list size. By maintaining a history of recently evicted file pages it can detect frequently used pages with an arbitrarily small inactive list size, and subsequently apply pressure on the active list based on actual demand for cache, not just overall eviction speed. Every zone maintains a counter that tracks inactive list aging speed. When a page is evicted, a snapshot of this counter is stored in the now-empty page cache radix tree slot. On refault, the minimum access distance of the page can be assessed, to evaluate whether the page should be part of the active list or not. This fixes the VM's blindness towards working set changes in excess of the inactive list. And it's the foundation to further improve the protection ability and reduce the minimum inactive list size of 50%. Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Rik van Riel <riel@redhat.com> Reviewed-by: Minchan Kim <minchan@kernel.org> Reviewed-by: Bob Liu <bob.liu@oracle.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Dave Chinner <david@fromorbit.com> Cc: Greg Thelen <gthelen@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jan Kara <jack@suse.cz> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Luigi Semenzato <semenzato@google.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Metin Doslu <metin@citusdata.com> Cc: Michel Lespinasse <walken@google.com> Cc: Ozgun Erdogan <ozgun@citusdata.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Roman Gushchin <klamm@yandex-team.ru> Cc: Ryan Mallon <rmallon@gmail.com> Cc: Tejun Heo <tj@kernel.org> Cc: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-03 21:47:51 +00:00
if (shadowp)
*shadowp = p;
mm: keep page cache radix tree nodes in check Previously, page cache radix tree nodes were freed after reclaim emptied out their page pointers. But now reclaim stores shadow entries in their place, which are only reclaimed when the inodes themselves are reclaimed. This is problematic for bigger files that are still in use after they have a significant amount of their cache reclaimed, without any of those pages actually refaulting. The shadow entries will just sit there and waste memory. In the worst case, the shadow entries will accumulate until the machine runs out of memory. To get this under control, the VM will track radix tree nodes exclusively containing shadow entries on a per-NUMA node list. Per-NUMA rather than global because we expect the radix tree nodes themselves to be allocated node-locally and we want to reduce cross-node references of otherwise independent cache workloads. A simple shrinker will then reclaim these nodes on memory pressure. A few things need to be stored in the radix tree node to implement the shadow node LRU and allow tree deletions coming from the list: 1. There is no index available that would describe the reverse path from the node up to the tree root, which is needed to perform a deletion. To solve this, encode in each node its offset inside the parent. This can be stored in the unused upper bits of the same member that stores the node's height at no extra space cost. 2. The number of shadow entries needs to be counted in addition to the regular entries, to quickly detect when the node is ready to go to the shadow node LRU list. The current entry count is an unsigned int but the maximum number of entries is 64, so a shadow counter can easily be stored in the unused upper bits. 3. Tree modification needs tree lock and tree root, which are located in the address space, so store an address_space backpointer in the node. The parent pointer of the node is in a union with the 2-word rcu_head, so the backpointer comes at no extra cost as well. 4. The node needs to be linked to an LRU list, which requires a list head inside the node. This does increase the size of the node, but it does not change the number of objects that fit into a slab page. [akpm@linux-foundation.org: export the right function] Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Rik van Riel <riel@redhat.com> Reviewed-by: Minchan Kim <minchan@kernel.org> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Bob Liu <bob.liu@oracle.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Dave Chinner <david@fromorbit.com> Cc: Greg Thelen <gthelen@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jan Kara <jack@suse.cz> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Luigi Semenzato <semenzato@google.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Metin Doslu <metin@citusdata.com> Cc: Michel Lespinasse <walken@google.com> Cc: Ozgun Erdogan <ozgun@citusdata.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Roman Gushchin <klamm@yandex-team.ru> Cc: Ryan Mallon <rmallon@gmail.com> Cc: Tejun Heo <tj@kernel.org> Cc: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-03 21:47:56 +00:00
mapping->nrshadows--;
if (node)
workingset_node_shadows_dec(node);
2014-04-03 21:47:46 +00:00
}
mm: keep page cache radix tree nodes in check Previously, page cache radix tree nodes were freed after reclaim emptied out their page pointers. But now reclaim stores shadow entries in their place, which are only reclaimed when the inodes themselves are reclaimed. This is problematic for bigger files that are still in use after they have a significant amount of their cache reclaimed, without any of those pages actually refaulting. The shadow entries will just sit there and waste memory. In the worst case, the shadow entries will accumulate until the machine runs out of memory. To get this under control, the VM will track radix tree nodes exclusively containing shadow entries on a per-NUMA node list. Per-NUMA rather than global because we expect the radix tree nodes themselves to be allocated node-locally and we want to reduce cross-node references of otherwise independent cache workloads. A simple shrinker will then reclaim these nodes on memory pressure. A few things need to be stored in the radix tree node to implement the shadow node LRU and allow tree deletions coming from the list: 1. There is no index available that would describe the reverse path from the node up to the tree root, which is needed to perform a deletion. To solve this, encode in each node its offset inside the parent. This can be stored in the unused upper bits of the same member that stores the node's height at no extra space cost. 2. The number of shadow entries needs to be counted in addition to the regular entries, to quickly detect when the node is ready to go to the shadow node LRU list. The current entry count is an unsigned int but the maximum number of entries is 64, so a shadow counter can easily be stored in the unused upper bits. 3. Tree modification needs tree lock and tree root, which are located in the address space, so store an address_space backpointer in the node. The parent pointer of the node is in a union with the 2-word rcu_head, so the backpointer comes at no extra cost as well. 4. The node needs to be linked to an LRU list, which requires a list head inside the node. This does increase the size of the node, but it does not change the number of objects that fit into a slab page. [akpm@linux-foundation.org: export the right function] Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Rik van Riel <riel@redhat.com> Reviewed-by: Minchan Kim <minchan@kernel.org> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Bob Liu <bob.liu@oracle.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Dave Chinner <david@fromorbit.com> Cc: Greg Thelen <gthelen@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jan Kara <jack@suse.cz> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Luigi Semenzato <semenzato@google.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Metin Doslu <metin@citusdata.com> Cc: Michel Lespinasse <walken@google.com> Cc: Ozgun Erdogan <ozgun@citusdata.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Roman Gushchin <klamm@yandex-team.ru> Cc: Ryan Mallon <rmallon@gmail.com> Cc: Tejun Heo <tj@kernel.org> Cc: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-03 21:47:56 +00:00
radix_tree_replace_slot(slot, page);
mapping->nrpages++;
if (node) {
workingset_node_pages_inc(node);
/*
* Don't track node that contains actual pages.
*
* Avoid acquiring the list_lru lock if already
* untracked. The list_empty() test is safe as
* node->private_list is protected by
* mapping->tree_lock.
*/
if (!list_empty(&node->private_list))
list_lru_del(&workingset_shadow_nodes,
&node->private_list);
}
return 0;
2014-04-03 21:47:46 +00:00
}
mm: thrash detection-based file cache sizing The VM maintains cached filesystem pages on two types of lists. One list holds the pages recently faulted into the cache, the other list holds pages that have been referenced repeatedly on that first list. The idea is to prefer reclaiming young pages over those that have shown to benefit from caching in the past. We call the recently usedbut ultimately was not significantly better than a FIFO policy and still thrashed cache based on eviction speed, rather than actual demand for cache. This patch solves one half of the problem by decoupling the ability to detect working set changes from the inactive list size. By maintaining a history of recently evicted file pages it can detect frequently used pages with an arbitrarily small inactive list size, and subsequently apply pressure on the active list based on actual demand for cache, not just overall eviction speed. Every zone maintains a counter that tracks inactive list aging speed. When a page is evicted, a snapshot of this counter is stored in the now-empty page cache radix tree slot. On refault, the minimum access distance of the page can be assessed, to evaluate whether the page should be part of the active list or not. This fixes the VM's blindness towards working set changes in excess of the inactive list. And it's the foundation to further improve the protection ability and reduce the minimum inactive list size of 50%. Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Rik van Riel <riel@redhat.com> Reviewed-by: Minchan Kim <minchan@kernel.org> Reviewed-by: Bob Liu <bob.liu@oracle.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Dave Chinner <david@fromorbit.com> Cc: Greg Thelen <gthelen@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jan Kara <jack@suse.cz> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Luigi Semenzato <semenzato@google.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Metin Doslu <metin@citusdata.com> Cc: Michel Lespinasse <walken@google.com> Cc: Ozgun Erdogan <ozgun@citusdata.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Roman Gushchin <klamm@yandex-team.ru> Cc: Ryan Mallon <rmallon@gmail.com> Cc: Tejun Heo <tj@kernel.org> Cc: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-03 21:47:51 +00:00
static int __add_to_page_cache_locked(struct page *page,
struct address_space *mapping,
pgoff_t offset, gfp_t gfp_mask,
void **shadowp)
{
mm: memcontrol: rewrite charge API These patches rework memcg charge lifetime to integrate more naturally with the lifetime of user pages. This drastically simplifies the code and reduces charging and uncharging overhead. The most expensive part of charging and uncharging is the page_cgroup bit spinlock, which is removed entirely after this series. Here are the top-10 profile entries of a stress test that reads a 128G sparse file on a freshly booted box, without even a dedicated cgroup (i.e. executing in the root memcg). Before: 15.36% cat [kernel.kallsyms] [k] copy_user_generic_string 13.31% cat [kernel.kallsyms] [k] memset 11.48% cat [kernel.kallsyms] [k] do_mpage_readpage 4.23% cat [kernel.kallsyms] [k] get_page_from_freelist 2.38% cat [kernel.kallsyms] [k] put_page 2.32% cat [kernel.kallsyms] [k] __mem_cgroup_commit_charge 2.18% kswapd0 [kernel.kallsyms] [k] __mem_cgroup_uncharge_common 1.92% kswapd0 [kernel.kallsyms] [k] shrink_page_list 1.86% cat [kernel.kallsyms] [k] __radix_tree_lookup 1.62% cat [kernel.kallsyms] [k] __pagevec_lru_add_fn After: 15.67% cat [kernel.kallsyms] [k] copy_user_generic_string 13.48% cat [kernel.kallsyms] [k] memset 11.42% cat [kernel.kallsyms] [k] do_mpage_readpage 3.98% cat [kernel.kallsyms] [k] get_page_from_freelist 2.46% cat [kernel.kallsyms] [k] put_page 2.13% kswapd0 [kernel.kallsyms] [k] shrink_page_list 1.88% cat [kernel.kallsyms] [k] __radix_tree_lookup 1.67% cat [kernel.kallsyms] [k] __pagevec_lru_add_fn 1.39% kswapd0 [kernel.kallsyms] [k] free_pcppages_bulk 1.30% cat [kernel.kallsyms] [k] kfree As you can see, the memcg footprint has shrunk quite a bit. text data bss dec hex filename 37970 9892 400 48262 bc86 mm/memcontrol.o.old 35239 9892 400 45531 b1db mm/memcontrol.o This patch (of 4): The memcg charge API charges pages before they are rmapped - i.e. have an actual "type" - and so every callsite needs its own set of charge and uncharge functions to know what type is being operated on. Worse, uncharge has to happen from a context that is still type-specific, rather than at the end of the page's lifetime with exclusive access, and so requires a lot of synchronization. Rewrite the charge API to provide a generic set of try_charge(), commit_charge() and cancel_charge() transaction operations, much like what's currently done for swap-in: mem_cgroup_try_charge() attempts to reserve a charge, reclaiming pages from the memcg if necessary. mem_cgroup_commit_charge() commits the page to the charge once it has a valid page->mapping and PageAnon() reliably tells the type. mem_cgroup_cancel_charge() aborts the transaction. This reduces the charge API and enables subsequent patches to drastically simplify uncharging. As pages need to be committed after rmap is established but before they are added to the LRU, page_add_new_anon_rmap() must stop doing LRU additions again. Revive lru_cache_add_active_or_unevictable(). [hughd@google.com: fix shmem_unuse] [hughd@google.com: Add comments on the private use of -EAGAIN] Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: Michal Hocko <mhocko@suse.cz> Cc: Tejun Heo <tj@kernel.org> Cc: Vladimir Davydov <vdavydov@parallels.com> Signed-off-by: Hugh Dickins <hughd@google.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-08 21:19:20 +00:00
int huge = PageHuge(page);
struct mem_cgroup *memcg;
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 02:45:30 +00:00
int error;
VM_BUG_ON_PAGE(!PageLocked(page), page);
VM_BUG_ON_PAGE(PageSwapBacked(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 02:45:30 +00:00
mm: memcontrol: rewrite charge API These patches rework memcg charge lifetime to integrate more naturally with the lifetime of user pages. This drastically simplifies the code and reduces charging and uncharging overhead. The most expensive part of charging and uncharging is the page_cgroup bit spinlock, which is removed entirely after this series. Here are the top-10 profile entries of a stress test that reads a 128G sparse file on a freshly booted box, without even a dedicated cgroup (i.e. executing in the root memcg). Before: 15.36% cat [kernel.kallsyms] [k] copy_user_generic_string 13.31% cat [kernel.kallsyms] [k] memset 11.48% cat [kernel.kallsyms] [k] do_mpage_readpage 4.23% cat [kernel.kallsyms] [k] get_page_from_freelist 2.38% cat [kernel.kallsyms] [k] put_page 2.32% cat [kernel.kallsyms] [k] __mem_cgroup_commit_charge 2.18% kswapd0 [kernel.kallsyms] [k] __mem_cgroup_uncharge_common 1.92% kswapd0 [kernel.kallsyms] [k] shrink_page_list 1.86% cat [kernel.kallsyms] [k] __radix_tree_lookup 1.62% cat [kernel.kallsyms] [k] __pagevec_lru_add_fn After: 15.67% cat [kernel.kallsyms] [k] copy_user_generic_string 13.48% cat [kernel.kallsyms] [k] memset 11.42% cat [kernel.kallsyms] [k] do_mpage_readpage 3.98% cat [kernel.kallsyms] [k] get_page_from_freelist 2.46% cat [kernel.kallsyms] [k] put_page 2.13% kswapd0 [kernel.kallsyms] [k] shrink_page_list 1.88% cat [kernel.kallsyms] [k] __radix_tree_lookup 1.67% cat [kernel.kallsyms] [k] __pagevec_lru_add_fn 1.39% kswapd0 [kernel.kallsyms] [k] free_pcppages_bulk 1.30% cat [kernel.kallsyms] [k] kfree As you can see, the memcg footprint has shrunk quite a bit. text data bss dec hex filename 37970 9892 400 48262 bc86 mm/memcontrol.o.old 35239 9892 400 45531 b1db mm/memcontrol.o This patch (of 4): The memcg charge API charges pages before they are rmapped - i.e. have an actual "type" - and so every callsite needs its own set of charge and uncharge functions to know what type is being operated on. Worse, uncharge has to happen from a context that is still type-specific, rather than at the end of the page's lifetime with exclusive access, and so requires a lot of synchronization. Rewrite the charge API to provide a generic set of try_charge(), commit_charge() and cancel_charge() transaction operations, much like what's currently done for swap-in: mem_cgroup_try_charge() attempts to reserve a charge, reclaiming pages from the memcg if necessary. mem_cgroup_commit_charge() commits the page to the charge once it has a valid page->mapping and PageAnon() reliably tells the type. mem_cgroup_cancel_charge() aborts the transaction. This reduces the charge API and enables subsequent patches to drastically simplify uncharging. As pages need to be committed after rmap is established but before they are added to the LRU, page_add_new_anon_rmap() must stop doing LRU additions again. Revive lru_cache_add_active_or_unevictable(). [hughd@google.com: fix shmem_unuse] [hughd@google.com: Add comments on the private use of -EAGAIN] Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: Michal Hocko <mhocko@suse.cz> Cc: Tejun Heo <tj@kernel.org> Cc: Vladimir Davydov <vdavydov@parallels.com> Signed-off-by: Hugh Dickins <hughd@google.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-08 21:19:20 +00:00
if (!huge) {
error = mem_cgroup_try_charge(page, current->mm,
gfp_mask, &memcg);
if (error)
return error;
}
lib/radix-tree.c: make radix_tree_node_alloc() work correctly within interrupt With users of radix_tree_preload() run from interrupt (block/blk-ioc.c is one such possible user), the following race can happen: radix_tree_preload() ... radix_tree_insert() radix_tree_node_alloc() if (rtp->nr) { ret = rtp->nodes[rtp->nr - 1]; <interrupt> ... radix_tree_preload() ... radix_tree_insert() radix_tree_node_alloc() if (rtp->nr) { ret = rtp->nodes[rtp->nr - 1]; And we give out one radix tree node twice. That clearly results in radix tree corruption with different results (usually OOPS) depending on which two users of radix tree race. We fix the problem by making radix_tree_node_alloc() always allocate fresh radix tree nodes when in interrupt. Using preloading when in interrupt doesn't make sense since all the allocations have to be atomic anyway and we cannot steal nodes from process-context users because some users rely on radix_tree_insert() succeeding after radix_tree_preload(). in_interrupt() check is somewhat ugly but we cannot simply key off passed gfp_mask as that is acquired from root_gfp_mask() and thus the same for all preload users. Another part of the fix is to avoid node preallocation in radix_tree_preload() when passed gfp_mask doesn't allow waiting. Again, preallocation in such case doesn't make sense and when preallocation would happen in interrupt we could possibly leak some allocated nodes. However, some users of radix_tree_preload() require following radix_tree_insert() to succeed. To avoid unexpected effects for these users, radix_tree_preload() only warns if passed gfp mask doesn't allow waiting and we provide a new function radix_tree_maybe_preload() for those users which get different gfp mask from different call sites and which are prepared to handle radix_tree_insert() failure. Signed-off-by: Jan Kara <jack@suse.cz> Cc: Jens Axboe <jaxboe@fusionio.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-09-11 21:26:05 +00:00
error = radix_tree_maybe_preload(gfp_mask & ~__GFP_HIGHMEM);
if (error) {
mm: memcontrol: rewrite charge API These patches rework memcg charge lifetime to integrate more naturally with the lifetime of user pages. This drastically simplifies the code and reduces charging and uncharging overhead. The most expensive part of charging and uncharging is the page_cgroup bit spinlock, which is removed entirely after this series. Here are the top-10 profile entries of a stress test that reads a 128G sparse file on a freshly booted box, without even a dedicated cgroup (i.e. executing in the root memcg). Before: 15.36% cat [kernel.kallsyms] [k] copy_user_generic_string 13.31% cat [kernel.kallsyms] [k] memset 11.48% cat [kernel.kallsyms] [k] do_mpage_readpage 4.23% cat [kernel.kallsyms] [k] get_page_from_freelist 2.38% cat [kernel.kallsyms] [k] put_page 2.32% cat [kernel.kallsyms] [k] __mem_cgroup_commit_charge 2.18% kswapd0 [kernel.kallsyms] [k] __mem_cgroup_uncharge_common 1.92% kswapd0 [kernel.kallsyms] [k] shrink_page_list 1.86% cat [kernel.kallsyms] [k] __radix_tree_lookup 1.62% cat [kernel.kallsyms] [k] __pagevec_lru_add_fn After: 15.67% cat [kernel.kallsyms] [k] copy_user_generic_string 13.48% cat [kernel.kallsyms] [k] memset 11.42% cat [kernel.kallsyms] [k] do_mpage_readpage 3.98% cat [kernel.kallsyms] [k] get_page_from_freelist 2.46% cat [kernel.kallsyms] [k] put_page 2.13% kswapd0 [kernel.kallsyms] [k] shrink_page_list 1.88% cat [kernel.kallsyms] [k] __radix_tree_lookup 1.67% cat [kernel.kallsyms] [k] __pagevec_lru_add_fn 1.39% kswapd0 [kernel.kallsyms] [k] free_pcppages_bulk 1.30% cat [kernel.kallsyms] [k] kfree As you can see, the memcg footprint has shrunk quite a bit. text data bss dec hex filename 37970 9892 400 48262 bc86 mm/memcontrol.o.old 35239 9892 400 45531 b1db mm/memcontrol.o This patch (of 4): The memcg charge API charges pages before they are rmapped - i.e. have an actual "type" - and so every callsite needs its own set of charge and uncharge functions to know what type is being operated on. Worse, uncharge has to happen from a context that is still type-specific, rather than at the end of the page's lifetime with exclusive access, and so requires a lot of synchronization. Rewrite the charge API to provide a generic set of try_charge(), commit_charge() and cancel_charge() transaction operations, much like what's currently done for swap-in: mem_cgroup_try_charge() attempts to reserve a charge, reclaiming pages from the memcg if necessary. mem_cgroup_commit_charge() commits the page to the charge once it has a valid page->mapping and PageAnon() reliably tells the type. mem_cgroup_cancel_charge() aborts the transaction. This reduces the charge API and enables subsequent patches to drastically simplify uncharging. As pages need to be committed after rmap is established but before they are added to the LRU, page_add_new_anon_rmap() must stop doing LRU additions again. Revive lru_cache_add_active_or_unevictable(). [hughd@google.com: fix shmem_unuse] [hughd@google.com: Add comments on the private use of -EAGAIN] Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: Michal Hocko <mhocko@suse.cz> Cc: Tejun Heo <tj@kernel.org> Cc: Vladimir Davydov <vdavydov@parallels.com> Signed-off-by: Hugh Dickins <hughd@google.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-08 21:19:20 +00:00
if (!huge)
mem_cgroup_cancel_charge(page, memcg);
return error;
}
page_cache_get(page);
page->mapping = mapping;
page->index = offset;
spin_lock_irq(&mapping->tree_lock);
mm: thrash detection-based file cache sizing The VM maintains cached filesystem pages on two types of lists. One list holds the pages recently faulted into the cache, the other list holds pages that have been referenced repeatedly on that first list. The idea is to prefer reclaiming young pages over those that have shown to benefit from caching in the past. We call the recently usedbut ultimately was not significantly better than a FIFO policy and still thrashed cache based on eviction speed, rather than actual demand for cache. This patch solves one half of the problem by decoupling the ability to detect working set changes from the inactive list size. By maintaining a history of recently evicted file pages it can detect frequently used pages with an arbitrarily small inactive list size, and subsequently apply pressure on the active list based on actual demand for cache, not just overall eviction speed. Every zone maintains a counter that tracks inactive list aging speed. When a page is evicted, a snapshot of this counter is stored in the now-empty page cache radix tree slot. On refault, the minimum access distance of the page can be assessed, to evaluate whether the page should be part of the active list or not. This fixes the VM's blindness towards working set changes in excess of the inactive list. And it's the foundation to further improve the protection ability and reduce the minimum inactive list size of 50%. Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Rik van Riel <riel@redhat.com> Reviewed-by: Minchan Kim <minchan@kernel.org> Reviewed-by: Bob Liu <bob.liu@oracle.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Dave Chinner <david@fromorbit.com> Cc: Greg Thelen <gthelen@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jan Kara <jack@suse.cz> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Luigi Semenzato <semenzato@google.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Metin Doslu <metin@citusdata.com> Cc: Michel Lespinasse <walken@google.com> Cc: Ozgun Erdogan <ozgun@citusdata.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Roman Gushchin <klamm@yandex-team.ru> Cc: Ryan Mallon <rmallon@gmail.com> Cc: Tejun Heo <tj@kernel.org> Cc: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-03 21:47:51 +00:00
error = page_cache_tree_insert(mapping, page, shadowp);
radix_tree_preload_end();
if (unlikely(error))
goto err_insert;
hugetlb: do not account hugetlb pages as NR_FILE_PAGES hugetlb pages uses add_to_page_cache to track shared mappings. This is OK from the data structure point of view but it is less so from the NR_FILE_PAGES accounting: - huge pages are accounted as 4k which is clearly wrong - this counter is used as the amount of the reclaimable page cache which is incorrect as well because hugetlb pages are special and not reclaimable - the counter is then exported to userspace via /proc/meminfo (in Cached:), /proc/vmstat and /proc/zoneinfo as nr_file_pages which is confusing at least: Cached: 8883504 kB HugePages_Free: 8348 ... Cached: 8916048 kB HugePages_Free: 156 ... thats 8192 huge pages allocated which is ~16G accounted as 32M There are usually not that many huge pages in the system for this to make any visible difference e.g. by fooling __vm_enough_memory or zone_pagecache_reclaimable. Fix this by special casing huge pages in both __delete_from_page_cache and __add_to_page_cache_locked. replace_page_cache_page is currently only used by fuse and that shouldn't touch hugetlb pages AFAICS but it is more robust to check for special casing there as well. Hugetlb pages shouldn't get to any other paths where we do accounting: - migration - we have a special handling via hugetlbfs_migrate_page - shmem - doesn't handle hugetlb pages directly even for SHM_HUGETLB resp. MAP_HUGETLB - swapcache - hugetlb is not swapable This has a user visible effect but I believe it is reasonable because the previously exported number is simply bogus. An alternative would be to account hugetlb pages with their real size and treat them similar to shmem. But this has some drawbacks. First we would have to special case in kernel users of NR_FILE_PAGES and considering how hugetlb is special we would have to do it everywhere. We do not want Cached exported by /proc/meminfo to include it because the value would be even more misleading. __vm_enough_memory and zone_pagecache_reclaimable would have to do the same thing because those pages are simply not reclaimable. The correction is even not trivial because we would have to consider all active hugetlb page sizes properly. Users of the counter outside of the kernel would have to do the same. So the question is why to account something that needs to be basically excluded for each reasonable usage. This doesn't make much sense to me. It seems that this has been broken since hugetlb was introduced but I haven't checked the whole history. [akpm@linux-foundation.org: tweak comments] Signed-off-by: Michal Hocko <mhocko@suse.cz> Acked-by: Mel Gorman <mgorman@suse.de> Tested-by: Mike Kravetz <mike.kravetz@oracle.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-06-24 23:57:24 +00:00
/* hugetlb pages do not participate in page cache accounting. */
if (!huge)
__inc_zone_page_state(page, NR_FILE_PAGES);
spin_unlock_irq(&mapping->tree_lock);
mm: memcontrol: rewrite charge API These patches rework memcg charge lifetime to integrate more naturally with the lifetime of user pages. This drastically simplifies the code and reduces charging and uncharging overhead. The most expensive part of charging and uncharging is the page_cgroup bit spinlock, which is removed entirely after this series. Here are the top-10 profile entries of a stress test that reads a 128G sparse file on a freshly booted box, without even a dedicated cgroup (i.e. executing in the root memcg). Before: 15.36% cat [kernel.kallsyms] [k] copy_user_generic_string 13.31% cat [kernel.kallsyms] [k] memset 11.48% cat [kernel.kallsyms] [k] do_mpage_readpage 4.23% cat [kernel.kallsyms] [k] get_page_from_freelist 2.38% cat [kernel.kallsyms] [k] put_page 2.32% cat [kernel.kallsyms] [k] __mem_cgroup_commit_charge 2.18% kswapd0 [kernel.kallsyms] [k] __mem_cgroup_uncharge_common 1.92% kswapd0 [kernel.kallsyms] [k] shrink_page_list 1.86% cat [kernel.kallsyms] [k] __radix_tree_lookup 1.62% cat [kernel.kallsyms] [k] __pagevec_lru_add_fn After: 15.67% cat [kernel.kallsyms] [k] copy_user_generic_string 13.48% cat [kernel.kallsyms] [k] memset 11.42% cat [kernel.kallsyms] [k] do_mpage_readpage 3.98% cat [kernel.kallsyms] [k] get_page_from_freelist 2.46% cat [kernel.kallsyms] [k] put_page 2.13% kswapd0 [kernel.kallsyms] [k] shrink_page_list 1.88% cat [kernel.kallsyms] [k] __radix_tree_lookup 1.67% cat [kernel.kallsyms] [k] __pagevec_lru_add_fn 1.39% kswapd0 [kernel.kallsyms] [k] free_pcppages_bulk 1.30% cat [kernel.kallsyms] [k] kfree As you can see, the memcg footprint has shrunk quite a bit. text data bss dec hex filename 37970 9892 400 48262 bc86 mm/memcontrol.o.old 35239 9892 400 45531 b1db mm/memcontrol.o This patch (of 4): The memcg charge API charges pages before they are rmapped - i.e. have an actual "type" - and so every callsite needs its own set of charge and uncharge functions to know what type is being operated on. Worse, uncharge has to happen from a context that is still type-specific, rather than at the end of the page's lifetime with exclusive access, and so requires a lot of synchronization. Rewrite the charge API to provide a generic set of try_charge(), commit_charge() and cancel_charge() transaction operations, much like what's currently done for swap-in: mem_cgroup_try_charge() attempts to reserve a charge, reclaiming pages from the memcg if necessary. mem_cgroup_commit_charge() commits the page to the charge once it has a valid page->mapping and PageAnon() reliably tells the type. mem_cgroup_cancel_charge() aborts the transaction. This reduces the charge API and enables subsequent patches to drastically simplify uncharging. As pages need to be committed after rmap is established but before they are added to the LRU, page_add_new_anon_rmap() must stop doing LRU additions again. Revive lru_cache_add_active_or_unevictable(). [hughd@google.com: fix shmem_unuse] [hughd@google.com: Add comments on the private use of -EAGAIN] Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: Michal Hocko <mhocko@suse.cz> Cc: Tejun Heo <tj@kernel.org> Cc: Vladimir Davydov <vdavydov@parallels.com> Signed-off-by: Hugh Dickins <hughd@google.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-08 21:19:20 +00:00
if (!huge)
mem_cgroup_commit_charge(page, memcg, false);
trace_mm_filemap_add_to_page_cache(page);
return 0;
err_insert:
page->mapping = NULL;
/* Leave page->index set: truncation relies upon it */
spin_unlock_irq(&mapping->tree_lock);
mm: memcontrol: rewrite charge API These patches rework memcg charge lifetime to integrate more naturally with the lifetime of user pages. This drastically simplifies the code and reduces charging and uncharging overhead. The most expensive part of charging and uncharging is the page_cgroup bit spinlock, which is removed entirely after this series. Here are the top-10 profile entries of a stress test that reads a 128G sparse file on a freshly booted box, without even a dedicated cgroup (i.e. executing in the root memcg). Before: 15.36% cat [kernel.kallsyms] [k] copy_user_generic_string 13.31% cat [kernel.kallsyms] [k] memset 11.48% cat [kernel.kallsyms] [k] do_mpage_readpage 4.23% cat [kernel.kallsyms] [k] get_page_from_freelist 2.38% cat [kernel.kallsyms] [k] put_page 2.32% cat [kernel.kallsyms] [k] __mem_cgroup_commit_charge 2.18% kswapd0 [kernel.kallsyms] [k] __mem_cgroup_uncharge_common 1.92% kswapd0 [kernel.kallsyms] [k] shrink_page_list 1.86% cat [kernel.kallsyms] [k] __radix_tree_lookup 1.62% cat [kernel.kallsyms] [k] __pagevec_lru_add_fn After: 15.67% cat [kernel.kallsyms] [k] copy_user_generic_string 13.48% cat [kernel.kallsyms] [k] memset 11.42% cat [kernel.kallsyms] [k] do_mpage_readpage 3.98% cat [kernel.kallsyms] [k] get_page_from_freelist 2.46% cat [kernel.kallsyms] [k] put_page 2.13% kswapd0 [kernel.kallsyms] [k] shrink_page_list 1.88% cat [kernel.kallsyms] [k] __radix_tree_lookup 1.67% cat [kernel.kallsyms] [k] __pagevec_lru_add_fn 1.39% kswapd0 [kernel.kallsyms] [k] free_pcppages_bulk 1.30% cat [kernel.kallsyms] [k] kfree As you can see, the memcg footprint has shrunk quite a bit. text data bss dec hex filename 37970 9892 400 48262 bc86 mm/memcontrol.o.old 35239 9892 400 45531 b1db mm/memcontrol.o This patch (of 4): The memcg charge API charges pages before they are rmapped - i.e. have an actual "type" - and so every callsite needs its own set of charge and uncharge functions to know what type is being operated on. Worse, uncharge has to happen from a context that is still type-specific, rather than at the end of the page's lifetime with exclusive access, and so requires a lot of synchronization. Rewrite the charge API to provide a generic set of try_charge(), commit_charge() and cancel_charge() transaction operations, much like what's currently done for swap-in: mem_cgroup_try_charge() attempts to reserve a charge, reclaiming pages from the memcg if necessary. mem_cgroup_commit_charge() commits the page to the charge once it has a valid page->mapping and PageAnon() reliably tells the type. mem_cgroup_cancel_charge() aborts the transaction. This reduces the charge API and enables subsequent patches to drastically simplify uncharging. As pages need to be committed after rmap is established but before they are added to the LRU, page_add_new_anon_rmap() must stop doing LRU additions again. Revive lru_cache_add_active_or_unevictable(). [hughd@google.com: fix shmem_unuse] [hughd@google.com: Add comments on the private use of -EAGAIN] Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: Michal Hocko <mhocko@suse.cz> Cc: Tejun Heo <tj@kernel.org> Cc: Vladimir Davydov <vdavydov@parallels.com> Signed-off-by: Hugh Dickins <hughd@google.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-08 21:19:20 +00:00
if (!huge)
mem_cgroup_cancel_charge(page, memcg);
page_cache_release(page);
return error;
}
mm: thrash detection-based file cache sizing The VM maintains cached filesystem pages on two types of lists. One list holds the pages recently faulted into the cache, the other list holds pages that have been referenced repeatedly on that first list. The idea is to prefer reclaiming young pages over those that have shown to benefit from caching in the past. We call the recently usedbut ultimately was not significantly better than a FIFO policy and still thrashed cache based on eviction speed, rather than actual demand for cache. This patch solves one half of the problem by decoupling the ability to detect working set changes from the inactive list size. By maintaining a history of recently evicted file pages it can detect frequently used pages with an arbitrarily small inactive list size, and subsequently apply pressure on the active list based on actual demand for cache, not just overall eviction speed. Every zone maintains a counter that tracks inactive list aging speed. When a page is evicted, a snapshot of this counter is stored in the now-empty page cache radix tree slot. On refault, the minimum access distance of the page can be assessed, to evaluate whether the page should be part of the active list or not. This fixes the VM's blindness towards working set changes in excess of the inactive list. And it's the foundation to further improve the protection ability and reduce the minimum inactive list size of 50%. Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Rik van Riel <riel@redhat.com> Reviewed-by: Minchan Kim <minchan@kernel.org> Reviewed-by: Bob Liu <bob.liu@oracle.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Dave Chinner <david@fromorbit.com> Cc: Greg Thelen <gthelen@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jan Kara <jack@suse.cz> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Luigi Semenzato <semenzato@google.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Metin Doslu <metin@citusdata.com> Cc: Michel Lespinasse <walken@google.com> Cc: Ozgun Erdogan <ozgun@citusdata.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Roman Gushchin <klamm@yandex-team.ru> Cc: Ryan Mallon <rmallon@gmail.com> Cc: Tejun Heo <tj@kernel.org> Cc: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-03 21:47:51 +00:00
/**
* 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
*
* 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.
