linux/mm/filemap.c

4416 lines
124 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* 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>
dax: support dirty DAX entries in radix tree Add support for tracking dirty DAX entries in the struct address_space radix tree. This tree is already used for dirty page writeback, and it already supports the use of exceptional (non struct page*) entries. In order to properly track dirty DAX pages we will insert new exceptional entries into the radix tree that represent dirty DAX PTE or PMD pages. These exceptional entries will also contain the writeback addresses for the PTE or PMD faults that we can use at fsync/msync time. There are currently two types of exceptional entries (shmem and shadow) that can be placed into the radix tree, and this adds a third. We rely on the fact that only one type of exceptional entry can be found in a given radix tree based on its usage. This happens for free with DAX vs shmem but we explicitly prevent shadow entries from being added to radix trees for DAX mappings. The only shadow entries that would be generated for DAX radix trees would be to track zero page mappings that were created for holes. These pages would receive minimal benefit from having shadow entries, and the choice to have only one type of exceptional entry in a given radix tree makes the logic simpler both in clear_exceptional_entry() and in the rest of DAX. Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: "J. Bruce Fields" <bfields@fieldses.org> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: Dave Chinner <david@fromorbit.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jan Kara <jack@suse.com> Cc: Jeff Layton <jlayton@poochiereds.net> Cc: Matthew Wilcox <willy@linux.intel.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Matthew Wilcox <matthew.r.wilcox@intel.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-01-22 23:10:40 +00:00
#include <linux/dax.h>
#include <linux/fs.h>
#include <linux/sched/signal.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>
mm/migrate.c: rework migration_entry_wait() to not take a pageref This fixes the FIXME in migrate_vma_check_page(). Before migrating a page migration code will take a reference and check there are no unexpected page references, failing the migration if there are. When a thread faults on a migration entry it will take a temporary reference to the page to wait for the page to become unlocked signifying the migration entry has been removed. This reference is dropped just prior to waiting on the page lock, however the extra reference can cause migration failures so it is desirable to avoid taking it. As migration code already has a reference to the migrating page an extra reference to wait on PG_locked is unnecessary so long as the reference can't be dropped whilst setting up the wait. When faulting on a migration entry the ptl is taken to check the migration entry. Removing a migration entry also requires the ptl, and migration code won't drop its page reference until after the migration entry has been removed. Therefore retaining the ptl of a migration entry is sufficient to ensure the page has a reference. Reworking migration_entry_wait() to hold the ptl until the wait setup is complete means the extra page reference is no longer needed. [apopple@nvidia.com: v5] Link: https://lkml.kernel.org/r/20211213033848.1973946-1-apopple@nvidia.com Link: https://lkml.kernel.org/r/20211118020754.954425-1-apopple@nvidia.com Signed-off-by: Alistair Popple <apopple@nvidia.com> Acked-by: David Hildenbrand <david@redhat.com> Cc: David Howells <dhowells@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Ralph Campbell <rcampbell@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-01-22 06:10:46 +00:00
#include <linux/swapops.h>
cachestat: implement cachestat syscall There is currently no good way to query the page cache state of large file sets and directory trees. There is mincore(), but it scales poorly: the kernel writes out a lot of bitmap data that userspace has to aggregate, when the user really doesn not care about per-page information in that case. The user also needs to mmap and unmap each file as it goes along, which can be quite slow as well. Some use cases where this information could come in handy: * Allowing database to decide whether to perform an index scan or direct table queries based on the in-memory cache state of the index. * Visibility into the writeback algorithm, for performance issues diagnostic. * Workload-aware writeback pacing: estimating IO fulfilled by page cache (and IO to be done) within a range of a file, allowing for more frequent syncing when and where there is IO capacity, and batching when there is not. * Computing memory usage of large files/directory trees, analogous to the du tool for disk usage. More information about these use cases could be found in the following thread: https://lore.kernel.org/lkml/20230315170934.GA97793@cmpxchg.org/ This patch implements a new syscall that queries cache state of a file and summarizes the number of cached pages, number of dirty pages, number of pages marked for writeback, number of (recently) evicted pages, etc. in a given range. Currently, the syscall is only wired in for x86 architecture. NAME cachestat - query the page cache statistics of a file. SYNOPSIS #include <sys/mman.h> struct cachestat_range { __u64 off; __u64 len; }; struct cachestat { __u64 nr_cache; __u64 nr_dirty; __u64 nr_writeback; __u64 nr_evicted; __u64 nr_recently_evicted; }; int cachestat(unsigned int fd, struct cachestat_range *cstat_range, struct cachestat *cstat, unsigned int flags); DESCRIPTION cachestat() queries the number of cached pages, number of dirty pages, number of pages marked for writeback, number of evicted pages, number of recently evicted pages, in the bytes range given by `off` and `len`. An evicted page is a page that is previously in the page cache but has been evicted since. A page is recently evicted if its last eviction was recent enough that its reentry to the cache would indicate that it is actively being used by the system, and that there is memory pressure on the system. These values are returned in a cachestat struct, whose address is given by the `cstat` argument. The `off` and `len` arguments must be non-negative integers. If `len` > 0, the queried range is [`off`, `off` + `len`]. If `len` == 0, we will query in the range from `off` to the end of the file. The `flags` argument is unused for now, but is included for future extensibility. User should pass 0 (i.e no flag specified). Currently, hugetlbfs is not supported. Because the status of a page can change after cachestat() checks it but before it returns to the application, the returned values may contain stale information. RETURN VALUE On success, cachestat returns 0. On error, -1 is returned, and errno is set to indicate the error. ERRORS EFAULT cstat or cstat_args points to an invalid address. EINVAL invalid flags. EBADF invalid file descriptor. EOPNOTSUPP file descriptor is of a hugetlbfs file [nphamcs@gmail.com: replace rounddown logic with the existing helper] Link: https://lkml.kernel.org/r/20230504022044.3675469-1-nphamcs@gmail.com Link: https://lkml.kernel.org/r/20230503013608.2431726-3-nphamcs@gmail.com Signed-off-by: Nhat Pham <nphamcs@gmail.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Brian Foster <bfoster@redhat.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-05-03 01:36:07 +00:00
#include <linux/syscalls.h>
#include <linux/mman.h>
#include <linux/pagemap.h>
#include <linux/file.h>
#include <linux/uio.h>
#include <linux/error-injection.h>
#include <linux/hash.h>
#include <linux/writeback.h>
#include <linux/backing-dev.h>
#include <linux/pagevec.h>
#include <linux/security.h>
#include <linux/cpuset.h>
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>
mm, truncate: do not check mapping for every page being truncated During truncation, the mapping has already been checked for shmem and dax so it's known that workingset_update_node is required. This patch avoids the checks on mapping for each page being truncated. In all other cases, a lookup helper is used to determine if workingset_update_node() needs to be called. The one danger is that the API is slightly harder to use as calling workingset_update_node directly without checking for dax or shmem mappings could lead to surprises. However, the API rarely needs to be used and hopefully the comment is enough to give people the hint. sparsetruncate (tiny) 4.14.0-rc4 4.14.0-rc4 oneirq-v1r1 pickhelper-v1r1 Min Time 141.00 ( 0.00%) 140.00 ( 0.71%) 1st-qrtle Time 142.00 ( 0.00%) 141.00 ( 0.70%) 2nd-qrtle Time 142.00 ( 0.00%) 142.00 ( 0.00%) 3rd-qrtle Time 143.00 ( 0.00%) 143.00 ( 0.00%) Max-90% Time 144.00 ( 0.00%) 144.00 ( 0.00%) Max-95% Time 147.00 ( 0.00%) 145.00 ( 1.36%) Max-99% Time 195.00 ( 0.00%) 191.00 ( 2.05%) Max Time 230.00 ( 0.00%) 205.00 ( 10.87%) Amean Time 144.37 ( 0.00%) 143.82 ( 0.38%) Stddev Time 10.44 ( 0.00%) 9.00 ( 13.74%) Coeff Time 7.23 ( 0.00%) 6.26 ( 13.41%) Best99%Amean Time 143.72 ( 0.00%) 143.34 ( 0.26%) Best95%Amean Time 142.37 ( 0.00%) 142.00 ( 0.26%) Best90%Amean Time 142.19 ( 0.00%) 141.85 ( 0.24%) Best75%Amean Time 141.92 ( 0.00%) 141.58 ( 0.24%) Best50%Amean Time 141.69 ( 0.00%) 141.31 ( 0.27%) Best25%Amean Time 141.38 ( 0.00%) 140.97 ( 0.29%) As you'd expect, the gain is marginal but it can be detected. The differences in bonnie are all within the noise which is not surprising given the impact on the microbenchmark. radix_tree_update_node_t is a callback for some radix operations that optionally passes in a private field. The only user of the callback is workingset_update_node and as it no longer requires a mapping, the private field is removed. Link: http://lkml.kernel.org/r/20171018075952.10627-3-mgorman@techsingularity.net Signed-off-by: Mel Gorman <mgorman@techsingularity.net> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Jan Kara <jack@suse.cz> Cc: Andi Kleen <ak@linux.intel.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-11-16 01:37:41 +00:00
#include <linux/shmem_fs.h>
#include <linux/rmap.h>
delayacct: track delays from thrashing cache pages Delay accounting already measures the time a task spends in direct reclaim and waiting for swapin, but in low memory situations tasks spend can spend a significant amount of their time waiting on thrashing page cache. This isn't tracked right now. To know the full impact of memory contention on an individual task, measure the delay when waiting for a recently evicted active cache page to read back into memory. Also update tools/accounting/getdelays.c: [hannes@computer accounting]$ sudo ./getdelays -d -p 1 print delayacct stats ON PID 1 CPU count real total virtual total delay total delay average 50318 745000000 847346785 400533713 0.008ms IO count delay total delay average 435 122601218 0ms SWAP count delay total delay average 0 0 0ms RECLAIM count delay total delay average 0 0 0ms THRASHING count delay total delay average 19 12621439 0ms Link: http://lkml.kernel.org/r/20180828172258.3185-4-hannes@cmpxchg.org Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Tested-by: Daniel Drake <drake@endlessm.com> Tested-by: Suren Baghdasaryan <surenb@google.com> Cc: Christopher Lameter <cl@linux.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Johannes Weiner <jweiner@fb.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Enderborg <peter.enderborg@sony.com> Cc: Randy Dunlap <rdunlap@infradead.org> Cc: Shakeel Butt <shakeelb@google.com> Cc: Tejun Heo <tj@kernel.org> Cc: Vinayak Menon <vinmenon@codeaurora.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-10-26 22:06:08 +00:00
#include <linux/delayacct.h>