*/
int add_to_page_cache_locked(struct page *page, struct address_space *mapping,
pgoff_t offset, gfp_t gfp_mask)
{
return __add_to_page_cache_locked(page, mapping, offset,
gfp_mask, NULL);
}
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 02:45:30 +00:00
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)
{
mm: thrash detection-based file cache sizing The VM maintains cached filesystem pages on two types of lists. One list holds the pages recently faulted into the cache, the other list holds pages that have been referenced repeatedly on that first list. The idea is to prefer reclaiming young pages over those that have shown to benefit from caching in the past. We call the recently usedbut ultimately was not significantly better than a FIFO policy and still thrashed cache based on eviction speed, rather than actual demand for cache. This patch solves one half of the problem by decoupling the ability to detect working set changes from the inactive list size. By maintaining a history of recently evicted file pages it can detect frequently used pages with an arbitrarily small inactive list size, and subsequently apply pressure on the active list based on actual demand for cache, not just overall eviction speed. Every zone maintains a counter that tracks inactive list aging speed. When a page is evicted, a snapshot of this counter is stored in the now-empty page cache radix tree slot. On refault, the minimum access distance of the page can be assessed, to evaluate whether the page should be part of the active list or not. This fixes the VM's blindness towards working set changes in excess of the inactive list. And it's the foundation to further improve the protection ability and reduce the minimum inactive list size of 50%. Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Rik van Riel <riel@redhat.com> Reviewed-by: Minchan Kim <minchan@kernel.org> Reviewed-by: Bob Liu <bob.liu@oracle.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Dave Chinner <david@fromorbit.com> Cc: Greg Thelen <gthelen@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jan Kara <jack@suse.cz> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Luigi Semenzato <semenzato@google.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Metin Doslu <metin@citusdata.com> Cc: Michel Lespinasse <walken@google.com> Cc: Ozgun Erdogan <ozgun@citusdata.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Roman Gushchin <klamm@yandex-team.ru> Cc: Ryan Mallon <rmallon@gmail.com> Cc: Tejun Heo <tj@kernel.org> Cc: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-03 21:47:51 +00:00
void *shadow = NULL;
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 03:26:32 +00:00
int ret;
mm: thrash detection-based file cache sizing The VM maintains cached filesystem pages on two types of lists. One list holds the pages recently faulted into the cache, the other list holds pages that have been referenced repeatedly on that first list. The idea is to prefer reclaiming young pages over those that have shown to benefit from caching in the past. We call the recently usedbut ultimately was not significantly better than a FIFO policy and still thrashed cache based on eviction speed, rather than actual demand for cache. This patch solves one half of the problem by decoupling the ability to detect working set changes from the inactive list size. By maintaining a history of recently evicted file pages it can detect frequently used pages with an arbitrarily small inactive list size, and subsequently apply pressure on the active list based on actual demand for cache, not just overall eviction speed. Every zone maintains a counter that tracks inactive list aging speed. When a page is evicted, a snapshot of this counter is stored in the now-empty page cache radix tree slot. On refault, the minimum access distance of the page can be assessed, to evaluate whether the page should be part of the active list or not. This fixes the VM's blindness towards working set changes in excess of the inactive list. And it's the foundation to further improve the protection ability and reduce the minimum inactive list size of 50%. Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Rik van Riel <riel@redhat.com> Reviewed-by: Minchan Kim <minchan@kernel.org> Reviewed-by: Bob Liu <bob.liu@oracle.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Dave Chinner <david@fromorbit.com> Cc: Greg Thelen <gthelen@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jan Kara <jack@suse.cz> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Luigi Semenzato <semenzato@google.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Metin Doslu <metin@citusdata.com> Cc: Michel Lespinasse <walken@google.com> Cc: Ozgun Erdogan <ozgun@citusdata.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Roman Gushchin <klamm@yandex-team.ru> Cc: Ryan Mallon <rmallon@gmail.com> Cc: Tejun Heo <tj@kernel.org> Cc: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-03 21:47:51 +00:00
__set_page_locked(page);
ret = __add_to_page_cache_locked(page, mapping, offset,
gfp_mask, &shadow);
if (unlikely(ret))
__clear_page_locked(page);
else {
/*
* The page might have been evicted from cache only
* recently, in which case it should be activated like
* any other repeatedly accessed page.
*/
if (shadow && workingset_refault(shadow)) {
SetPageActive(page);
workingset_activation(page);
} else
ClearPageActive(page);
lru_cache_add(page);
}
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>
2010-05-24 21:32:08 +00:00
int n;
struct page *page;
if (cpuset_do_page_mem_spread()) {
cpuset: mm: reduce large amounts of memory barrier related damage v3 Commit c0ff7453bb5c ("cpuset,mm: fix no node to alloc memory when changing cpuset's mems") wins a super prize for the largest number of memory barriers entered into fast paths for one commit. [get|put]_mems_allowed is incredibly heavy with pairs of full memory barriers inserted into a number of hot paths. This was detected while investigating at large page allocator slowdown introduced some time after 2.6.32. The largest portion of this overhead was shown by oprofile to be at an mfence introduced by this commit into the page allocator hot path. For extra style points, the commit introduced the use of yield() in an implementation of what looks like a spinning mutex. This patch replaces the full memory barriers on both read and write sides with a sequence counter with just read barriers on the fast path side. This is much cheaper on some architectures, including x86. The main bulk of the patch is the retry logic if the nodemask changes in a manner that can cause a false failure. While updating the nodemask, a check is made to see if a false failure is a risk. If it is, the sequence number gets bumped and parallel allocators will briefly stall while the nodemask update takes place. In a page fault test microbenchmark, oprofile samples from __alloc_pages_nodemask went from 4.53% of all samples to 1.15%. The actual results were 3.3.0-rc3 3.3.0-rc3 rc3-vanilla nobarrier-v2r1 Clients 1 UserTime 0.07 ( 0.00%) 0.08 (-14.19%) Clients 2 UserTime 0.07 ( 0.00%) 0.07 ( 2.72%) Clients 4 UserTime 0.08 ( 0.00%) 0.07 ( 3.29%) Clients 1 SysTime 0.70 ( 0.00%) 0.65 ( 6.65%) Clients 2 SysTime 0.85 ( 0.00%) 0.82 ( 3.65%) Clients 4 SysTime 1.41 ( 0.00%) 1.41 ( 0.32%) Clients 1 WallTime 0.77 ( 0.00%) 0.74 ( 4.19%) Clients 2 WallTime 0.47 ( 0.00%) 0.45 ( 3.73%) Clients 4 WallTime 0.38 ( 0.00%) 0.37 ( 1.58%) Clients 1 Flt/sec/cpu 497620.28 ( 0.00%) 520294.53 ( 4.56%) Clients 2 Flt/sec/cpu 414639.05 ( 0.00%) 429882.01 ( 3.68%) Clients 4 Flt/sec/cpu 257959.16 ( 0.00%) 258761.48 ( 0.31%) Clients 1 Flt/sec 495161.39 ( 0.00%) 517292.87 ( 4.47%) Clients 2 Flt/sec 820325.95 ( 0.00%) 850289.77 ( 3.65%) Clients 4 Flt/sec 1020068.93 ( 0.00%) 1022674.06 ( 0.26%) MMTests Statistics: duration Sys Time Running Test (seconds) 135.68 132.17 User+Sys Time Running Test (seconds) 164.2 160.13 Total Elapsed Time (seconds) 123.46 120.87 The overall improvement is small but the System CPU time is much improved and roughly in correlation to what oprofile reported (these performance figures are without profiling so skew is expected). The actual number of page faults is noticeably improved. For benchmarks like kernel builds, the overall benefit is marginal but the system CPU time is slightly reduced. To test the actual bug the commit fixed I opened two terminals. The first ran within a cpuset and continually ran a small program that faulted 100M of anonymous data. In a second window, the nodemask of the cpuset was continually randomised in a loop. Without the commit, the program would fail every so often (usually within 10 seconds) and obviously with the commit everything worked fine. With this patch applied, it also worked fine so the fix should be functionally equivalent. Signed-off-by: Mel Gorman <mgorman@suse.de> Cc: Miao Xie <miaox@cn.fujitsu.com> Cc: David Rientjes <rientjes@google.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Christoph Lameter <cl@linux.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-21 23:34:11 +00:00
unsigned int cpuset_mems_cookie;
do {
cpuset_mems_cookie = read_mems_allowed_begin();
cpuset: mm: reduce large amounts of memory barrier related damage v3 Commit c0ff7453bb5c ("cpuset,mm: fix no node to alloc memory when changing cpuset's mems") wins a super prize for the largest number of memory barriers entered into fast paths for one commit. [get|put]_mems_allowed is incredibly heavy with pairs of full memory barriers inserted into a number of hot paths. This was detected while investigating at large page allocator slowdown introduced some time after 2.6.32. The largest portion of this overhead was shown by oprofile to be at an mfence introduced by this commit into the page allocator hot path. For extra style points, the commit introduced the use of yield() in an implementation of what looks like a spinning mutex. This patch replaces the full memory barriers on both read and write sides with a sequence counter with just read barriers on the fast path side. This is much cheaper on some architectures, including x86. The main bulk of the patch is the retry logic if the nodemask changes in a manner that can cause a false failure. While updating the nodemask, a check is made to see if a false failure is a risk. If it is, the sequence number gets bumped and parallel allocators will briefly stall while the nodemask update takes place. In a page fault test microbenchmark, oprofile samples from __alloc_pages_nodemask went from 4.53% of all samples to 1.15%. The actual results were 3.3.0-rc3 3.3.0-rc3 rc3-vanilla nobarrier-v2r1 Clients 1 UserTime 0.07 ( 0.00%) 0.08 (-14.19%) Clients 2 UserTime 0.07 ( 0.00%) 0.07 ( 2.72%) Clients 4 UserTime 0.08 ( 0.00%) 0.07 ( 3.29%) Clients 1 SysTime 0.70 ( 0.00%) 0.65 ( 6.65%) Clients 2 SysTime 0.85 ( 0.00%) 0.82 ( 3.65%) Clients 4 SysTime 1.41 ( 0.00%) 1.41 ( 0.32%) Clients 1 WallTime 0.77 ( 0.00%) 0.74 ( 4.19%) Clients 2 WallTime 0.47 ( 0.00%) 0.45 ( 3.73%) Clients 4 WallTime 0.38 ( 0.00%) 0.37 ( 1.58%) Clients 1 Flt/sec/cpu 497620.28 ( 0.00%) 520294.53 ( 4.56%) Clients 2 Flt/sec/cpu 414639.05 ( 0.00%) 429882.01 ( 3.68%) Clients 4 Flt/sec/cpu 257959.16 ( 0.00%) 258761.48 ( 0.31%) Clients 1 Flt/sec 495161.39 ( 0.00%) 517292.87 ( 4.47%) Clients 2 Flt/sec 820325.95 ( 0.00%) 850289.77 ( 3.65%) Clients 4 Flt/sec 1020068.93 ( 0.00%) 1022674.06 ( 0.26%) MMTests Statistics: duration Sys Time Running Test (seconds) 135.68 132.17 User+Sys Time Running Test (seconds) 164.2 160.13 Total Elapsed Time (seconds) 123.46 120.87 The overall improvement is small but the System CPU time is much improved and roughly in correlation to what oprofile reported (these performance figures are without profiling so skew is expected). The actual number of page faults is noticeably improved. For benchmarks like kernel builds, the overall benefit is marginal but the system CPU time is slightly reduced. To test the actual bug the commit fixed I opened two terminals. The first ran within a cpuset and continually ran a small program that faulted 100M of anonymous data. In a second window, the nodemask of the cpuset was continually randomised in a loop. Without the commit, the program would fail every so often (usually within 10 seconds) and obviously with the commit everything worked fine. With this patch applied, it also worked fine so the fix should be functionally equivalent. Signed-off-by: Mel Gorman <mgorman@suse.de> Cc: Miao Xie <miaox@cn.fujitsu.com> Cc: David Rientjes <rientjes@google.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Christoph Lameter <cl@linux.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-21 23:34:11 +00:00
n = cpuset_mem_spread_node();
mm: rename alloc_pages_exact_node() to __alloc_pages_node() alloc_pages_exact_node() was introduced in commit 6484eb3e2a81 ("page allocator: do not check NUMA node ID when the caller knows the node is valid") as an optimized variant of alloc_pages_node(), that doesn't fallback to current node for nid == NUMA_NO_NODE. Unfortunately the name of the function can easily suggest that the allocation is restricted to the given node and fails otherwise. In truth, the node is only preferred, unless __GFP_THISNODE is passed among the gfp flags. The misleading name has lead to mistakes in the past, see for example commits 5265047ac301 ("mm, thp: really limit transparent hugepage allocation to local node") and b360edb43f8e ("mm, mempolicy: migrate_to_node should only migrate to node"). Another issue with the name is that there's a family of alloc_pages_exact*() functions where 'exact' means exact size (instead of page order), which leads to more confusion. To prevent further mistakes, this patch effectively renames alloc_pages_exact_node() to __alloc_pages_node() to better convey that it's an optimized variant of alloc_pages_node() not intended for general usage. Both functions get described in comments. It has been also considered to really provide a convenience function for allocations restricted to a node, but the major opinion seems to be that __GFP_THISNODE already provides that functionality and we shouldn't duplicate the API needlessly. The number of users would be small anyway. Existing callers of alloc_pages_exact_node() are simply converted to call __alloc_pages_node(), with the exception of sba_alloc_coherent() which open-codes the check for NUMA_NO_NODE, so it is converted to use alloc_pages_node() instead. This means it no longer performs some VM_BUG_ON checks, and since the current check for nid in alloc_pages_node() uses a 'nid < 0' comparison (which includes NUMA_NO_NODE), it may hide wrong values which would be previously exposed. Both differences will be rectified by the next patch. To sum up, this patch makes no functional changes, except temporarily hiding potentially buggy callers. Restricting the checks in alloc_pages_node() is left for the next patch which can in turn expose more existing buggy callers. Signed-off-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: Robin Holt <robinmholt@gmail.com> Acked-by: Michal Hocko <mhocko@suse.com> Acked-by: Christoph Lameter <cl@linux.com> Acked-by: Michael Ellerman <mpe@ellerman.id.au> Cc: Mel Gorman <mgorman@suse.de> Cc: David Rientjes <rientjes@google.com> Cc: Greg Thelen <gthelen@google.com> Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Tony Luck <tony.luck@intel.com> Cc: Fenghua Yu <fenghua.yu@intel.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Gleb Natapov <gleb@kernel.org> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Cliff Whickman <cpw@sgi.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-08 22:03:50 +00:00
page = __alloc_pages_node(n, gfp, 0);
} while (!page && read_mems_allowed_retry(cpuset_mems_cookie));
cpuset: mm: reduce large amounts of memory barrier related damage v3 Commit c0ff7453bb5c ("cpuset,mm: fix no node to alloc memory when changing cpuset's mems") wins a super prize for the largest number of memory barriers entered into fast paths for one commit. [get|put]_mems_allowed is incredibly heavy with pairs of full memory barriers inserted into a number of hot paths. This was detected while investigating at large page allocator slowdown introduced some time after 2.6.32. The largest portion of this overhead was shown by oprofile to be at an mfence introduced by this commit into the page allocator hot path. For extra style points, the commit introduced the use of yield() in an implementation of what looks like a spinning mutex. This patch replaces the full memory barriers on both read and write sides with a sequence counter with just read barriers on the fast path side. This is much cheaper on some architectures, including x86. The main bulk of the patch is the retry logic if the nodemask changes in a manner that can cause a false failure. While updating the nodemask, a check is made to see if a false failure is a risk. If it is, the sequence number gets bumped and parallel allocators will briefly stall while the nodemask update takes place. In a page fault test microbenchmark, oprofile samples from __alloc_pages_nodemask went from 4.53% of all samples to 1.15%. The actual results were 3.3.0-rc3 3.3.0-rc3 rc3-vanilla nobarrier-v2r1 Clients 1 UserTime 0.07 ( 0.00%) 0.08 (-14.19%) Clients 2 UserTime 0.07 ( 0.00%) 0.07 ( 2.72%) Clients 4 UserTime 0.08 ( 0.00%) 0.07 ( 3.29%) Clients 1 SysTime 0.70 ( 0.00%) 0.65 ( 6.65%) Clients 2 SysTime 0.85 ( 0.00%) 0.82 ( 3.65%) Clients 4 SysTime 1.41 ( 0.00%) 1.41 ( 0.32%) Clients 1 WallTime 0.77 ( 0.00%) 0.74 ( 4.19%) Clients 2 WallTime 0.47 ( 0.00%) 0.45 ( 3.73%) Clients 4 WallTime 0.38 ( 0.00%) 0.37 ( 1.58%) Clients 1 Flt/sec/cpu 497620.28 ( 0.00%) 520294.53 ( 4.56%) Clients 2 Flt/sec/cpu 414639.05 ( 0.00%) 429882.01 ( 3.68%) Clients 4 Flt/sec/cpu 257959.16 ( 0.00%) 258761.48 ( 0.31%) Clients 1 Flt/sec 495161.39 ( 0.00%) 517292.87 ( 4.47%) Clients 2 Flt/sec 820325.95 ( 0.00%) 850289.77 ( 3.65%) Clients 4 Flt/sec 1020068.93 ( 0.00%) 1022674.06 ( 0.26%) MMTests Statistics: duration Sys Time Running Test (seconds) 135.68 132.17 User+Sys Time Running Test (seconds) 164.2 160.13 Total Elapsed Time (seconds) 123.46 120.87 The overall improvement is small but the System CPU time is much improved and roughly in correlation to what oprofile reported (these performance figures are without profiling so skew is expected). The actual number of page faults is noticeably improved. For benchmarks like kernel builds, the overall benefit is marginal but the system CPU time is slightly reduced. To test the actual bug the commit fixed I opened two terminals. The first ran within a cpuset and continually ran a small program that faulted 100M of anonymous data. In a second window, the nodemask of the cpuset was continually randomised in a loop. Without the commit, the program would fail every so often (usually within 10 seconds) and obviously with the commit everything worked fine. With this patch applied, it also worked fine so the fix should be functionally equivalent. Signed-off-by: Mel Gorman <mgorman@suse.de> Cc: Miao Xie <miaox@cn.fujitsu.com> Cc: David Rientjes <rientjes@google.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Christoph Lameter <cl@linux.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-21 23:34:11 +00:00
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>
2010-05-24 21:32:08 +00:00
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.
*/
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)];
}
EXPORT_SYMBOL(page_waitqueue);
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))
sched: Remove proliferation of wait_on_bit() action functions The current "wait_on_bit" interface requires an 'action' function to be provided which does the actual waiting. There are over 20 such functions, many of them identical. Most cases can be satisfied by one of just two functions, one which uses io_schedule() and one which just uses schedule(). So: Rename wait_on_bit and wait_on_bit_lock to wait_on_bit_action and wait_on_bit_lock_action to make it explicit that they need an action function. Introduce new wait_on_bit{,_lock} and wait_on_bit{,_lock}_io which are *not* given an action function but implicitly use a standard one. The decision to error-out if a signal is pending is now made based on the 'mode' argument rather than being encoded in the action function. All instances of the old wait_on_bit and wait_on_bit_lock which can use the new version have been changed accordingly and their action functions have been discarded. wait_on_bit{_lock} does not return any specific error code in the event of a signal so the caller must check for non-zero and interpolate their own error code as appropriate. The wait_on_bit() call in __fscache_wait_on_invalidate() was ambiguous as it specified TASK_UNINTERRUPTIBLE but used fscache_wait_bit_interruptible as an action function. David Howells confirms this should be uniformly "uninterruptible" The main remaining user of wait_on_bit{,_lock}_action is NFS which needs to use a freezer-aware schedule() call. A comment in fs/gfs2/glock.c notes that having multiple 'action' functions is useful as they display differently in the 'wchan' field of 'ps'. (and /proc/$PID/wchan). As the new bit_wait{,_io} functions are tagged "__sched", they will not show up at all, but something higher in the stack. So the distinction will still be visible, only with different function names (gds2_glock_wait versus gfs2_glock_dq_wait in the gfs2/glock.c case). Since first version of this patch (against 3.15) two new action functions appeared, on in NFS and one in CIFS. CIFS also now uses an action function that makes the same freezer aware schedule call as NFS. Signed-off-by: NeilBrown <neilb@suse.de> Acked-by: David Howells <dhowells@redhat.com> (fscache, keys) Acked-by: Steven Whitehouse <swhiteho@redhat.com> (gfs2) Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Steve French <sfrench@samba.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/20140707051603.28027.72349.stgit@notabene.brown Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-07-07 05:16:04 +00:00
__wait_on_bit(page_waitqueue(page), &wait, bit_wait_io,
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,
sched: Remove proliferation of wait_on_bit() action functions The current "wait_on_bit" interface requires an 'action' function to be provided which does the actual waiting. There are over 20 such functions, many of them identical. Most cases can be satisfied by one of just two functions, one which uses io_schedule() and one which just uses schedule(). So: Rename wait_on_bit and wait_on_bit_lock to wait_on_bit_action and wait_on_bit_lock_action to make it explicit that they need an action function. Introduce new wait_on_bit{,_lock} and wait_on_bit{,_lock}_io which are *not* given an action function but implicitly use a standard one. The decision to error-out if a signal is pending is now made based on the 'mode' argument rather than being encoded in the action function. All instances of the old wait_on_bit and wait_on_bit_lock which can use the new version have been changed accordingly and their action functions have been discarded. wait_on_bit{_lock} does not return any specific error code in the event of a signal so the caller must check for non-zero and interpolate their own error code as appropriate. The wait_on_bit() call in __fscache_wait_on_invalidate() was ambiguous as it specified TASK_UNINTERRUPTIBLE but used fscache_wait_bit_interruptible as an action function. David Howells confirms this should be uniformly "uninterruptible" The main remaining user of wait_on_bit{,_lock}_action is NFS which needs to use a freezer-aware schedule() call. A comment in fs/gfs2/glock.c notes that having multiple 'action' functions is useful as they display differently in the 'wchan' field of 'ps'. (and /proc/$PID/wchan). As the new bit_wait{,_io} functions are tagged "__sched", they will not show up at all, but something higher in the stack. So the distinction will still be visible, only with different function names (gds2_glock_wait versus gfs2_glock_dq_wait in the gfs2/glock.c case). Since first version of this patch (against 3.15) two new action functions appeared, on in NFS and one in CIFS. CIFS also now uses an action function that makes the same freezer aware schedule call as NFS. Signed-off-by: NeilBrown <neilb@suse.de> Acked-by: David Howells <dhowells@redhat.com> (fscache, keys) Acked-by: Steven Whitehouse <swhiteho@redhat.com> (gfs2) Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Steve French <sfrench@samba.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/20140707051603.28027.72349.stgit@notabene.brown Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-07-07 05:16:04 +00:00
bit_wait_io, TASK_KILLABLE);
}
int wait_on_page_bit_killable_timeout(struct page *page,
int bit_nr, unsigned long timeout)
{
DEFINE_WAIT_BIT(wait, &page->flags, bit_nr);
wait.key.timeout = jiffies + timeout;
if (!test_bit(bit_nr, &page->flags))
return 0;
return __wait_on_bit(page_waitqueue(page), &wait,
bit_wait_io_timeout, TASK_KILLABLE);
}
EXPORT_SYMBOL_GPL(wait_on_page_bit_killable_timeout);
/**
* 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
* mechanism 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_PAGE(!PageLocked(page), page);
clear_bit_unlock(PG_locked, &page->flags);
smp_mb__after_atomic();
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)
{
/*
* TestClearPageReclaim could be used here but it is an atomic
* operation and overkill in this particular case. Failing to
* shuffle a page marked for immediate reclaim is too mild to
* justify taking an atomic operation penalty at the end of
* ever page writeback.