psi: pressure stall information for CPU, memory, and IO When systems are overcommitted and resources become contended, it's hard to tell exactly the impact this has on workload productivity, or how close the system is to lockups and OOM kills. In particular, when machines work multiple jobs concurrently, the impact of overcommit in terms of latency and throughput on the individual job can be enormous. In order to maximize hardware utilization without sacrificing individual job health or risk complete machine lockups, this patch implements a way to quantify resource pressure in the system. A kernel built with CONFIG_PSI=y creates files in /proc/pressure/ that expose the percentage of time the system is stalled on CPU, memory, or IO, respectively. Stall states are aggregate versions of the per-task delay accounting delays: cpu: some tasks are runnable but not executing on a CPU memory: tasks are reclaiming, or waiting for swapin or thrashing cache io: tasks are waiting for io completions These percentages of walltime can be thought of as pressure percentages, and they give a general sense of system health and productivity loss incurred by resource overcommit. They can also indicate when the system is approaching lockup scenarios and OOMs. To do this, psi keeps track of the task states associated with each CPU and samples the time they spend in stall states. Every 2 seconds, the samples are averaged across CPUs - weighted by the CPUs' non-idle time to eliminate artifacts from unused CPUs - and translated into percentages of walltime. A running average of those percentages is maintained over 10s, 1m, and 5m periods (similar to the loadaverage). [hannes@cmpxchg.org: doc fixlet, per Randy] Link: http://lkml.kernel.org/r/20180828205625.GA14030@cmpxchg.org [hannes@cmpxchg.org: code optimization] Link: http://lkml.kernel.org/r/20180907175015.GA8479@cmpxchg.org [hannes@cmpxchg.org: rename psi_clock() to psi_update_work(), per Peter] Link: http://lkml.kernel.org/r/20180907145404.GB11088@cmpxchg.org [hannes@cmpxchg.org: fix build] Link: http://lkml.kernel.org/r/20180913014222.GA2370@cmpxchg.org Link: http://lkml.kernel.org/r/20180828172258.3185-9-hannes@cmpxchg.org Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Tested-by: Daniel Drake <drake@endlessm.com> Tested-by: Suren Baghdasaryan <surenb@google.com> Cc: Christopher Lameter <cl@linux.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Johannes Weiner <jweiner@fb.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Enderborg <peter.enderborg@sony.com> Cc: Randy Dunlap <rdunlap@infradead.org> Cc: Shakeel Butt <shakeelb@google.com> Cc: Tejun Heo <tj@kernel.org> Cc: Vinayak Menon <vinmenon@codeaurora.org> Cc: Randy Dunlap <rdunlap@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-10-26 22:06:27 +00:00
#include <linux/psi.h>
#include <linux/ramfs.h>
#include <linux/page_idle.h>
mm/migrate.c: rework migration_entry_wait() to not take a pageref This fixes the FIXME in migrate_vma_check_page(). Before migrating a page migration code will take a reference and check there are no unexpected page references, failing the migration if there are. When a thread faults on a migration entry it will take a temporary reference to the page to wait for the page to become unlocked signifying the migration entry has been removed. This reference is dropped just prior to waiting on the page lock, however the extra reference can cause migration failures so it is desirable to avoid taking it. As migration code already has a reference to the migrating page an extra reference to wait on PG_locked is unnecessary so long as the reference can't be dropped whilst setting up the wait. When faulting on a migration entry the ptl is taken to check the migration entry. Removing a migration entry also requires the ptl, and migration code won't drop its page reference until after the migration entry has been removed. Therefore retaining the ptl of a migration entry is sufficient to ensure the page has a reference. Reworking migration_entry_wait() to hold the ptl until the wait setup is complete means the extra page reference is no longer needed. [apopple@nvidia.com: v5] Link: https://lkml.kernel.org/r/20211213033848.1973946-1-apopple@nvidia.com Link: https://lkml.kernel.org/r/20211118020754.954425-1-apopple@nvidia.com Signed-off-by: Alistair Popple <apopple@nvidia.com> Acked-by: David Hildenbrand <david@redhat.com> Cc: David Howells <dhowells@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Ralph Campbell <rcampbell@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-01-22 06:10:46 +00:00
#include <linux/migrate.h>
#include <linux/pipe_fs_i.h>
#include <linux/splice.h>
#include <linux/rcupdate_wait.h>
#include <asm/pgalloc.h>
#include <asm/tlbflush.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>
cachestat: implement cachestat syscall There is currently no good way to query the page cache state of large file sets and directory trees. There is mincore(), but it scales poorly: the kernel writes out a lot of bitmap data that userspace has to aggregate, when the user really doesn not care about per-page information in that case. The user also needs to mmap and unmap each file as it goes along, which can be quite slow as well. Some use cases where this information could come in handy: * Allowing database to decide whether to perform an index scan or direct table queries based on the in-memory cache state of the index. * Visibility into the writeback algorithm, for performance issues diagnostic. * Workload-aware writeback pacing: estimating IO fulfilled by page cache (and IO to be done) within a range of a file, allowing for more frequent syncing when and where there is IO capacity, and batching when there is not. * Computing memory usage of large files/directory trees, analogous to the du tool for disk usage. More information about these use cases could be found in the following thread: https://lore.kernel.org/lkml/20230315170934.GA97793@cmpxchg.org/ This patch implements a new syscall that queries cache state of a file and summarizes the number of cached pages, number of dirty pages, number of pages marked for writeback, number of (recently) evicted pages, etc. in a given range. Currently, the syscall is only wired in for x86 architecture. NAME cachestat - query the page cache statistics of a file. SYNOPSIS #include <sys/mman.h> struct cachestat_range { __u64 off; __u64 len; }; struct cachestat { __u64 nr_cache; __u64 nr_dirty; __u64 nr_writeback; __u64 nr_evicted; __u64 nr_recently_evicted; }; int cachestat(unsigned int fd, struct cachestat_range *cstat_range, struct cachestat *cstat, unsigned int flags); DESCRIPTION cachestat() queries the number of cached pages, number of dirty pages, number of pages marked for writeback, number of evicted pages, number of recently evicted pages, in the bytes range given by `off` and `len`. An evicted page is a page that is previously in the page cache but has been evicted since. A page is recently evicted if its last eviction was recent enough that its reentry to the cache would indicate that it is actively being used by the system, and that there is memory pressure on the system. These values are returned in a cachestat struct, whose address is given by the `cstat` argument. The `off` and `len` arguments must be non-negative integers. If `len` > 0, the queried range is [`off`, `off` + `len`]. If `len` == 0, we will query in the range from `off` to the end of the file. The `flags` argument is unused for now, but is included for future extensibility. User should pass 0 (i.e no flag specified). Currently, hugetlbfs is not supported. Because the status of a page can change after cachestat() checks it but before it returns to the application, the returned values may contain stale information. RETURN VALUE On success, cachestat returns 0. On error, -1 is returned, and errno is set to indicate the error. ERRORS EFAULT cstat or cstat_args points to an invalid address. EINVAL invalid flags. EBADF invalid file descriptor. EOPNOTSUPP file descriptor is of a hugetlbfs file [nphamcs@gmail.com: replace rounddown logic with the existing helper] Link: https://lkml.kernel.org/r/20230504022044.3675469-1-nphamcs@gmail.com Link: https://lkml.kernel.org/r/20230503013608.2431726-3-nphamcs@gmail.com Signed-off-by: Nhat Pham <nphamcs@gmail.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Brian Foster <bfoster@redhat.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-05-03 01:36:07 +00:00
#include "swap.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->block_dirty_folio)
* ->swap_lock (exclusive_swap_page, others)
* ->i_pages lock
*
* ->i_rwsem
* ->invalidate_lock (acquired by fs in truncate path)
* ->i_mmap_rwsem (truncate->unmap_mapping_range)
*
* ->mmap_lock
* ->i_mmap_rwsem
* ->page_table_lock or pte_lock (various, mainly in memory.c)
* ->i_pages lock (arch-dependent flush_dcache_mmap_lock)
*
* ->mmap_lock
* ->invalidate_lock (filemap_fault)
* ->lock_page (filemap_fault, access_process_vm)
*
* ->i_rwsem (generic_perform_write)
* ->mmap_lock (fault_in_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)
* ->i_pages lock (__sync_single_inode)
*
* ->i_mmap_rwsem
* ->anon_vma.lock (vma_merge)
*
* ->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)
* ->i_pages lock (try_to_unmap_one)
mm/lru: revise the comments of lru_lock Since we changed the pgdat->lru_lock to lruvec->lru_lock, it's time to fix the incorrect comments in code. Also fixed some zone->lru_lock comment error from ancient time. etc. I struggled to understand the comment above move_pages_to_lru() (surely it never calls page_referenced()), and eventually realized that most of it had got separated from shrink_active_list(): move that comment back. Link: https://lkml.kernel.org/r/1604566549-62481-20-git-send-email-alex.shi@linux.alibaba.com Signed-off-by: Hugh Dickins <hughd@google.com> Signed-off-by: Alex Shi <alex.shi@linux.alibaba.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Tejun Heo <tj@kernel.org> Cc: Andrey Ryabinin <aryabinin@virtuozzo.com> Cc: Jann Horn <jannh@google.com> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: Matthew Wilcox <willy@infradead.org> Cc: Alexander Duyck <alexander.duyck@gmail.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: "Chen, Rong A" <rong.a.chen@intel.com> Cc: Daniel Jordan <daniel.m.jordan@oracle.com> Cc: "Huang, Ying" <ying.huang@intel.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Kirill A. Shutemov <kirill@shutemov.name> Cc: Konstantin Khlebnikov <khlebnikov@yandex-team.ru> Cc: Michal Hocko <mhocko@kernel.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Mika Penttilä <mika.penttila@nextfour.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Shakeel Butt <shakeelb@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Wei Yang <richard.weiyang@gmail.com> Cc: Yang Shi <yang.shi@linux.alibaba.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-12-15 22:21:31 +00:00
* ->lruvec->lru_lock (follow_page->mark_page_accessed)
* ->lruvec->lru_lock (check_pte_range->isolate_lru_page)
* ->private_lock (folio_remove_rmap_pte->set_page_dirty)
* ->i_pages lock (folio_remove_rmap_pte->set_page_dirty)
* bdi.wb->list_lock (folio_remove_rmap_pte->set_page_dirty)
* ->inode->i_lock (folio_remove_rmap_pte->set_page_dirty)
* ->memcg->move_lock (folio_remove_rmap_pte->folio_memcg_lock)
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->block_dirty_folio)
*/
static void mapping_set_update(struct xa_state *xas,
struct address_space *mapping)
{
if (dax_mapping(mapping) || shmem_mapping(mapping))
return;
xas_set_update(xas, workingset_update_node);
xas_set_lru(xas, &shadow_nodes);
}
static void page_cache_delete(struct address_space *mapping,
struct folio *folio, void *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
{
XA_STATE(xas, &mapping->i_pages, folio->index);
long nr = 1;
mapping_set_update(&xas, mapping);
mm/filemap: remove hugetlb special casing in filemap.c Remove special cased hugetlb handling code within the page cache by changing the granularity of ->index to the base page size rather than the huge page size. The motivation of this patch is to reduce complexity within the filemap code while also increasing performance by removing branches that are evaluated on every page cache lookup. To support the change in index, new wrappers for hugetlb page cache interactions are added. These wrappers perform the conversion to a linear index which is now expected by the page cache for huge pages. ========================= PERFORMANCE ====================================== Perf was used to check the performance differences after the patch. Overall the performance is similar to mainline with a very small larger overhead that occurs in __filemap_add_folio() and hugetlb_add_to_page_cache(). This is because of the larger overhead that occurs in xa_load() and xa_store() as the xarray is now using more entries to store hugetlb folios in the page cache. Timing aarch64 2MB Page Size 6.5-rc3 + this patch: [root@sidhakum-ol9-1 hugepages]# time fallocate -l 700GB test.txt real 1m49.568s user 0m0.000s sys 1m49.461s 6.5-rc3: [root]# time fallocate -l 700GB test.txt real 1m47.495s user 0m0.000s sys 1m47.370s 1GB Page Size 6.5-rc3 + this patch: [root@sidhakum-ol9-1 hugepages1G]# time fallocate -l 700GB test.txt real 1m47.024s user 0m0.000s sys 1m46.921s 6.5-rc3: [root@sidhakum-ol9-1 hugepages1G]# time fallocate -l 700GB test.txt real 1m44.551s user 0m0.000s sys 1m44.438s x86 2MB Page Size 6.5-rc3 + this patch: [root@sidhakum-ol9-2 hugepages]# time fallocate -l 100GB test.txt real 0m22.383s user 0m0.000s sys 0m22.255s 6.5-rc3: [opc@sidhakum-ol9-2 hugepages]$ time sudo fallocate -l 100GB /dev/hugepages/test.txt real 0m22.735s user 0m0.038s sys 0m22.567s 1GB Page Size 6.5-rc3 + this patch: [root@sidhakum-ol9-2 hugepages1GB]# time fallocate -l 100GB test.txt real 0m25.786s user 0m0.001s sys 0m25.589s 6.5-rc3: [root@sidhakum-ol9-2 hugepages1G]# time fallocate -l 100GB test.txt real 0m33.454s user 0m0.001s sys 0m33.193s aarch64: workload - fallocate a 700GB file backed by huge pages 6.5-rc3 + this patch: 2MB Page Size: --100.00%--__arm64_sys_fallocate ksys_fallocate vfs_fallocate hugetlbfs_fallocate | |--95.04%--__pi_clear_page | |--3.57%--clear_huge_page | | | |--2.63%--rcu_all_qs | | | --0.91%--__cond_resched | --0.67%--__cond_resched 0.17% 0.00% 0 fallocate [kernel.vmlinux] [k] hugetlb_add_to_page_cache 0.14% 0.10% 11 fallocate [kernel.vmlinux] [k] __filemap_add_folio 6.5-rc3 2MB Page Size: --100.00%--__arm64_sys_fallocate ksys_fallocate vfs_fallocate hugetlbfs_fallocate | |--94.91%--__pi_clear_page | |--4.11%--clear_huge_page | | | |--3.00%--rcu_all_qs | | | --1.10%--__cond_resched | --0.59%--__cond_resched 0.08% 0.01% 1 fallocate [kernel.kallsyms] [k] hugetlb_add_to_page_cache 0.05% 0.03% 3 fallocate [kernel.kallsyms] [k] __filemap_add_folio x86 workload - fallocate a 100GB file backed by huge pages 6.5-rc3 + this patch: 2MB Page Size: hugetlbfs_fallocate | --99.57%--clear_huge_page | --98.47%--clear_page_erms | --0.53%--asm_sysvec_apic_timer_interrupt 0.04% 0.04% 1 fallocate [kernel.kallsyms] [k] xa_load 0.04% 0.00% 0 fallocate [kernel.kallsyms] [k] hugetlb_add_to_page_cache 0.04% 0.00% 0 fallocate [kernel.kallsyms] [k] __filemap_add_folio 0.04% 0.00% 0 fallocate [kernel.kallsyms] [k] xas_store 6.5-rc3 2MB Page Size: --99.93%--__x64_sys_fallocate vfs_fallocate hugetlbfs_fallocate | --99.38%--clear_huge_page | |--98.40%--clear_page_erms | --0.59%--__cond_resched 0.03% 0.03% 1 fallocate [kernel.kallsyms] [k] __filemap_add_folio ========================= TESTING ====================================== This patch passes libhugetlbfs tests and LTP hugetlb tests ********** TEST SUMMARY * 2M * 32-bit 64-bit * Total testcases: 110 113 * Skipped: 0 0 * PASS: 107 113 * FAIL: 0 0 * Killed by signal: 3 0 * Bad configuration: 0 0 * Expected FAIL: 0 0 * Unexpected PASS: 0 0 * Test not present: 0 0 * Strange test result: 0 0 ********** Done executing testcases. LTP Version: 20220527-178-g2761a81c4 page migration was also tested using Mike Kravetz's test program.[8] [dan.carpenter@linaro.org: fix an NULL vs IS_ERR() bug] Link: https://lkml.kernel.org/r/1772c296-1417-486f-8eef-171af2192681@moroto.mountain Link: https://lkml.kernel.org/r/20230926192017.98183-1-sidhartha.kumar@oracle.com Signed-off-by: Sidhartha Kumar <sidhartha.kumar@oracle.com> Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org> Reported-and-tested-by: syzbot+c225dea486da4d5592bd@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=c225dea486da4d5592bd Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Muchun Song <songmuchun@bytedance.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-09-26 19:20:17 +00:00
xas_set_order(&xas, folio->index, folio_order(folio));
nr = folio_nr_pages(folio);
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
VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
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
xas_store(&xas, shadow);
xas_init_marks(&xas);
mm: filemap: don't plant shadow entries without radix tree node When the underflow checks were added to workingset_node_shadow_dec(), they triggered immediately: kernel BUG at ./include/linux/swap.h:276! invalid opcode: 0000 [#1] SMP Modules linked in: isofs usb_storage fuse xt_CHECKSUM ipt_MASQUERADE nf_nat_masquerade_ipv4 tun nf_conntrack_netbios_ns nf_conntrack_broadcast ip6t_REJECT nf_reject_ipv6 soundcore wmi acpi_als pinctrl_sunrisepoint kfifo_buf tpm_tis industrialio acpi_pad pinctrl_intel tpm_tis_core tpm nfsd auth_rpcgss nfs_acl lockd grace sunrpc dm_crypt CPU: 0 PID: 20929 Comm: blkid Not tainted 4.8.0-rc8-00087-gbe67d60ba944 #1 Hardware name: System manufacturer System Product Name/Z170-K, BIOS 1803 05/06/2016 task: ffff8faa93ecd940 task.stack: ffff8faa7f478000 RIP: page_cache_tree_insert+0xf1/0x100 Call Trace: __add_to_page_cache_locked+0x12e/0x270 add_to_page_cache_lru+0x4e/0xe0 mpage_readpages+0x112/0x1d0 blkdev_readpages+0x1d/0x20 __do_page_cache_readahead+0x1ad/0x290 force_page_cache_readahead+0xaa/0x100 page_cache_sync_readahead+0x3f/0x50 generic_file_read_iter+0x5af/0x740 blkdev_read_iter+0x35/0x40 __vfs_read+0xe1/0x130 vfs_read+0x96/0x130 SyS_read+0x55/0xc0 entry_SYSCALL_64_fastpath+0x13/0x8f Code: 03 00 48 8b 5d d8 65 48 33 1c 25 28 00 00 00 44 89 e8 75 19 48 83 c4 18 5b 41 5c 41 5d 41 5e 5d c3 0f 0b 41 bd ef ff ff ff eb d7 <0f> 0b e8 88 68 ef ff 0f 1f 84 00 RIP page_cache_tree_insert+0xf1/0x100 This is a long-standing bug in the way shadow entries are accounted in the radix tree nodes. The shrinker needs to know when radix tree nodes contain only shadow entries, no pages, so node->count is split in half to count shadows in the upper bits and pages in the lower bits. Unfortunately, the radix tree implementation doesn't know of this and assumes all entries are in node->count. When there is a shadow entry directly in root->rnode and the tree is later extended, the radix tree implementation will copy that entry into the new node and and bump its node->count, i.e. increases the page count bits. Once the shadow gets removed and we subtract from the upper counter, node->count underflows and triggers the warning. Afterwards, without node->count reaching 0 again, the radix tree node is leaked. Limit shadow entries to when we have actual radix tree nodes and can count them properly. That means we lose the ability to detect refaults from files that had only the first page faulted in at eviction time. Fixes: 449dd6984d0e ("mm: keep page cache radix tree nodes in check") Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reported-and-tested-by: Linus Torvalds <torvalds@linux-foundation.org> Reviewed-by: Jan Kara <jack@suse.cz> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: stable@vger.kernel.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-04 20:02:08 +00:00
folio->mapping = NULL;
/* Leave page->index set: truncation lookup relies upon it */
mm: filemap: don't plant shadow entries without radix tree node When the underflow checks were added to workingset_node_shadow_dec(), they triggered immediately: kernel BUG at ./include/linux/swap.h:276! invalid opcode: 0000 [#1] SMP Modules linked in: isofs usb_storage fuse xt_CHECKSUM ipt_MASQUERADE nf_nat_masquerade_ipv4 tun nf_conntrack_netbios_ns nf_conntrack_broadcast ip6t_REJECT nf_reject_ipv6 soundcore wmi acpi_als pinctrl_sunrisepoint kfifo_buf tpm_tis industrialio acpi_pad pinctrl_intel tpm_tis_core tpm nfsd auth_rpcgss nfs_acl lockd grace sunrpc dm_crypt CPU: 0 PID: 20929 Comm: blkid Not tainted 4.8.0-rc8-00087-gbe67d60ba944 #1 Hardware name: System manufacturer System Product Name/Z170-K, BIOS 1803 05/06/2016 task: ffff8faa93ecd940 task.stack: ffff8faa7f478000 RIP: page_cache_tree_insert+0xf1/0x100 Call Trace: __add_to_page_cache_locked+0x12e/0x270 add_to_page_cache_lru+0x4e/0xe0 mpage_readpages+0x112/0x1d0 blkdev_readpages+0x1d/0x20 __do_page_cache_readahead+0x1ad/0x290 force_page_cache_readahead+0xaa/0x100 page_cache_sync_readahead+0x3f/0x50 generic_file_read_iter+0x5af/0x740 blkdev_read_iter+0x35/0x40 __vfs_read+0xe1/0x130 vfs_read+0x96/0x130 SyS_read+0x55/0xc0 entry_SYSCALL_64_fastpath+0x13/0x8f Code: 03 00 48 8b 5d d8 65 48 33 1c 25 28 00 00 00 44 89 e8 75 19 48 83 c4 18 5b 41 5c 41 5d 41 5e 5d c3 0f 0b 41 bd ef ff ff ff eb d7 <0f> 0b e8 88 68 ef ff 0f 1f 84 00 RIP page_cache_tree_insert+0xf1/0x100 This is a long-standing bug in the way shadow entries are accounted in the radix tree nodes. The shrinker needs to know when radix tree nodes contain only shadow entries, no pages, so node->count is split in half to count shadows in the upper bits and pages in the lower bits. Unfortunately, the radix tree implementation doesn't know of this and assumes all entries are in node->count. When there is a shadow entry directly in root->rnode and the tree is later extended, the radix tree implementation will copy that entry into the new node and and bump its node->count, i.e. increases the page count bits. Once the shadow gets removed and we subtract from the upper counter, node->count underflows and triggers the warning. Afterwards, without node->count reaching 0 again, the radix tree node is leaked. Limit shadow entries to when we have actual radix tree nodes and can count them properly. That means we lose the ability to detect refaults from files that had only the first page faulted in at eviction time. Fixes: 449dd6984d0e ("mm: keep page cache radix tree nodes in check") Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reported-and-tested-by: Linus Torvalds <torvalds@linux-foundation.org> Reviewed-by: Jan Kara <jack@suse.cz> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: stable@vger.kernel.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-04 20:02:08 +00:00
mapping->nrpages -= nr;
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 filemap_unaccount_folio(struct address_space *mapping,
struct folio *folio)
{
long nr;
VM_BUG_ON_FOLIO(folio_mapped(folio), folio);
if (!IS_ENABLED(CONFIG_DEBUG_VM) && unlikely(folio_mapped(folio))) {
mm: __delete_from_page_cache show Bad page if mapped Commit e1534ae95004 ("mm: differentiate page_mapped() from page_mapcount() for compound pages") changed the famous BUG_ON(page_mapped(page)) in __delete_from_page_cache() to VM_BUG_ON_PAGE(page_mapped(page)): which gives us more info when CONFIG_DEBUG_VM=y, but nothing at all when not. Although it has not usually been very helpul, being hit long after the error in question, we do need to know if it actually happens on users' systems; but reinstating a crash there is likely to be opposed :) In the non-debug case, pr_alert("BUG: Bad page cache") plus dump_page(), dump_stack(), add_taint() - I don't really believe LOCKDEP_NOW_UNRELIABLE, but that seems to be the standard procedure now. Move that, or the VM_BUG_ON_PAGE(), up before the deletion from tree: so that the unNULLified page->mapping gives a little more information. If the inode is being evicted (rather than truncated), it won't have any vmas left, so it's safe(ish) to assume that the raised mapcount is erroneous, and we can discount it from page_count to avoid leaking the page (I'm less worried by leaking the occasional 4kB, than losing a potential 2MB page with each 4kB page leaked). Signed-off-by: Hugh Dickins <hughd@google.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Sasha Levin <sasha.levin@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-03-09 22:08:07 +00:00
pr_alert("BUG: Bad page cache in process %s pfn:%05lx\n",
current->comm, folio_pfn(folio));
dump_page(&folio->page, "still mapped when deleted");
mm: __delete_from_page_cache show Bad page if mapped Commit e1534ae95004 ("mm: differentiate page_mapped() from page_mapcount() for compound pages") changed the famous BUG_ON(page_mapped(page)) in __delete_from_page_cache() to VM_BUG_ON_PAGE(page_mapped(page)): which gives us more info when CONFIG_DEBUG_VM=y, but nothing at all when not. Although it has not usually been very helpul, being hit long after the error in question, we do need to know if it actually happens on users' systems; but reinstating a crash there is likely to be opposed :) In the non-debug case, pr_alert("BUG: Bad page cache") plus dump_page(), dump_stack(), add_taint() - I don't really believe LOCKDEP_NOW_UNRELIABLE, but that seems to be the standard procedure now. Move that, or the VM_BUG_ON_PAGE(), up before the deletion from tree: so that the unNULLified page->mapping gives a little more information. If the inode is being evicted (rather than truncated), it won't have any vmas left, so it's safe(ish) to assume that the raised mapcount is erroneous, and we can discount it from page_count to avoid leaking the page (I'm less worried by leaking the occasional 4kB, than losing a potential 2MB page with each 4kB page leaked). Signed-off-by: Hugh Dickins <hughd@google.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Sasha Levin <sasha.levin@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-03-09 22:08:07 +00:00
dump_stack();
add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE);
if (mapping_exiting(mapping) && !folio_test_large(folio)) {
int mapcount = folio_mapcount(folio);
if (folio_ref_count(folio) >= mapcount + 2) {
/*
* All vmas have already been torn down, so it's
* a good bet that actually the page is unmapped
* and we'd rather not leak it: if we're wrong,
* another bad page check should catch it later.