*/
if (PageReclaim(page)) {
ClearPageReclaim(page);
rotate_reclaimable_page(page);
}
if (!test_clear_page_writeback(page))
BUG();
smp_mb__after_atomic();
wake_up_page(page, PG_writeback);
}
EXPORT_SYMBOL(end_page_writeback);
/*
* After completing I/O on a page, call this routine to update the page
* flags appropriately
*/
void page_endio(struct page *page, int rw, int err)
{
if (rw == READ) {
if (!err) {
SetPageUptodate(page);
} else {
ClearPageUptodate(page);
SetPageError(page);
}
unlock_page(page);
} else { /* rw == WRITE */
if (err) {
SetPageError(page);
if (page->mapping)
mapping_set_error(page->mapping, err);
}
end_page_writeback(page);
}
}
EXPORT_SYMBOL_GPL(page_endio);
/**
* __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);
sched: Remove proliferation of wait_on_bit() action functions The current "wait_on_bit" interface requires an 'action' function to be provided which does the actual waiting. There are over 20 such functions, many of them identical. Most cases can be satisfied by one of just two functions, one which uses io_schedule() and one which just uses schedule(). So: Rename wait_on_bit and wait_on_bit_lock to wait_on_bit_action and wait_on_bit_lock_action to make it explicit that they need an action function. Introduce new wait_on_bit{,_lock} and wait_on_bit{,_lock}_io which are *not* given an action function but implicitly use a standard one. The decision to error-out if a signal is pending is now made based on the 'mode' argument rather than being encoded in the action function. All instances of the old wait_on_bit and wait_on_bit_lock which can use the new version have been changed accordingly and their action functions have been discarded. wait_on_bit{_lock} does not return any specific error code in the event of a signal so the caller must check for non-zero and interpolate their own error code as appropriate. The wait_on_bit() call in __fscache_wait_on_invalidate() was ambiguous as it specified TASK_UNINTERRUPTIBLE but used fscache_wait_bit_interruptible as an action function. David Howells confirms this should be uniformly "uninterruptible" The main remaining user of wait_on_bit{,_lock}_action is NFS which needs to use a freezer-aware schedule() call. A comment in fs/gfs2/glock.c notes that having multiple 'action' functions is useful as they display differently in the 'wchan' field of 'ps'. (and /proc/$PID/wchan). As the new bit_wait{,_io} functions are tagged "__sched", they will not show up at all, but something higher in the stack. So the distinction will still be visible, only with different function names (gds2_glock_wait versus gfs2_glock_dq_wait in the gfs2/glock.c case). Since first version of this patch (against 3.15) two new action functions appeared, on in NFS and one in CIFS. CIFS also now uses an action function that makes the same freezer aware schedule call as NFS. Signed-off-by: NeilBrown <neilb@suse.de> Acked-by: David Howells <dhowells@redhat.com> (fscache, keys) Acked-by: Steven Whitehouse <swhiteho@redhat.com> (gfs2) Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Steve French <sfrench@samba.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/20140707051603.28027.72349.stgit@notabene.brown Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-07-07 05:16:04 +00:00
__wait_on_bit_lock(page_waitqueue(page), &wait, bit_wait_io,
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,
sched: Remove proliferation of wait_on_bit() action functions The current "wait_on_bit" interface requires an 'action' function to be provided which does the actual waiting. There are over 20 such functions, many of them identical. Most cases can be satisfied by one of just two functions, one which uses io_schedule() and one which just uses schedule(). So: Rename wait_on_bit and wait_on_bit_lock to wait_on_bit_action and wait_on_bit_lock_action to make it explicit that they need an action function. Introduce new wait_on_bit{,_lock} and wait_on_bit{,_lock}_io which are *not* given an action function but implicitly use a standard one. The decision to error-out if a signal is pending is now made based on the 'mode' argument rather than being encoded in the action function. All instances of the old wait_on_bit and wait_on_bit_lock which can use the new version have been changed accordingly and their action functions have been discarded. wait_on_bit{_lock} does not return any specific error code in the event of a signal so the caller must check for non-zero and interpolate their own error code as appropriate. The wait_on_bit() call in __fscache_wait_on_invalidate() was ambiguous as it specified TASK_UNINTERRUPTIBLE but used fscache_wait_bit_interruptible as an action function. David Howells confirms this should be uniformly "uninterruptible" The main remaining user of wait_on_bit{,_lock}_action is NFS which needs to use a freezer-aware schedule() call. A comment in fs/gfs2/glock.c notes that having multiple 'action' functions is useful as they display differently in the 'wchan' field of 'ps'. (and /proc/$PID/wchan). As the new bit_wait{,_io} functions are tagged "__sched", they will not show up at all, but something higher in the stack. So the distinction will still be visible, only with different function names (gds2_glock_wait versus gfs2_glock_dq_wait in the gfs2/glock.c case). Since first version of this patch (against 3.15) two new action functions appeared, on in NFS and one in CIFS. CIFS also now uses an action function that makes the same freezer aware schedule call as NFS. Signed-off-by: NeilBrown <neilb@suse.de> Acked-by: David Howells <dhowells@redhat.com> (fscache, keys) Acked-by: Steven Whitehouse <swhiteho@redhat.com> (gfs2) Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Steve French <sfrench@samba.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/20140707051603.28027.72349.stgit@notabene.brown Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-07-07 05:16:04 +00:00
bit_wait_io, TASK_KILLABLE);
}
EXPORT_SYMBOL_GPL(__lock_page_killable);
/*
* Return values:
* 1 - page is locked; mmap_sem is still held.
* 0 - page is not locked.
* mmap_sem has been released (up_read()), unless flags had both
* FAULT_FLAG_ALLOW_RETRY and FAULT_FLAG_RETRY_NOWAIT set, in
* which case mmap_sem is still held.
*
* If neither ALLOW_RETRY nor KILLABLE are set, will always return 1
* with the page locked and the mmap_sem unperturbed.
*/
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>
2010-10-26 21:21:57 +00:00
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>
2010-10-26 21:21:57 +00:00
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>
2010-10-26 21:21:57 +00:00
}
}
mm: filemap: move radix tree hole searching here The radix tree hole searching code is only used for page cache, for example the readahead code trying to get a a picture of the area surrounding a fault. It sufficed to rely on the radix tree definition of holes, which is "empty tree slot". But this is about to change, though, as shadow page descriptors will be stored in the page cache after the actual pages get evicted from memory. Move the functions over to mm/filemap.c and make them native page cache operations, where they can later be adapted to handle the new definition of "page cache hole". Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Rik van Riel <riel@redhat.com> Reviewed-by: Minchan Kim <minchan@kernel.org> Acked-by: Mel Gorman <mgorman@suse.de> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Bob Liu <bob.liu@oracle.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Dave Chinner <david@fromorbit.com> Cc: Greg Thelen <gthelen@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jan Kara <jack@suse.cz> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Luigi Semenzato <semenzato@google.com> Cc: Metin Doslu <metin@citusdata.com> Cc: Michel Lespinasse <walken@google.com> Cc: Ozgun Erdogan <ozgun@citusdata.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Roman Gushchin <klamm@yandex-team.ru> Cc: Ryan Mallon <rmallon@gmail.com> Cc: Tejun Heo <tj@kernel.org> Cc: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-03 21:47:44 +00:00
/**
* page_cache_next_hole - find the next hole (not-present entry)
* @mapping: mapping
* @index: index
* @max_scan: maximum range to search
*
* Search the set [index, min(index+max_scan-1, MAX_INDEX)] for the
* lowest indexed hole.
*
* Returns: the index of the hole if found, otherwise returns an index
* outside of the set specified (in which case 'return - index >=
* max_scan' will be true). In rare cases of index wrap-around, 0 will
* be returned.
*
* page_cache_next_hole may be called under rcu_read_lock. However,
* like radix_tree_gang_lookup, this will not atomically search a
* snapshot of the tree at a single point in time. For example, if a
* hole is created at index 5, then subsequently a hole is created at
* index 10, page_cache_next_hole covering both indexes may return 10
* if called under rcu_read_lock.
*/
pgoff_t page_cache_next_hole(struct address_space *mapping,
pgoff_t index, unsigned long max_scan)
{
unsigned long i;
for (i = 0; i < max_scan; i++) {
2014-04-03 21:47:46 +00:00
struct page *page;
page = radix_tree_lookup(&mapping->page_tree, index);
if (!page || radix_tree_exceptional_entry(page))
mm: filemap: move radix tree hole searching here The radix tree hole searching code is only used for page cache, for example the readahead code trying to get a a picture of the area surrounding a fault. It sufficed to rely on the radix tree definition of holes, which is "empty tree slot". But this is about to change, though, as shadow page descriptors will be stored in the page cache after the actual pages get evicted from memory. Move the functions over to mm/filemap.c and make them native page cache operations, where they can later be adapted to handle the new definition of "page cache hole". Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Rik van Riel <riel@redhat.com> Reviewed-by: Minchan Kim <minchan@kernel.org> Acked-by: Mel Gorman <mgorman@suse.de> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Bob Liu <bob.liu@oracle.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Dave Chinner <david@fromorbit.com> Cc: Greg Thelen <gthelen@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jan Kara <jack@suse.cz> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Luigi Semenzato <semenzato@google.com> Cc: Metin Doslu <metin@citusdata.com> Cc: Michel Lespinasse <walken@google.com> Cc: Ozgun Erdogan <ozgun@citusdata.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Roman Gushchin <klamm@yandex-team.ru> Cc: Ryan Mallon <rmallon@gmail.com> Cc: Tejun Heo <tj@kernel.org> Cc: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-03 21:47:44 +00:00
break;
index++;
if (index == 0)
break;
}
return index;
}
EXPORT_SYMBOL(page_cache_next_hole);
/**
* page_cache_prev_hole - find the prev hole (not-present entry)
* @mapping: mapping
* @index: index
* @max_scan: maximum range to search
*
* Search backwards in the range [max(index-max_scan+1, 0), index] for
* the first hole.
*
* Returns: the index of the hole if found, otherwise returns an index
* outside of the set specified (in which case 'index - return >=
* max_scan' will be true). In rare cases of wrap-around, ULONG_MAX
* will be returned.
*
* page_cache_prev_hole may be called under rcu_read_lock. However,
* like radix_tree_gang_lookup, this will not atomically search a
* snapshot of the tree at a single point in time. For example, if a
* hole is created at index 10, then subsequently a hole is created at
* index 5, page_cache_prev_hole covering both indexes may return 5 if
* called under rcu_read_lock.
*/
pgoff_t page_cache_prev_hole(struct address_space *mapping,
pgoff_t index, unsigned long max_scan)
{
unsigned long i;
for (i = 0; i < max_scan; i++) {
2014-04-03 21:47:46 +00:00
struct page *page;
page = radix_tree_lookup(&mapping->page_tree, index);
if (!page || radix_tree_exceptional_entry(page))
mm: filemap: move radix tree hole searching here The radix tree hole searching code is only used for page cache, for example the readahead code trying to get a a picture of the area surrounding a fault. It sufficed to rely on the radix tree definition of holes, which is "empty tree slot". But this is about to change, though, as shadow page descriptors will be stored in the page cache after the actual pages get evicted from memory. Move the functions over to mm/filemap.c and make them native page cache operations, where they can later be adapted to handle the new definition of "page cache hole". Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Rik van Riel <riel@redhat.com> Reviewed-by: Minchan Kim <minchan@kernel.org> Acked-by: Mel Gorman <mgorman@suse.de> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Bob Liu <bob.liu@oracle.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Dave Chinner <david@fromorbit.com> Cc: Greg Thelen <gthelen@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jan Kara <jack@suse.cz> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Luigi Semenzato <semenzato@google.com> Cc: Metin Doslu <metin@citusdata.com> Cc: Michel Lespinasse <walken@google.com> Cc: Ozgun Erdogan <ozgun@citusdata.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Roman Gushchin <klamm@yandex-team.ru> Cc: Ryan Mallon <rmallon@gmail.com> Cc: Tejun Heo <tj@kernel.org> Cc: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-03 21:47:44 +00:00
break;
index--;
if (index == ULONG_MAX)
break;
}
return index;
}
EXPORT_SYMBOL(page_cache_prev_hole);
/**
2014-04-03 21:47:46 +00:00
* find_get_entry - find and get a page cache entry
* @mapping: the address_space to search
2014-04-03 21:47:46 +00:00
* @offset: the page cache index
*
* Looks up the page cache slot at @mapping & @offset. If there is a
* page cache page, it is returned with an increased refcount.
*
mm: filemap: update find_get_pages_tag() to deal with shadow entries Dave Jones reports the following crash when find_get_pages_tag() runs into an exceptional entry: kernel BUG at mm/filemap.c:1347! RIP: find_get_pages_tag+0x1cb/0x220 Call Trace: find_get_pages_tag+0x36/0x220 pagevec_lookup_tag+0x21/0x30 filemap_fdatawait_range+0xbe/0x1e0 filemap_fdatawait+0x27/0x30 sync_inodes_sb+0x204/0x2a0 sync_inodes_one_sb+0x19/0x20 iterate_supers+0xb2/0x110 sys_sync+0x44/0xb0 ia32_do_call+0x13/0x13 1343 /* 1344 * This function is never used on a shmem/tmpfs 1345 * mapping, so a swap entry won't be found here. 1346 */ 1347 BUG(); After commit 0cd6144aadd2 ("mm + fs: prepare for non-page entries in page cache radix trees") this comment and BUG() are out of date because exceptional entries can now appear in all mappings - as shadows of recently evicted pages. However, as Hugh Dickins notes, "it is truly surprising for a PAGECACHE_TAG_WRITEBACK (and probably any other PAGECACHE_TAG_*) to appear on an exceptional entry. I expect it comes down to an occasional race in RCU lookup of the radix_tree: lacking absolute synchronization, we might sometimes catch an exceptional entry, with the tag which really belongs with the unexceptional entry which was there an instant before." And indeed, not only is the tree walk lockless, the tags are also read in chunks, one radix tree node at a time. There is plenty of time for page reclaim to swoop in and replace a page that was already looked up as tagged with a shadow entry. Remove the BUG() and update the comment. While reviewing all other lookup sites for whether they properly deal with shadow entries of evicted pages, update all the comments and fix memcg file charge moving to not miss shmem/tmpfs swapcache pages. Fixes: 0cd6144aadd2 ("mm + fs: prepare for non-page entries in page cache radix trees") Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reported-by: Dave Jones <davej@redhat.com> Acked-by: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-05-06 19:50:05 +00:00
* If the slot holds a shadow entry of a previously evicted page, or a
* swap entry from shmem/tmpfs, it is returned.
2014-04-03 21:47:46 +00:00
*
* Otherwise, %NULL is returned.
*/
2014-04-03 21:47:46 +00:00
struct page *find_get_entry(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;
mm: let swap use exceptional entries If swap entries are to be stored along with struct page pointers in a radix tree, they need to be distinguished as exceptional entries. Most of the handling of swap entries in radix tree will be contained in shmem.c, but a few functions in filemap.c's common code need to check for their appearance: find_get_page(), find_lock_page(), find_get_pages() and find_get_pages_contig(). So as not to slow their fast paths, tuck those checks inside the existing checks for unlikely radix_tree_deref_slot(); except for find_lock_page(), where it is an added test. And make it a BUG in find_get_pages_tag(), which is not applied to tmpfs files. A part of the reason for eliminating shmem_readpage() earlier, was to minimize the places where common code would need to allow for swap entries. The swp_entry_t known to swapfile.c must be massaged into a slightly different form when stored in the radix tree, just as it gets massaged into a pte_t when stored in page tables. In an i386 kernel this limits its information (type and page offset) to 30 bits: given 32 "types" of swapfile and 4kB pagesize, that's a maximum swapfile size of 128GB. Which is less than the 512GB we previously allowed with X86_PAE (where the swap entry can occupy the entire upper 32 bits of a pte_t), but not a new limitation on 32-bit without PAE; and there's not a new limitation on 64-bit (where swap filesize is already limited to 16TB by a 32-bit page offset). Thirty areas of 128GB is probably still enough swap for a 64GB 32-bit machine. Provide swp_to_radix_entry() and radix_to_swp_entry() conversions, and enforce filesize limit in read_swap_header(), just as for ptes. Signed-off-by: Hugh Dickins <hughd@google.com> Acked-by: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-08-03 23:21:19 +00:00
if (radix_tree_exception(page)) {
if (radix_tree_deref_retry(page))
goto repeat;
/*
mm: filemap: update find_get_pages_tag() to deal with shadow entries Dave Jones reports the following crash when find_get_pages_tag() runs into an exceptional entry: kernel BUG at mm/filemap.c:1347! RIP: find_get_pages_tag+0x1cb/0x220 Call Trace: find_get_pages_tag+0x36/0x220 pagevec_lookup_tag+0x21/0x30 filemap_fdatawait_range+0xbe/0x1e0 filemap_fdatawait+0x27/0x30 sync_inodes_sb+0x204/0x2a0 sync_inodes_one_sb+0x19/0x20 iterate_supers+0xb2/0x110 sys_sync+0x44/0xb0 ia32_do_call+0x13/0x13 1343 /* 1344 * This function is never used on a shmem/tmpfs 1345 * mapping, so a swap entry won't be found here. 1346 */ 1347 BUG(); After commit 0cd6144aadd2 ("mm + fs: prepare for non-page entries in page cache radix trees") this comment and BUG() are out of date because exceptional entries can now appear in all mappings - as shadows of recently evicted pages. However, as Hugh Dickins notes, "it is truly surprising for a PAGECACHE_TAG_WRITEBACK (and probably any other PAGECACHE_TAG_*) to appear on an exceptional entry. I expect it comes down to an occasional race in RCU lookup of the radix_tree: lacking absolute synchronization, we might sometimes catch an exceptional entry, with the tag which really belongs with the unexceptional entry which was there an instant before." And indeed, not only is the tree walk lockless, the tags are also read in chunks, one radix tree node at a time. There is plenty of time for page reclaim to swoop in and replace a page that was already looked up as tagged with a shadow entry. Remove the BUG() and update the comment. While reviewing all other lookup sites for whether they properly deal with shadow entries of evicted pages, update all the comments and fix memcg file charge moving to not miss shmem/tmpfs swapcache pages. Fixes: 0cd6144aadd2 ("mm + fs: prepare for non-page entries in page cache radix trees") Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reported-by: Dave Jones <davej@redhat.com> Acked-by: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-05-06 19:50:05 +00:00
* A shadow entry of a recently evicted page,
* or a swap entry from shmem/tmpfs. Return
* it without attempting to raise page count.
*/
goto out;
mm: let swap use exceptional entries If swap entries are to be stored along with struct page pointers in a radix tree, they need to be distinguished as exceptional entries. Most of the handling of swap entries in radix tree will be contained in shmem.c, but a few functions in filemap.c's common code need to check for their appearance: find_get_page(), find_lock_page(), find_get_pages() and find_get_pages_contig(). So as not to slow their fast paths, tuck those checks inside the existing checks for unlikely radix_tree_deref_slot(); except for find_lock_page(), where it is an added test. And make it a BUG in find_get_pages_tag(), which is not applied to tmpfs files. A part of the reason for eliminating shmem_readpage() earlier, was to minimize the places where common code would need to allow for swap entries. The swp_entry_t known to swapfile.c must be massaged into a slightly different form when stored in the radix tree, just as it gets massaged into a pte_t when stored in page tables. In an i386 kernel this limits its information (type and page offset) to 30 bits: given 32 "types" of swapfile and 4kB pagesize, that's a maximum swapfile size of 128GB. Which is less than the 512GB we previously allowed with X86_PAE (where the swap entry can occupy the entire upper 32 bits of a pte_t), but not a new limitation on 32-bit without PAE; and there's not a new limitation on 64-bit (where swap filesize is already limited to 16TB by a 32-bit page offset). Thirty areas of 128GB is probably still enough swap for a 64GB 32-bit machine. Provide swp_to_radix_entry() and radix_to_swp_entry() conversions, and enforce filesize limit in read_swap_header(), just as for ptes. Signed-off-by: Hugh Dickins <hughd@google.com> Acked-by: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-08-03 23:21:19 +00:00
}
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;
}
2014-04-03 21:47:46 +00:00
EXPORT_SYMBOL(find_get_entry);
2014-04-03 21:47:46 +00:00
/**
* find_lock_entry - locate, pin and lock a page cache entry
* @mapping: the address_space to search
* @offset: the page cache index
*
* Looks up the page cache slot at @mapping & @offset. If there is a
* page cache page, it is returned locked and with an increased
* refcount.
*
mm: filemap: update find_get_pages_tag() to deal with shadow entries Dave Jones reports the following crash when find_get_pages_tag() runs into an exceptional entry: kernel BUG at mm/filemap.c:1347! RIP: find_get_pages_tag+0x1cb/0x220 Call Trace: find_get_pages_tag+0x36/0x220 pagevec_lookup_tag+0x21/0x30 filemap_fdatawait_range+0xbe/0x1e0 filemap_fdatawait+0x27/0x30 sync_inodes_sb+0x204/0x2a0 sync_inodes_one_sb+0x19/0x20 iterate_supers+0xb2/0x110 sys_sync+0x44/0xb0 ia32_do_call+0x13/0x13 1343 /* 1344 * This function is never used on a shmem/tmpfs 1345 * mapping, so a swap entry won't be found here. 1346 */ 1347 BUG(); After commit 0cd6144aadd2 ("mm + fs: prepare for non-page entries in page cache radix trees") this comment and BUG() are out of date because exceptional entries can now appear in all mappings - as shadows of recently evicted pages. However, as Hugh Dickins notes, "it is truly surprising for a PAGECACHE_TAG_WRITEBACK (and probably any other PAGECACHE_TAG_*) to appear on an exceptional entry. I expect it comes down to an occasional race in RCU lookup of the radix_tree: lacking absolute synchronization, we might sometimes catch an exceptional entry, with the tag which really belongs with the unexceptional entry which was there an instant before." And indeed, not only is the tree walk lockless, the tags are also read in chunks, one radix tree node at a time. There is plenty of time for page reclaim to swoop in and replace a page that was already looked up as tagged with a shadow entry. Remove the BUG() and update the comment. While reviewing all other lookup sites for whether they properly deal with shadow entries of evicted pages, update all the comments and fix memcg file charge moving to not miss shmem/tmpfs swapcache pages. Fixes: 0cd6144aadd2 ("mm + fs: prepare for non-page entries in page cache radix trees") Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reported-by: Dave Jones <davej@redhat.com> Acked-by: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-05-06 19:50:05 +00:00
* If the slot holds a shadow entry of a previously evicted page, or a
* swap entry from shmem/tmpfs, it is returned.
2014-04-03 21:47:46 +00:00
*
* Otherwise, %NULL is returned.
*
* find_lock_entry() may sleep.
*/
struct page *find_lock_entry(struct address_space *mapping, pgoff_t offset)
{
struct page *page;
repeat:
2014-04-03 21:47:46 +00:00
page = find_get_entry(mapping, offset);
mm: let swap use exceptional entries If swap entries are to be stored along with struct page pointers in a radix tree, they need to be distinguished as exceptional entries. Most of the handling of swap entries in radix tree will be contained in shmem.c, but a few functions in filemap.c's common code need to check for their appearance: find_get_page(), find_lock_page(), find_get_pages() and find_get_pages_contig(). So as not to slow their fast paths, tuck those checks inside the existing checks for unlikely radix_tree_deref_slot(); except for find_lock_page(), where it is an added test. And make it a BUG in find_get_pages_tag(), which is not applied to tmpfs files. A part of the reason for eliminating shmem_readpage() earlier, was to minimize the places where common code would need to allow for swap entries. The swp_entry_t known to swapfile.c must be massaged into a slightly different form when stored in the radix tree, just as it gets massaged into a pte_t when stored in page tables. In an i386 kernel this limits its information (type and page offset) to 30 bits: given 32 "types" of swapfile and 4kB pagesize, that's a maximum swapfile size of 128GB. Which is less than the 512GB we previously allowed with X86_PAE (where the swap entry can occupy the entire upper 32 bits of a pte_t), but not a new limitation on 32-bit without PAE; and there's not a new limitation on 64-bit (where swap filesize is already limited to 16TB by a 32-bit page offset). Thirty areas of 128GB is probably still enough swap for a 64GB 32-bit machine. Provide swp_to_radix_entry() and radix_to_swp_entry() conversions, and enforce filesize limit in read_swap_header(), just as for ptes. Signed-off-by: Hugh Dickins <hughd@google.com> Acked-by: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-08-03 23:21:19 +00:00
if (page && !radix_tree_exception(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(page->index != offset, page);
}
return page;
}
2014-04-03 21:47:46 +00:00
EXPORT_SYMBOL(find_lock_entry);
/**
mm: non-atomically mark page accessed during page cache allocation where possible aops->write_begin may allocate a new page and make it visible only to have mark_page_accessed called almost immediately after. Once the page is visible the atomic operations are necessary which is noticable overhead when writing to an in-memory filesystem like tmpfs but should also be noticable with fast storage. The objective of the patch is to initialse the accessed information with non-atomic operations before the page is visible. The bulk of filesystems directly or indirectly use grab_cache_page_write_begin or find_or_create_page for the initial allocation of a page cache page. This patch adds an init_page_accessed() helper which behaves like the first call to mark_page_accessed() but may called before the page is visible and can be done non-atomically. The primary APIs of concern in this care are the following and are used by most filesystems. find_get_page find_lock_page find_or_create_page grab_cache_page_nowait grab_cache_page_write_begin All of them are very similar in detail to the patch creates a core helper pagecache_get_page() which takes a flags parameter that affects its behavior such as whether the page should be marked accessed or not. Then old API is preserved but is basically a thin wrapper around this core function. Each of the filesystems are then updated to avoid calling mark_page_accessed when it is known that the VM interfaces have already done the job. There is a slight snag in that the timing of the mark_page_accessed() has now changed so in rare cases it's possible a page gets to the end of the LRU as PageReferenced where as previously it might have been repromoted. This is expected to be rare but it's worth the filesystem people thinking about it in case they see a problem with the timing change. It is also the case that some filesystems may be marking pages accessed that previously did not but it makes sense that filesystems have consistent behaviour in this regard. The test case used to evaulate this is a simple dd of a large file done multiple times with the file deleted on each iterations. The size of the file is 1/10th physical memory to avoid dirty page balancing. In the async case it will be possible that the workload completes without even hitting the disk and will have variable results but highlight the impact of mark_page_accessed for async IO. The sync results are expected to be more stable. The exception is tmpfs where the normal case is for the "IO" to not hit the disk. The test machine was single socket and UMA to avoid any scheduling or NUMA artifacts. Throughput and wall times are presented for sync IO, only wall times are shown for async as the granularity reported by dd and the variability is unsuitable for comparison. As async results were variable do to writback timings, I'm only reporting the maximum figures. The sync results were stable enough to make the mean and stddev uninteresting. The performance results are reported based on a run with no profiling. Profile data is based on a separate run with oprofile running. async dd 3.15.0-rc3 3.15.0-rc3 vanilla accessed-v2 ext3 Max elapsed 13.9900 ( 0.00%) 11.5900 ( 17.16%) tmpfs Max elapsed 0.5100 ( 0.00%) 0.4900 ( 3.92%) btrfs Max elapsed 12.8100 ( 0.00%) 12.7800 ( 0.23%) ext4 Max elapsed 18.6000 ( 0.00%) 13.3400 ( 28.28%) xfs Max elapsed 12.5600 ( 0.00%) 2.0900 ( 83.36%) The XFS figure is a bit strange as it managed to avoid a worst case by sheer luck but the average figures looked reasonable. samples percentage ext3 86107 0.9783 vmlinux-3.15.0-rc4-vanilla mark_page_accessed ext3 23833 0.2710 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed ext3 5036 0.0573 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed ext4 64566 0.8961 vmlinux-3.15.0-rc4-vanilla mark_page_accessed ext4 5322 0.0713 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed ext4 2869 0.0384 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed xfs 62126 1.7675 vmlinux-3.15.0-rc4-vanilla mark_page_accessed xfs 1904 0.0554 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed xfs 103 0.0030 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed btrfs 10655 0.1338 vmlinux-3.15.0-rc4-vanilla mark_page_accessed btrfs 2020 0.0273 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed btrfs 587 0.0079 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed tmpfs 59562 3.2628 vmlinux-3.15.0-rc4-vanilla mark_page_accessed tmpfs 1210 0.0696 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed tmpfs 94 0.0054 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed [akpm@linux-foundation.org: don't run init_page_accessed() against an uninitialised pointer] Signed-off-by: Mel Gorman <mgorman@suse.de> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Jan Kara <jack@suse.cz> Cc: Michal Hocko <mhocko@suse.cz> Cc: Hugh Dickins <hughd@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Theodore Ts'o <tytso@mit.edu> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Tested-by: Prabhakar Lad <prabhakar.csengg@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-06-04 23:10:31 +00:00
* pagecache_get_page - find and get a page reference
2014-04-03 21:47:46 +00:00
* @mapping: the address_space to search
* @offset: the page index
mm: non-atomically mark page accessed during page cache allocation where possible aops->write_begin may allocate a new page and make it visible only to have mark_page_accessed called almost immediately after. Once the page is visible the atomic operations are necessary which is noticable overhead when writing to an in-memory filesystem like tmpfs but should also be noticable with fast storage. The objective of the patch is to initialse the accessed information with non-atomic operations before the page is visible. The bulk of filesystems directly or indirectly use grab_cache_page_write_begin or find_or_create_page for the initial allocation of a page cache page. This patch adds an init_page_accessed() helper which behaves like the first call to mark_page_accessed() but may called before the page is visible and can be done non-atomically. The primary APIs of concern in this care are the following and are used by most filesystems. find_get_page find_lock_page find_or_create_page grab_cache_page_nowait grab_cache_page_write_begin All of them are very similar in detail to the patch creates a core helper pagecache_get_page() which takes a flags parameter that affects its behavior such as whether the page should be marked accessed or not. Then old API is preserved but is basically a thin wrapper around this core function. Each of the filesystems are then updated to avoid calling mark_page_accessed when it is known that the VM interfaces have already done the job. There is a slight snag in that the timing of the mark_page_accessed() has now changed so in rare cases it's possible a page gets to the end of the LRU as PageReferenced where as previously it might have been repromoted. This is expected to be rare but it's worth the filesystem people thinking about it in case they see a problem with the timing change. It is also the case that some filesystems may be marking pages accessed that previously did not but it makes sense that filesystems have consistent behaviour in this regard. The test case used to evaulate this is a simple dd of a large file done multiple times with the file deleted on each iterations. The size of the file is 1/10th physical memory to avoid dirty page balancing. In the async case it will be possible that the workload completes without even hitting the disk and will have variable results but highlight the impact of mark_page_accessed for async IO. The sync results are expected to be more stable. The exception is tmpfs where the normal case is for the "IO" to not hit the disk. The test machine was single socket and UMA to avoid any scheduling or NUMA artifacts. Throughput and wall times are presented for sync IO, only wall times are shown for async as the granularity reported by dd and the variability is unsuitable for comparison. As async results were variable do to writback timings, I'm only reporting the maximum figures. The sync results were stable enough to make the mean and stddev uninteresting. The performance results are reported based on a run with no profiling. Profile data is based on a separate run with oprofile running. async dd 3.15.0-rc3 3.15.0-rc3 vanilla accessed-v2 ext3 Max elapsed 13.9900 ( 0.00%) 11.5900 ( 17.16%) tmpfs Max elapsed 0.5100 ( 0.00%) 0.4900 ( 3.92%) btrfs Max elapsed 12.8100 ( 0.00%) 12.7800 ( 0.23%) ext4 Max elapsed 18.6000 ( 0.00%) 13.3400 ( 28.28%) xfs Max elapsed 12.5600 ( 0.00%) 2.0900 ( 83.36%) The XFS figure is a bit strange as it managed to avoid a worst case by sheer luck but the average figures looked reasonable. samples percentage ext3 86107 0.9783 vmlinux-3.15.0-rc4-vanilla mark_page_accessed ext3 23833 0.2710 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed ext3 5036 0.0573 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed ext4 64566 0.8961 vmlinux-3.15.0-rc4-vanilla mark_page_accessed ext4 5322 0.0713 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed ext4 2869 0.0384 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed xfs 62126 1.7675 vmlinux-3.15.0-rc4-vanilla mark_page_accessed xfs 1904 0.0554 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed xfs 103 0.0030 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed btrfs 10655 0.1338 vmlinux-3.15.0-rc4-vanilla mark_page_accessed btrfs 2020 0.0273 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed btrfs 587 0.0079 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed tmpfs 59562 3.2628 vmlinux-3.15.0-rc4-vanilla mark_page_accessed tmpfs 1210 0.0696 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed tmpfs 94 0.0054 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed [akpm@linux-foundation.org: don't run init_page_accessed() against an uninitialised pointer] Signed-off-by: Mel Gorman <mgorman@suse.de> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Jan Kara <jack@suse.cz> Cc: Michal Hocko <mhocko@suse.cz> Cc: Hugh Dickins <hughd@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Theodore Ts'o <tytso@mit.edu> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Tested-by: Prabhakar Lad <prabhakar.csengg@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-06-04 23:10:31 +00:00
* @fgp_flags: PCG flags
* @gfp_mask: gfp mask to use for the page cache data page allocation
2014-04-03 21:47:46 +00:00
*
mm: non-atomically mark page accessed during page cache allocation where possible aops->write_begin may allocate a new page and make it visible only to have mark_page_accessed called almost immediately after. Once the page is visible the atomic operations are necessary which is noticable overhead when writing to an in-memory filesystem like tmpfs but should also be noticable with fast storage. The objective of the patch is to initialse the accessed information with non-atomic operations before the page is visible. The bulk of filesystems directly or indirectly use grab_cache_page_write_begin or find_or_create_page for the initial allocation of a page cache page. This patch adds an init_page_accessed() helper which behaves like the first call to mark_page_accessed() but may called before the page is visible and can be done non-atomically. The primary APIs of concern in this care are the following and are used by most filesystems. find_get_page find_lock_page find_or_create_page grab_cache_page_nowait grab_cache_page_write_begin All of them are very similar in detail to the patch creates a core helper pagecache_get_page() which takes a flags parameter that affects its behavior such as whether the page should be marked accessed or not. Then old API is preserved but is basically a thin wrapper around this core function. Each of the filesystems are then updated to avoid calling mark_page_accessed when it is known that the VM interfaces have already done the job. There is a slight snag in that the timing of the mark_page_accessed() has now changed so in rare cases it's possible a page gets to the end of the LRU as PageReferenced where as previously it might have been repromoted. This is expected to be rare but it's worth the filesystem people thinking about it in case they see a problem with the timing change. It is also the case that some filesystems may be marking pages accessed that previously did not but it makes sense that filesystems have consistent behaviour in this regard. The test case used to evaulate this is a simple dd of a large file done multiple times with the file deleted on each iterations. The size of the file is 1/10th physical memory to avoid dirty page balancing. In the async case it will be possible that the workload completes without even hitting the disk and will have variable results but highlight the impact of mark_page_accessed for async IO. The sync results are expected to be more stable. The exception is tmpfs where the normal case is for the "IO" to not hit the disk. The test machine was single socket and UMA to avoid any scheduling or NUMA artifacts. Throughput and wall times are presented for sync IO, only wall times are shown for async as the granularity reported by dd and the variability is unsuitable for comparison. As async results were variable do to writback timings, I'm only reporting the maximum figures. The sync results were stable enough to make the mean and stddev uninteresting. The performance results are reported based on a run with no profiling. Profile data is based on a separate run with oprofile running. async dd 3.15.0-rc3 3.15.0-rc3 vanilla accessed-v2 ext3 Max elapsed 13.9900 ( 0.00%) 11.5900 ( 17.16%) tmpfs Max elapsed 0.5100 ( 0.00%) 0.4900 ( 3.92%) btrfs Max elapsed 12.8100 ( 0.00%) 12.7800 ( 0.23%) ext4 Max elapsed 18.6000 ( 0.00%) 13.3400 ( 28.28%) xfs Max elapsed 12.5600 ( 0.00%) 2.0900 ( 83.36%) The XFS figure is a bit strange as it managed to avoid a worst case by sheer luck but the average figures looked reasonable. samples percentage ext3 86107 0.9783 vmlinux-3.15.0-rc4-vanilla mark_page_accessed ext3 23833 0.2710 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed ext3 5036 0.0573 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed ext4 64566 0.8961 vmlinux-3.15.0-rc4-vanilla mark_page_accessed ext4 5322 0.0713 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed ext4 2869 0.0384 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed xfs 62126 1.7675 vmlinux-3.15.0-rc4-vanilla mark_page_accessed xfs 1904 0.0554 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed xfs 103 0.0030 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed btrfs 10655 0.1338 vmlinux-3.15.0-rc4-vanilla mark_page_accessed btrfs 2020 0.0273 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed btrfs 587 0.0079 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed tmpfs 59562 3.2628 vmlinux-3.15.0-rc4-vanilla mark_page_accessed tmpfs 1210 0.0696 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed tmpfs 94 0.0054 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed [akpm@linux-foundation.org: don't run init_page_accessed() against an uninitialised pointer] Signed-off-by: Mel Gorman <mgorman@suse.de> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Jan Kara <jack@suse.cz> Cc: Michal Hocko <mhocko@suse.cz> Cc: Hugh Dickins <hughd@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Theodore Ts'o <tytso@mit.edu> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Tested-by: Prabhakar Lad <prabhakar.csengg@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-06-04 23:10:31 +00:00
* Looks up the page cache slot at @mapping & @offset.