*/
page_mapcount_reset(&folio->page);
folio_ref_sub(folio, mapcount);
}
mm: __delete_from_page_cache show Bad page if mapped Commit e1534ae95004 ("mm: differentiate page_mapped() from page_mapcount() for compound pages") changed the famous BUG_ON(page_mapped(page)) in __delete_from_page_cache() to VM_BUG_ON_PAGE(page_mapped(page)): which gives us more info when CONFIG_DEBUG_VM=y, but nothing at all when not. Although it has not usually been very helpul, being hit long after the error in question, we do need to know if it actually happens on users' systems; but reinstating a crash there is likely to be opposed :) In the non-debug case, pr_alert("BUG: Bad page cache") plus dump_page(), dump_stack(), add_taint() - I don't really believe LOCKDEP_NOW_UNRELIABLE, but that seems to be the standard procedure now. Move that, or the VM_BUG_ON_PAGE(), up before the deletion from tree: so that the unNULLified page->mapping gives a little more information. If the inode is being evicted (rather than truncated), it won't have any vmas left, so it's safe(ish) to assume that the raised mapcount is erroneous, and we can discount it from page_count to avoid leaking the page (I'm less worried by leaking the occasional 4kB, than losing a potential 2MB page with each 4kB page leaked). Signed-off-by: Hugh Dickins <hughd@google.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Sasha Levin <sasha.levin@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-03-09 22:08:07 +00:00
}
}
/* hugetlb folios do not participate in page cache accounting. */
if (folio_test_hugetlb(folio))
return;
nr = folio_nr_pages(folio);
__lruvec_stat_mod_folio(folio, NR_FILE_PAGES, -nr);
if (folio_test_swapbacked(folio)) {
__lruvec_stat_mod_folio(folio, NR_SHMEM, -nr);
if (folio_test_pmd_mappable(folio))
__lruvec_stat_mod_folio(folio, NR_SHMEM_THPS, -nr);
} else if (folio_test_pmd_mappable(folio)) {
__lruvec_stat_mod_folio(folio, NR_FILE_THPS, -nr);
filemap_nr_thps_dec(mapping);
}
/*
* At this point folio must be either written or cleaned by
* truncate. Dirty folio here signals a bug and loss of
* unwritten data - on ordinary filesystems.
*
* But it's harmless on in-memory filesystems like tmpfs; and can
* occur when a driver which did get_user_pages() sets page dirty
* before putting it, while the inode is being finally evicted.
*
* Below fixes dirty accounting after removing the folio entirely
* but leaves the dirty flag set: it has no effect for truncated
* folio and anyway will be cleared before returning folio to
* buddy allocator.
*/
if (WARN_ON_ONCE(folio_test_dirty(folio) &&
mapping_can_writeback(mapping)))
folio_account_cleaned(folio, inode_to_wb(mapping->host));
}
/*
* Delete a page from the page cache and free it. Caller has to make
* sure the page is locked and that nobody else uses it - or that usage
* is safe. The caller must hold the i_pages lock.
*/
void __filemap_remove_folio(struct folio *folio, void *shadow)
{
struct address_space *mapping = folio->mapping;
trace_mm_filemap_delete_from_page_cache(folio);
filemap_unaccount_folio(mapping, folio);
page_cache_delete(mapping, folio, shadow);
}
void filemap_free_folio(struct address_space *mapping, struct folio *folio)
{
void (*free_folio)(struct folio *);
int refs = 1;
free_folio = mapping->a_ops->free_folio;
if (free_folio)
free_folio(folio);
mm/filemap: remove hugetlb special casing in filemap.c Remove special cased hugetlb handling code within the page cache by changing the granularity of ->index to the base page size rather than the huge page size. The motivation of this patch is to reduce complexity within the filemap code while also increasing performance by removing branches that are evaluated on every page cache lookup. To support the change in index, new wrappers for hugetlb page cache interactions are added. These wrappers perform the conversion to a linear index which is now expected by the page cache for huge pages. ========================= PERFORMANCE ====================================== Perf was used to check the performance differences after the patch. Overall the performance is similar to mainline with a very small larger overhead that occurs in __filemap_add_folio() and hugetlb_add_to_page_cache(). This is because of the larger overhead that occurs in xa_load() and xa_store() as the xarray is now using more entries to store hugetlb folios in the page cache. Timing aarch64 2MB Page Size 6.5-rc3 + this patch: [root@sidhakum-ol9-1 hugepages]# time fallocate -l 700GB test.txt real 1m49.568s user 0m0.000s sys 1m49.461s 6.5-rc3: [root]# time fallocate -l 700GB test.txt real 1m47.495s user 0m0.000s sys 1m47.370s 1GB Page Size 6.5-rc3 + this patch: [root@sidhakum-ol9-1 hugepages1G]# time fallocate -l 700GB test.txt real 1m47.024s user 0m0.000s sys 1m46.921s 6.5-rc3: [root@sidhakum-ol9-1 hugepages1G]# time fallocate -l 700GB test.txt real 1m44.551s user 0m0.000s sys 1m44.438s x86 2MB Page Size 6.5-rc3 + this patch: [root@sidhakum-ol9-2 hugepages]# time fallocate -l 100GB test.txt real 0m22.383s user 0m0.000s sys 0m22.255s 6.5-rc3: [opc@sidhakum-ol9-2 hugepages]$ time sudo fallocate -l 100GB /dev/hugepages/test.txt real 0m22.735s user 0m0.038s sys 0m22.567s 1GB Page Size 6.5-rc3 + this patch: [root@sidhakum-ol9-2 hugepages1GB]# time fallocate -l 100GB test.txt real 0m25.786s user 0m0.001s sys 0m25.589s 6.5-rc3: [root@sidhakum-ol9-2 hugepages1G]# time fallocate -l 100GB test.txt real 0m33.454s user 0m0.001s sys 0m33.193s aarch64: workload - fallocate a 700GB file backed by huge pages 6.5-rc3 + this patch: 2MB Page Size: --100.00%--__arm64_sys_fallocate ksys_fallocate vfs_fallocate hugetlbfs_fallocate | |--95.04%--__pi_clear_page | |--3.57%--clear_huge_page | | | |--2.63%--rcu_all_qs | | | --0.91%--__cond_resched | --0.67%--__cond_resched 0.17% 0.00% 0 fallocate [kernel.vmlinux] [k] hugetlb_add_to_page_cache 0.14% 0.10% 11 fallocate [kernel.vmlinux] [k] __filemap_add_folio 6.5-rc3 2MB Page Size: --100.00%--__arm64_sys_fallocate ksys_fallocate vfs_fallocate hugetlbfs_fallocate | |--94.91%--__pi_clear_page | |--4.11%--clear_huge_page | | | |--3.00%--rcu_all_qs | | | --1.10%--__cond_resched | --0.59%--__cond_resched 0.08% 0.01% 1 fallocate [kernel.kallsyms] [k] hugetlb_add_to_page_cache 0.05% 0.03% 3 fallocate [kernel.kallsyms] [k] __filemap_add_folio x86 workload - fallocate a 100GB file backed by huge pages 6.5-rc3 + this patch: 2MB Page Size: hugetlbfs_fallocate | --99.57%--clear_huge_page | --98.47%--clear_page_erms | --0.53%--asm_sysvec_apic_timer_interrupt 0.04% 0.04% 1 fallocate [kernel.kallsyms] [k] xa_load 0.04% 0.00% 0 fallocate [kernel.kallsyms] [k] hugetlb_add_to_page_cache 0.04% 0.00% 0 fallocate [kernel.kallsyms] [k] __filemap_add_folio 0.04% 0.00% 0 fallocate [kernel.kallsyms] [k] xas_store 6.5-rc3 2MB Page Size: --99.93%--__x64_sys_fallocate vfs_fallocate hugetlbfs_fallocate | --99.38%--clear_huge_page | |--98.40%--clear_page_erms | --0.59%--__cond_resched 0.03% 0.03% 1 fallocate [kernel.kallsyms] [k] __filemap_add_folio ========================= TESTING ====================================== This patch passes libhugetlbfs tests and LTP hugetlb tests ********** TEST SUMMARY * 2M * 32-bit 64-bit * Total testcases: 110 113 * Skipped: 0 0 * PASS: 107 113 * FAIL: 0 0 * Killed by signal: 3 0 * Bad configuration: 0 0 * Expected FAIL: 0 0 * Unexpected PASS: 0 0 * Test not present: 0 0 * Strange test result: 0 0 ********** Done executing testcases. LTP Version: 20220527-178-g2761a81c4 page migration was also tested using Mike Kravetz's test program.[8] [dan.carpenter@linaro.org: fix an NULL vs IS_ERR() bug] Link: https://lkml.kernel.org/r/1772c296-1417-486f-8eef-171af2192681@moroto.mountain Link: https://lkml.kernel.org/r/20230926192017.98183-1-sidhartha.kumar@oracle.com Signed-off-by: Sidhartha Kumar <sidhartha.kumar@oracle.com> Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org> Reported-and-tested-by: syzbot+c225dea486da4d5592bd@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=c225dea486da4d5592bd Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Muchun Song <songmuchun@bytedance.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-09-26 19:20:17 +00:00
if (folio_test_large(folio))
refs = folio_nr_pages(folio);
folio_put_refs(folio, refs);
}
/**
* filemap_remove_folio - Remove folio from page cache.
* @folio: The folio.
*
* This must be called only on folios that are locked and have been
* verified to be in the page cache. It will never put the folio into
* the free list because the caller has a reference on the page.
*/
void filemap_remove_folio(struct folio *folio)
{
struct address_space *mapping = folio->mapping;
BUG_ON(!folio_test_locked(folio));
vfs: keep inodes with page cache off the inode shrinker LRU Historically (pre-2.5), the inode shrinker used to reclaim only empty inodes and skip over those that still contained page cache. This caused problems on highmem hosts: struct inode could put fill lowmem zones before the cache was getting reclaimed in the highmem zones. To address this, the inode shrinker started to strip page cache to facilitate reclaiming lowmem. However, this comes with its own set of problems: the shrinkers may drop actively used page cache just because the inodes are not currently open or dirty - think working with a large git tree. It further doesn't respect cgroup memory protection settings and can cause priority inversions between containers. Nowadays, the page cache also holds non-resident info for evicted cache pages in order to detect refaults. We've come to rely heavily on this data inside reclaim for protecting the cache workingset and driving swap behavior. We also use it to quantify and report workload health through psi. The latter in turn is used for fleet health monitoring, as well as driving automated memory sizing of workloads and containers, proactive reclaim and memory offloading schemes. The consequences of dropping page cache prematurely is that we're seeing subtle and not-so-subtle failures in all of the above-mentioned scenarios, with the workload generally entering unexpected thrashing states while losing the ability to reliably detect it. To fix this on non-highmem systems at least, going back to rotating inodes on the LRU isn't feasible. We've tried (commit a76cf1a474d7 ("mm: don't reclaim inodes with many attached pages")) and failed (commit 69056ee6a8a3 ("Revert "mm: don't reclaim inodes with many attached pages"")). The issue is mostly that shrinker pools attract pressure based on their size, and when objects get skipped the shrinkers remember this as deferred reclaim work. This accumulates excessive pressure on the remaining inodes, and we can quickly eat into heavily used ones, or dirty ones that require IO to reclaim, when there potentially is plenty of cold, clean cache around still. Instead, this patch keeps populated inodes off the inode LRU in the first place - just like an open file or dirty state would. An otherwise clean and unused inode then gets queued when the last cache entry disappears. This solves the problem without reintroducing the reclaim issues, and generally is a bit more scalable than having to wade through potentially hundreds of thousands of busy inodes. Locking is a bit tricky because the locks protecting the inode state (i_lock) and the inode LRU (lru_list.lock) don't nest inside the irq-safe page cache lock (i_pages.xa_lock). Page cache deletions are serialized through i_lock, taken before the i_pages lock, to make sure depopulated inodes are queued reliably. Additions may race with deletions, but we'll check again in the shrinker. If additions race with the shrinker itself, we're protected by the i_lock: if find_inode() or iput() win, the shrinker will bail on the elevated i_count or I_REFERENCED; if the shrinker wins and goes ahead with the inode, it will set I_FREEING and inhibit further igets(), which will cause the other side to create a new instance of the inode instead. Link: https://lkml.kernel.org/r/20210614211904.14420-4-hannes@cmpxchg.org Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Roman Gushchin <guro@fb.com> Cc: Tejun Heo <tj@kernel.org> Cc: Dave Chinner <david@fromorbit.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-11-09 02:31:24 +00:00
spin_lock(&mapping->host->i_lock);
xa_lock_irq(&mapping->i_pages);
__filemap_remove_folio(folio, NULL);
xa_unlock_irq(&mapping->i_pages);
vfs: keep inodes with page cache off the inode shrinker LRU Historically (pre-2.5), the inode shrinker used to reclaim only empty inodes and skip over those that still contained page cache. This caused problems on highmem hosts: struct inode could put fill lowmem zones before the cache was getting reclaimed in the highmem zones. To address this, the inode shrinker started to strip page cache to facilitate reclaiming lowmem. However, this comes with its own set of problems: the shrinkers may drop actively used page cache just because the inodes are not currently open or dirty - think working with a large git tree. It further doesn't respect cgroup memory protection settings and can cause priority inversions between containers. Nowadays, the page cache also holds non-resident info for evicted cache pages in order to detect refaults. We've come to rely heavily on this data inside reclaim for protecting the cache workingset and driving swap behavior. We also use it to quantify and report workload health through psi. The latter in turn is used for fleet health monitoring, as well as driving automated memory sizing of workloads and containers, proactive reclaim and memory offloading schemes. The consequences of dropping page cache prematurely is that we're seeing subtle and not-so-subtle failures in all of the above-mentioned scenarios, with the workload generally entering unexpected thrashing states while losing the ability to reliably detect it. To fix this on non-highmem systems at least, going back to rotating inodes on the LRU isn't feasible. We've tried (commit a76cf1a474d7 ("mm: don't reclaim inodes with many attached pages")) and failed (commit 69056ee6a8a3 ("Revert "mm: don't reclaim inodes with many attached pages"")). The issue is mostly that shrinker pools attract pressure based on their size, and when objects get skipped the shrinkers remember this as deferred reclaim work. This accumulates excessive pressure on the remaining inodes, and we can quickly eat into heavily used ones, or dirty ones that require IO to reclaim, when there potentially is plenty of cold, clean cache around still. Instead, this patch keeps populated inodes off the inode LRU in the first place - just like an open file or dirty state would. An otherwise clean and unused inode then gets queued when the last cache entry disappears. This solves the problem without reintroducing the reclaim issues, and generally is a bit more scalable than having to wade through potentially hundreds of thousands of busy inodes. Locking is a bit tricky because the locks protecting the inode state (i_lock) and the inode LRU (lru_list.lock) don't nest inside the irq-safe page cache lock (i_pages.xa_lock). Page cache deletions are serialized through i_lock, taken before the i_pages lock, to make sure depopulated inodes are queued reliably. Additions may race with deletions, but we'll check again in the shrinker. If additions race with the shrinker itself, we're protected by the i_lock: if find_inode() or iput() win, the shrinker will bail on the elevated i_count or I_REFERENCED; if the shrinker wins and goes ahead with the inode, it will set I_FREEING and inhibit further igets(), which will cause the other side to create a new instance of the inode instead. Link: https://lkml.kernel.org/r/20210614211904.14420-4-hannes@cmpxchg.org Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Roman Gushchin <guro@fb.com> Cc: Tejun Heo <tj@kernel.org> Cc: Dave Chinner <david@fromorbit.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-11-09 02:31:24 +00:00
if (mapping_shrinkable(mapping))
inode_add_lru(mapping->host);
spin_unlock(&mapping->host->i_lock);
filemap_free_folio(mapping, folio);
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_delete_batch - delete several folios from page cache
* @mapping: the mapping to which folios belong
* @fbatch: batch of folios to delete
*
* The function walks over mapping->i_pages and removes folios passed in
* @fbatch from the mapping. The function expects @fbatch to be sorted
* by page index and is optimised for it to be dense.
* It tolerates holes in @fbatch (mapping entries at those indices are not
* modified).
*
* The function expects the i_pages lock to be held.
*/
static void page_cache_delete_batch(struct address_space *mapping,
struct folio_batch *fbatch)
{
XA_STATE(xas, &mapping->i_pages, fbatch->folios[0]->index);
long total_pages = 0;
int i = 0;
struct folio *folio;
mapping_set_update(&xas, mapping);
xas_for_each(&xas, folio, ULONG_MAX) {
if (i >= folio_batch_count(fbatch))
break;
/* A swap/dax/shadow entry got inserted? Skip it. */
if (xa_is_value(folio))
continue;
/*
* A page got inserted in our range? Skip it. We have our
* pages locked so they are protected from being removed.
* If we see a page whose index is higher than ours, it
* means our page has been removed, which shouldn't be
* possible because we're holding the PageLock.
*/
if (folio != fbatch->folios[i]) {
VM_BUG_ON_FOLIO(folio->index >
fbatch->folios[i]->index, folio);
continue;
}
WARN_ON_ONCE(!folio_test_locked(folio));
folio->mapping = NULL;
/* Leave folio->index set: truncation lookup relies on it */
i++;
xas_store(&xas, NULL);
total_pages += folio_nr_pages(folio);
}
mapping->nrpages -= total_pages;
}
void delete_from_page_cache_batch(struct address_space *mapping,
struct folio_batch *fbatch)
{
int i;
if (!folio_batch_count(fbatch))
return;
vfs: keep inodes with page cache off the inode shrinker LRU Historically (pre-2.5), the inode shrinker used to reclaim only empty inodes and skip over those that still contained page cache. This caused problems on highmem hosts: struct inode could put fill lowmem zones before the cache was getting reclaimed in the highmem zones. To address this, the inode shrinker started to strip page cache to facilitate reclaiming lowmem. However, this comes with its own set of problems: the shrinkers may drop actively used page cache just because the inodes are not currently open or dirty - think working with a large git tree. It further doesn't respect cgroup memory protection settings and can cause priority inversions between containers. Nowadays, the page cache also holds non-resident info for evicted cache pages in order to detect refaults. We've come to rely heavily on this data inside reclaim for protecting the cache workingset and driving swap behavior. We also use it to quantify and report workload health through psi. The latter in turn is used for fleet health monitoring, as well as driving automated memory sizing of workloads and containers, proactive reclaim and memory offloading schemes. The consequences of dropping page cache prematurely is that we're seeing subtle and not-so-subtle failures in all of the above-mentioned scenarios, with the workload generally entering unexpected thrashing states while losing the ability to reliably detect it. To fix this on non-highmem systems at least, going back to rotating inodes on the LRU isn't feasible. We've tried (commit a76cf1a474d7 ("mm: don't reclaim inodes with many attached pages")) and failed (commit 69056ee6a8a3 ("Revert "mm: don't reclaim inodes with many attached pages"")). The issue is mostly that shrinker pools attract pressure based on their size, and when objects get skipped the shrinkers remember this as deferred reclaim work. This accumulates excessive pressure on the remaining inodes, and we can quickly eat into heavily used ones, or dirty ones that require IO to reclaim, when there potentially is plenty of cold, clean cache around still. Instead, this patch keeps populated inodes off the inode LRU in the first place - just like an open file or dirty state would. An otherwise clean and unused inode then gets queued when the last cache entry disappears. This solves the problem without reintroducing the reclaim issues, and generally is a bit more scalable than having to wade through potentially hundreds of thousands of busy inodes. Locking is a bit tricky because the locks protecting the inode state (i_lock) and the inode LRU (lru_list.lock) don't nest inside the irq-safe page cache lock (i_pages.xa_lock). Page cache deletions are serialized through i_lock, taken before the i_pages lock, to make sure depopulated inodes are queued reliably. Additions may race with deletions, but we'll check again in the shrinker. If additions race with the shrinker itself, we're protected by the i_lock: if find_inode() or iput() win, the shrinker will bail on the elevated i_count or I_REFERENCED; if the shrinker wins and goes ahead with the inode, it will set I_FREEING and inhibit further igets(), which will cause the other side to create a new instance of the inode instead. Link: https://lkml.kernel.org/r/20210614211904.14420-4-hannes@cmpxchg.org Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Roman Gushchin <guro@fb.com> Cc: Tejun Heo <tj@kernel.org> Cc: Dave Chinner <david@fromorbit.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-11-09 02:31:24 +00:00
spin_lock(&mapping->host->i_lock);
xa_lock_irq(&mapping->i_pages);
for (i = 0; i < folio_batch_count(fbatch); i++) {
struct folio *folio = fbatch->folios[i];
trace_mm_filemap_delete_from_page_cache(folio);
filemap_unaccount_folio(mapping, folio);
}
page_cache_delete_batch(mapping, fbatch);
xa_unlock_irq(&mapping->i_pages);
vfs: keep inodes with page cache off the inode shrinker LRU Historically (pre-2.5), the inode shrinker used to reclaim only empty inodes and skip over those that still contained page cache. This caused problems on highmem hosts: struct inode could put fill lowmem zones before the cache was getting reclaimed in the highmem zones. To address this, the inode shrinker started to strip page cache to facilitate reclaiming lowmem. However, this comes with its own set of problems: the shrinkers may drop actively used page cache just because the inodes are not currently open or dirty - think working with a large git tree. It further doesn't respect cgroup memory protection settings and can cause priority inversions between containers. Nowadays, the page cache also holds non-resident info for evicted cache pages in order to detect refaults. We've come to rely heavily on this data inside reclaim for protecting the cache workingset and driving swap behavior. We also use it to quantify and report workload health through psi. The latter in turn is used for fleet health monitoring, as well as driving automated memory sizing of workloads and containers, proactive reclaim and memory offloading schemes. The consequences of dropping page cache prematurely is that we're seeing subtle and not-so-subtle failures in all of the above-mentioned scenarios, with the workload generally entering unexpected thrashing states while losing the ability to reliably detect it. To fix this on non-highmem systems at least, going back to rotating inodes on the LRU isn't feasible. We've tried (commit a76cf1a474d7 ("mm: don't reclaim inodes with many attached pages")) and failed (commit 69056ee6a8a3 ("Revert "mm: don't reclaim inodes with many attached pages"")). The issue is mostly that shrinker pools attract pressure based on their size, and when objects get skipped the shrinkers remember this as deferred reclaim work. This accumulates excessive pressure on the remaining inodes, and we can quickly eat into heavily used ones, or dirty ones that require IO to reclaim, when there potentially is plenty of cold, clean cache around still. Instead, this patch keeps populated inodes off the inode LRU in the first place - just like an open file or dirty state would. An otherwise clean and unused inode then gets queued when the last cache entry disappears. This solves the problem without reintroducing the reclaim issues, and generally is a bit more scalable than having to wade through potentially hundreds of thousands of busy inodes. Locking is a bit tricky because the locks protecting the inode state (i_lock) and the inode LRU (lru_list.lock) don't nest inside the irq-safe page cache lock (i_pages.xa_lock). Page cache deletions are serialized through i_lock, taken before the i_pages lock, to make sure depopulated inodes are queued reliably. Additions may race with deletions, but we'll check again in the shrinker. If additions race with the shrinker itself, we're protected by the i_lock: if find_inode() or iput() win, the shrinker will bail on the elevated i_count or I_REFERENCED; if the shrinker wins and goes ahead with the inode, it will set I_FREEING and inhibit further igets(), which will cause the other side to create a new instance of the inode instead. Link: https://lkml.kernel.org/r/20210614211904.14420-4-hannes@cmpxchg.org Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Roman Gushchin <guro@fb.com> Cc: Tejun Heo <tj@kernel.org> Cc: Dave Chinner <david@fromorbit.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-11-09 02:31:24 +00:00
if (mapping_shrinkable(mapping))
inode_add_lru(mapping->host);
spin_unlock(&mapping->host->i_lock);
for (i = 0; i < folio_batch_count(fbatch); i++)
filemap_free_folio(mapping, fbatch->folios[i]);
}
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;
}
EXPORT_SYMBOL(filemap_check_errors);
static int filemap_check_and_keep_errors(struct address_space *mapping)
{
/* Check for outstanding write errors */
if (test_bit(AS_EIO, &mapping->flags))
return -EIO;
if (test_bit(AS_ENOSPC, &mapping->flags))
return -ENOSPC;
return 0;
}
fs: add a filemap_fdatawrite_wbc helper Btrfs sometimes needs to flush dirty pages on a bunch of dirty inodes in order to reclaim metadata reservations. Unfortunately most helpers in this area are too smart for us: 1) The normal filemap_fdata* helpers only take range and sync modes, and don't give any indication of how much was written, so we can only flush full inodes, which isn't what we want in most cases. 2) The normal writeback path requires us to have the s_umount sem held, but we can't unconditionally take it in this path because we could deadlock. 3) The normal writeback path also skips inodes with I_SYNC set if we write with WB_SYNC_NONE. This isn't the behavior we want under heavy ENOSPC pressure, we want to actually make sure the pages are under writeback before returning, and if another thread is in the middle of writing the file we may return before they're under writeback and miss our ordered extents and not properly wait for completion. 4) sync_inode() uses the normal writeback path and has the same problem as #3. What we really want is to call do_writepages() with our wbc. This way we can make sure that writeback is actually started on the pages, and we can control how many pages are written as a whole as we write many inodes using the same wbc. Accomplish this with a new helper that does just that so we can use it for our ENOSPC flushing infrastructure. Reviewed-by: Nikolay Borisov <nborisov@suse.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Josef Bacik <josef@toxicpanda.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-14 18:47:22 +00:00
/**
* filemap_fdatawrite_wbc - start writeback on mapping dirty pages in range
* @mapping: address space structure to write
* @wbc: the writeback_control controlling the writeout
*
* Call writepages on the mapping using the provided wbc to control the
* writeout.
*
* Return: %0 on success, negative error code otherwise.