*
* PCG flags modify how the page is returned.
2014-04-03 21:47:46 +00:00
*
mm: non-atomically mark page accessed during page cache allocation where possible aops->write_begin may allocate a new page and make it visible only to have mark_page_accessed called almost immediately after. Once the page is visible the atomic operations are necessary which is noticable overhead when writing to an in-memory filesystem like tmpfs but should also be noticable with fast storage. The objective of the patch is to initialse the accessed information with non-atomic operations before the page is visible. The bulk of filesystems directly or indirectly use grab_cache_page_write_begin or find_or_create_page for the initial allocation of a page cache page. This patch adds an init_page_accessed() helper which behaves like the first call to mark_page_accessed() but may called before the page is visible and can be done non-atomically. The primary APIs of concern in this care are the following and are used by most filesystems. find_get_page find_lock_page find_or_create_page grab_cache_page_nowait grab_cache_page_write_begin All of them are very similar in detail to the patch creates a core helper pagecache_get_page() which takes a flags parameter that affects its behavior such as whether the page should be marked accessed or not. Then old API is preserved but is basically a thin wrapper around this core function. Each of the filesystems are then updated to avoid calling mark_page_accessed when it is known that the VM interfaces have already done the job. There is a slight snag in that the timing of the mark_page_accessed() has now changed so in rare cases it's possible a page gets to the end of the LRU as PageReferenced where as previously it might have been repromoted. This is expected to be rare but it's worth the filesystem people thinking about it in case they see a problem with the timing change. It is also the case that some filesystems may be marking pages accessed that previously did not but it makes sense that filesystems have consistent behaviour in this regard. The test case used to evaulate this is a simple dd of a large file done multiple times with the file deleted on each iterations. The size of the file is 1/10th physical memory to avoid dirty page balancing. In the async case it will be possible that the workload completes without even hitting the disk and will have variable results but highlight the impact of mark_page_accessed for async IO. The sync results are expected to be more stable. The exception is tmpfs where the normal case is for the "IO" to not hit the disk. The test machine was single socket and UMA to avoid any scheduling or NUMA artifacts. Throughput and wall times are presented for sync IO, only wall times are shown for async as the granularity reported by dd and the variability is unsuitable for comparison. As async results were variable do to writback timings, I'm only reporting the maximum figures. The sync results were stable enough to make the mean and stddev uninteresting. The performance results are reported based on a run with no profiling. Profile data is based on a separate run with oprofile running. async dd 3.15.0-rc3 3.15.0-rc3 vanilla accessed-v2 ext3 Max elapsed 13.9900 ( 0.00%) 11.5900 ( 17.16%) tmpfs Max elapsed 0.5100 ( 0.00%) 0.4900 ( 3.92%) btrfs Max elapsed 12.8100 ( 0.00%) 12.7800 ( 0.23%) ext4 Max elapsed 18.6000 ( 0.00%) 13.3400 ( 28.28%) xfs Max elapsed 12.5600 ( 0.00%) 2.0900 ( 83.36%) The XFS figure is a bit strange as it managed to avoid a worst case by sheer luck but the average figures looked reasonable. samples percentage ext3 86107 0.9783 vmlinux-3.15.0-rc4-vanilla mark_page_accessed ext3 23833 0.2710 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed ext3 5036 0.0573 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed ext4 64566 0.8961 vmlinux-3.15.0-rc4-vanilla mark_page_accessed ext4 5322 0.0713 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed ext4 2869 0.0384 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed xfs 62126 1.7675 vmlinux-3.15.0-rc4-vanilla mark_page_accessed xfs 1904 0.0554 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed xfs 103 0.0030 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed btrfs 10655 0.1338 vmlinux-3.15.0-rc4-vanilla mark_page_accessed btrfs 2020 0.0273 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed btrfs 587 0.0079 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed tmpfs 59562 3.2628 vmlinux-3.15.0-rc4-vanilla mark_page_accessed tmpfs 1210 0.0696 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed tmpfs 94 0.0054 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed [akpm@linux-foundation.org: don't run init_page_accessed() against an uninitialised pointer] Signed-off-by: Mel Gorman <mgorman@suse.de> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Jan Kara <jack@suse.cz> Cc: Michal Hocko <mhocko@suse.cz> Cc: Hugh Dickins <hughd@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Theodore Ts'o <tytso@mit.edu> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Tested-by: Prabhakar Lad <prabhakar.csengg@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-06-04 23:10:31 +00:00
* FGP_ACCESSED: the page will be marked accessed
* FGP_LOCK: Page is return locked
* FGP_CREAT: If page is not present then a new page is allocated using
* @gfp_mask and added to the page cache and the VM's LRU
* list. The page is returned locked and with an increased
* refcount. Otherwise, %NULL is returned.
*
mm: non-atomically mark page accessed during page cache allocation where possible aops->write_begin may allocate a new page and make it visible only to have mark_page_accessed called almost immediately after. Once the page is visible the atomic operations are necessary which is noticable overhead when writing to an in-memory filesystem like tmpfs but should also be noticable with fast storage. The objective of the patch is to initialse the accessed information with non-atomic operations before the page is visible. The bulk of filesystems directly or indirectly use grab_cache_page_write_begin or find_or_create_page for the initial allocation of a page cache page. This patch adds an init_page_accessed() helper which behaves like the first call to mark_page_accessed() but may called before the page is visible and can be done non-atomically. The primary APIs of concern in this care are the following and are used by most filesystems. find_get_page find_lock_page find_or_create_page grab_cache_page_nowait grab_cache_page_write_begin All of them are very similar in detail to the patch creates a core helper pagecache_get_page() which takes a flags parameter that affects its behavior such as whether the page should be marked accessed or not. Then old API is preserved but is basically a thin wrapper around this core function. Each of the filesystems are then updated to avoid calling mark_page_accessed when it is known that the VM interfaces have already done the job. There is a slight snag in that the timing of the mark_page_accessed() has now changed so in rare cases it's possible a page gets to the end of the LRU as PageReferenced where as previously it might have been repromoted. This is expected to be rare but it's worth the filesystem people thinking about it in case they see a problem with the timing change. It is also the case that some filesystems may be marking pages accessed that previously did not but it makes sense that filesystems have consistent behaviour in this regard. The test case used to evaulate this is a simple dd of a large file done multiple times with the file deleted on each iterations. The size of the file is 1/10th physical memory to avoid dirty page balancing. In the async case it will be possible that the workload completes without even hitting the disk and will have variable results but highlight the impact of mark_page_accessed for async IO. The sync results are expected to be more stable. The exception is tmpfs where the normal case is for the "IO" to not hit the disk. The test machine was single socket and UMA to avoid any scheduling or NUMA artifacts. Throughput and wall times are presented for sync IO, only wall times are shown for async as the granularity reported by dd and the variability is unsuitable for comparison. As async results were variable do to writback timings, I'm only reporting the maximum figures. The sync results were stable enough to make the mean and stddev uninteresting. The performance results are reported based on a run with no profiling. Profile data is based on a separate run with oprofile running. async dd 3.15.0-rc3 3.15.0-rc3 vanilla accessed-v2 ext3 Max elapsed 13.9900 ( 0.00%) 11.5900 ( 17.16%) tmpfs Max elapsed 0.5100 ( 0.00%) 0.4900 ( 3.92%) btrfs Max elapsed 12.8100 ( 0.00%) 12.7800 ( 0.23%) ext4 Max elapsed 18.6000 ( 0.00%) 13.3400 ( 28.28%) xfs Max elapsed 12.5600 ( 0.00%) 2.0900 ( 83.36%) The XFS figure is a bit strange as it managed to avoid a worst case by sheer luck but the average figures looked reasonable. samples percentage ext3 86107 0.9783 vmlinux-3.15.0-rc4-vanilla mark_page_accessed ext3 23833 0.2710 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed ext3 5036 0.0573 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed ext4 64566 0.8961 vmlinux-3.15.0-rc4-vanilla mark_page_accessed ext4 5322 0.0713 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed ext4 2869 0.0384 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed xfs 62126 1.7675 vmlinux-3.15.0-rc4-vanilla mark_page_accessed xfs 1904 0.0554 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed xfs 103 0.0030 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed btrfs 10655 0.1338 vmlinux-3.15.0-rc4-vanilla mark_page_accessed btrfs 2020 0.0273 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed btrfs 587 0.0079 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed tmpfs 59562 3.2628 vmlinux-3.15.0-rc4-vanilla mark_page_accessed tmpfs 1210 0.0696 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed tmpfs 94 0.0054 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed [akpm@linux-foundation.org: don't run init_page_accessed() against an uninitialised pointer] Signed-off-by: Mel Gorman <mgorman@suse.de> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Jan Kara <jack@suse.cz> Cc: Michal Hocko <mhocko@suse.cz> Cc: Hugh Dickins <hughd@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Theodore Ts'o <tytso@mit.edu> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Tested-by: Prabhakar Lad <prabhakar.csengg@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-06-04 23:10:31 +00:00
* If FGP_LOCK or FGP_CREAT are specified then the function may sleep even
* if the GFP flags specified for FGP_CREAT are atomic.
*
mm: non-atomically mark page accessed during page cache allocation where possible aops->write_begin may allocate a new page and make it visible only to have mark_page_accessed called almost immediately after. Once the page is visible the atomic operations are necessary which is noticable overhead when writing to an in-memory filesystem like tmpfs but should also be noticable with fast storage. The objective of the patch is to initialse the accessed information with non-atomic operations before the page is visible. The bulk of filesystems directly or indirectly use grab_cache_page_write_begin or find_or_create_page for the initial allocation of a page cache page. This patch adds an init_page_accessed() helper which behaves like the first call to mark_page_accessed() but may called before the page is visible and can be done non-atomically. The primary APIs of concern in this care are the following and are used by most filesystems. find_get_page find_lock_page find_or_create_page grab_cache_page_nowait grab_cache_page_write_begin All of them are very similar in detail to the patch creates a core helper pagecache_get_page() which takes a flags parameter that affects its behavior such as whether the page should be marked accessed or not. Then old API is preserved but is basically a thin wrapper around this core function. Each of the filesystems are then updated to avoid calling mark_page_accessed when it is known that the VM interfaces have already done the job. There is a slight snag in that the timing of the mark_page_accessed() has now changed so in rare cases it's possible a page gets to the end of the LRU as PageReferenced where as previously it might have been repromoted. This is expected to be rare but it's worth the filesystem people thinking about it in case they see a problem with the timing change. It is also the case that some filesystems may be marking pages accessed that previously did not but it makes sense that filesystems have consistent behaviour in this regard. The test case used to evaulate this is a simple dd of a large file done multiple times with the file deleted on each iterations. The size of the file is 1/10th physical memory to avoid dirty page balancing. In the async case it will be possible that the workload completes without even hitting the disk and will have variable results but highlight the impact of mark_page_accessed for async IO. The sync results are expected to be more stable. The exception is tmpfs where the normal case is for the "IO" to not hit the disk. The test machine was single socket and UMA to avoid any scheduling or NUMA artifacts. Throughput and wall times are presented for sync IO, only wall times are shown for async as the granularity reported by dd and the variability is unsuitable for comparison. As async results were variable do to writback timings, I'm only reporting the maximum figures. The sync results were stable enough to make the mean and stddev uninteresting. The performance results are reported based on a run with no profiling. Profile data is based on a separate run with oprofile running. async dd 3.15.0-rc3 3.15.0-rc3 vanilla accessed-v2 ext3 Max elapsed 13.9900 ( 0.00%) 11.5900 ( 17.16%) tmpfs Max elapsed 0.5100 ( 0.00%) 0.4900 ( 3.92%) btrfs Max elapsed 12.8100 ( 0.00%) 12.7800 ( 0.23%) ext4 Max elapsed 18.6000 ( 0.00%) 13.3400 ( 28.28%) xfs Max elapsed 12.5600 ( 0.00%) 2.0900 ( 83.36%) The XFS figure is a bit strange as it managed to avoid a worst case by sheer luck but the average figures looked reasonable. samples percentage ext3 86107 0.9783 vmlinux-3.15.0-rc4-vanilla mark_page_accessed ext3 23833 0.2710 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed ext3 5036 0.0573 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed ext4 64566 0.8961 vmlinux-3.15.0-rc4-vanilla mark_page_accessed ext4 5322 0.0713 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed ext4 2869 0.0384 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed xfs 62126 1.7675 vmlinux-3.15.0-rc4-vanilla mark_page_accessed xfs 1904 0.0554 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed xfs 103 0.0030 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed btrfs 10655 0.1338 vmlinux-3.15.0-rc4-vanilla mark_page_accessed btrfs 2020 0.0273 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed btrfs 587 0.0079 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed tmpfs 59562 3.2628 vmlinux-3.15.0-rc4-vanilla mark_page_accessed tmpfs 1210 0.0696 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed tmpfs 94 0.0054 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed [akpm@linux-foundation.org: don't run init_page_accessed() against an uninitialised pointer] Signed-off-by: Mel Gorman <mgorman@suse.de> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Jan Kara <jack@suse.cz> Cc: Michal Hocko <mhocko@suse.cz> Cc: Hugh Dickins <hughd@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Theodore Ts'o <tytso@mit.edu> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Tested-by: Prabhakar Lad <prabhakar.csengg@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-06-04 23:10:31 +00:00
* If there is a page cache page, it is returned with an increased refcount.
*/
mm: non-atomically mark page accessed during page cache allocation where possible aops->write_begin may allocate a new page and make it visible only to have mark_page_accessed called almost immediately after. Once the page is visible the atomic operations are necessary which is noticable overhead when writing to an in-memory filesystem like tmpfs but should also be noticable with fast storage. The objective of the patch is to initialse the accessed information with non-atomic operations before the page is visible. The bulk of filesystems directly or indirectly use grab_cache_page_write_begin or find_or_create_page for the initial allocation of a page cache page. This patch adds an init_page_accessed() helper which behaves like the first call to mark_page_accessed() but may called before the page is visible and can be done non-atomically. The primary APIs of concern in this care are the following and are used by most filesystems. find_get_page find_lock_page find_or_create_page grab_cache_page_nowait grab_cache_page_write_begin All of them are very similar in detail to the patch creates a core helper pagecache_get_page() which takes a flags parameter that affects its behavior such as whether the page should be marked accessed or not. Then old API is preserved but is basically a thin wrapper around this core function. Each of the filesystems are then updated to avoid calling mark_page_accessed when it is known that the VM interfaces have already done the job. There is a slight snag in that the timing of the mark_page_accessed() has now changed so in rare cases it's possible a page gets to the end of the LRU as PageReferenced where as previously it might have been repromoted. This is expected to be rare but it's worth the filesystem people thinking about it in case they see a problem with the timing change. It is also the case that some filesystems may be marking pages accessed that previously did not but it makes sense that filesystems have consistent behaviour in this regard. The test case used to evaulate this is a simple dd of a large file done multiple times with the file deleted on each iterations. The size of the file is 1/10th physical memory to avoid dirty page balancing. In the async case it will be possible that the workload completes without even hitting the disk and will have variable results but highlight the impact of mark_page_accessed for async IO. The sync results are expected to be more stable. The exception is tmpfs where the normal case is for the "IO" to not hit the disk. The test machine was single socket and UMA to avoid any scheduling or NUMA artifacts. Throughput and wall times are presented for sync IO, only wall times are shown for async as the granularity reported by dd and the variability is unsuitable for comparison. As async results were variable do to writback timings, I'm only reporting the maximum figures. The sync results were stable enough to make the mean and stddev uninteresting. The performance results are reported based on a run with no profiling. Profile data is based on a separate run with oprofile running. async dd 3.15.0-rc3 3.15.0-rc3 vanilla accessed-v2 ext3 Max elapsed 13.9900 ( 0.00%) 11.5900 ( 17.16%) tmpfs Max elapsed 0.5100 ( 0.00%) 0.4900 ( 3.92%) btrfs Max elapsed 12.8100 ( 0.00%) 12.7800 ( 0.23%) ext4 Max elapsed 18.6000 ( 0.00%) 13.3400 ( 28.28%) xfs Max elapsed 12.5600 ( 0.00%) 2.0900 ( 83.36%) The XFS figure is a bit strange as it managed to avoid a worst case by sheer luck but the average figures looked reasonable. samples percentage ext3 86107 0.9783 vmlinux-3.15.0-rc4-vanilla mark_page_accessed ext3 23833 0.2710 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed ext3 5036 0.0573 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed ext4 64566 0.8961 vmlinux-3.15.0-rc4-vanilla mark_page_accessed ext4 5322 0.0713 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed ext4 2869 0.0384 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed xfs 62126 1.7675 vmlinux-3.15.0-rc4-vanilla mark_page_accessed xfs 1904 0.0554 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed xfs 103 0.0030 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed btrfs 10655 0.1338 vmlinux-3.15.0-rc4-vanilla mark_page_accessed btrfs 2020 0.0273 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed btrfs 587 0.0079 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed tmpfs 59562 3.2628 vmlinux-3.15.0-rc4-vanilla mark_page_accessed tmpfs 1210 0.0696 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed tmpfs 94 0.0054 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed [akpm@linux-foundation.org: don't run init_page_accessed() against an uninitialised pointer] Signed-off-by: Mel Gorman <mgorman@suse.de> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Jan Kara <jack@suse.cz> Cc: Michal Hocko <mhocko@suse.cz> Cc: Hugh Dickins <hughd@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Theodore Ts'o <tytso@mit.edu> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Tested-by: Prabhakar Lad <prabhakar.csengg@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-06-04 23:10:31 +00:00
struct page *pagecache_get_page(struct address_space *mapping, pgoff_t offset,
int fgp_flags, gfp_t gfp_mask)
{
struct page *page;
mm: non-atomically mark page accessed during page cache allocation where possible aops->write_begin may allocate a new page and make it visible only to have mark_page_accessed called almost immediately after. Once the page is visible the atomic operations are necessary which is noticable overhead when writing to an in-memory filesystem like tmpfs but should also be noticable with fast storage. The objective of the patch is to initialse the accessed information with non-atomic operations before the page is visible. The bulk of filesystems directly or indirectly use grab_cache_page_write_begin or find_or_create_page for the initial allocation of a page cache page. This patch adds an init_page_accessed() helper which behaves like the first call to mark_page_accessed() but may called before the page is visible and can be done non-atomically. The primary APIs of concern in this care are the following and are used by most filesystems. find_get_page find_lock_page find_or_create_page grab_cache_page_nowait grab_cache_page_write_begin All of them are very similar in detail to the patch creates a core helper pagecache_get_page() which takes a flags parameter that affects its behavior such as whether the page should be marked accessed or not. Then old API is preserved but is basically a thin wrapper around this core function. Each of the filesystems are then updated to avoid calling mark_page_accessed when it is known that the VM interfaces have already done the job. There is a slight snag in that the timing of the mark_page_accessed() has now changed so in rare cases it's possible a page gets to the end of the LRU as PageReferenced where as previously it might have been repromoted. This is expected to be rare but it's worth the filesystem people thinking about it in case they see a problem with the timing change. It is also the case that some filesystems may be marking pages accessed that previously did not but it makes sense that filesystems have consistent behaviour in this regard. The test case used to evaulate this is a simple dd of a large file done multiple times with the file deleted on each iterations. The size of the file is 1/10th physical memory to avoid dirty page balancing. In the async case it will be possible that the workload completes without even hitting the disk and will have variable results but highlight the impact of mark_page_accessed for async IO. The sync results are expected to be more stable. The exception is tmpfs where the normal case is for the "IO" to not hit the disk. The test machine was single socket and UMA to avoid any scheduling or NUMA artifacts. Throughput and wall times are presented for sync IO, only wall times are shown for async as the granularity reported by dd and the variability is unsuitable for comparison. As async results were variable do to writback timings, I'm only reporting the maximum figures. The sync results were stable enough to make the mean and stddev uninteresting. The performance results are reported based on a run with no profiling. Profile data is based on a separate run with oprofile running. async dd 3.15.0-rc3 3.15.0-rc3 vanilla accessed-v2 ext3 Max elapsed 13.9900 ( 0.00%) 11.5900 ( 17.16%) tmpfs Max elapsed 0.5100 ( 0.00%) 0.4900 ( 3.92%) btrfs Max elapsed 12.8100 ( 0.00%) 12.7800 ( 0.23%) ext4 Max elapsed 18.6000 ( 0.00%) 13.3400 ( 28.28%) xfs Max elapsed 12.5600 ( 0.00%) 2.0900 ( 83.36%) The XFS figure is a bit strange as it managed to avoid a worst case by sheer luck but the average figures looked reasonable. samples percentage ext3 86107 0.9783 vmlinux-3.15.0-rc4-vanilla mark_page_accessed ext3 23833 0.2710 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed ext3 5036 0.0573 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed ext4 64566 0.8961 vmlinux-3.15.0-rc4-vanilla mark_page_accessed ext4 5322 0.0713 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed ext4 2869 0.0384 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed xfs 62126 1.7675 vmlinux-3.15.0-rc4-vanilla mark_page_accessed xfs 1904 0.0554 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed xfs 103 0.0030 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed btrfs 10655 0.1338 vmlinux-3.15.0-rc4-vanilla mark_page_accessed btrfs 2020 0.0273 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed btrfs 587 0.0079 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed tmpfs 59562 3.2628 vmlinux-3.15.0-rc4-vanilla mark_page_accessed tmpfs 1210 0.0696 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed tmpfs 94 0.0054 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed [akpm@linux-foundation.org: don't run init_page_accessed() against an uninitialised pointer] Signed-off-by: Mel Gorman <mgorman@suse.de> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Jan Kara <jack@suse.cz> Cc: Michal Hocko <mhocko@suse.cz> Cc: Hugh Dickins <hughd@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Theodore Ts'o <tytso@mit.edu> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Tested-by: Prabhakar Lad <prabhakar.csengg@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-06-04 23:10:31 +00:00
repeat:
mm: non-atomically mark page accessed during page cache allocation where possible aops->write_begin may allocate a new page and make it visible only to have mark_page_accessed called almost immediately after. Once the page is visible the atomic operations are necessary which is noticable overhead when writing to an in-memory filesystem like tmpfs but should also be noticable with fast storage. The objective of the patch is to initialse the accessed information with non-atomic operations before the page is visible. The bulk of filesystems directly or indirectly use grab_cache_page_write_begin or find_or_create_page for the initial allocation of a page cache page. This patch adds an init_page_accessed() helper which behaves like the first call to mark_page_accessed() but may called before the page is visible and can be done non-atomically. The primary APIs of concern in this care are the following and are used by most filesystems. find_get_page find_lock_page find_or_create_page grab_cache_page_nowait grab_cache_page_write_begin All of them are very similar in detail to the patch creates a core helper pagecache_get_page() which takes a flags parameter that affects its behavior such as whether the page should be marked accessed or not. Then old API is preserved but is basically a thin wrapper around this core function. Each of the filesystems are then updated to avoid calling mark_page_accessed when it is known that the VM interfaces have already done the job. There is a slight snag in that the timing of the mark_page_accessed() has now changed so in rare cases it's possible a page gets to the end of the LRU as PageReferenced where as previously it might have been repromoted. This is expected to be rare but it's worth the filesystem people thinking about it in case they see a problem with the timing change. It is also the case that some filesystems may be marking pages accessed that previously did not but it makes sense that filesystems have consistent behaviour in this regard. The test case used to evaulate this is a simple dd of a large file done multiple times with the file deleted on each iterations. The size of the file is 1/10th physical memory to avoid dirty page balancing. In the async case it will be possible that the workload completes without even hitting the disk and will have variable results but highlight the impact of mark_page_accessed for async IO. The sync results are expected to be more stable. The exception is tmpfs where the normal case is for the "IO" to not hit the disk. The test machine was single socket and UMA to avoid any scheduling or NUMA artifacts. Throughput and wall times are presented for sync IO, only wall times are shown for async as the granularity reported by dd and the variability is unsuitable for comparison. As async results were variable do to writback timings, I'm only reporting the maximum figures. The sync results were stable enough to make the mean and stddev uninteresting. The performance results are reported based on a run with no profiling. Profile data is based on a separate run with oprofile running. async dd 3.15.0-rc3 3.15.0-rc3 vanilla accessed-v2 ext3 Max elapsed 13.9900 ( 0.00%) 11.5900 ( 17.16%) tmpfs Max elapsed 0.5100 ( 0.00%) 0.4900 ( 3.92%) btrfs Max elapsed 12.8100 ( 0.00%) 12.7800 ( 0.23%) ext4 Max elapsed 18.6000 ( 0.00%) 13.3400 ( 28.28%) xfs Max elapsed 12.5600 ( 0.00%) 2.0900 ( 83.36%) The XFS figure is a bit strange as it managed to avoid a worst case by sheer luck but the average figures looked reasonable. samples percentage ext3 86107 0.9783 vmlinux-3.15.0-rc4-vanilla mark_page_accessed ext3 23833 0.2710 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed ext3 5036 0.0573 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed ext4 64566 0.8961 vmlinux-3.15.0-rc4-vanilla mark_page_accessed ext4 5322 0.0713 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed ext4 2869 0.0384 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed xfs 62126 1.7675 vmlinux-3.15.0-rc4-vanilla mark_page_accessed xfs 1904 0.0554 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed xfs 103 0.0030 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed btrfs 10655 0.1338 vmlinux-3.15.0-rc4-vanilla mark_page_accessed btrfs 2020 0.0273 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed btrfs 587 0.0079 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed tmpfs 59562 3.2628 vmlinux-3.15.0-rc4-vanilla mark_page_accessed tmpfs 1210 0.0696 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed tmpfs 94 0.0054 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed [akpm@linux-foundation.org: don't run init_page_accessed() against an uninitialised pointer] Signed-off-by: Mel Gorman <mgorman@suse.de> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Jan Kara <jack@suse.cz> Cc: Michal Hocko <mhocko@suse.cz> Cc: Hugh Dickins <hughd@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Theodore Ts'o <tytso@mit.edu> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Tested-by: Prabhakar Lad <prabhakar.csengg@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-06-04 23:10:31 +00:00
page = find_get_entry(mapping, offset);
if (radix_tree_exceptional_entry(page))
page = NULL;
if (!page)
goto no_page;
if (fgp_flags & FGP_LOCK) {
if (fgp_flags & FGP_NOWAIT) {
if (!trylock_page(page)) {
page_cache_release(page);
return NULL;
}
} else {
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(page->index != offset, page);
}
if (page && (fgp_flags & FGP_ACCESSED))
mark_page_accessed(page);
no_page:
if (!page && (fgp_flags & FGP_CREAT)) {
int err;
if ((fgp_flags & FGP_WRITE) && mapping_cap_account_dirty(mapping))
gfp_mask |= __GFP_WRITE;
if (fgp_flags & FGP_NOFS)
gfp_mask &= ~__GFP_FS;
mm: non-atomically mark page accessed during page cache allocation where possible aops->write_begin may allocate a new page and make it visible only to have mark_page_accessed called almost immediately after. Once the page is visible the atomic operations are necessary which is noticable overhead when writing to an in-memory filesystem like tmpfs but should also be noticable with fast storage. The objective of the patch is to initialse the accessed information with non-atomic operations before the page is visible. The bulk of filesystems directly or indirectly use grab_cache_page_write_begin or find_or_create_page for the initial allocation of a page cache page. This patch adds an init_page_accessed() helper which behaves like the first call to mark_page_accessed() but may called before the page is visible and can be done non-atomically. The primary APIs of concern in this care are the following and are used by most filesystems. find_get_page find_lock_page find_or_create_page grab_cache_page_nowait grab_cache_page_write_begin All of them are very similar in detail to the patch creates a core helper pagecache_get_page() which takes a flags parameter that affects its behavior such as whether the page should be marked accessed or not. Then old API is preserved but is basically a thin wrapper around this core function. Each of the filesystems are then updated to avoid calling mark_page_accessed when it is known that the VM interfaces have already done the job. There is a slight snag in that the timing of the mark_page_accessed() has now changed so in rare cases it's possible a page gets to the end of the LRU as PageReferenced where as previously it might have been repromoted. This is expected to be rare but it's worth the filesystem people thinking about it in case they see a problem with the timing change. It is also the case that some filesystems may be marking pages accessed that previously did not but it makes sense that filesystems have consistent behaviour in this regard. The test case used to evaulate this is a simple dd of a large file done multiple times with the file deleted on each iterations. The size of the file is 1/10th physical memory to avoid dirty page balancing. In the async case it will be possible that the workload completes without even hitting the disk and will have variable results but highlight the impact of mark_page_accessed for async IO. The sync results are expected to be more stable. The exception is tmpfs where the normal case is for the "IO" to not hit the disk. The test machine was single socket and UMA to avoid any scheduling or NUMA artifacts. Throughput and wall times are presented for sync IO, only wall times are shown for async as the granularity reported by dd and the variability is unsuitable for comparison. As async results were variable do to writback timings, I'm only reporting the maximum figures. The sync results were stable enough to make the mean and stddev uninteresting. The performance results are reported based on a run with no profiling. Profile data is based on a separate run with oprofile running. async dd 3.15.0-rc3 3.15.0-rc3 vanilla accessed-v2 ext3 Max elapsed 13.9900 ( 0.00%) 11.5900 ( 17.16%) tmpfs Max elapsed 0.5100 ( 0.00%) 0.4900 ( 3.92%) btrfs Max elapsed 12.8100 ( 0.00%) 12.7800 ( 0.23%) ext4 Max elapsed 18.6000 ( 0.00%) 13.3400 ( 28.28%) xfs Max elapsed 12.5600 ( 0.00%) 2.0900 ( 83.36%) The XFS figure is a bit strange as it managed to avoid a worst case by sheer luck but the average figures looked reasonable. samples percentage ext3 86107 0.9783 vmlinux-3.15.0-rc4-vanilla mark_page_accessed ext3 23833 0.2710 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed ext3 5036 0.0573 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed ext4 64566 0.8961 vmlinux-3.15.0-rc4-vanilla mark_page_accessed ext4 5322 0.0713 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed ext4 2869 0.0384 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed xfs 62126 1.7675 vmlinux-3.15.0-rc4-vanilla mark_page_accessed xfs 1904 0.0554 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed xfs 103 0.0030 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed btrfs 10655 0.1338 vmlinux-3.15.0-rc4-vanilla mark_page_accessed btrfs 2020 0.0273 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed btrfs 587 0.0079 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed tmpfs 59562 3.2628 vmlinux-3.15.0-rc4-vanilla mark_page_accessed tmpfs 1210 0.0696 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed tmpfs 94 0.0054 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed [akpm@linux-foundation.org: don't run init_page_accessed() against an uninitialised pointer] Signed-off-by: Mel Gorman <mgorman@suse.de> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Jan Kara <jack@suse.cz> Cc: Michal Hocko <mhocko@suse.cz> Cc: Hugh Dickins <hughd@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Theodore Ts'o <tytso@mit.edu> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Tested-by: Prabhakar Lad <prabhakar.csengg@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-06-04 23:10:31 +00:00
page = __page_cache_alloc(gfp_mask);
if (!page)
return NULL;
mm: non-atomically mark page accessed during page cache allocation where possible aops->write_begin may allocate a new page and make it visible only to have mark_page_accessed called almost immediately after. Once the page is visible the atomic operations are necessary which is noticable overhead when writing to an in-memory filesystem like tmpfs but should also be noticable with fast storage. The objective of the patch is to initialse the accessed information with non-atomic operations before the page is visible. The bulk of filesystems directly or indirectly use grab_cache_page_write_begin or find_or_create_page for the initial allocation of a page cache page. This patch adds an init_page_accessed() helper which behaves like the first call to mark_page_accessed() but may called before the page is visible and can be done non-atomically. The primary APIs of concern in this care are the following and are used by most filesystems. find_get_page find_lock_page find_or_create_page grab_cache_page_nowait grab_cache_page_write_begin All of them are very similar in detail to the patch creates a core helper pagecache_get_page() which takes a flags parameter that affects its behavior such as whether the page should be marked accessed or not. Then old API is preserved but is basically a thin wrapper around this core function. Each of the filesystems are then updated to avoid calling mark_page_accessed when it is known that the VM interfaces have already done the job. There is a slight snag in that the timing of the mark_page_accessed() has now changed so in rare cases it's possible a page gets to the end of the LRU as PageReferenced where as previously it might have been repromoted. This is expected to be rare but it's worth the filesystem people thinking about it in case they see a problem with the timing change. It is also the case that some filesystems may be marking pages accessed that previously did not but it makes sense that filesystems have consistent behaviour in this regard. The test case used to evaulate this is a simple dd of a large file done multiple times with the file deleted on each iterations. The size of the file is 1/10th physical memory to avoid dirty page balancing. In the async case it will be possible that the workload completes without even hitting the disk and will have variable results but highlight the impact of mark_page_accessed for async IO. The sync results are expected to be more stable. The exception is tmpfs where the normal case is for the "IO" to not hit the disk. The test machine was single socket and UMA to avoid any scheduling or NUMA artifacts. Throughput and wall times are presented for sync IO, only wall times are shown for async as the granularity reported by dd and the variability is unsuitable for comparison. As async results were variable do to writback timings, I'm only reporting the maximum figures. The sync results were stable enough to make the mean and stddev uninteresting. The performance results are reported based on a run with no profiling. Profile data is based on a separate run with oprofile running. async dd 3.15.0-rc3 3.15.0-rc3 vanilla accessed-v2 ext3 Max elapsed 13.9900 ( 0.00%) 11.5900 ( 17.16%) tmpfs Max elapsed 0.5100 ( 0.00%) 0.4900 ( 3.92%) btrfs Max elapsed 12.8100 ( 0.00%) 12.7800 ( 0.23%) ext4 Max elapsed 18.6000 ( 0.00%) 13.3400 ( 28.28%) xfs Max elapsed 12.5600 ( 0.00%) 2.0900 ( 83.36%) The XFS figure is a bit strange as it managed to avoid a worst case by sheer luck but the average figures looked reasonable. samples percentage ext3 86107 0.9783 vmlinux-3.15.0-rc4-vanilla mark_page_accessed ext3 23833 0.2710 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed ext3 5036 0.0573 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed ext4 64566 0.8961 vmlinux-3.15.0-rc4-vanilla mark_page_accessed ext4 5322 0.0713 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed ext4 2869 0.0384 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed xfs 62126 1.7675 vmlinux-3.15.0-rc4-vanilla mark_page_accessed xfs 1904 0.0554 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed xfs 103 0.0030 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed btrfs 10655 0.1338 vmlinux-3.15.0-rc4-vanilla mark_page_accessed btrfs 2020 0.0273 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed btrfs 587 0.0079 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed tmpfs 59562 3.2628 vmlinux-3.15.0-rc4-vanilla mark_page_accessed tmpfs 1210 0.0696 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed tmpfs 94 0.0054 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed [akpm@linux-foundation.org: don't run init_page_accessed() against an uninitialised pointer] Signed-off-by: Mel Gorman <mgorman@suse.de> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Jan Kara <jack@suse.cz> Cc: Michal Hocko <mhocko@suse.cz> Cc: Hugh Dickins <hughd@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Theodore Ts'o <tytso@mit.edu> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Tested-by: Prabhakar Lad <prabhakar.csengg@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-06-04 23:10:31 +00:00
if (WARN_ON_ONCE(!(fgp_flags & FGP_LOCK)))
fgp_flags |= FGP_LOCK;
/* Init accessed so avoid atomic mark_page_accessed later */
mm: non-atomically mark page accessed during page cache allocation where possible aops->write_begin may allocate a new page and make it visible only to have mark_page_accessed called almost immediately after. Once the page is visible the atomic operations are necessary which is noticable overhead when writing to an in-memory filesystem like tmpfs but should also be noticable with fast storage. The objective of the patch is to initialse the accessed information with non-atomic operations before the page is visible. The bulk of filesystems directly or indirectly use grab_cache_page_write_begin or find_or_create_page for the initial allocation of a page cache page. This patch adds an init_page_accessed() helper which behaves like the first call to mark_page_accessed() but may called before the page is visible and can be done non-atomically. The primary APIs of concern in this care are the following and are used by most filesystems. find_get_page find_lock_page find_or_create_page grab_cache_page_nowait grab_cache_page_write_begin All of them are very similar in detail to the patch creates a core helper pagecache_get_page() which takes a flags parameter that affects its behavior such as whether the page should be marked accessed or not. Then old API is preserved but is basically a thin wrapper around this core function. Each of the filesystems are then updated to avoid calling mark_page_accessed when it is known that the VM interfaces have already done the job. There is a slight snag in that the timing of the mark_page_accessed() has now changed so in rare cases it's possible a page gets to the end of the LRU as PageReferenced where as previously it might have been repromoted. This is expected to be rare but it's worth the filesystem people thinking about it in case they see a problem with the timing change. It is also the case that some filesystems may be marking pages accessed that previously did not but it makes sense that filesystems have consistent behaviour in this regard. The test case used to evaulate this is a simple dd of a large file done multiple times with the file deleted on each iterations. The size of the file is 1/10th physical memory to avoid dirty page balancing. In the async case it will be possible that the workload completes without even hitting the disk and will have variable results but highlight the impact of mark_page_accessed for async IO. The sync results are expected to be more stable. The exception is tmpfs where the normal case is for the "IO" to not hit the disk. The test machine was single socket and UMA to avoid any scheduling or NUMA artifacts. Throughput and wall times are presented for sync IO, only wall times are shown for async as the granularity reported by dd and the variability is unsuitable for comparison. As async results were variable do to writback timings, I'm only reporting the maximum figures. The sync results were stable enough to make the mean and stddev uninteresting. The performance results are reported based on a run with no profiling. Profile data is based on a separate run with oprofile running. async dd 3.15.0-rc3 3.15.0-rc3 vanilla accessed-v2 ext3 Max elapsed 13.9900 ( 0.00%) 11.5900 ( 17.16%) tmpfs Max elapsed 0.5100 ( 0.00%) 0.4900 ( 3.92%) btrfs Max elapsed 12.8100 ( 0.00%) 12.7800 ( 0.23%) ext4 Max elapsed 18.6000 ( 0.00%) 13.3400 ( 28.28%) xfs Max elapsed 12.5600 ( 0.00%) 2.0900 ( 83.36%) The XFS figure is a bit strange as it managed to avoid a worst case by sheer luck but the average figures looked reasonable. samples percentage ext3 86107 0.9783 vmlinux-3.15.0-rc4-vanilla mark_page_accessed ext3 23833 0.2710 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed ext3 5036 0.0573 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed ext4 64566 0.8961 vmlinux-3.15.0-rc4-vanilla mark_page_accessed ext4 5322 0.0713 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed ext4 2869 0.0384 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed xfs 62126 1.7675 vmlinux-3.15.0-rc4-vanilla mark_page_accessed xfs 1904 0.0554 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed xfs 103 0.0030 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed btrfs 10655 0.1338 vmlinux-3.15.0-rc4-vanilla mark_page_accessed btrfs 2020 0.0273 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed btrfs 587 0.0079 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed tmpfs 59562 3.2628 vmlinux-3.15.0-rc4-vanilla mark_page_accessed tmpfs 1210 0.0696 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed tmpfs 94 0.0054 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed [akpm@linux-foundation.org: don't run init_page_accessed() against an uninitialised pointer] Signed-off-by: Mel Gorman <mgorman@suse.de> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Jan Kara <jack@suse.cz> Cc: Michal Hocko <mhocko@suse.cz> Cc: Hugh Dickins <hughd@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Theodore Ts'o <tytso@mit.edu> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Tested-by: Prabhakar Lad <prabhakar.csengg@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-06-04 23:10:31 +00:00
if (fgp_flags & FGP_ACCESSED)
__SetPageReferenced(page);
mm: non-atomically mark page accessed during page cache allocation where possible aops->write_begin may allocate a new page and make it visible only to have mark_page_accessed called almost immediately after. Once the page is visible the atomic operations are necessary which is noticable overhead when writing to an in-memory filesystem like tmpfs but should also be noticable with fast storage. The objective of the patch is to initialse the accessed information with non-atomic operations before the page is visible. The bulk of filesystems directly or indirectly use grab_cache_page_write_begin or find_or_create_page for the initial allocation of a page cache page. This patch adds an init_page_accessed() helper which behaves like the first call to mark_page_accessed() but may called before the page is visible and can be done non-atomically. The primary APIs of concern in this care are the following and are used by most filesystems. find_get_page find_lock_page find_or_create_page grab_cache_page_nowait grab_cache_page_write_begin All of them are very similar in detail to the patch creates a core helper pagecache_get_page() which takes a flags parameter that affects its behavior such as whether the page should be marked accessed or not. Then old API is preserved but is basically a thin wrapper around this core function. Each of the filesystems are then updated to avoid calling mark_page_accessed when it is known that the VM interfaces have already done the job. There is a slight snag in that the timing of the mark_page_accessed() has now changed so in rare cases it's possible a page gets to the end of the LRU as PageReferenced where as previously it might have been repromoted. This is expected to be rare but it's worth the filesystem people thinking about it in case they see a problem with the timing change. It is also the case that some filesystems may be marking pages accessed that previously did not but it makes sense that filesystems have consistent behaviour in this regard. The test case used to evaulate this is a simple dd of a large file done multiple times with the file deleted on each iterations. The size of the file is 1/10th physical memory to avoid dirty page balancing. In the async case it will be possible that the workload completes without even hitting the disk and will have variable results but highlight the impact of mark_page_accessed for async IO. The sync results are expected to be more stable. The exception is tmpfs where the normal case is for the "IO" to not hit the disk. The test machine was single socket and UMA to avoid any scheduling or NUMA artifacts. Throughput and wall times are presented for sync IO, only wall times are shown for async as the granularity reported by dd and the variability is unsuitable for comparison. As async results were variable do to writback timings, I'm only reporting the maximum figures. The sync results were stable enough to make the mean and stddev uninteresting. The performance results are reported based on a run with no profiling. Profile data is based on a separate run with oprofile running. async dd 3.15.0-rc3 3.15.0-rc3 vanilla accessed-v2 ext3 Max elapsed 13.9900 ( 0.00%) 11.5900 ( 17.16%) tmpfs Max elapsed 0.5100 ( 0.00%) 0.4900 ( 3.92%) btrfs Max elapsed 12.8100 ( 0.00%) 12.7800 ( 0.23%) ext4 Max elapsed 18.6000 ( 0.00%) 13.3400 ( 28.28%) xfs Max elapsed 12.5600 ( 0.00%) 2.0900 ( 83.36%) The XFS figure is a bit strange as it managed to avoid a worst case by sheer luck but the average figures looked reasonable. samples percentage ext3 86107 0.9783 vmlinux-3.15.0-rc4-vanilla mark_page_accessed ext3 23833 0.2710 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed ext3 5036 0.0573 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed ext4 64566 0.8961 vmlinux-3.15.0-rc4-vanilla mark_page_accessed ext4 5322 0.0713 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed ext4 2869 0.0384 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed xfs 62126 1.7675 vmlinux-3.15.0-rc4-vanilla mark_page_accessed xfs 1904 0.0554 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed xfs 103 0.0030 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed btrfs 10655 0.1338 vmlinux-3.15.0-rc4-vanilla mark_page_accessed btrfs 2020 0.0273 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed btrfs 587 0.0079 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed tmpfs 59562 3.2628 vmlinux-3.15.0-rc4-vanilla mark_page_accessed tmpfs 1210 0.0696 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed tmpfs 94 0.0054 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed [akpm@linux-foundation.org: don't run init_page_accessed() against an uninitialised pointer] Signed-off-by: Mel Gorman <mgorman@suse.de> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Jan Kara <jack@suse.cz> Cc: Michal Hocko <mhocko@suse.cz> Cc: Hugh Dickins <hughd@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Theodore Ts'o <tytso@mit.edu> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Tested-by: Prabhakar Lad <prabhakar.csengg@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-06-04 23:10:31 +00:00
err = add_to_page_cache_lru(page, mapping, offset,
gfp_mask & GFP_RECLAIM_MASK);
if (unlikely(err)) {
page_cache_release(page);
page = NULL;
if (err == -EEXIST)
goto repeat;
}
}
mm: non-atomically mark page accessed during page cache allocation where possible aops->write_begin may allocate a new page and make it visible only to have mark_page_accessed called almost immediately after. Once the page is visible the atomic operations are necessary which is noticable overhead when writing to an in-memory filesystem like tmpfs but should also be noticable with fast storage. The objective of the patch is to initialse the accessed information with non-atomic operations before the page is visible. The bulk of filesystems directly or indirectly use grab_cache_page_write_begin or find_or_create_page for the initial allocation of a page cache page. This patch adds an init_page_accessed() helper which behaves like the first call to mark_page_accessed() but may called before the page is visible and can be done non-atomically. The primary APIs of concern in this care are the following and are used by most filesystems. find_get_page find_lock_page find_or_create_page grab_cache_page_nowait grab_cache_page_write_begin All of them are very similar in detail to the patch creates a core helper pagecache_get_page() which takes a flags parameter that affects its behavior such as whether the page should be marked accessed or not. Then old API is preserved but is basically a thin wrapper around this core function. Each of the filesystems are then updated to avoid calling mark_page_accessed when it is known that the VM interfaces have already done the job. There is a slight snag in that the timing of the mark_page_accessed() has now changed so in rare cases it's possible a page gets to the end of the LRU as PageReferenced where as previously it might have been repromoted. This is expected to be rare but it's worth the filesystem people thinking about it in case they see a problem with the timing change. It is also the case that some filesystems may be marking pages accessed that previously did not but it makes sense that filesystems have consistent behaviour in this regard. The test case used to evaulate this is a simple dd of a large file done multiple times with the file deleted on each iterations. The size of the file is 1/10th physical memory to avoid dirty page balancing. In the async case it will be possible that the workload completes without even hitting the disk and will have variable results but highlight the impact of mark_page_accessed for async IO. The sync results are expected to be more stable. The exception is tmpfs where the normal case is for the "IO" to not hit the disk. The test machine was single socket and UMA to avoid any scheduling or NUMA artifacts. Throughput and wall times are presented for sync IO, only wall times are shown for async as the granularity reported by dd and the variability is unsuitable for comparison. As async results were variable do to writback timings, I'm only reporting the maximum figures. The sync results were stable enough to make the mean and stddev uninteresting. The performance results are reported based on a run with no profiling. Profile data is based on a separate run with oprofile running. async dd 3.15.0-rc3 3.15.0-rc3 vanilla accessed-v2 ext3 Max elapsed 13.9900 ( 0.00%) 11.5900 ( 17.16%) tmpfs Max elapsed 0.5100 ( 0.00%) 0.4900 ( 3.92%) btrfs Max elapsed 12.8100 ( 0.00%) 12.7800 ( 0.23%) ext4 Max elapsed 18.6000 ( 0.00%) 13.3400 ( 28.28%) xfs Max elapsed 12.5600 ( 0.00%) 2.0900 ( 83.36%) The XFS figure is a bit strange as it managed to avoid a worst case by sheer luck but the average figures looked reasonable. samples percentage ext3 86107 0.9783 vmlinux-3.15.0-rc4-vanilla mark_page_accessed ext3 23833 0.2710 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed ext3 5036 0.0573 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed ext4 64566 0.8961 vmlinux-3.15.0-rc4-vanilla mark_page_accessed ext4 5322 0.0713 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed ext4 2869 0.0384 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed xfs 62126 1.7675 vmlinux-3.15.0-rc4-vanilla mark_page_accessed xfs 1904 0.0554 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed xfs 103 0.0030 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed btrfs 10655 0.1338 vmlinux-3.15.0-rc4-vanilla mark_page_accessed btrfs 2020 0.0273 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed btrfs 587 0.0079 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed tmpfs 59562 3.2628 vmlinux-3.15.0-rc4-vanilla mark_page_accessed tmpfs 1210 0.0696 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed tmpfs 94 0.0054 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed [akpm@linux-foundation.org: don't run init_page_accessed() against an uninitialised pointer] Signed-off-by: Mel Gorman <mgorman@suse.de> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Jan Kara <jack@suse.cz> Cc: Michal Hocko <mhocko@suse.cz> Cc: Hugh Dickins <hughd@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Theodore Ts'o <tytso@mit.edu> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Tested-by: Prabhakar Lad <prabhakar.csengg@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-06-04 23:10:31 +00:00
return page;
}
mm: non-atomically mark page accessed during page cache allocation where possible aops->write_begin may allocate a new page and make it visible only to have mark_page_accessed called almost immediately after. Once the page is visible the atomic operations are necessary which is noticable overhead when writing to an in-memory filesystem like tmpfs but should also be noticable with fast storage. The objective of the patch is to initialse the accessed information with non-atomic operations before the page is visible. The bulk of filesystems directly or indirectly use grab_cache_page_write_begin or find_or_create_page for the initial allocation of a page cache page. This patch adds an init_page_accessed() helper which behaves like the first call to mark_page_accessed() but may called before the page is visible and can be done non-atomically. The primary APIs of concern in this care are the following and are used by most filesystems. find_get_page find_lock_page find_or_create_page grab_cache_page_nowait grab_cache_page_write_begin All of them are very similar in detail to the patch creates a core helper pagecache_get_page() which takes a flags parameter that affects its behavior such as whether the page should be marked accessed or not. Then old API is preserved but is basically a thin wrapper around this core function. Each of the filesystems are then updated to avoid calling mark_page_accessed when it is known that the VM interfaces have already done the job. There is a slight snag in that the timing of the mark_page_accessed() has now changed so in rare cases it's possible a page gets to the end of the LRU as PageReferenced where as previously it might have been repromoted. This is expected to be rare but it's worth the filesystem people thinking about it in case they see a problem with the timing change. It is also the case that some filesystems may be marking pages accessed that previously did not but it makes sense that filesystems have consistent behaviour in this regard. The test case used to evaulate this is a simple dd of a large file done multiple times with the file deleted on each iterations. The size of the file is 1/10th physical memory to avoid dirty page balancing. In the async case it will be possible that the workload completes without even hitting the disk and will have variable results but highlight the impact of mark_page_accessed for async IO. The sync results are expected to be more stable. The exception is tmpfs where the normal case is for the "IO" to not hit the disk. The test machine was single socket and UMA to avoid any scheduling or NUMA artifacts. Throughput and wall times are presented for sync IO, only wall times are shown for async as the granularity reported by dd and the variability is unsuitable for comparison. As async results were variable do to writback timings, I'm only reporting the maximum figures. The sync results were stable enough to make the mean and stddev uninteresting. The performance results are reported based on a run with no profiling. Profile data is based on a separate run with oprofile running. async dd 3.15.0-rc3 3.15.0-rc3 vanilla accessed-v2 ext3 Max elapsed 13.9900 ( 0.00%) 11.5900 ( 17.16%) tmpfs Max elapsed 0.5100 ( 0.00%) 0.4900 ( 3.92%) btrfs Max elapsed 12.8100 ( 0.00%) 12.7800 ( 0.23%) ext4 Max elapsed 18.6000 ( 0.00%) 13.3400 ( 28.28%) xfs Max elapsed 12.5600 ( 0.00%) 2.0900 ( 83.36%) The XFS figure is a bit strange as it managed to avoid a worst case by sheer luck but the average figures looked reasonable. samples percentage ext3 86107 0.9783 vmlinux-3.15.0-rc4-vanilla mark_page_accessed ext3 23833 0.2710 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed ext3 5036 0.0573 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed ext4 64566 0.8961 vmlinux-3.15.0-rc4-vanilla mark_page_accessed ext4 5322 0.0713 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed ext4 2869 0.0384 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed xfs 62126 1.7675 vmlinux-3.15.0-rc4-vanilla mark_page_accessed xfs 1904 0.0554 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed xfs 103 0.0030 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed btrfs 10655 0.1338 vmlinux-3.15.0-rc4-vanilla mark_page_accessed btrfs 2020 0.0273 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed btrfs 587 0.0079 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed tmpfs 59562 3.2628 vmlinux-3.15.0-rc4-vanilla mark_page_accessed tmpfs 1210 0.0696 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed tmpfs 94 0.0054 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed [akpm@linux-foundation.org: don't run init_page_accessed() against an uninitialised pointer] Signed-off-by: Mel Gorman <mgorman@suse.de> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Jan Kara <jack@suse.cz> Cc: Michal Hocko <mhocko@suse.cz> Cc: Hugh Dickins <hughd@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Theodore Ts'o <tytso@mit.edu> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Tested-by: Prabhakar Lad <prabhakar.csengg@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-06-04 23:10:31 +00:00
EXPORT_SYMBOL(pagecache_get_page);
2014-04-03 21:47:46 +00:00
/**
* find_get_entries - gang pagecache lookup
* @mapping: The address_space to search
* @start: The starting page cache index
* @nr_entries: The maximum number of entries
* @entries: Where the resulting entries are placed
* @indices: The cache indices corresponding to the entries in @entries
*
* find_get_entries() will search for and return a group of up to
* @nr_entries entries in the mapping. The entries are placed at
* @entries. find_get_entries() takes a reference against any actual
* pages it returns.
*
* The search returns a group of mapping-contiguous page cache entries
* with ascending indexes. There may be holes in the indices due to
* not-present pages.
*
mm: filemap: update find_get_pages_tag() to deal with shadow entries Dave Jones reports the following crash when find_get_pages_tag() runs into an exceptional entry: kernel BUG at mm/filemap.c:1347! RIP: find_get_pages_tag+0x1cb/0x220 Call Trace: find_get_pages_tag+0x36/0x220 pagevec_lookup_tag+0x21/0x30 filemap_fdatawait_range+0xbe/0x1e0 filemap_fdatawait+0x27/0x30 sync_inodes_sb+0x204/0x2a0 sync_inodes_one_sb+0x19/0x20 iterate_supers+0xb2/0x110 sys_sync+0x44/0xb0 ia32_do_call+0x13/0x13 1343 /* 1344 * This function is never used on a shmem/tmpfs 1345 * mapping, so a swap entry won't be found here. 1346 */ 1347 BUG(); After commit 0cd6144aadd2 ("mm + fs: prepare for non-page entries in page cache radix trees") this comment and BUG() are out of date because exceptional entries can now appear in all mappings - as shadows of recently evicted pages. However, as Hugh Dickins notes, "it is truly surprising for a PAGECACHE_TAG_WRITEBACK (and probably any other PAGECACHE_TAG_*) to appear on an exceptional entry. I expect it comes down to an occasional race in RCU lookup of the radix_tree: lacking absolute synchronization, we might sometimes catch an exceptional entry, with the tag which really belongs with the unexceptional entry which was there an instant before." And indeed, not only is the tree walk lockless, the tags are also read in chunks, one radix tree node at a time. There is plenty of time for page reclaim to swoop in and replace a page that was already looked up as tagged with a shadow entry. Remove the BUG() and update the comment. While reviewing all other lookup sites for whether they properly deal with shadow entries of evicted pages, update all the comments and fix memcg file charge moving to not miss shmem/tmpfs swapcache pages. Fixes: 0cd6144aadd2 ("mm + fs: prepare for non-page entries in page cache radix trees") Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reported-by: Dave Jones <davej@redhat.com> Acked-by: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-05-06 19:50:05 +00:00
* Any shadow entries of evicted pages, or swap entries from
* shmem/tmpfs, are included in the returned array.