*/
int filemap_fdatawrite_wbc(struct address_space *mapping,
struct writeback_control *wbc)
{
int ret;
if (!mapping_can_writeback(mapping) ||
!mapping_tagged(mapping, PAGECACHE_TAG_DIRTY))
return 0;
wbc_attach_fdatawrite_inode(wbc, mapping->host);
ret = do_writepages(mapping, wbc);
wbc_detach_inode(wbc);
return ret;
}
EXPORT_SYMBOL(filemap_fdatawrite_wbc);
/**
* __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.
*
* Return: %0 on success, negative error code otherwise.
*/
[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)
{
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,
};
fs: add a filemap_fdatawrite_wbc helper Btrfs sometimes needs to flush dirty pages on a bunch of dirty inodes in order to reclaim metadata reservations. Unfortunately most helpers in this area are too smart for us: 1) The normal filemap_fdata* helpers only take range and sync modes, and don't give any indication of how much was written, so we can only flush full inodes, which isn't what we want in most cases. 2) The normal writeback path requires us to have the s_umount sem held, but we can't unconditionally take it in this path because we could deadlock. 3) The normal writeback path also skips inodes with I_SYNC set if we write with WB_SYNC_NONE. This isn't the behavior we want under heavy ENOSPC pressure, we want to actually make sure the pages are under writeback before returning, and if another thread is in the middle of writing the file we may return before they're under writeback and miss our ordered extents and not properly wait for completion. 4) sync_inode() uses the normal writeback path and has the same problem as #3. What we really want is to call do_writepages() with our wbc. This way we can make sure that writeback is actually started on the pages, and we can control how many pages are written as a whole as we write many inodes using the same wbc. Accomplish this with a new helper that does just that so we can use it for our ENOSPC flushing infrastructure. Reviewed-by: Nikolay Borisov <nborisov@suse.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Josef Bacik <josef@toxicpanda.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-14 18:47:22 +00:00
return filemap_fdatawrite_wbc(mapping, &wbc);
}
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.
*
* Return: %0 on success, negative error code otherwise.
*/
int filemap_flush(struct address_space *mapping)
{
return __filemap_fdatawrite(mapping, WB_SYNC_NONE);
}
EXPORT_SYMBOL(filemap_flush);
/**
* filemap_range_has_page - check if a page exists in range.
* @mapping: address space within which to check
* @start_byte: offset in bytes where the range starts
* @end_byte: offset in bytes where the range ends (inclusive)
*
* Find at least one page in the range supplied, usually used to check if
* direct writing in this range will trigger a writeback.
*
* Return: %true if at least one page exists in the specified range,
* %false otherwise.
*/
bool filemap_range_has_page(struct address_space *mapping,
loff_t start_byte, loff_t end_byte)
{
struct folio *folio;
XA_STATE(xas, &mapping->i_pages, start_byte >> PAGE_SHIFT);
pgoff_t max = end_byte >> PAGE_SHIFT;
if (end_byte < start_byte)
return false;
rcu_read_lock();
for (;;) {
folio = xas_find(&xas, max);
if (xas_retry(&xas, folio))
continue;
/* Shadow entries don't count */
if (xa_is_value(folio))
continue;
/*
* We don't need to try to pin this page; we're about to
* release the RCU lock anyway. It is enough to know that
* there was a page here recently.
*/
break;
}
rcu_read_unlock();
return folio != NULL;
}
EXPORT_SYMBOL(filemap_range_has_page);
static void __filemap_fdatawait_range(struct address_space *mapping,
loff_t start_byte, loff_t end_byte)
{
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 12:29:47 +00:00
pgoff_t index = start_byte >> PAGE_SHIFT;
pgoff_t end = end_byte >> PAGE_SHIFT;
struct folio_batch fbatch;
unsigned nr_folios;
folio_batch_init(&fbatch);
while (index <= end) {
unsigned i;
nr_folios = filemap_get_folios_tag(mapping, &index, end,
PAGECACHE_TAG_WRITEBACK, &fbatch);
if (!nr_folios)
break;
for (i = 0; i < nr_folios; i++) {
struct folio *folio = fbatch.folios[i];
folio_wait_writeback(folio);
folio_clear_error(folio);
}
folio_batch_release(&fbatch);
cond_resched();
}
}
/**
* 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. Check error status of
* the address space and return it.
*
* Since the error status of the address space is cleared by this function,
* callers are responsible for checking the return value and handling and/or
* reporting the error.
*
* Return: error status of the address space.
*/
int filemap_fdatawait_range(struct address_space *mapping, loff_t start_byte,
loff_t end_byte)
{
__filemap_fdatawait_range(mapping, start_byte, end_byte);
return filemap_check_errors(mapping);
}
EXPORT_SYMBOL(filemap_fdatawait_range);
/**
* filemap_fdatawait_range_keep_errors - 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. Unlike filemap_fdatawait_range(),
* this function does not clear error status of the address space.
*
* Use this function if callers don't handle errors themselves. Expected
* call sites are system-wide / filesystem-wide data flushers: e.g. sync(2),
* fsfreeze(8)
*/
int filemap_fdatawait_range_keep_errors(struct address_space *mapping,
loff_t start_byte, loff_t end_byte)
{
__filemap_fdatawait_range(mapping, start_byte, end_byte);
return filemap_check_and_keep_errors(mapping);
}
EXPORT_SYMBOL(filemap_fdatawait_range_keep_errors);
/**
* file_fdatawait_range - wait for writeback to complete
* @file: file pointing to 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 address space that file
* refers to, in the given range and wait for all of them. Check error
* status of the address space vs. the file->f_wb_err cursor and return it.
*
* Since the error status of the file is advanced by this function,
* callers are responsible for checking the return value and handling and/or
* reporting the error.
*
* Return: error status of the address space vs. the file->f_wb_err cursor.
*/
int file_fdatawait_range(struct file *file, loff_t start_byte, loff_t end_byte)
{
struct address_space *mapping = file->f_mapping;
__filemap_fdatawait_range(mapping, start_byte, end_byte);
return file_check_and_advance_wb_err(file);
}
EXPORT_SYMBOL(file_fdatawait_range);
/**
* filemap_fdatawait_keep_errors - wait for writeback without clearing errors
* @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. Unlike filemap_fdatawait(), this function
* does not clear error status of the address space.
*
* Use this function if callers don't handle errors themselves. Expected
* call sites are system-wide / filesystem-wide data flushers: e.g. sync(2),
* fsfreeze(8)
*
* Return: error status of the address space.
*/
int filemap_fdatawait_keep_errors(struct address_space *mapping)
{
__filemap_fdatawait_range(mapping, 0, LLONG_MAX);
return filemap_check_and_keep_errors(mapping);
}
EXPORT_SYMBOL(filemap_fdatawait_keep_errors);
/* Returns true if writeback might be needed or already in progress. */
static bool mapping_needs_writeback(struct address_space *mapping)
{
return mapping->nrpages;
}
bool filemap_range_has_writeback(struct address_space *mapping,
loff_t start_byte, loff_t end_byte)
{
XA_STATE(xas, &mapping->i_pages, start_byte >> PAGE_SHIFT);
pgoff_t max = end_byte >> PAGE_SHIFT;
struct folio *folio;
if (end_byte < start_byte)
return false;
rcu_read_lock();
xas_for_each(&xas, folio, max) {
if (xas_retry(&xas, folio))
continue;
if (xa_is_value(folio))
continue;
if (folio_test_dirty(folio) || folio_test_locked(folio) ||
folio_test_writeback(folio))
break;
}
rcu_read_unlock();
return folio != NULL;
mm: provide filemap_range_needs_writeback() helper Patch series "Improve IOCB_NOWAIT O_DIRECT reads", v3. An internal workload complained because it was using too much CPU, and when I took a look, we had a lot of io_uring workers going to town. For an async buffered read like workload, I am normally expecting _zero_ offloads to a worker thread, but this one had tons of them. I'd drop caches and things would look good again, but then a minute later we'd regress back to using workers. Turns out that every minute something was reading parts of the device, which would add page cache for that inode. I put patches like these in for our kernel, and the problem was solved. Don't -EAGAIN IOCB_NOWAIT dio reads just because we have page cache entries for the given range. This causes unnecessary work from the callers side, when the IO could have been issued totally fine without blocking on writeback when there is none. This patch (of 3): For O_DIRECT reads/writes, we check if we need to issue a call to filemap_write_and_wait_range() to issue and/or wait for writeback for any page in the given range. The existing mechanism just checks for a page in the range, which is suboptimal for IOCB_NOWAIT as we'll fallback to the slow path (and needing retry) if there's just a clean page cache page in the range. Provide filemap_range_needs_writeback() which tries a little harder to check if we actually need to issue and/or wait for writeback in the range. Link: https://lkml.kernel.org/r/20210224164455.1096727-1-axboe@kernel.dk Link: https://lkml.kernel.org/r/20210224164455.1096727-2-axboe@kernel.dk Signed-off-by: Jens Axboe <axboe@kernel.dk> Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org> Reviewed-by: Jan Kara <jack@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-04-30 05:55:18 +00:00
}
EXPORT_SYMBOL_GPL(filemap_range_has_writeback);
mm: provide filemap_range_needs_writeback() helper Patch series "Improve IOCB_NOWAIT O_DIRECT reads", v3. An internal workload complained because it was using too much CPU, and when I took a look, we had a lot of io_uring workers going to town. For an async buffered read like workload, I am normally expecting _zero_ offloads to a worker thread, but this one had tons of them. I'd drop caches and things would look good again, but then a minute later we'd regress back to using workers. Turns out that every minute something was reading parts of the device, which would add page cache for that inode. I put patches like these in for our kernel, and the problem was solved. Don't -EAGAIN IOCB_NOWAIT dio reads just because we have page cache entries for the given range. This causes unnecessary work from the callers side, when the IO could have been issued totally fine without blocking on writeback when there is none. This patch (of 3): For O_DIRECT reads/writes, we check if we need to issue a call to filemap_write_and_wait_range() to issue and/or wait for writeback for any page in the given range. The existing mechanism just checks for a page in the range, which is suboptimal for IOCB_NOWAIT as we'll fallback to the slow path (and needing retry) if there's just a clean page cache page in the range. Provide filemap_range_needs_writeback() which tries a little harder to check if we actually need to issue and/or wait for writeback in the range. Link: https://lkml.kernel.org/r/20210224164455.1096727-1-axboe@kernel.dk Link: https://lkml.kernel.org/r/20210224164455.1096727-2-axboe@kernel.dk Signed-off-by: Jens Axboe <axboe@kernel.dk> Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org> Reviewed-by: Jan Kara <jack@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-04-30 05:55:18 +00:00
/**
* 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).
*
* Return: error status of the address space.