2014-04-03 21:47:46 +00:00
*
* find_get_entries() returns the number of pages and shadow entries
* which were found.
*/
unsigned find_get_entries(struct address_space *mapping,
pgoff_t start, unsigned int nr_entries,
struct page **entries, pgoff_t *indices)
{
void **slot;
unsigned int ret = 0;
struct radix_tree_iter iter;
if (!nr_entries)
return 0;
rcu_read_lock();
restart:
radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, start) {
struct page *page;
repeat:
page = radix_tree_deref_slot(slot);
if (unlikely(!page))
continue;
if (radix_tree_exception(page)) {
if (radix_tree_deref_retry(page))
goto restart;
/*
mm: filemap: update find_get_pages_tag() to deal with shadow entries Dave Jones reports the following crash when find_get_pages_tag() runs into an exceptional entry: kernel BUG at mm/filemap.c:1347! RIP: find_get_pages_tag+0x1cb/0x220 Call Trace: find_get_pages_tag+0x36/0x220 pagevec_lookup_tag+0x21/0x30 filemap_fdatawait_range+0xbe/0x1e0 filemap_fdatawait+0x27/0x30 sync_inodes_sb+0x204/0x2a0 sync_inodes_one_sb+0x19/0x20 iterate_supers+0xb2/0x110 sys_sync+0x44/0xb0 ia32_do_call+0x13/0x13 1343 /* 1344 * This function is never used on a shmem/tmpfs 1345 * mapping, so a swap entry won't be found here. 1346 */ 1347 BUG(); After commit 0cd6144aadd2 ("mm + fs: prepare for non-page entries in page cache radix trees") this comment and BUG() are out of date because exceptional entries can now appear in all mappings - as shadows of recently evicted pages. However, as Hugh Dickins notes, "it is truly surprising for a PAGECACHE_TAG_WRITEBACK (and probably any other PAGECACHE_TAG_*) to appear on an exceptional entry. I expect it comes down to an occasional race in RCU lookup of the radix_tree: lacking absolute synchronization, we might sometimes catch an exceptional entry, with the tag which really belongs with the unexceptional entry which was there an instant before." And indeed, not only is the tree walk lockless, the tags are also read in chunks, one radix tree node at a time. There is plenty of time for page reclaim to swoop in and replace a page that was already looked up as tagged with a shadow entry. Remove the BUG() and update the comment. While reviewing all other lookup sites for whether they properly deal with shadow entries of evicted pages, update all the comments and fix memcg file charge moving to not miss shmem/tmpfs swapcache pages. Fixes: 0cd6144aadd2 ("mm + fs: prepare for non-page entries in page cache radix trees") Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reported-by: Dave Jones <davej@redhat.com> Acked-by: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-05-06 19:50:05 +00:00
* A shadow entry of a recently evicted page,
* or a swap entry from shmem/tmpfs. Return
* it without attempting to raise page count.
2014-04-03 21:47:46 +00:00
*/
goto export;
}
if (!page_cache_get_speculative(page))
goto repeat;
/* Has the page moved? */
if (unlikely(page != *slot)) {
page_cache_release(page);
goto repeat;
}
export:
indices[ret] = iter.index;
entries[ret] = page;
if (++ret == nr_entries)
break;
}
rcu_read_unlock();
return ret;
}
/**
* 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)
{
struct radix_tree_iter iter;
void **slot;
unsigned ret = 0;
if (unlikely(!nr_pages))
return 0;
rcu_read_lock();
restart:
radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, start) {
struct page *page;
repeat:
page = radix_tree_deref_slot(slot);
if (unlikely(!page))
continue;
mm: let swap use exceptional entries If swap entries are to be stored along with struct page pointers in a radix tree, they need to be distinguished as exceptional entries. Most of the handling of swap entries in radix tree will be contained in shmem.c, but a few functions in filemap.c's common code need to check for their appearance: find_get_page(), find_lock_page(), find_get_pages() and find_get_pages_contig(). So as not to slow their fast paths, tuck those checks inside the existing checks for unlikely radix_tree_deref_slot(); except for find_lock_page(), where it is an added test. And make it a BUG in find_get_pages_tag(), which is not applied to tmpfs files. A part of the reason for eliminating shmem_readpage() earlier, was to minimize the places where common code would need to allow for swap entries. The swp_entry_t known to swapfile.c must be massaged into a slightly different form when stored in the radix tree, just as it gets massaged into a pte_t when stored in page tables. In an i386 kernel this limits its information (type and page offset) to 30 bits: given 32 "types" of swapfile and 4kB pagesize, that's a maximum swapfile size of 128GB. Which is less than the 512GB we previously allowed with X86_PAE (where the swap entry can occupy the entire upper 32 bits of a pte_t), but not a new limitation on 32-bit without PAE; and there's not a new limitation on 64-bit (where swap filesize is already limited to 16TB by a 32-bit page offset). Thirty areas of 128GB is probably still enough swap for a 64GB 32-bit machine. Provide swp_to_radix_entry() and radix_to_swp_entry() conversions, and enforce filesize limit in read_swap_header(), just as for ptes. Signed-off-by: Hugh Dickins <hughd@google.com> Acked-by: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-08-03 23:21:19 +00:00
if (radix_tree_exception(page)) {
if (radix_tree_deref_retry(page)) {
/*
* Transient condition which can only trigger
* when entry at index 0 moves out of or back
* to root: none yet gotten, safe to restart.
*/
WARN_ON(iter.index);
goto restart;
}
mm: let swap use exceptional entries If swap entries are to be stored along with struct page pointers in a radix tree, they need to be distinguished as exceptional entries. Most of the handling of swap entries in radix tree will be contained in shmem.c, but a few functions in filemap.c's common code need to check for their appearance: find_get_page(), find_lock_page(), find_get_pages() and find_get_pages_contig(). So as not to slow their fast paths, tuck those checks inside the existing checks for unlikely radix_tree_deref_slot(); except for find_lock_page(), where it is an added test. And make it a BUG in find_get_pages_tag(), which is not applied to tmpfs files. A part of the reason for eliminating shmem_readpage() earlier, was to minimize the places where common code would need to allow for swap entries. The swp_entry_t known to swapfile.c must be massaged into a slightly different form when stored in the radix tree, just as it gets massaged into a pte_t when stored in page tables. In an i386 kernel this limits its information (type and page offset) to 30 bits: given 32 "types" of swapfile and 4kB pagesize, that's a maximum swapfile size of 128GB. Which is less than the 512GB we previously allowed with X86_PAE (where the swap entry can occupy the entire upper 32 bits of a pte_t), but not a new limitation on 32-bit without PAE; and there's not a new limitation on 64-bit (where swap filesize is already limited to 16TB by a 32-bit page offset). Thirty areas of 128GB is probably still enough swap for a 64GB 32-bit machine. Provide swp_to_radix_entry() and radix_to_swp_entry() conversions, and enforce filesize limit in read_swap_header(), just as for ptes. Signed-off-by: Hugh Dickins <hughd@google.com> Acked-by: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-08-03 23:21:19 +00:00
/*
mm: filemap: update find_get_pages_tag() to deal with shadow entries Dave Jones reports the following crash when find_get_pages_tag() runs into an exceptional entry: kernel BUG at mm/filemap.c:1347! RIP: find_get_pages_tag+0x1cb/0x220 Call Trace: find_get_pages_tag+0x36/0x220 pagevec_lookup_tag+0x21/0x30 filemap_fdatawait_range+0xbe/0x1e0 filemap_fdatawait+0x27/0x30 sync_inodes_sb+0x204/0x2a0 sync_inodes_one_sb+0x19/0x20 iterate_supers+0xb2/0x110 sys_sync+0x44/0xb0 ia32_do_call+0x13/0x13 1343 /* 1344 * This function is never used on a shmem/tmpfs 1345 * mapping, so a swap entry won't be found here. 1346 */ 1347 BUG(); After commit 0cd6144aadd2 ("mm + fs: prepare for non-page entries in page cache radix trees") this comment and BUG() are out of date because exceptional entries can now appear in all mappings - as shadows of recently evicted pages. However, as Hugh Dickins notes, "it is truly surprising for a PAGECACHE_TAG_WRITEBACK (and probably any other PAGECACHE_TAG_*) to appear on an exceptional entry. I expect it comes down to an occasional race in RCU lookup of the radix_tree: lacking absolute synchronization, we might sometimes catch an exceptional entry, with the tag which really belongs with the unexceptional entry which was there an instant before." And indeed, not only is the tree walk lockless, the tags are also read in chunks, one radix tree node at a time. There is plenty of time for page reclaim to swoop in and replace a page that was already looked up as tagged with a shadow entry. Remove the BUG() and update the comment. While reviewing all other lookup sites for whether they properly deal with shadow entries of evicted pages, update all the comments and fix memcg file charge moving to not miss shmem/tmpfs swapcache pages. Fixes: 0cd6144aadd2 ("mm + fs: prepare for non-page entries in page cache radix trees") Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reported-by: Dave Jones <davej@redhat.com> Acked-by: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-05-06 19:50:05 +00:00
* A shadow entry of a recently evicted page,
* or a swap entry from shmem/tmpfs. Skip
* over it.
mm: let swap use exceptional entries If swap entries are to be stored along with struct page pointers in a radix tree, they need to be distinguished as exceptional entries. Most of the handling of swap entries in radix tree will be contained in shmem.c, but a few functions in filemap.c's common code need to check for their appearance: find_get_page(), find_lock_page(), find_get_pages() and find_get_pages_contig(). So as not to slow their fast paths, tuck those checks inside the existing checks for unlikely radix_tree_deref_slot(); except for find_lock_page(), where it is an added test. And make it a BUG in find_get_pages_tag(), which is not applied to tmpfs files. A part of the reason for eliminating shmem_readpage() earlier, was to minimize the places where common code would need to allow for swap entries. The swp_entry_t known to swapfile.c must be massaged into a slightly different form when stored in the radix tree, just as it gets massaged into a pte_t when stored in page tables. In an i386 kernel this limits its information (type and page offset) to 30 bits: given 32 "types" of swapfile and 4kB pagesize, that's a maximum swapfile size of 128GB. Which is less than the 512GB we previously allowed with X86_PAE (where the swap entry can occupy the entire upper 32 bits of a pte_t), but not a new limitation on 32-bit without PAE; and there's not a new limitation on 64-bit (where swap filesize is already limited to 16TB by a 32-bit page offset). Thirty areas of 128GB is probably still enough swap for a 64GB 32-bit machine. Provide swp_to_radix_entry() and radix_to_swp_entry() conversions, and enforce filesize limit in read_swap_header(), just as for ptes. Signed-off-by: Hugh Dickins <hughd@google.com> Acked-by: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-08-03 23:21:19 +00:00
*/
continue;
}
if (!page_cache_get_speculative(page))
goto repeat;
/* Has the page moved? */
if (unlikely(page != *slot)) {
page_cache_release(page);
goto repeat;
}
pages[ret] = page;
if (++ret == nr_pages)
break;
}
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)
{
struct radix_tree_iter iter;
void **slot;
unsigned int ret = 0;
if (unlikely(!nr_pages))
return 0;
rcu_read_lock();
restart:
radix_tree_for_each_contig(slot, &mapping->page_tree, &iter, index) {
struct page *page;
repeat:
page = radix_tree_deref_slot(slot);
/* The hole, there no reason to continue */
if (unlikely(!page))
break;
mm: let swap use exceptional entries If swap entries are to be stored along with struct page pointers in a radix tree, they need to be distinguished as exceptional entries. Most of the handling of swap entries in radix tree will be contained in shmem.c, but a few functions in filemap.c's common code need to check for their appearance: find_get_page(), find_lock_page(), find_get_pages() and find_get_pages_contig(). So as not to slow their fast paths, tuck those checks inside the existing checks for unlikely radix_tree_deref_slot(); except for find_lock_page(), where it is an added test. And make it a BUG in find_get_pages_tag(), which is not applied to tmpfs files. A part of the reason for eliminating shmem_readpage() earlier, was to minimize the places where common code would need to allow for swap entries. The swp_entry_t known to swapfile.c must be massaged into a slightly different form when stored in the radix tree, just as it gets massaged into a pte_t when stored in page tables. In an i386 kernel this limits its information (type and page offset) to 30 bits: given 32 "types" of swapfile and 4kB pagesize, that's a maximum swapfile size of 128GB. Which is less than the 512GB we previously allowed with X86_PAE (where the swap entry can occupy the entire upper 32 bits of a pte_t), but not a new limitation on 32-bit without PAE; and there's not a new limitation on 64-bit (where swap filesize is already limited to 16TB by a 32-bit page offset). Thirty areas of 128GB is probably still enough swap for a 64GB 32-bit machine. Provide swp_to_radix_entry() and radix_to_swp_entry() conversions, and enforce filesize limit in read_swap_header(), just as for ptes. Signed-off-by: Hugh Dickins <hughd@google.com> Acked-by: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-08-03 23:21:19 +00:00
if (radix_tree_exception(page)) {
if (radix_tree_deref_retry(page)) {
/*
* Transient condition which can only trigger
* when entry at index 0 moves out of or back
* to root: none yet gotten, safe to restart.
*/
goto restart;
}
mm: let swap use exceptional entries If swap entries are to be stored along with struct page pointers in a radix tree, they need to be distinguished as exceptional entries. Most of the handling of swap entries in radix tree will be contained in shmem.c, but a few functions in filemap.c's common code need to check for their appearance: find_get_page(), find_lock_page(), find_get_pages() and find_get_pages_contig(). So as not to slow their fast paths, tuck those checks inside the existing checks for unlikely radix_tree_deref_slot(); except for find_lock_page(), where it is an added test. And make it a BUG in find_get_pages_tag(), which is not applied to tmpfs files. A part of the reason for eliminating shmem_readpage() earlier, was to minimize the places where common code would need to allow for swap entries. The swp_entry_t known to swapfile.c must be massaged into a slightly different form when stored in the radix tree, just as it gets massaged into a pte_t when stored in page tables. In an i386 kernel this limits its information (type and page offset) to 30 bits: given 32 "types" of swapfile and 4kB pagesize, that's a maximum swapfile size of 128GB. Which is less than the 512GB we previously allowed with X86_PAE (where the swap entry can occupy the entire upper 32 bits of a pte_t), but not a new limitation on 32-bit without PAE; and there's not a new limitation on 64-bit (where swap filesize is already limited to 16TB by a 32-bit page offset). Thirty areas of 128GB is probably still enough swap for a 64GB 32-bit machine. Provide swp_to_radix_entry() and radix_to_swp_entry() conversions, and enforce filesize limit in read_swap_header(), just as for ptes. Signed-off-by: Hugh Dickins <hughd@google.com> Acked-by: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-08-03 23:21:19 +00:00
/*
mm: filemap: update find_get_pages_tag() to deal with shadow entries Dave Jones reports the following crash when find_get_pages_tag() runs into an exceptional entry: kernel BUG at mm/filemap.c:1347! RIP: find_get_pages_tag+0x1cb/0x220 Call Trace: find_get_pages_tag+0x36/0x220 pagevec_lookup_tag+0x21/0x30 filemap_fdatawait_range+0xbe/0x1e0 filemap_fdatawait+0x27/0x30 sync_inodes_sb+0x204/0x2a0 sync_inodes_one_sb+0x19/0x20 iterate_supers+0xb2/0x110 sys_sync+0x44/0xb0 ia32_do_call+0x13/0x13 1343 /* 1344 * This function is never used on a shmem/tmpfs 1345 * mapping, so a swap entry won't be found here. 1346 */ 1347 BUG(); After commit 0cd6144aadd2 ("mm + fs: prepare for non-page entries in page cache radix trees") this comment and BUG() are out of date because exceptional entries can now appear in all mappings - as shadows of recently evicted pages. However, as Hugh Dickins notes, "it is truly surprising for a PAGECACHE_TAG_WRITEBACK (and probably any other PAGECACHE_TAG_*) to appear on an exceptional entry. I expect it comes down to an occasional race in RCU lookup of the radix_tree: lacking absolute synchronization, we might sometimes catch an exceptional entry, with the tag which really belongs with the unexceptional entry which was there an instant before." And indeed, not only is the tree walk lockless, the tags are also read in chunks, one radix tree node at a time. There is plenty of time for page reclaim to swoop in and replace a page that was already looked up as tagged with a shadow entry. Remove the BUG() and update the comment. While reviewing all other lookup sites for whether they properly deal with shadow entries of evicted pages, update all the comments and fix memcg file charge moving to not miss shmem/tmpfs swapcache pages. Fixes: 0cd6144aadd2 ("mm + fs: prepare for non-page entries in page cache radix trees") Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reported-by: Dave Jones <davej@redhat.com> Acked-by: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-05-06 19:50:05 +00:00
* A shadow entry of a recently evicted page,
* or a swap entry from shmem/tmpfs. Stop
* looking for contiguous pages.
mm: let swap use exceptional entries If swap entries are to be stored along with struct page pointers in a radix tree, they need to be distinguished as exceptional entries. Most of the handling of swap entries in radix tree will be contained in shmem.c, but a few functions in filemap.c's common code need to check for their appearance: find_get_page(), find_lock_page(), find_get_pages() and find_get_pages_contig(). So as not to slow their fast paths, tuck those checks inside the existing checks for unlikely radix_tree_deref_slot(); except for find_lock_page(), where it is an added test. And make it a BUG in find_get_pages_tag(), which is not applied to tmpfs files. A part of the reason for eliminating shmem_readpage() earlier, was to minimize the places where common code would need to allow for swap entries. The swp_entry_t known to swapfile.c must be massaged into a slightly different form when stored in the radix tree, just as it gets massaged into a pte_t when stored in page tables. In an i386 kernel this limits its information (type and page offset) to 30 bits: given 32 "types" of swapfile and 4kB pagesize, that's a maximum swapfile size of 128GB. Which is less than the 512GB we previously allowed with X86_PAE (where the swap entry can occupy the entire upper 32 bits of a pte_t), but not a new limitation on 32-bit without PAE; and there's not a new limitation on 64-bit (where swap filesize is already limited to 16TB by a 32-bit page offset). Thirty areas of 128GB is probably still enough swap for a 64GB 32-bit machine. Provide swp_to_radix_entry() and radix_to_swp_entry() conversions, and enforce filesize limit in read_swap_header(), just as for ptes. Signed-off-by: Hugh Dickins <hughd@google.com> Acked-by: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-08-03 23:21:19 +00:00
*/
break;
mm: let swap use exceptional entries If swap entries are to be stored along with struct page pointers in a radix tree, they need to be distinguished as exceptional entries. Most of the handling of swap entries in radix tree will be contained in shmem.c, but a few functions in filemap.c's common code need to check for their appearance: find_get_page(), find_lock_page(), find_get_pages() and find_get_pages_contig(). So as not to slow their fast paths, tuck those checks inside the existing checks for unlikely radix_tree_deref_slot(); except for find_lock_page(), where it is an added test. And make it a BUG in find_get_pages_tag(), which is not applied to tmpfs files. A part of the reason for eliminating shmem_readpage() earlier, was to minimize the places where common code would need to allow for swap entries. The swp_entry_t known to swapfile.c must be massaged into a slightly different form when stored in the radix tree, just as it gets massaged into a pte_t when stored in page tables. In an i386 kernel this limits its information (type and page offset) to 30 bits: given 32 "types" of swapfile and 4kB pagesize, that's a maximum swapfile size of 128GB. Which is less than the 512GB we previously allowed with X86_PAE (where the swap entry can occupy the entire upper 32 bits of a pte_t), but not a new limitation on 32-bit without PAE; and there's not a new limitation on 64-bit (where swap filesize is already limited to 16TB by a 32-bit page offset). Thirty areas of 128GB is probably still enough swap for a 64GB 32-bit machine. Provide swp_to_radix_entry() and radix_to_swp_entry() conversions, and enforce filesize limit in read_swap_header(), just as for ptes. Signed-off-by: Hugh Dickins <hughd@google.com> Acked-by: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-08-03 23:21:19 +00:00
}
if (!page_cache_get_speculative(page))
goto repeat;
/* Has the page moved? */
if (unlikely(page != *slot)) {
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 != iter.index) {
page_cache_release(page);
break;
}
pages[ret] = page;
if (++ret == nr_pages)
break;
}
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)
{
struct radix_tree_iter iter;
void **slot;
unsigned ret = 0;
if (unlikely(!nr_pages))
return 0;
rcu_read_lock();
restart:
radix_tree_for_each_tagged(slot, &mapping->page_tree,
&iter, *index, tag) {
struct page *page;
repeat:
page = radix_tree_deref_slot(slot);
if (unlikely(!page))
continue;
mm: let swap use exceptional entries If swap entries are to be stored along with struct page pointers in a radix tree, they need to be distinguished as exceptional entries. Most of the handling of swap entries in radix tree will be contained in shmem.c, but a few functions in filemap.c's common code need to check for their appearance: find_get_page(), find_lock_page(), find_get_pages() and find_get_pages_contig(). So as not to slow their fast paths, tuck those checks inside the existing checks for unlikely radix_tree_deref_slot(); except for find_lock_page(), where it is an added test. And make it a BUG in find_get_pages_tag(), which is not applied to tmpfs files. A part of the reason for eliminating shmem_readpage() earlier, was to minimize the places where common code would need to allow for swap entries. The swp_entry_t known to swapfile.c must be massaged into a slightly different form when stored in the radix tree, just as it gets massaged into a pte_t when stored in page tables. In an i386 kernel this limits its information (type and page offset) to 30 bits: given 32 "types" of swapfile and 4kB pagesize, that's a maximum swapfile size of 128GB. Which is less than the 512GB we previously allowed with X86_PAE (where the swap entry can occupy the entire upper 32 bits of a pte_t), but not a new limitation on 32-bit without PAE; and there's not a new limitation on 64-bit (where swap filesize is already limited to 16TB by a 32-bit page offset). Thirty areas of 128GB is probably still enough swap for a 64GB 32-bit machine. Provide swp_to_radix_entry() and radix_to_swp_entry() conversions, and enforce filesize limit in read_swap_header(), just as for ptes. Signed-off-by: Hugh Dickins <hughd@google.com> Acked-by: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-08-03 23:21:19 +00:00
if (radix_tree_exception(page)) {
if (radix_tree_deref_retry(page)) {
/*
* Transient condition which can only trigger
* when entry at index 0 moves out of or back
* to root: none yet gotten, safe to restart.
*/
goto restart;
}
mm: let swap use exceptional entries If swap entries are to be stored along with struct page pointers in a radix tree, they need to be distinguished as exceptional entries. Most of the handling of swap entries in radix tree will be contained in shmem.c, but a few functions in filemap.c's common code need to check for their appearance: find_get_page(), find_lock_page(), find_get_pages() and find_get_pages_contig(). So as not to slow their fast paths, tuck those checks inside the existing checks for unlikely radix_tree_deref_slot(); except for find_lock_page(), where it is an added test. And make it a BUG in find_get_pages_tag(), which is not applied to tmpfs files. A part of the reason for eliminating shmem_readpage() earlier, was to minimize the places where common code would need to allow for swap entries. The swp_entry_t known to swapfile.c must be massaged into a slightly different form when stored in the radix tree, just as it gets massaged into a pte_t when stored in page tables. In an i386 kernel this limits its information (type and page offset) to 30 bits: given 32 "types" of swapfile and 4kB pagesize, that's a maximum swapfile size of 128GB. Which is less than the 512GB we previously allowed with X86_PAE (where the swap entry can occupy the entire upper 32 bits of a pte_t), but not a new limitation on 32-bit without PAE; and there's not a new limitation on 64-bit (where swap filesize is already limited to 16TB by a 32-bit page offset). Thirty areas of 128GB is probably still enough swap for a 64GB 32-bit machine. Provide swp_to_radix_entry() and radix_to_swp_entry() conversions, and enforce filesize limit in read_swap_header(), just as for ptes. Signed-off-by: Hugh Dickins <hughd@google.com> Acked-by: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-08-03 23:21:19 +00:00
/*
mm: filemap: update find_get_pages_tag() to deal with shadow entries Dave Jones reports the following crash when find_get_pages_tag() runs into an exceptional entry: kernel BUG at mm/filemap.c:1347! RIP: find_get_pages_tag+0x1cb/0x220 Call Trace: find_get_pages_tag+0x36/0x220 pagevec_lookup_tag+0x21/0x30 filemap_fdatawait_range+0xbe/0x1e0 filemap_fdatawait+0x27/0x30 sync_inodes_sb+0x204/0x2a0 sync_inodes_one_sb+0x19/0x20 iterate_supers+0xb2/0x110 sys_sync+0x44/0xb0 ia32_do_call+0x13/0x13 1343 /* 1344 * This function is never used on a shmem/tmpfs 1345 * mapping, so a swap entry won't be found here. 1346 */ 1347 BUG(); After commit 0cd6144aadd2 ("mm + fs: prepare for non-page entries in page cache radix trees") this comment and BUG() are out of date because exceptional entries can now appear in all mappings - as shadows of recently evicted pages. However, as Hugh Dickins notes, "it is truly surprising for a PAGECACHE_TAG_WRITEBACK (and probably any other PAGECACHE_TAG_*) to appear on an exceptional entry. I expect it comes down to an occasional race in RCU lookup of the radix_tree: lacking absolute synchronization, we might sometimes catch an exceptional entry, with the tag which really belongs with the unexceptional entry which was there an instant before." And indeed, not only is the tree walk lockless, the tags are also read in chunks, one radix tree node at a time. There is plenty of time for page reclaim to swoop in and replace a page that was already looked up as tagged with a shadow entry. Remove the BUG() and update the comment. While reviewing all other lookup sites for whether they properly deal with shadow entries of evicted pages, update all the comments and fix memcg file charge moving to not miss shmem/tmpfs swapcache pages. Fixes: 0cd6144aadd2 ("mm + fs: prepare for non-page entries in page cache radix trees") Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reported-by: Dave Jones <davej@redhat.com> Acked-by: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-05-06 19:50:05 +00:00
* A shadow entry of a recently evicted page.
*
* Those entries should never be tagged, but
* this tree walk is lockless and the tags are
* looked up in bulk, one radix tree node at a
* time, so there is a sizable window for page
* reclaim to evict a page we saw tagged.
*
* Skip over it.
mm: let swap use exceptional entries If swap entries are to be stored along with struct page pointers in a radix tree, they need to be distinguished as exceptional entries. Most of the handling of swap entries in radix tree will be contained in shmem.c, but a few functions in filemap.c's common code need to check for their appearance: find_get_page(), find_lock_page(), find_get_pages() and find_get_pages_contig(). So as not to slow their fast paths, tuck those checks inside the existing checks for unlikely radix_tree_deref_slot(); except for find_lock_page(), where it is an added test. And make it a BUG in find_get_pages_tag(), which is not applied to tmpfs files. A part of the reason for eliminating shmem_readpage() earlier, was to minimize the places where common code would need to allow for swap entries. The swp_entry_t known to swapfile.c must be massaged into a slightly different form when stored in the radix tree, just as it gets massaged into a pte_t when stored in page tables. In an i386 kernel this limits its information (type and page offset) to 30 bits: given 32 "types" of swapfile and 4kB pagesize, that's a maximum swapfile size of 128GB. Which is less than the 512GB we previously allowed with X86_PAE (where the swap entry can occupy the entire upper 32 bits of a pte_t), but not a new limitation on 32-bit without PAE; and there's not a new limitation on 64-bit (where swap filesize is already limited to 16TB by a 32-bit page offset). Thirty areas of 128GB is probably still enough swap for a 64GB 32-bit machine. Provide swp_to_radix_entry() and radix_to_swp_entry() conversions, and enforce filesize limit in read_swap_header(), just as for ptes. Signed-off-by: Hugh Dickins <hughd@google.com> Acked-by: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-08-03 23:21:19 +00:00
*/
mm: filemap: update find_get_pages_tag() to deal with shadow entries Dave Jones reports the following crash when find_get_pages_tag() runs into an exceptional entry: kernel BUG at mm/filemap.c:1347! RIP: find_get_pages_tag+0x1cb/0x220 Call Trace: find_get_pages_tag+0x36/0x220 pagevec_lookup_tag+0x21/0x30 filemap_fdatawait_range+0xbe/0x1e0 filemap_fdatawait+0x27/0x30 sync_inodes_sb+0x204/0x2a0 sync_inodes_one_sb+0x19/0x20 iterate_supers+0xb2/0x110 sys_sync+0x44/0xb0 ia32_do_call+0x13/0x13 1343 /* 1344 * This function is never used on a shmem/tmpfs 1345 * mapping, so a swap entry won't be found here. 1346 */ 1347 BUG(); After commit 0cd6144aadd2 ("mm + fs: prepare for non-page entries in page cache radix trees") this comment and BUG() are out of date because exceptional entries can now appear in all mappings - as shadows of recently evicted pages. However, as Hugh Dickins notes, "it is truly surprising for a PAGECACHE_TAG_WRITEBACK (and probably any other PAGECACHE_TAG_*) to appear on an exceptional entry. I expect it comes down to an occasional race in RCU lookup of the radix_tree: lacking absolute synchronization, we might sometimes catch an exceptional entry, with the tag which really belongs with the unexceptional entry which was there an instant before." And indeed, not only is the tree walk lockless, the tags are also read in chunks, one radix tree node at a time. There is plenty of time for page reclaim to swoop in and replace a page that was already looked up as tagged with a shadow entry. Remove the BUG() and update the comment. While reviewing all other lookup sites for whether they properly deal with shadow entries of evicted pages, update all the comments and fix memcg file charge moving to not miss shmem/tmpfs swapcache pages. Fixes: 0cd6144aadd2 ("mm + fs: prepare for non-page entries in page cache radix trees") Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reported-by: Dave Jones <davej@redhat.com> Acked-by: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-05-06 19:50:05 +00:00
continue;
mm: let swap use exceptional entries If swap entries are to be stored along with struct page pointers in a radix tree, they need to be distinguished as exceptional entries. Most of the handling of swap entries in radix tree will be contained in shmem.c, but a few functions in filemap.c's common code need to check for their appearance: find_get_page(), find_lock_page(), find_get_pages() and find_get_pages_contig(). So as not to slow their fast paths, tuck those checks inside the existing checks for unlikely radix_tree_deref_slot(); except for find_lock_page(), where it is an added test. And make it a BUG in find_get_pages_tag(), which is not applied to tmpfs files. A part of the reason for eliminating shmem_readpage() earlier, was to minimize the places where common code would need to allow for swap entries. The swp_entry_t known to swapfile.c must be massaged into a slightly different form when stored in the radix tree, just as it gets massaged into a pte_t when stored in page tables. In an i386 kernel this limits its information (type and page offset) to 30 bits: given 32 "types" of swapfile and 4kB pagesize, that's a maximum swapfile size of 128GB. Which is less than the 512GB we previously allowed with X86_PAE (where the swap entry can occupy the entire upper 32 bits of a pte_t), but not a new limitation on 32-bit without PAE; and there's not a new limitation on 64-bit (where swap filesize is already limited to 16TB by a 32-bit page offset). Thirty areas of 128GB is probably still enough swap for a 64GB 32-bit machine. Provide swp_to_radix_entry() and radix_to_swp_entry() conversions, and enforce filesize limit in read_swap_header(), just as for ptes. Signed-off-by: Hugh Dickins <hughd@google.com> Acked-by: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-08-03 23:21:19 +00:00
}
if (!page_cache_get_speculative(page))
goto repeat;
/* Has the page moved? */
if (unlikely(page != *slot)) {
page_cache_release(page);
goto repeat;
}
pages[ret] = page;
if (++ret == nr_pages)
break;
}
rcu_read_unlock();
if (ret)
*index = pages[ret - 1]->index + 1;
return ret;
}
EXPORT_SYMBOL(find_get_pages_tag);
[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 12:48:43 +00:00
/*
* 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
* @iter: data destination
* @written: already copied
*
* 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 ssize_t do_generic_file_read(struct file *filp, loff_t *ppos,
struct iov_iter *iter, ssize_t written)
{
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 = 0;
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 + iter->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 11:03:04 +00:00
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>
2008-07-28 22:46:36 +00:00
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>
2008-07-28 22:46:36 +00:00
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>
2010-11-11 22:05:15 +00:00
/* 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>
2008-07-28 22:46:36 +00:00
if (!mapping->a_ops->is_partially_uptodate(page,
offset, iter->count))
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>
2008-07-28 22:46:36 +00:00
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 11:03:04 +00:00
/*
* 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...
*/
ret = copy_page_to_iter(page, offset, nr, iter);
offset += ret;
index += offset >> PAGE_CACHE_SHIFT;
offset &= ~PAGE_CACHE_MASK;
prev_offset = offset;
page_cache_release(page);
written += ret;
if (!iov_iter_count(iter))
goto out;
if (ret < nr) {
error = -EFAULT;
goto out;
}
continue;
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>
2008-07-28 22:46:36 +00:00
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);
error = 0;
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 */
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) {
error = -ENOMEM;
goto out;
}
error = add_to_page_cache_lru(page, mapping, index,
GFP_KERNEL & mapping_gfp_mask(mapping));
if (error) {
page_cache_release(page);
if (error == -EEXIST) {
error = 0;
goto find_page;
}
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);
return written ? written : error;
}
/**
* generic_file_read_iter - generic filesystem read routine
* @iocb: kernel I/O control block
* @iter: destination for the data read
*
* This is the "read_iter()" routine for all filesystems
* that can use the page cache directly.
*/
ssize_t
generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
{
struct file *file = iocb->ki_filp;
ssize_t retval = 0;
loff_t *ppos = &iocb->ki_pos;
loff_t pos = *ppos;
if (iocb->ki_flags & IOCB_DIRECT) {
struct address_space *mapping = file->f_mapping;
struct inode *inode = mapping->host;
size_t count = iov_iter_count(iter);
loff_t size;
if (!count)
goto out; /* skip atime */
size = i_size_read(inode);
Fix race when checking i_size on direct i/o read So far I've had one ACK for this, and no other comments. So I think it is probably time to send this via some suitable tree. I'm guessing that the vfs tree would be the most appropriate route, but not sure that there is one at the moment (don't see anything recent at kernel.org) so in that case I think -mm is the "back up plan". Al, please let me know if you will take this? Steve. --------------------- Following on from the "Re: [PATCH v3] vfs: fix a bug when we do some dio reads with append dio writes" thread on linux-fsdevel, this patch is my current version of the fix proposed as option (b) in that thread. Removing the i_size test from the direct i/o read path at vfs level means that filesystems now have to deal with requests which are beyond i_size themselves. These I've divided into three sets: a) Those with "no op" ->direct_IO (9p, cifs, ceph) These are obviously not going to be an issue b) Those with "home brew" ->direct_IO (nfs, fuse) I've been told that NFS should not have any problem with the larger i_size, however I've added an extra test to FUSE to duplicate the original behaviour just to be on the safe side. c) Those using __blockdev_direct_IO() These call through to ->get_block() which should deal with the EOF condition correctly. I've verified that with GFS2 and I believe that Zheng has verified it for ext4. I've also run the test on XFS and it passes both before and after this change. The part of the patch in filemap.c looks a lot larger than it really is - there are only two lines of real change. The rest is just indentation of the contained code. There remains a test of i_size though, which was added for btrfs. It doesn't cause the other filesystems a problem as the test is performed after ->direct_IO has been called. It is possible that there is a race that does matter to btrfs, however this patch doesn't change that, so its still an overall improvement. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com> Reported-by: Zheng Liu <gnehzuil.liu@gmail.com> Cc: Jan Kara <jack@suse.cz> Cc: Dave Chinner <david@fromorbit.com> Acked-by: Miklos Szeredi <miklos@szeredi.hu> Cc: Chris Mason <clm@fb.com> Cc: Josef Bacik <jbacik@fb.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2014-01-24 14:42:22 +00:00
retval = filemap_write_and_wait_range(mapping, pos,
pos + count - 1);
Fix race when checking i_size on direct i/o read So far I've had one ACK for this, and no other comments. So I think it is probably time to send this via some suitable tree. I'm guessing that the vfs tree would be the most appropriate route, but not sure that there is one at the moment (don't see anything recent at kernel.org) so in that case I think -mm is the "back up plan". Al, please let me know if you will take this? Steve. --------------------- Following on from the "Re: [PATCH v3] vfs: fix a bug when we do some dio reads with append dio writes" thread on linux-fsdevel, this patch is my current version of the fix proposed as option (b) in that thread. Removing the i_size test from the direct i/o read path at vfs level means that filesystems now have to deal with requests which are beyond i_size themselves. These I've divided into three sets: a) Those with "no op" ->direct_IO (9p, cifs, ceph) These are obviously not going to be an issue b) Those with "home brew" ->direct_IO (nfs, fuse) I've been told that NFS should not have any problem with the larger i_size, however I've added an extra test to FUSE to duplicate the original behaviour just to be on the safe side. c) Those using __blockdev_direct_IO() These call through to ->get_block() which should deal with the EOF condition correctly. I've verified that with GFS2 and I believe that Zheng has verified it for ext4. I've also run the test on XFS and it passes both before and after this change. The part of the patch in filemap.c looks a lot larger than it really is - there are only two lines of real change. The rest is just indentation of the contained code. There remains a test of i_size though, which was added for btrfs. It doesn't cause the other filesystems a problem as the test is performed after ->direct_IO has been called. It is possible that there is a race that does matter to btrfs, however this patch doesn't change that, so its still an overall improvement. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com> Reported-by: Zheng Liu <gnehzuil.liu@gmail.com> Cc: Jan Kara <jack@suse.cz> Cc: Dave Chinner <david@fromorbit.com> Acked-by: Miklos Szeredi <miklos@szeredi.hu> Cc: Chris Mason <clm@fb.com> Cc: Josef Bacik <jbacik@fb.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2014-01-24 14:42:22 +00:00
if (!retval) {
struct iov_iter data = *iter;
retval = mapping->a_ops->direct_IO(iocb, &data, pos);
Fix race when checking i_size on direct i/o read So far I've had one ACK for this, and no other comments. So I think it is probably time to send this via some suitable tree. I'm guessing that the vfs tree would be the most appropriate route, but not sure that there is one at the moment (don't see anything recent at kernel.org) so in that case I think -mm is the "back up plan". Al, please let me know if you will take this? Steve. --------------------- Following on from the "Re: [PATCH v3] vfs: fix a bug when we do some dio reads with append dio writes" thread on linux-fsdevel, this patch is my current version of the fix proposed as option (b) in that thread. Removing the i_size test from the direct i/o read path at vfs level means that filesystems now have to deal with requests which are beyond i_size themselves. These I've divided into three sets: a) Those with "no op" ->direct_IO (9p, cifs, ceph) These are obviously not going to be an issue b) Those with "home brew" ->direct_IO (nfs, fuse) I've been told that NFS should not have any problem with the larger i_size, however I've added an extra test to FUSE to duplicate the original behaviour just to be on the safe side. c) Those using __blockdev_direct_IO() These call through to ->get_block() which should deal with the EOF condition correctly. I've verified that with GFS2 and I believe that Zheng has verified it for ext4. I've also run the test on XFS and it passes both before and after this change. The part of the patch in filemap.c looks a lot larger than it really is - there are only two lines of real change. The rest is just indentation of the contained code. There remains a test of i_size though, which was added for btrfs. It doesn't cause the other filesystems a problem as the test is performed after ->direct_IO has been called. It is possible that there is a race that does matter to btrfs, however this patch doesn't change that, so its still an overall improvement. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com> Reported-by: Zheng Liu <gnehzuil.liu@gmail.com> Cc: Jan Kara <jack@suse.cz> Cc: Dave Chinner <david@fromorbit.com> Acked-by: Miklos Szeredi <miklos@szeredi.hu> Cc: Chris Mason <clm@fb.com> Cc: Josef Bacik <jbacik@fb.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2014-01-24 14:42:22 +00:00
}
Fix race when checking i_size on direct i/o read So far I've had one ACK for this, and no other comments. So I think it is probably time to send this via some suitable tree. I'm guessing that the vfs tree would be the most appropriate route, but not sure that there is one at the moment (don't see anything recent at kernel.org) so in that case I think -mm is the "back up plan". Al, please let me know if you will take this? Steve. --------------------- Following on from the "Re: [PATCH v3] vfs: fix a bug when we do some dio reads with append dio writes" thread on linux-fsdevel, this patch is my current version of the fix proposed as option (b) in that thread. Removing the i_size test from the direct i/o read path at vfs level means that filesystems now have to deal with requests which are beyond i_size themselves. These I've divided into three sets: a) Those with "no op" ->direct_IO (9p, cifs, ceph) These are obviously not going to be an issue b) Those with "home brew" ->direct_IO (nfs, fuse) I've been told that NFS should not have any problem with the larger i_size, however I've added an extra test to FUSE to duplicate the original behaviour just to be on the safe side. c) Those using __blockdev_direct_IO() These call through to ->get_block() which should deal with the EOF condition correctly. I've verified that with GFS2 and I believe that Zheng has verified it for ext4. I've also run the test on XFS and it passes both before and after this change. The part of the patch in filemap.c looks a lot larger than it really is - there are only two lines of real change. The rest is just indentation of the contained code. There remains a test of i_size though, which was added for btrfs. It doesn't cause the other filesystems a problem as the test is performed after ->direct_IO has been called. It is possible that there is a race that does matter to btrfs, however this patch doesn't change that, so its still an overall improvement. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com> Reported-by: Zheng Liu <gnehzuil.liu@gmail.com> Cc: Jan Kara <jack@suse.cz> Cc: Dave Chinner <david@fromorbit.com> Acked-by: Miklos Szeredi <miklos@szeredi.hu> Cc: Chris Mason <clm@fb.com> Cc: Josef Bacik <jbacik@fb.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2014-01-24 14:42:22 +00:00
if (retval > 0) {
*ppos = pos + retval;
iov_iter_advance(iter, retval);
Fix race when checking i_size on direct i/o read So far I've had one ACK for this, and no other comments. So I think it is probably time to send this via some suitable tree. I'm guessing that the vfs tree would be the most appropriate route, but not sure that there is one at the moment (don't see anything recent at kernel.org) so in that case I think -mm is the "back up plan". Al, please let me know if you will take this? Steve. --------------------- Following on from the "Re: [PATCH v3] vfs: fix a bug when we do some dio reads with append dio writes" thread on linux-fsdevel, this patch is my current version of the fix proposed as option (b) in that thread. Removing the i_size test from the direct i/o read path at vfs level means that filesystems now have to deal with requests which are beyond i_size themselves. These I've divided into three sets: a) Those with "no op" ->direct_IO (9p, cifs, ceph) These are obviously not going to be an issue b) Those with "home brew" ->direct_IO (nfs, fuse) I've been told that NFS should not have any problem with the larger i_size, however I've added an extra test to FUSE to duplicate the original behaviour just to be on the safe side. c) Those using __blockdev_direct_IO() These call through to ->get_block() which should deal with the EOF condition correctly. I've verified that with GFS2 and I believe that Zheng has verified it for ext4. I've also run the test on XFS and it passes both before and after this change. The part of the patch in filemap.c looks a lot larger than it really is - there are only two lines of real change. The rest is just indentation of the contained code. There remains a test of i_size though, which was added for btrfs. It doesn't cause the other filesystems a problem as the test is performed after ->direct_IO has been called. It is possible that there is a race that does matter to btrfs, however this patch doesn't change that, so its still an overall improvement. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com> Reported-by: Zheng Liu <gnehzuil.liu@gmail.com> Cc: Jan Kara <jack@suse.cz> Cc: Dave Chinner <david@fromorbit.com> Acked-by: Miklos Szeredi <miklos@szeredi.hu> Cc: Chris Mason <clm@fb.com> Cc: Josef Bacik <jbacik@fb.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2014-01-24 14:42:22 +00:00
}
Fix race when checking i_size on direct i/o read So far I've had one ACK for this, and no other comments. So I think it is probably time to send this via some suitable tree. I'm guessing that the vfs tree would be the most appropriate route, but not sure that there is one at the moment (don't see anything recent at kernel.org) so in that case I think -mm is the "back up plan". Al, please let me know if you will take this? Steve. --------------------- Following on from the "Re: [PATCH v3] vfs: fix a bug when we do some dio reads with append dio writes" thread on linux-fsdevel, this patch is my current version of the fix proposed as option (b) in that thread. Removing the i_size test from the direct i/o read path at vfs level means that filesystems now have to deal with requests which are beyond i_size themselves. These I've divided into three sets: a) Those with "no op" ->direct_IO (9p, cifs, ceph) These are obviously not going to be an issue b) Those with "home brew" ->direct_IO (nfs, fuse) I've been told that NFS should not have any problem with the larger i_size, however I've added an extra test to FUSE to duplicate the original behaviour just to be on the safe side. c) Those using __blockdev_direct_IO() These call through to ->get_block() which should deal with the EOF condition correctly. I've verified that with GFS2 and I believe that Zheng has verified it for ext4. I've also run the test on XFS and it passes both before and after this change. The part of the patch in filemap.c looks a lot larger than it really is - there are only two lines of real change. The rest is just indentation of the contained code. There remains a test of i_size though, which was added for btrfs. It doesn't cause the other filesystems a problem as the test is performed after ->direct_IO has been called. It is possible that there is a race that does matter to btrfs, however this patch doesn't change that, so its still an overall improvement. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com> Reported-by: Zheng Liu <gnehzuil.liu@gmail.com> Cc: Jan Kara <jack@suse.cz> Cc: Dave Chinner <david@fromorbit.com> Acked-by: Miklos Szeredi <miklos@szeredi.hu> Cc: Chris Mason <clm@fb.com> Cc: Josef Bacik <jbacik@fb.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2014-01-24 14:42:22 +00:00
/*
* 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. Buffered reads will not work for
* DAX files, so don't bother trying.
Fix race when checking i_size on direct i/o read So far I've had one ACK for this, and no other comments. So I think it is probably time to send this via some suitable tree. I'm guessing that the vfs tree would be the most appropriate route, but not sure that there is one at the moment (don't see anything recent at kernel.org) so in that case I think -mm is the "back up plan". Al, please let me know if you will take this? Steve. --------------------- Following on from the "Re: [PATCH v3] vfs: fix a bug when we do some dio reads with append dio writes" thread on linux-fsdevel, this patch is my current version of the fix proposed as option (b) in that thread. Removing the i_size test from the direct i/o read path at vfs level means that filesystems now have to deal with requests which are beyond i_size themselves. These I've divided into three sets: a) Those with "no op" ->direct_IO (9p, cifs, ceph) These are obviously not going to be an issue b) Those with "home brew" ->direct_IO (nfs, fuse) I've been told that NFS should not have any problem with the larger i_size, however I've added an extra test to FUSE to duplicate the original behaviour just to be on the safe side. c) Those using __blockdev_direct_IO() These call through to ->get_block() which should deal with the EOF condition correctly. I've verified that with GFS2 and I believe that Zheng has verified it for ext4. I've also run the test on XFS and it passes both before and after this change. The part of the patch in filemap.c looks a lot larger than it really is - there are only two lines of real change. The rest is just indentation of the contained code. There remains a test of i_size though, which was added for btrfs. It doesn't cause the other filesystems a problem as the test is performed after ->direct_IO has been called. It is possible that there is a race that does matter to btrfs, however this patch doesn't change that, so its still an overall improvement. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com> Reported-by: Zheng Liu <gnehzuil.liu@gmail.com> Cc: Jan Kara <jack@suse.cz> Cc: Dave Chinner <david@fromorbit.com> Acked-by: Miklos Szeredi <miklos@szeredi.hu> Cc: Chris Mason <clm@fb.com> Cc: Josef Bacik <jbacik@fb.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2014-01-24 14:42:22 +00:00
*/
if (retval < 0 || !iov_iter_count(iter) || *ppos >= size ||
IS_DAX(inode)) {
file_accessed(file);
Fix race when checking i_size on direct i/o read So far I've had one ACK for this, and no other comments. So I think it is probably time to send this via some suitable tree. I'm guessing that the vfs tree would be the most appropriate route, but not sure that there is one at the moment (don't see anything recent at kernel.org) so in that case I think -mm is the "back up plan". Al, please let me know if you will take this? Steve. --------------------- Following on from the "Re: [PATCH v3] vfs: fix a bug when we do some dio reads with append dio writes" thread on linux-fsdevel, this patch is my current version of the fix proposed as option (b) in that thread. Removing the i_size test from the direct i/o read path at vfs level means that filesystems now have to deal with requests which are beyond i_size themselves. These I've divided into three sets: a) Those with "no op" ->direct_IO (9p, cifs, ceph) These are obviously not going to be an issue b) Those with "home brew" ->direct_IO (nfs, fuse) I've been told that NFS should not have any problem with the larger i_size, however I've added an extra test to FUSE to duplicate the original behaviour just to be on the safe side. c) Those using __blockdev_direct_IO() These call through to ->get_block() which should deal with the EOF condition correctly. I've verified that with GFS2 and I believe that Zheng has verified it for ext4. I've also run the test on XFS and it passes both before and after this change. The part of the patch in filemap.c looks a lot larger than it really is - there are only two lines of real change. The rest is just indentation of the contained code. There remains a test of i_size though, which was added for btrfs. It doesn't cause the other filesystems a problem as the test is performed after ->direct_IO has been called. It is possible that there is a race that does matter to btrfs, however this patch doesn't change that, so its still an overall improvement. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com> Reported-by: Zheng Liu <gnehzuil.liu@gmail.com> Cc: Jan Kara <jack@suse.cz> Cc: Dave Chinner <david@fromorbit.com> Acked-by: Miklos Szeredi <miklos@szeredi.hu> Cc: Chris Mason <clm@fb.com> Cc: Josef Bacik <jbacik@fb.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2014-01-24 14:42:22 +00:00
goto out;
}
}
retval = do_generic_file_read(file, ppos, iter, retval);
out:
return retval;
}
EXPORT_SYMBOL(generic_file_read_iter);
#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 & mapping_gfp_mask(mapping));
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 (vma->vm_flags & VM_RAND_READ)
return;
if (!ra->ra_pages)
return;
if (vma->vm_flags & VM_SEQ_READ) {
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>
2009-06-16 22:31:38 +00:00
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 (vma->vm_flags & VM_RAND_READ)
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>
2009-06-16 22:31:29 +00:00
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 08:46:59 +00:00
* 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 08:46:59 +00:00
* 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.
*
* vma->vm_mm->mmap_sem must be held on entry.
*
* If our return value has VM_FAULT_RETRY set, it's because
* lock_page_or_retry() returned 0.
* The mmap_sem has usually been released in this case.
* See __lock_page_or_retry() for the exception.
*
* If our return value does not have VM_FAULT_RETRY set, the mmap_sem
* has not been released.
*
* We never return with VM_FAULT_RETRY and a bit from VM_FAULT_ERROR set.
*/
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 08:46:59 +00:00
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;
loff_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 08:47:05 +00:00
int ret = 0;
size = round_up(i_size_read(inode), PAGE_CACHE_SIZE);
if (offset >= size >> PAGE_CACHE_SHIFT)
return VM_FAULT_SIGBUS;
/*
* Do we have something in the page cache already?
*/
page = find_get_page(mapping, offset);
if (likely(page) && !(vmf->flags & FAULT_FLAG_TRIED)) {
/*
* We found the page, so try async readahead before
* waiting for the lock.
*/
do_async_mmap_readahead(vma, ra, file, page, offset);
} else if (!page) {
/* No page in the page cache at all */
do_sync_mmap_readahead(vma, ra, file, offset);
count_vm_event(PGMAJFAULT);
memcg: add the pagefault count into memcg stats Two new stats in per-memcg memory.stat which tracks the number of page faults and number of major page faults. "pgfault" "pgmajfault" They are different from "pgpgin"/"pgpgout" stat which count number of pages charged/discharged to the cgroup and have no meaning of reading/ writing page to disk. It is valuable to track the two stats for both measuring application's performance as well as the efficiency of the kernel page reclaim path. Counting pagefaults per process is useful, but we also need the aggregated value since processes are monitored and controlled in cgroup basis in memcg. Functional test: check the total number of pgfault/pgmajfault of all memcgs and compare with global vmstat value: $ cat /proc/vmstat | grep fault pgfault 1070751 pgmajfault 553 $ cat /dev/cgroup/memory.stat | grep fault pgfault 1071138 pgmajfault 553 total_pgfault 1071142 total_pgmajfault 553 $ cat /dev/cgroup/A/memory.stat | grep fault pgfault 199 pgmajfault 0 total_pgfault 199 total_pgmajfault 0 Performance test: run page fault test(pft) wit 16 thread on faulting in 15G anon pages in 16G container. There is no regression noticed on the "flt/cpu/s" Sample output from pft: TAG pft:anon-sys-default: Gb Thr CLine User System Wall flt/cpu/s fault/wsec 15 16 1 0.67s 233.41s 14.76s 16798.546 266356.260 +-------------------------------------------------------------------------+ N Min Max Median Avg Stddev x 10 16682.962 17344.027 16913.524 16928.812 166.5362 + 10 16695.568 16923.896 16820.604 16824.652 84.816568 No difference proven at 95.0% confidence [akpm@linux-foundation.org: fix build] [hughd@google.com: shmem fix] Signed-off-by: Ying Han <yinghan@google.com> Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Acked-by: Balbir Singh <balbir@linux.vnet.ibm.com> Signed-off-by: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-05-26 23:25:38 +00:00
mem_cgroup_count_vm_event(vma->vm_mm, 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>
2010-10-26 21:21:57 +00:00
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(page->index != offset, page);
/*
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 08:46:57 +00:00
* 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 08:46:57 +00:00
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.
*/
size = round_up(i_size_read(inode), PAGE_CACHE_SIZE);
if (unlikely(offset >= size >> PAGE_CACHE_SHIFT)) {
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 08:46:57 +00:00
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 08:46:57 +00:00
}
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 08:47:05 +00:00
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 08:46:57 +00:00
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 08:46:57 +00:00
/* 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 12:48:43 +00:00
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 08:46:59 +00:00
}
EXPORT_SYMBOL(filemap_fault);
void filemap_map_pages(struct vm_area_struct *vma, struct vm_fault *vmf)
{
struct radix_tree_iter iter;
void **slot;
struct file *file = vma->vm_file;
struct address_space *mapping = file->f_mapping;
loff_t size;
struct page *page;
unsigned long address = (unsigned long) vmf->virtual_address;
unsigned long addr;
pte_t *pte;
rcu_read_lock();
radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, vmf->pgoff) {
if (iter.index > vmf->max_pgoff)
break;
repeat:
page = radix_tree_deref_slot(slot);
if (unlikely(!page))
goto next;
if (radix_tree_exception(page)) {
if (radix_tree_deref_retry(page))
break;
else
goto next;
}
if (!page_cache_get_speculative(page))
goto repeat;
/* Has the page moved? */
if (unlikely(page != *slot)) {
page_cache_release(page);
goto repeat;
}
if (!PageUptodate(page) ||
PageReadahead(page) ||
PageHWPoison(page))
goto skip;
if (!trylock_page(page))
goto skip;
if (page->mapping != mapping || !PageUptodate(page))
goto unlock;
size = round_up(i_size_read(mapping->host), PAGE_CACHE_SIZE);
if (page->index >= size >> PAGE_CACHE_SHIFT)
goto unlock;
pte = vmf->pte + page->index - vmf->pgoff;
if (!pte_none(*pte))
goto unlock;
if (file->f_ra.mmap_miss > 0)
file->f_ra.mmap_miss--;
addr = address + (page->index - vmf->pgoff) * PAGE_SIZE;
do_set_pte(vma, addr, page, pte, false, false);
unlock_page(page);
goto next;
unlock:
unlock_page(page);
skip:
page_cache_release(page);
next:
if (iter.index == vmf->max_pgoff)
break;
}
rcu_read_unlock();
}
EXPORT_SYMBOL(filemap_map_pages);
int filemap_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
{
struct page *page = vmf->page;
struct inode *inode = file_inode(vma->vm_file);
int ret = VM_FAULT_LOCKED;
sb_start_pagefault(inode->i_sb);
file_update_time(vma->vm_file);
lock_page(page);
if (page->mapping != inode->i_mapping) {
unlock_page(page);
ret = VM_FAULT_NOPAGE;
goto out;
}
/*
* We mark the page dirty already here so that when freeze is in
* progress, we are guaranteed that writeback during freezing will
* see the dirty page and writeprotect it again.