*/
int filemap_write_and_wait_range(struct address_space *mapping,
loff_t lstart, loff_t lend)
{
int err = 0, err2;
filemap: skip write and wait if end offset precedes start Patch series "filemap: skip write and wait if end offset precedes start", v2. A fix for the odd write and wait behavior described in the patch 1 commit log. Technically patch 1 could simply remove the check rather than lift it into the callers, but this seemed a bit more user friendly to me. Patch 2 is appended after observation that fadvise() interacted poorly with the v1 patch. This is no longer a problem with v2, making patch 2 purely a cleanup. This series survived both fstests and ltp regression runs without observable problems. I had (end < start) warning checks in each relevant function, with fadvise() being the only caller that triggered them. That said, I dropped the warnings after testing because there seemed to much potential for noise from the various other callers. This patch (of 2): A call to file[map]_write_and_wait_range() with an end offset that precedes the start offset but happens to land in the same page can trigger writeback submission but fails to wait on the submitted page. Writeback submission occurs because __filemap_fdatawrite_range() passes both offsets down into write_cache_pages(), which rounds down to page indexes before it starts processing writeback. However, __filemap_fdatawait_range() immediately returns if the byte-granular end offset precedes the start offset. This behavior was observed in the form of unpredictable latency from a frequent write and wait call with incorrect parameters. The behavior gave the impression that the fdatawait path might occasionally fail to wait on writeback, but further investigation showed the latency was from write_cache_pages() waiting on writeback state to clear for a page already under writeback. Therefore, this indicated that fdatawait actually never waits on writeback in this particular situation. The byte granular check in __filemap_fdatawait_range() goes all the way back to the old wait_on_page_writeback() helper. It originally used page offsets and so would have waited in this problematic case. That changed to byte granularity file offsets in commit 94004ed726f3 ("kill wait_on_page_writeback_range"), which subtly changed this behavior. The check itself has become somewhat redundant since the error checking code that used to follow the wait loop (at the time of the aforementioned commit) has now been removed and lifted into the higher level callers. Therefore, we can restore historical fdatawait behavior by simply removing the check. Since the current fdatawait behavior has been in place for quite some time and is consistent with other interfaces that use file offsets, instead lift the check into the file[map]_write_and_wait_range() helpers to provide consistent behavior between the write and wait. Link: https://lkml.kernel.org/r/20221128155632.3950447-1-bfoster@redhat.com Link: https://lkml.kernel.org/r/20221128155632.3950447-2-bfoster@redhat.com Signed-off-by: Brian Foster <bfoster@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-11-28 15:56:31 +00:00
if (lend < lstart)
return 0;
if (mapping_needs_writeback(mapping)) {
err = __filemap_fdatawrite_range(mapping, lstart, lend,
WB_SYNC_ALL);
/*
* 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)
__filemap_fdatawait_range(mapping, lstart, lend);
}
err2 = filemap_check_errors(mapping);
if (!err)
err = err2;
return err;
}
EXPORT_SYMBOL(filemap_write_and_wait_range);
fs: new infrastructure for writeback error handling and reporting Most filesystems currently use mapping_set_error and filemap_check_errors for setting and reporting/clearing writeback errors at the mapping level. filemap_check_errors is indirectly called from most of the filemap_fdatawait_* functions and from filemap_write_and_wait*. These functions are called from all sorts of contexts to wait on writeback to finish -- e.g. mostly in fsync, but also in truncate calls, getattr, etc. The non-fsync callers are problematic. We should be reporting writeback errors during fsync, but many places spread over the tree clear out errors before they can be properly reported, or report errors at nonsensical times. If I get -EIO on a stat() call, there is no reason for me to assume that it is because some previous writeback failed. The fact that it also clears out the error such that a subsequent fsync returns 0 is a bug, and a nasty one since that's potentially silent data corruption. This patch adds a small bit of new infrastructure for setting and reporting errors during address_space writeback. While the above was my original impetus for adding this, I think it's also the case that current fsync semantics are just problematic for userland. Most applications that call fsync do so to ensure that the data they wrote has hit the backing store. In the case where there are multiple writers to the file at the same time, this is really hard to determine. The first one to call fsync will see any stored error, and the rest get back 0. The processes with open fds may not be associated with one another in any way. They could even be in different containers, so ensuring coordination between all fsync callers is not really an option. One way to remedy this would be to track what file descriptor was used to dirty the file, but that's rather cumbersome and would likely be slow. However, there is a simpler way to improve the semantics here without incurring too much overhead. This set adds an errseq_t to struct address_space, and a corresponding one is added to struct file. Writeback errors are recorded in the mapping's errseq_t, and the one in struct file is used as the "since" value. This changes the semantics of the Linux fsync implementation such that applications can now use it to determine whether there were any writeback errors since fsync(fd) was last called (or since the file was opened in the case of fsync having never been called). Note that those writeback errors may have occurred when writing data that was dirtied via an entirely different fd, but that's the case now with the current mapping_set_error/filemap_check_error infrastructure. This will at least prevent you from getting a false report of success. The new behavior is still consistent with the POSIX spec, and is more reliable for application developers. This patch just adds some basic infrastructure for doing this, and ensures that the f_wb_err "cursor" is properly set when a file is opened. Later patches will change the existing code to use this new infrastructure for reporting errors at fsync time. Signed-off-by: Jeff Layton <jlayton@redhat.com> Reviewed-by: Jan Kara <jack@suse.cz>
2017-07-06 11:02:25 +00:00
void __filemap_set_wb_err(struct address_space *mapping, int err)
{
errseq_t eseq = errseq_set(&mapping->wb_err, err);
fs: new infrastructure for writeback error handling and reporting Most filesystems currently use mapping_set_error and filemap_check_errors for setting and reporting/clearing writeback errors at the mapping level. filemap_check_errors is indirectly called from most of the filemap_fdatawait_* functions and from filemap_write_and_wait*. These functions are called from all sorts of contexts to wait on writeback to finish -- e.g. mostly in fsync, but also in truncate calls, getattr, etc. The non-fsync callers are problematic. We should be reporting writeback errors during fsync, but many places spread over the tree clear out errors before they can be properly reported, or report errors at nonsensical times. If I get -EIO on a stat() call, there is no reason for me to assume that it is because some previous writeback failed. The fact that it also clears out the error such that a subsequent fsync returns 0 is a bug, and a nasty one since that's potentially silent data corruption. This patch adds a small bit of new infrastructure for setting and reporting errors during address_space writeback. While the above was my original impetus for adding this, I think it's also the case that current fsync semantics are just problematic for userland. Most applications that call fsync do so to ensure that the data they wrote has hit the backing store. In the case where there are multiple writers to the file at the same time, this is really hard to determine. The first one to call fsync will see any stored error, and the rest get back 0. The processes with open fds may not be associated with one another in any way. They could even be in different containers, so ensuring coordination between all fsync callers is not really an option. One way to remedy this would be to track what file descriptor was used to dirty the file, but that's rather cumbersome and would likely be slow. However, there is a simpler way to improve the semantics here without incurring too much overhead. This set adds an errseq_t to struct address_space, and a corresponding one is added to struct file. Writeback errors are recorded in the mapping's errseq_t, and the one in struct file is used as the "since" value. This changes the semantics of the Linux fsync implementation such that applications can now use it to determine whether there were any writeback errors since fsync(fd) was last called (or since the file was opened in the case of fsync having never been called). Note that those writeback errors may have occurred when writing data that was dirtied via an entirely different fd, but that's the case now with the current mapping_set_error/filemap_check_error infrastructure. This will at least prevent you from getting a false report of success. The new behavior is still consistent with the POSIX spec, and is more reliable for application developers. This patch just adds some basic infrastructure for doing this, and ensures that the f_wb_err "cursor" is properly set when a file is opened. Later patches will change the existing code to use this new infrastructure for reporting errors at fsync time. Signed-off-by: Jeff Layton <jlayton@redhat.com> Reviewed-by: Jan Kara <jack@suse.cz>
2017-07-06 11:02:25 +00:00
trace_filemap_set_wb_err(mapping, eseq);
}
EXPORT_SYMBOL(__filemap_set_wb_err);
/**
* file_check_and_advance_wb_err - report wb error (if any) that was previously
* and advance wb_err to current one
* @file: struct file on which the error is being reported
*
* When userland calls fsync (or something like nfsd does the equivalent), we
* want to report any writeback errors that occurred since the last fsync (or
* since the file was opened if there haven't been any).
*
* Grab the wb_err from the mapping. If it matches what we have in the file,
* then just quickly return 0. The file is all caught up.
*
* If it doesn't match, then take the mapping value, set the "seen" flag in
* it and try to swap it into place. If it works, or another task beat us
* to it with the new value, then update the f_wb_err and return the error
* portion. The error at this point must be reported via proper channels
* (a'la fsync, or NFS COMMIT operation, etc.).
*
* While we handle mapping->wb_err with atomic operations, the f_wb_err
* value is protected by the f_lock since we must ensure that it reflects
* the latest value swapped in for this file descriptor.
*
* Return: %0 on success, negative error code otherwise.
fs: new infrastructure for writeback error handling and reporting Most filesystems currently use mapping_set_error and filemap_check_errors for setting and reporting/clearing writeback errors at the mapping level. filemap_check_errors is indirectly called from most of the filemap_fdatawait_* functions and from filemap_write_and_wait*. These functions are called from all sorts of contexts to wait on writeback to finish -- e.g. mostly in fsync, but also in truncate calls, getattr, etc. The non-fsync callers are problematic. We should be reporting writeback errors during fsync, but many places spread over the tree clear out errors before they can be properly reported, or report errors at nonsensical times. If I get -EIO on a stat() call, there is no reason for me to assume that it is because some previous writeback failed. The fact that it also clears out the error such that a subsequent fsync returns 0 is a bug, and a nasty one since that's potentially silent data corruption. This patch adds a small bit of new infrastructure for setting and reporting errors during address_space writeback. While the above was my original impetus for adding this, I think it's also the case that current fsync semantics are just problematic for userland. Most applications that call fsync do so to ensure that the data they wrote has hit the backing store. In the case where there are multiple writers to the file at the same time, this is really hard to determine. The first one to call fsync will see any stored error, and the rest get back 0. The processes with open fds may not be associated with one another in any way. They could even be in different containers, so ensuring coordination between all fsync callers is not really an option. One way to remedy this would be to track what file descriptor was used to dirty the file, but that's rather cumbersome and would likely be slow. However, there is a simpler way to improve the semantics here without incurring too much overhead. This set adds an errseq_t to struct address_space, and a corresponding one is added to struct file. Writeback errors are recorded in the mapping's errseq_t, and the one in struct file is used as the "since" value. This changes the semantics of the Linux fsync implementation such that applications can now use it to determine whether there were any writeback errors since fsync(fd) was last called (or since the file was opened in the case of fsync having never been called). Note that those writeback errors may have occurred when writing data that was dirtied via an entirely different fd, but that's the case now with the current mapping_set_error/filemap_check_error infrastructure. This will at least prevent you from getting a false report of success. The new behavior is still consistent with the POSIX spec, and is more reliable for application developers. This patch just adds some basic infrastructure for doing this, and ensures that the f_wb_err "cursor" is properly set when a file is opened. Later patches will change the existing code to use this new infrastructure for reporting errors at fsync time. Signed-off-by: Jeff Layton <jlayton@redhat.com> Reviewed-by: Jan Kara <jack@suse.cz>
2017-07-06 11:02:25 +00:00
*/
int file_check_and_advance_wb_err(struct file *file)
{
int err = 0;
errseq_t old = READ_ONCE(file->f_wb_err);
struct address_space *mapping = file->f_mapping;
/* Locklessly handle the common case where nothing has changed */
if (errseq_check(&mapping->wb_err, old)) {
/* Something changed, must use slow path */
spin_lock(&file->f_lock);
old = file->f_wb_err;
err = errseq_check_and_advance(&mapping->wb_err,
&file->f_wb_err);
trace_file_check_and_advance_wb_err(file, old);
spin_unlock(&file->f_lock);
}
/*
* We're mostly using this function as a drop in replacement for
* filemap_check_errors. Clear AS_EIO/AS_ENOSPC to emulate the effect
* that the legacy code would have had on these flags.
*/
clear_bit(AS_EIO, &mapping->flags);
clear_bit(AS_ENOSPC, &mapping->flags);
fs: new infrastructure for writeback error handling and reporting Most filesystems currently use mapping_set_error and filemap_check_errors for setting and reporting/clearing writeback errors at the mapping level. filemap_check_errors is indirectly called from most of the filemap_fdatawait_* functions and from filemap_write_and_wait*. These functions are called from all sorts of contexts to wait on writeback to finish -- e.g. mostly in fsync, but also in truncate calls, getattr, etc. The non-fsync callers are problematic. We should be reporting writeback errors during fsync, but many places spread over the tree clear out errors before they can be properly reported, or report errors at nonsensical times. If I get -EIO on a stat() call, there is no reason for me to assume that it is because some previous writeback failed. The fact that it also clears out the error such that a subsequent fsync returns 0 is a bug, and a nasty one since that's potentially silent data corruption. This patch adds a small bit of new infrastructure for setting and reporting errors during address_space writeback. While the above was my original impetus for adding this, I think it's also the case that current fsync semantics are just problematic for userland. Most applications that call fsync do so to ensure that the data they wrote has hit the backing store. In the case where there are multiple writers to the file at the same time, this is really hard to determine. The first one to call fsync will see any stored error, and the rest get back 0. The processes with open fds may not be associated with one another in any way. They could even be in different containers, so ensuring coordination between all fsync callers is not really an option. One way to remedy this would be to track what file descriptor was used to dirty the file, but that's rather cumbersome and would likely be slow. However, there is a simpler way to improve the semantics here without incurring too much overhead. This set adds an errseq_t to struct address_space, and a corresponding one is added to struct file. Writeback errors are recorded in the mapping's errseq_t, and the one in struct file is used as the "since" value. This changes the semantics of the Linux fsync implementation such that applications can now use it to determine whether there were any writeback errors since fsync(fd) was last called (or since the file was opened in the case of fsync having never been called). Note that those writeback errors may have occurred when writing data that was dirtied via an entirely different fd, but that's the case now with the current mapping_set_error/filemap_check_error infrastructure. This will at least prevent you from getting a false report of success. The new behavior is still consistent with the POSIX spec, and is more reliable for application developers. This patch just adds some basic infrastructure for doing this, and ensures that the f_wb_err "cursor" is properly set when a file is opened. Later patches will change the existing code to use this new infrastructure for reporting errors at fsync time. Signed-off-by: Jeff Layton <jlayton@redhat.com> Reviewed-by: Jan Kara <jack@suse.cz>
2017-07-06 11:02:25 +00:00
return err;
}
EXPORT_SYMBOL(file_check_and_advance_wb_err);
/**
* file_write_and_wait_range - write out & wait on a file range
* @file: file pointing to address_space with 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).