*/
set_page_dirty(page);
mm: only enforce stable page writes if the backing device requires it Create a helper function to check if a backing device requires stable page writes and, if so, performs the necessary wait. Then, make it so that all points in the memory manager that handle making pages writable use the helper function. This should provide stable page write support to most filesystems, while eliminating unnecessary waiting for devices that don't require the feature. Before this patchset, all filesystems would block, regardless of whether or not it was necessary. ext3 would wait, but still generate occasional checksum errors. The network filesystems were left to do their own thing, so they'd wait too. After this patchset, all the disk filesystems except ext3 and btrfs will wait only if the hardware requires it. ext3 (if necessary) snapshots pages instead of blocking, and btrfs provides its own bdi so the mm will never wait. Network filesystems haven't been touched, so either they provide their own stable page guarantees or they don't block at all. The blocking behavior is back to what it was before 3.0 if you don't have a disk requiring stable page writes. Here's the result of using dbench to test latency on ext2: 3.8.0-rc3: Operation Count AvgLat MaxLat ---------------------------------------- WriteX 109347 0.028 59.817 ReadX 347180 0.004 3.391 Flush 15514 29.828 287.283 Throughput 57.429 MB/sec 4 clients 4 procs max_latency=287.290 ms 3.8.0-rc3 + patches: WriteX 105556 0.029 4.273 ReadX 335004 0.005 4.112 Flush 14982 30.540 298.634 Throughput 55.4496 MB/sec 4 clients 4 procs max_latency=298.650 ms As you can see, the maximum write latency drops considerably with this patch enabled. The other filesystems (ext3/ext4/xfs/btrfs) behave similarly, but see the cover letter for those results. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Acked-by: Steven Whitehouse <swhiteho@redhat.com> Reviewed-by: Jan Kara <jack@suse.cz> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Artem Bityutskiy <dedekind1@gmail.com> Cc: Joel Becker <jlbec@evilplan.org> Cc: Mark Fasheh <mfasheh@suse.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Eric Van Hensbergen <ericvh@gmail.com> Cc: Ron Minnich <rminnich@sandia.gov> Cc: Latchesar Ionkov <lucho@ionkov.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-22 00:42:51 +00:00
wait_for_stable_page(page);
out:
sb_end_pagefault(inode->i_sb);
return ret;
}
EXPORT_SYMBOL(filemap_page_mkwrite);
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 08:46:59 +00:00
.fault = filemap_fault,
.map_pages = filemap_map_pages,
.page_mkwrite = filemap_page_mkwrite,
};
/* 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;
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);
mm: remove read_cache_page_async() This patch removes read_cache_page_async() which wasn't really needed anywhere and simplifies the code around it a bit. read_cache_page_async() is useful when we want to read a page into the cache without waiting for it to complete. This happens when the appropriate callback 'filler' doesn't complete its read operation and releases the page lock immediately, and instead queues a different completion routine to do that. This never actually happened anywhere in the code. read_cache_page_async() had 3 different callers: - read_cache_page() which is the sync version, it would just wait for the requested read to complete using wait_on_page_read(). - JFFS2 would call it from jffs2_gc_fetch_page(), but the filler function it supplied doesn't do any async reads, and would complete before the filler function returns - making it actually a sync read. - CRAMFS would call it using the read_mapping_page_async() wrapper, with a similar story to JFFS2 - the filler function doesn't do anything that reminds async reads and would always complete before the filler function returns. To sum it up, the code in mm/filemap.c never took advantage of having read_cache_page_async(). While there are filler callbacks that do async reads (such as the block one), we always called it with the read_cache_page(). This patch adds a mandatory wait for read to complete when adding a new page to the cache, and removes read_cache_page_async() and its wrappers. Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-03 21:48:18 +00:00
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;
}
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);
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);
mm: remove read_cache_page_async() This patch removes read_cache_page_async() which wasn't really needed anywhere and simplifies the code around it a bit. read_cache_page_async() is useful when we want to read a page into the cache without waiting for it to complete. This happens when the appropriate callback 'filler' doesn't complete its read operation and releases the page lock immediately, and instead queues a different completion routine to do that. This never actually happened anywhere in the code. read_cache_page_async() had 3 different callers: - read_cache_page() which is the sync version, it would just wait for the requested read to complete using wait_on_page_read(). - JFFS2 would call it from jffs2_gc_fetch_page(), but the filler function it supplied doesn't do any async reads, and would complete before the filler function returns - making it actually a sync read. - CRAMFS would call it using the read_mapping_page_async() wrapper, with a similar story to JFFS2 - the filler function doesn't do anything that reminds async reads and would always complete before the filler function returns. To sum it up, the code in mm/filemap.c never took advantage of having read_cache_page_async(). While there are filler callbacks that do async reads (such as the block one), we always called it with the read_cache_page(). This patch adds a mandatory wait for read to complete when adding a new page to the cache, and removes read_cache_page_async() and its wrappers. Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-03 21:48:18 +00:00
} else {
page = wait_on_page_read(page);
}
}
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);
mm: remove read_cache_page_async() This patch removes read_cache_page_async() which wasn't really needed anywhere and simplifies the code around it a bit. read_cache_page_async() is useful when we want to read a page into the cache without waiting for it to complete. This happens when the appropriate callback 'filler' doesn't complete its read operation and releases the page lock immediately, and instead queues a different completion routine to do that. This never actually happened anywhere in the code. read_cache_page_async() had 3 different callers: - read_cache_page() which is the sync version, it would just wait for the requested read to complete using wait_on_page_read(). - JFFS2 would call it from jffs2_gc_fetch_page(), but the filler function it supplied doesn't do any async reads, and would complete before the filler function returns - making it actually a sync read. - CRAMFS would call it using the read_mapping_page_async() wrapper, with a similar story to JFFS2 - the filler function doesn't do anything that reminds async reads and would always complete before the filler function returns. To sum it up, the code in mm/filemap.c never took advantage of having read_cache_page_async(). While there are filler callbacks that do async reads (such as the block one), we always called it with the read_cache_page(). This patch adds a mandatory wait for read to complete when adding a new page to the cache, and removes read_cache_page_async() and its wrappers. Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-03 21:48:18 +00:00
} else {
page = wait_on_page_read(page);
if (IS_ERR(page))
return page;
}
out:
mark_page_accessed(page);
return page;
}
/**
mm: remove read_cache_page_async() This patch removes read_cache_page_async() which wasn't really needed anywhere and simplifies the code around it a bit. read_cache_page_async() is useful when we want to read a page into the cache without waiting for it to complete. This happens when the appropriate callback 'filler' doesn't complete its read operation and releases the page lock immediately, and instead queues a different completion routine to do that. This never actually happened anywhere in the code. read_cache_page_async() had 3 different callers: - read_cache_page() which is the sync version, it would just wait for the requested read to complete using wait_on_page_read(). - JFFS2 would call it from jffs2_gc_fetch_page(), but the filler function it supplied doesn't do any async reads, and would complete before the filler function returns - making it actually a sync read. - CRAMFS would call it using the read_mapping_page_async() wrapper, with a similar story to JFFS2 - the filler function doesn't do anything that reminds async reads and would always complete before the filler function returns. To sum it up, the code in mm/filemap.c never took advantage of having read_cache_page_async(). While there are filler callbacks that do async reads (such as the block one), we always called it with the read_cache_page(). This patch adds a mandatory wait for read to complete when adding a new page to the cache, and removes read_cache_page_async() and its wrappers. Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-03 21:48:18 +00:00
* 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: first arg to filler(data, page) function, often left as NULL
*
* Read into the page cache. If a page already exists, and PageUptodate() is
mm: remove read_cache_page_async() This patch removes read_cache_page_async() which wasn't really needed anywhere and simplifies the code around it a bit. read_cache_page_async() is useful when we want to read a page into the cache without waiting for it to complete. This happens when the appropriate callback 'filler' doesn't complete its read operation and releases the page lock immediately, and instead queues a different completion routine to do that. This never actually happened anywhere in the code. read_cache_page_async() had 3 different callers: - read_cache_page() which is the sync version, it would just wait for the requested read to complete using wait_on_page_read(). - JFFS2 would call it from jffs2_gc_fetch_page(), but the filler function it supplied doesn't do any async reads, and would complete before the filler function returns - making it actually a sync read. - CRAMFS would call it using the read_mapping_page_async() wrapper, with a similar story to JFFS2 - the filler function doesn't do anything that reminds async reads and would always complete before the filler function returns. To sum it up, the code in mm/filemap.c never took advantage of having read_cache_page_async(). While there are filler callbacks that do async reads (such as the block one), we always called it with the read_cache_page(). This patch adds a mandatory wait for read to complete when adding a new page to the cache, and removes read_cache_page_async() and its wrappers. Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-03 21:48:18 +00:00
* not set, try to fill the page and wait for it to become unlocked.
*
* If the page does not get brought uptodate, return -EIO.
*/
mm: remove read_cache_page_async() This patch removes read_cache_page_async() which wasn't really needed anywhere and simplifies the code around it a bit. read_cache_page_async() is useful when we want to read a page into the cache without waiting for it to complete. This happens when the appropriate callback 'filler' doesn't complete its read operation and releases the page lock immediately, and instead queues a different completion routine to do that. This never actually happened anywhere in the code. read_cache_page_async() had 3 different callers: - read_cache_page() which is the sync version, it would just wait for the requested read to complete using wait_on_page_read(). - JFFS2 would call it from jffs2_gc_fetch_page(), but the filler function it supplied doesn't do any async reads, and would complete before the filler function returns - making it actually a sync read. - CRAMFS would call it using the read_mapping_page_async() wrapper, with a similar story to JFFS2 - the filler function doesn't do anything that reminds async reads and would always complete before the filler function returns. To sum it up, the code in mm/filemap.c never took advantage of having read_cache_page_async(). While there are filler callbacks that do async reads (such as the block one), we always called it with the read_cache_page(). This patch adds a mandatory wait for read to complete when adding a new page to the cache, and removes read_cache_page_async() and its wrappers. Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-03 21:48:18 +00:00
struct page *read_cache_page(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));
}
mm: remove read_cache_page_async() This patch removes read_cache_page_async() which wasn't really needed anywhere and simplifies the code around it a bit. read_cache_page_async() is useful when we want to read a page into the cache without waiting for it to complete. This happens when the appropriate callback 'filler' doesn't complete its read operation and releases the page lock immediately, and instead queues a different completion routine to do that. This never actually happened anywhere in the code. read_cache_page_async() had 3 different callers: - read_cache_page() which is the sync version, it would just wait for the requested read to complete using wait_on_page_read(). - JFFS2 would call it from jffs2_gc_fetch_page(), but the filler function it supplied doesn't do any async reads, and would complete before the filler function returns - making it actually a sync read. - CRAMFS would call it using the read_mapping_page_async() wrapper, with a similar story to JFFS2 - the filler function doesn't do anything that reminds async reads and would always complete before the filler function returns. To sum it up, the code in mm/filemap.c never took advantage of having read_cache_page_async(). While there are filler callbacks that do async reads (such as the block one), we always called it with the read_cache_page(). This patch adds a mandatory wait for read to complete when adding a new page to the cache, and removes read_cache_page_async() and its wrappers. Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-03 21:48:18 +00:00
EXPORT_SYMBOL(read_cache_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.
*
* 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;
mm: remove read_cache_page_async() This patch removes read_cache_page_async() which wasn't really needed anywhere and simplifies the code around it a bit. read_cache_page_async() is useful when we want to read a page into the cache without waiting for it to complete. This happens when the appropriate callback 'filler' doesn't complete its read operation and releases the page lock immediately, and instead queues a different completion routine to do that. This never actually happened anywhere in the code. read_cache_page_async() had 3 different callers: - read_cache_page() which is the sync version, it would just wait for the requested read to complete using wait_on_page_read(). - JFFS2 would call it from jffs2_gc_fetch_page(), but the filler function it supplied doesn't do any async reads, and would complete before the filler function returns - making it actually a sync read. - CRAMFS would call it using the read_mapping_page_async() wrapper, with a similar story to JFFS2 - the filler function doesn't do anything that reminds async reads and would always complete before the filler function returns. To sum it up, the code in mm/filemap.c never took advantage of having read_cache_page_async(). While there are filler callbacks that do async reads (such as the block one), we always called it with the read_cache_page(). This patch adds a mandatory wait for read to complete when adding a new page to the cache, and removes read_cache_page_async() and its wrappers. Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-03 21:48:18 +00:00
return do_read_cache_page(mapping, index, filler, NULL, gfp);
}
EXPORT_SYMBOL(read_cache_page_gfp);
/*
* 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 ssize_t generic_write_checks(struct kiocb *iocb, struct iov_iter *from)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
unsigned long limit = rlimit(RLIMIT_FSIZE);
loff_t pos;
if (!iov_iter_count(from))
return 0;
/* FIXME: this is for backwards compatibility with 2.4 */
if (iocb->ki_flags & IOCB_APPEND)
iocb->ki_pos = i_size_read(inode);
pos = iocb->ki_pos;
if (limit != RLIM_INFINITY) {
if (iocb->ki_pos >= limit) {
send_sig(SIGXFSZ, current, 0);
return -EFBIG;
}
iov_iter_truncate(from, limit - (unsigned long)pos);
}
/*
* LFS rule
*/
if (unlikely(pos + iov_iter_count(from) > MAX_NON_LFS &&
!(file->f_flags & O_LARGEFILE))) {
if (pos >= MAX_NON_LFS)
return -EFBIG;
iov_iter_truncate(from, 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 (unlikely(pos >= inode->i_sb->s_maxbytes))
return -EFBIG;
iov_iter_truncate(from, inode->i_sb->s_maxbytes - pos);
return iov_iter_count(from);
}
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;
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, struct iov_iter *from, loff_t pos)
{
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;
struct iov_iter data;
write_len = iov_iter_count(from);
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>
2008-09-02 21:35:40 +00:00
* 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>
2008-09-02 21:35:40 +00:00
/*
* 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>
2008-09-02 21:35:40 +00:00
}
}
data = *from;
written = mapping->a_ops->direct_IO(iocb, &data, pos);
/*
* 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;
iov_iter_advance(from, written);
if (pos > i_size_read(inode) && !S_ISBLK(inode->i_mode)) {
i_size_write(inode, pos);
mark_inode_dirty(inode);
}
iocb->ki_pos = 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>
2009-01-04 20:00:53 +00:00
struct page *grab_cache_page_write_begin(struct address_space *mapping,
pgoff_t index, unsigned flags)
{
struct page *page;
mm: non-atomically mark page accessed during page cache allocation where possible aops->write_begin may allocate a new page and make it visible only to have mark_page_accessed called almost immediately after. Once the page is visible the atomic operations are necessary which is noticable overhead when writing to an in-memory filesystem like tmpfs but should also be noticable with fast storage. The objective of the patch is to initialse the accessed information with non-atomic operations before the page is visible. The bulk of filesystems directly or indirectly use grab_cache_page_write_begin or find_or_create_page for the initial allocation of a page cache page. This patch adds an init_page_accessed() helper which behaves like the first call to mark_page_accessed() but may called before the page is visible and can be done non-atomically. The primary APIs of concern in this care are the following and are used by most filesystems. find_get_page find_lock_page find_or_create_page grab_cache_page_nowait grab_cache_page_write_begin All of them are very similar in detail to the patch creates a core helper pagecache_get_page() which takes a flags parameter that affects its behavior such as whether the page should be marked accessed or not. Then old API is preserved but is basically a thin wrapper around this core function. Each of the filesystems are then updated to avoid calling mark_page_accessed when it is known that the VM interfaces have already done the job. There is a slight snag in that the timing of the mark_page_accessed() has now changed so in rare cases it's possible a page gets to the end of the LRU as PageReferenced where as previously it might have been repromoted. This is expected to be rare but it's worth the filesystem people thinking about it in case they see a problem with the timing change. It is also the case that some filesystems may be marking pages accessed that previously did not but it makes sense that filesystems have consistent behaviour in this regard. The test case used to evaulate this is a simple dd of a large file done multiple times with the file deleted on each iterations. The size of the file is 1/10th physical memory to avoid dirty page balancing. In the async case it will be possible that the workload completes without even hitting the disk and will have variable results but highlight the impact of mark_page_accessed for async IO. The sync results are expected to be more stable. The exception is tmpfs where the normal case is for the "IO" to not hit the disk. The test machine was single socket and UMA to avoid any scheduling or NUMA artifacts. Throughput and wall times are presented for sync IO, only wall times are shown for async as the granularity reported by dd and the variability is unsuitable for comparison. As async results were variable do to writback timings, I'm only reporting the maximum figures. The sync results were stable enough to make the mean and stddev uninteresting. The performance results are reported based on a run with no profiling. Profile data is based on a separate run with oprofile running. async dd 3.15.0-rc3 3.15.0-rc3 vanilla accessed-v2 ext3 Max elapsed 13.9900 ( 0.00%) 11.5900 ( 17.16%) tmpfs Max elapsed 0.5100 ( 0.00%) 0.4900 ( 3.92%) btrfs Max elapsed 12.8100 ( 0.00%) 12.7800 ( 0.23%) ext4 Max elapsed 18.6000 ( 0.00%) 13.3400 ( 28.28%) xfs Max elapsed 12.5600 ( 0.00%) 2.0900 ( 83.36%) The XFS figure is a bit strange as it managed to avoid a worst case by sheer luck but the average figures looked reasonable. samples percentage ext3 86107 0.9783 vmlinux-3.15.0-rc4-vanilla mark_page_accessed ext3 23833 0.2710 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed ext3 5036 0.0573 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed ext4 64566 0.8961 vmlinux-3.15.0-rc4-vanilla mark_page_accessed ext4 5322 0.0713 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed ext4 2869 0.0384 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed xfs 62126 1.7675 vmlinux-3.15.0-rc4-vanilla mark_page_accessed xfs 1904 0.0554 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed xfs 103 0.0030 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed btrfs 10655 0.1338 vmlinux-3.15.0-rc4-vanilla mark_page_accessed btrfs 2020 0.0273 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed btrfs 587 0.0079 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed tmpfs 59562 3.2628 vmlinux-3.15.0-rc4-vanilla mark_page_accessed tmpfs 1210 0.0696 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed tmpfs 94 0.0054 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed [akpm@linux-foundation.org: don't run init_page_accessed() against an uninitialised pointer] Signed-off-by: Mel Gorman <mgorman@suse.de> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Jan Kara <jack@suse.cz> Cc: Michal Hocko <mhocko@suse.cz> Cc: Hugh Dickins <hughd@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Theodore Ts'o <tytso@mit.edu> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Tested-by: Prabhakar Lad <prabhakar.csengg@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-06-04 23:10:31 +00:00
int fgp_flags = FGP_LOCK|FGP_ACCESSED|FGP_WRITE|FGP_CREAT;
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>
2009-01-04 20:00:53 +00:00
if (flags & AOP_FLAG_NOFS)
mm: non-atomically mark page accessed during page cache allocation where possible aops->write_begin may allocate a new page and make it visible only to have mark_page_accessed called almost immediately after. Once the page is visible the atomic operations are necessary which is noticable overhead when writing to an in-memory filesystem like tmpfs but should also be noticable with fast storage. The objective of the patch is to initialse the accessed information with non-atomic operations before the page is visible. The bulk of filesystems directly or indirectly use grab_cache_page_write_begin or find_or_create_page for the initial allocation of a page cache page. This patch adds an init_page_accessed() helper which behaves like the first call to mark_page_accessed() but may called before the page is visible and can be done non-atomically. The primary APIs of concern in this care are the following and are used by most filesystems. find_get_page find_lock_page find_or_create_page grab_cache_page_nowait grab_cache_page_write_begin All of them are very similar in detail to the patch creates a core helper pagecache_get_page() which takes a flags parameter that affects its behavior such as whether the page should be marked accessed or not. Then old API is preserved but is basically a thin wrapper around this core function. Each of the filesystems are then updated to avoid calling mark_page_accessed when it is known that the VM interfaces have already done the job. There is a slight snag in that the timing of the mark_page_accessed() has now changed so in rare cases it's possible a page gets to the end of the LRU as PageReferenced where as previously it might have been repromoted. This is expected to be rare but it's worth the filesystem people thinking about it in case they see a problem with the timing change. It is also the case that some filesystems may be marking pages accessed that previously did not but it makes sense that filesystems have consistent behaviour in this regard. The test case used to evaulate this is a simple dd of a large file done multiple times with the file deleted on each iterations. The size of the file is 1/10th physical memory to avoid dirty page balancing. In the async case it will be possible that the workload completes without even hitting the disk and will have variable results but highlight the impact of mark_page_accessed for async IO. The sync results are expected to be more stable. The exception is tmpfs where the normal case is for the "IO" to not hit the disk. The test machine was single socket and UMA to avoid any scheduling or NUMA artifacts. Throughput and wall times are presented for sync IO, only wall times are shown for async as the granularity reported by dd and the variability is unsuitable for comparison. As async results were variable do to writback timings, I'm only reporting the maximum figures. The sync results were stable enough to make the mean and stddev uninteresting. The performance results are reported based on a run with no profiling. Profile data is based on a separate run with oprofile running. async dd 3.15.0-rc3 3.15.0-rc3 vanilla accessed-v2 ext3 Max elapsed 13.9900 ( 0.00%) 11.5900 ( 17.16%) tmpfs Max elapsed 0.5100 ( 0.00%) 0.4900 ( 3.92%) btrfs Max elapsed 12.8100 ( 0.00%) 12.7800 ( 0.23%) ext4 Max elapsed 18.6000 ( 0.00%) 13.3400 ( 28.28%) xfs Max elapsed 12.5600 ( 0.00%) 2.0900 ( 83.36%) The XFS figure is a bit strange as it managed to avoid a worst case by sheer luck but the average figures looked reasonable. samples percentage ext3 86107 0.9783 vmlinux-3.15.0-rc4-vanilla mark_page_accessed ext3 23833 0.2710 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed ext3 5036 0.0573 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed ext4 64566 0.8961 vmlinux-3.15.0-rc4-vanilla mark_page_accessed ext4 5322 0.0713 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed ext4 2869 0.0384 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed xfs 62126 1.7675 vmlinux-3.15.0-rc4-vanilla mark_page_accessed xfs 1904 0.0554 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed xfs 103 0.0030 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed btrfs 10655 0.1338 vmlinux-3.15.0-rc4-vanilla mark_page_accessed btrfs 2020 0.0273 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed btrfs 587 0.0079 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed tmpfs 59562 3.2628 vmlinux-3.15.0-rc4-vanilla mark_page_accessed tmpfs 1210 0.0696 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed tmpfs 94 0.0054 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed [akpm@linux-foundation.org: don't run init_page_accessed() against an uninitialised pointer] Signed-off-by: Mel Gorman <mgorman@suse.de> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Jan Kara <jack@suse.cz> Cc: Michal Hocko <mhocko@suse.cz> Cc: Hugh Dickins <hughd@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Theodore Ts'o <tytso@mit.edu> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Tested-by: Prabhakar Lad <prabhakar.csengg@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-06-04 23:10:31 +00:00
fgp_flags |= FGP_NOFS;
page = pagecache_get_page(mapping, index, fgp_flags,
mapping_gfp_mask(mapping));
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>
2011-01-13 23:46:18 +00:00
if (page)
mm: non-atomically mark page accessed during page cache allocation where possible aops->write_begin may allocate a new page and make it visible only to have mark_page_accessed called almost immediately after. Once the page is visible the atomic operations are necessary which is noticable overhead when writing to an in-memory filesystem like tmpfs but should also be noticable with fast storage. The objective of the patch is to initialse the accessed information with non-atomic operations before the page is visible. The bulk of filesystems directly or indirectly use grab_cache_page_write_begin or find_or_create_page for the initial allocation of a page cache page. This patch adds an init_page_accessed() helper which behaves like the first call to mark_page_accessed() but may called before the page is visible and can be done non-atomically. The primary APIs of concern in this care are the following and are used by most filesystems. find_get_page find_lock_page find_or_create_page grab_cache_page_nowait grab_cache_page_write_begin All of them are very similar in detail to the patch creates a core helper pagecache_get_page() which takes a flags parameter that affects its behavior such as whether the page should be marked accessed or not. Then old API is preserved but is basically a thin wrapper around this core function. Each of the filesystems are then updated to avoid calling mark_page_accessed when it is known that the VM interfaces have already done the job. There is a slight snag in that the timing of the mark_page_accessed() has now changed so in rare cases it's possible a page gets to the end of the LRU as PageReferenced where as previously it might have been repromoted. This is expected to be rare but it's worth the filesystem people thinking about it in case they see a problem with the timing change. It is also the case that some filesystems may be marking pages accessed that previously did not but it makes sense that filesystems have consistent behaviour in this regard. The test case used to evaulate this is a simple dd of a large file done multiple times with the file deleted on each iterations. The size of the file is 1/10th physical memory to avoid dirty page balancing. In the async case it will be possible that the workload completes without even hitting the disk and will have variable results but highlight the impact of mark_page_accessed for async IO. The sync results are expected to be more stable. The exception is tmpfs where the normal case is for the "IO" to not hit the disk. The test machine was single socket and UMA to avoid any scheduling or NUMA artifacts. Throughput and wall times are presented for sync IO, only wall times are shown for async as the granularity reported by dd and the variability is unsuitable for comparison. As async results were variable do to writback timings, I'm only reporting the maximum figures. The sync results were stable enough to make the mean and stddev uninteresting. The performance results are reported based on a run with no profiling. Profile data is based on a separate run with oprofile running. async dd 3.15.0-rc3 3.15.0-rc3 vanilla accessed-v2 ext3 Max elapsed 13.9900 ( 0.00%) 11.5900 ( 17.16%) tmpfs Max elapsed 0.5100 ( 0.00%) 0.4900 ( 3.92%) btrfs Max elapsed 12.8100 ( 0.00%) 12.7800 ( 0.23%) ext4 Max elapsed 18.6000 ( 0.00%) 13.3400 ( 28.28%) xfs Max elapsed 12.5600 ( 0.00%) 2.0900 ( 83.36%) The XFS figure is a bit strange as it managed to avoid a worst case by sheer luck but the average figures looked reasonable. samples percentage ext3 86107 0.9783 vmlinux-3.15.0-rc4-vanilla mark_page_accessed ext3 23833 0.2710 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed ext3 5036 0.0573 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed ext4 64566 0.8961 vmlinux-3.15.0-rc4-vanilla mark_page_accessed ext4 5322 0.0713 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed ext4 2869 0.0384 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed xfs 62126 1.7675 vmlinux-3.15.0-rc4-vanilla mark_page_accessed xfs 1904 0.0554 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed xfs 103 0.0030 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed btrfs 10655 0.1338 vmlinux-3.15.0-rc4-vanilla mark_page_accessed btrfs 2020 0.0273 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed btrfs 587 0.0079 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed tmpfs 59562 3.2628 vmlinux-3.15.0-rc4-vanilla mark_page_accessed tmpfs 1210 0.0696 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed tmpfs 94 0.0054 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed [akpm@linux-foundation.org: don't run init_page_accessed() against an uninitialised pointer] Signed-off-by: Mel Gorman <mgorman@suse.de> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Jan Kara <jack@suse.cz> Cc: Michal Hocko <mhocko@suse.cz> Cc: Hugh Dickins <hughd@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Theodore Ts'o <tytso@mit.edu> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Tested-by: Prabhakar Lad <prabhakar.csengg@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-06-04 23:10:31 +00:00
wait_for_stable_page(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>
2009-01-04 20:00:53 +00:00
EXPORT_SYMBOL(grab_cache_page_write_begin);
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 (!iter_is_iovec(i))
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;
}
if (fatal_signal_pending(current)) {
status = -EINTR;
break;
}
status = a_ops->write_begin(file, mapping, pos, bytes, flags,
&page, &fsdata);
mm: non-atomically mark page accessed during page cache allocation where possible aops->write_begin may allocate a new page and make it visible only to have mark_page_accessed called almost immediately after. Once the page is visible the atomic operations are necessary which is noticable overhead when writing to an in-memory filesystem like tmpfs but should also be noticable with fast storage. The objective of the patch is to initialse the accessed information with non-atomic operations before the page is visible. The bulk of filesystems directly or indirectly use grab_cache_page_write_begin or find_or_create_page for the initial allocation of a page cache page. This patch adds an init_page_accessed() helper which behaves like the first call to mark_page_accessed() but may called before the page is visible and can be done non-atomically. The primary APIs of concern in this care are the following and are used by most filesystems. find_get_page find_lock_page find_or_create_page grab_cache_page_nowait grab_cache_page_write_begin All of them are very similar in detail to the patch creates a core helper pagecache_get_page() which takes a flags parameter that affects its behavior such as whether the page should be marked accessed or not. Then old API is preserved but is basically a thin wrapper around this core function. Each of the filesystems are then updated to avoid calling mark_page_accessed when it is known that the VM interfaces have already done the job. There is a slight snag in that the timing of the mark_page_accessed() has now changed so in rare cases it's possible a page gets to the end of the LRU as PageReferenced where as previously it might have been repromoted. This is expected to be rare but it's worth the filesystem people thinking about it in case they see a problem with the timing change. It is also the case that some filesystems may be marking pages accessed that previously did not but it makes sense that filesystems have consistent behaviour in this regard. The test case used to evaulate this is a simple dd of a large file done multiple times with the file deleted on each iterations. The size of the file is 1/10th physical memory to avoid dirty page balancing. In the async case it will be possible that the workload completes without even hitting the disk and will have variable results but highlight the impact of mark_page_accessed for async IO. The sync results are expected to be more stable. The exception is tmpfs where the normal case is for the "IO" to not hit the disk. The test machine was single socket and UMA to avoid any scheduling or NUMA artifacts. Throughput and wall times are presented for sync IO, only wall times are shown for async as the granularity reported by dd and the variability is unsuitable for comparison. As async results were variable do to writback timings, I'm only reporting the maximum figures. The sync results were stable enough to make the mean and stddev uninteresting. The performance results are reported based on a run with no profiling. Profile data is based on a separate run with oprofile running. async dd 3.15.0-rc3 3.15.0-rc3 vanilla accessed-v2 ext3 Max elapsed 13.9900 ( 0.00%) 11.5900 ( 17.16%) tmpfs Max elapsed 0.5100 ( 0.00%) 0.4900 ( 3.92%) btrfs Max elapsed 12.8100 ( 0.00%) 12.7800 ( 0.23%) ext4 Max elapsed 18.6000 ( 0.00%) 13.3400 ( 28.28%) xfs Max elapsed 12.5600 ( 0.00%) 2.0900 ( 83.36%) The XFS figure is a bit strange as it managed to avoid a worst case by sheer luck but the average figures looked reasonable. samples percentage ext3 86107 0.9783 vmlinux-3.15.0-rc4-vanilla mark_page_accessed ext3 23833 0.2710 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed ext3 5036 0.0573 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed ext4 64566 0.8961 vmlinux-3.15.0-rc4-vanilla mark_page_accessed ext4 5322 0.0713 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed ext4 2869 0.0384 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed xfs 62126 1.7675 vmlinux-3.15.0-rc4-vanilla mark_page_accessed xfs 1904 0.0554 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed xfs 103 0.0030 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed btrfs 10655 0.1338 vmlinux-3.15.0-rc4-vanilla mark_page_accessed btrfs 2020 0.0273 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed btrfs 587 0.0079 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed tmpfs 59562 3.2628 vmlinux-3.15.0-rc4-vanilla mark_page_accessed tmpfs 1210 0.0696 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed tmpfs 94 0.0054 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed [akpm@linux-foundation.org: don't run init_page_accessed() against an uninitialised pointer] Signed-off-by: Mel Gorman <mgorman@suse.de> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Jan Kara <jack@suse.cz> Cc: Michal Hocko <mhocko@suse.cz> Cc: Hugh Dickins <hughd@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Theodore Ts'o <tytso@mit.edu> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Tested-by: Prabhakar Lad <prabhakar.csengg@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-06-04 23:10:31 +00:00
if (unlikely(status < 0))
break;
if (mapping_writably_mapped(mapping))
flush_dcache_page(page);
copied = iov_iter_copy_from_user_atomic(page, i, offset, bytes);
flush_dcache_page(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;
}
EXPORT_SYMBOL(generic_perform_write);
/**
* __generic_file_write_iter - write data to a file
* @iocb: IO state structure (file, offset, etc.)
* @from: iov_iter with data 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_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
struct file *file = iocb->ki_filp;
struct address_space * mapping = file->f_mapping;
struct inode *inode = mapping->host;
ssize_t written = 0;
ssize_t err;
ssize_t status;
/* We can write back this queue in page reclaim */
current->backing_dev_info = inode_to_bdi(inode);
err = file_remove_privs(file);
if (err)
goto out;
err = file_update_time(file);
if (err)
goto out;
if (iocb->ki_flags & IOCB_DIRECT) {
loff_t pos, endbyte;
written = generic_file_direct_write(iocb, from, iocb->ki_pos);
/*
* If the write stopped short of completing, fall back to
* buffered writes. Some filesystems do this for writes to
* holes, for example. For DAX files, a buffered write will
* not succeed (even if it did, DAX does not handle dirty
* page-cache pages correctly).
*/
if (written < 0 || !iov_iter_count(from) || IS_DAX(inode))
goto out;
status = generic_perform_write(file, from, pos = iocb->ki_pos);
/*
* If generic_perform_write() returned 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 (unlikely(status < 0)) {
err = status;
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 + status - 1;
err = filemap_write_and_wait_range(mapping, pos, endbyte);
if (err == 0) {
iocb->ki_pos = endbyte + 1;
written += status;
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_perform_write(file, from, iocb->ki_pos);
if (likely(written > 0))
iocb->ki_pos += written;
}
out:
current->backing_dev_info = NULL;
return written ? written : err;
}
EXPORT_SYMBOL(__generic_file_write_iter);
/**
* generic_file_write_iter - write data to a file
* @iocb: IO state structure
* @from: iov_iter with data to write
*
* This is a wrapper around __generic_file_write_iter() 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_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
ssize_t ret;
mutex_lock(&inode->i_mutex);
ret = generic_write_checks(iocb, from);
if (ret > 0)
ret = __generic_file_write_iter(iocb, from);
mutex_unlock(&inode->i_mutex);
if (ret > 0) {
ssize_t err;
err = generic_write_sync(file, iocb->ki_pos - ret, ret);
if (err < 0)
ret = err;
}
return ret;
}
EXPORT_SYMBOL(generic_file_write_iter);
/**
* 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);