*
* After writing out and waiting on the data, we check and advance the
* f_wb_err cursor to the latest value, and return any errors detected there.
*
* Return: %0 on success, negative error code otherwise.
fs: new infrastructure for writeback error handling and reporting Most filesystems currently use mapping_set_error and filemap_check_errors for setting and reporting/clearing writeback errors at the mapping level. filemap_check_errors is indirectly called from most of the filemap_fdatawait_* functions and from filemap_write_and_wait*. These functions are called from all sorts of contexts to wait on writeback to finish -- e.g. mostly in fsync, but also in truncate calls, getattr, etc. The non-fsync callers are problematic. We should be reporting writeback errors during fsync, but many places spread over the tree clear out errors before they can be properly reported, or report errors at nonsensical times. If I get -EIO on a stat() call, there is no reason for me to assume that it is because some previous writeback failed. The fact that it also clears out the error such that a subsequent fsync returns 0 is a bug, and a nasty one since that's potentially silent data corruption. This patch adds a small bit of new infrastructure for setting and reporting errors during address_space writeback. While the above was my original impetus for adding this, I think it's also the case that current fsync semantics are just problematic for userland. Most applications that call fsync do so to ensure that the data they wrote has hit the backing store. In the case where there are multiple writers to the file at the same time, this is really hard to determine. The first one to call fsync will see any stored error, and the rest get back 0. The processes with open fds may not be associated with one another in any way. They could even be in different containers, so ensuring coordination between all fsync callers is not really an option. One way to remedy this would be to track what file descriptor was used to dirty the file, but that's rather cumbersome and would likely be slow. However, there is a simpler way to improve the semantics here without incurring too much overhead. This set adds an errseq_t to struct address_space, and a corresponding one is added to struct file. Writeback errors are recorded in the mapping's errseq_t, and the one in struct file is used as the "since" value. This changes the semantics of the Linux fsync implementation such that applications can now use it to determine whether there were any writeback errors since fsync(fd) was last called (or since the file was opened in the case of fsync having never been called). Note that those writeback errors may have occurred when writing data that was dirtied via an entirely different fd, but that's the case now with the current mapping_set_error/filemap_check_error infrastructure. This will at least prevent you from getting a false report of success. The new behavior is still consistent with the POSIX spec, and is more reliable for application developers. This patch just adds some basic infrastructure for doing this, and ensures that the f_wb_err "cursor" is properly set when a file is opened. Later patches will change the existing code to use this new infrastructure for reporting errors at fsync time. Signed-off-by: Jeff Layton <jlayton@redhat.com> Reviewed-by: Jan Kara <jack@suse.cz>
2017-07-06 11:02:25 +00:00
*/
int file_write_and_wait_range(struct file *file, loff_t lstart, loff_t lend)
{
int err = 0, err2;
struct address_space *mapping = file->f_mapping;
filemap: skip write and wait if end offset precedes start Patch series "filemap: skip write and wait if end offset precedes start", v2. A fix for the odd write and wait behavior described in the patch 1 commit log. Technically patch 1 could simply remove the check rather than lift it into the callers, but this seemed a bit more user friendly to me. Patch 2 is appended after observation that fadvise() interacted poorly with the v1 patch. This is no longer a problem with v2, making patch 2 purely a cleanup. This series survived both fstests and ltp regression runs without observable problems. I had (end < start) warning checks in each relevant function, with fadvise() being the only caller that triggered them. That said, I dropped the warnings after testing because there seemed to much potential for noise from the various other callers. This patch (of 2): A call to file[map]_write_and_wait_range() with an end offset that precedes the start offset but happens to land in the same page can trigger writeback submission but fails to wait on the submitted page. Writeback submission occurs because __filemap_fdatawrite_range() passes both offsets down into write_cache_pages(), which rounds down to page indexes before it starts processing writeback. However, __filemap_fdatawait_range() immediately returns if the byte-granular end offset precedes the start offset. This behavior was observed in the form of unpredictable latency from a frequent write and wait call with incorrect parameters. The behavior gave the impression that the fdatawait path might occasionally fail to wait on writeback, but further investigation showed the latency was from write_cache_pages() waiting on writeback state to clear for a page already under writeback. Therefore, this indicated that fdatawait actually never waits on writeback in this particular situation. The byte granular check in __filemap_fdatawait_range() goes all the way back to the old wait_on_page_writeback() helper. It originally used page offsets and so would have waited in this problematic case. That changed to byte granularity file offsets in commit 94004ed726f3 ("kill wait_on_page_writeback_range"), which subtly changed this behavior. The check itself has become somewhat redundant since the error checking code that used to follow the wait loop (at the time of the aforementioned commit) has now been removed and lifted into the higher level callers. Therefore, we can restore historical fdatawait behavior by simply removing the check. Since the current fdatawait behavior has been in place for quite some time and is consistent with other interfaces that use file offsets, instead lift the check into the file[map]_write_and_wait_range() helpers to provide consistent behavior between the write and wait. Link: https://lkml.kernel.org/r/20221128155632.3950447-1-bfoster@redhat.com Link: https://lkml.kernel.org/r/20221128155632.3950447-2-bfoster@redhat.com Signed-off-by: Brian Foster <bfoster@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-11-28 15:56:31 +00:00
if (lend < lstart)
return 0;
if (mapping_needs_writeback(mapping)) {
fs: new infrastructure for writeback error handling and reporting Most filesystems currently use mapping_set_error and filemap_check_errors for setting and reporting/clearing writeback errors at the mapping level. filemap_check_errors is indirectly called from most of the filemap_fdatawait_* functions and from filemap_write_and_wait*. These functions are called from all sorts of contexts to wait on writeback to finish -- e.g. mostly in fsync, but also in truncate calls, getattr, etc. The non-fsync callers are problematic. We should be reporting writeback errors during fsync, but many places spread over the tree clear out errors before they can be properly reported, or report errors at nonsensical times. If I get -EIO on a stat() call, there is no reason for me to assume that it is because some previous writeback failed. The fact that it also clears out the error such that a subsequent fsync returns 0 is a bug, and a nasty one since that's potentially silent data corruption. This patch adds a small bit of new infrastructure for setting and reporting errors during address_space writeback. While the above was my original impetus for adding this, I think it's also the case that current fsync semantics are just problematic for userland. Most applications that call fsync do so to ensure that the data they wrote has hit the backing store. In the case where there are multiple writers to the file at the same time, this is really hard to determine. The first one to call fsync will see any stored error, and the rest get back 0. The processes with open fds may not be associated with one another in any way. They could even be in different containers, so ensuring coordination between all fsync callers is not really an option. One way to remedy this would be to track what file descriptor was used to dirty the file, but that's rather cumbersome and would likely be slow. However, there is a simpler way to improve the semantics here without incurring too much overhead. This set adds an errseq_t to struct address_space, and a corresponding one is added to struct file. Writeback errors are recorded in the mapping's errseq_t, and the one in struct file is used as the "since" value. This changes the semantics of the Linux fsync implementation such that applications can now use it to determine whether there were any writeback errors since fsync(fd) was last called (or since the file was opened in the case of fsync having never been called). Note that those writeback errors may have occurred when writing data that was dirtied via an entirely different fd, but that's the case now with the current mapping_set_error/filemap_check_error infrastructure. This will at least prevent you from getting a false report of success. The new behavior is still consistent with the POSIX spec, and is more reliable for application developers. This patch just adds some basic infrastructure for doing this, and ensures that the f_wb_err "cursor" is properly set when a file is opened. Later patches will change the existing code to use this new infrastructure for reporting errors at fsync time. Signed-off-by: Jeff Layton <jlayton@redhat.com> Reviewed-by: Jan Kara <jack@suse.cz>
2017-07-06 11:02:25 +00:00
err = __filemap_fdatawrite_range(mapping, lstart, lend,
WB_SYNC_ALL);
/* See comment of filemap_write_and_wait() */
if (err != -EIO)
__filemap_fdatawait_range(mapping, lstart, lend);
}
err2 = file_check_and_advance_wb_err(file);
if (!err)
err = err2;
return err;
}
EXPORT_SYMBOL(file_write_and_wait_range);
/**
* replace_page_cache_folio - replace a pagecache folio with a new one
* @old: folio to be replaced
* @new: folio to replace with
*
* This function replaces a folio in the pagecache with a new one. On
* success it acquires the pagecache reference for the new folio and
* drops it for the old folio. Both the old and new folios must be
* locked. This function does not add the new folio to the LRU, the
* caller must do that.
*
* The remove + add is atomic. This function cannot fail.
*/
void replace_page_cache_folio(struct folio *old, struct folio *new)
{
struct address_space *mapping = old->mapping;
void (*free_folio)(struct folio *) = mapping->a_ops->free_folio;
pgoff_t offset = old->index;
XA_STATE(xas, &mapping->i_pages, offset);
VM_BUG_ON_FOLIO(!folio_test_locked(old), old);
VM_BUG_ON_FOLIO(!folio_test_locked(new), new);
VM_BUG_ON_FOLIO(new->mapping, new);
folio_get(new);
new->mapping = mapping;
new->index = offset;
2023-10-06 18:46:27 +00:00
mem_cgroup_replace_folio(old, new);
xas_lock_irq(&xas);
xas_store(&xas, new);
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
old->mapping = NULL;
/* hugetlb pages do not participate in page cache accounting. */
if (!folio_test_hugetlb(old))
__lruvec_stat_sub_folio(old, NR_FILE_PAGES);
if (!folio_test_hugetlb(new))
__lruvec_stat_add_folio(new, NR_FILE_PAGES);
if (folio_test_swapbacked(old))
__lruvec_stat_sub_folio(old, NR_SHMEM);
if (folio_test_swapbacked(new))
__lruvec_stat_add_folio(new, NR_SHMEM);
xas_unlock_irq(&xas);
if (free_folio)
free_folio(old);
folio_put(old);
}
EXPORT_SYMBOL_GPL(replace_page_cache_folio);
noinline int __filemap_add_folio(struct address_space *mapping,
struct folio *folio, pgoff_t index, gfp_t gfp, void **shadowp)
{
XA_STATE(xas, &mapping->i_pages, index);
mm/filemap: optimize filemap folio adding Instead of doing multiple tree walks, do one optimism range check with lock hold, and exit if raced with another insertion. If a shadow exists, check it with a new xas_get_order helper before releasing the lock to avoid redundant tree walks for getting its order. Drop the lock and do the allocation only if a split is needed. In the best case, it only need to walk the tree once. If it needs to alloc and split, 3 walks are issued (One for first ranged conflict check and order retrieving, one for the second check after allocation, one for the insert after split). Testing with 4K pages, in an 8G cgroup, with 16G brd as block device: echo 3 > /proc/sys/vm/drop_caches fio -name=cached --numjobs=16 --filename=/mnt/test.img \ --buffered=1 --ioengine=mmap --rw=randread --time_based \ --ramp_time=30s --runtime=5m --group_reporting Before: bw ( MiB/s): min= 1027, max= 3520, per=100.00%, avg=2445.02, stdev=18.90, samples=8691 iops : min=263001, max=901288, avg=625924.36, stdev=4837.28, samples=8691 After (+7.3%): bw ( MiB/s): min= 493, max= 3947, per=100.00%, avg=2625.56, stdev=25.74, samples=8651 iops : min=126454, max=1010681, avg=672142.61, stdev=6590.48, samples=8651 Test result with THP (do a THP randread then switch to 4K page in hope it issues a lot of splitting): echo 3 > /proc/sys/vm/drop_caches fio -name=cached --numjobs=16 --filename=/mnt/test.img \ --buffered=1 --ioengine=mmap -thp=1 --readonly \ --rw=randread --time_based --ramp_time=30s --runtime=10m \ --group_reporting fio -name=cached --numjobs=16 --filename=/mnt/test.img \ --buffered=1 --ioengine=mmap \ --rw=randread --time_based --runtime=5s --group_reporting Before: bw ( KiB/s): min= 4141, max=14202, per=100.00%, avg=7935.51, stdev=96.85, samples=18976 iops : min= 1029, max= 3548, avg=1979.52, stdev=24.23, samples=18976· READ: bw=4545B/s (4545B/s), 4545B/s-4545B/s (4545B/s-4545B/s), io=64.0KiB (65.5kB), run=14419-14419msec After (+12.5%): bw ( KiB/s): min= 4611, max=15370, per=100.00%, avg=8928.74, stdev=105.17, samples=19146 iops : min= 1151, max= 3842, avg=2231.27, stdev=26.29, samples=19146 READ: bw=4635B/s (4635B/s), 4635B/s-4635B/s (4635B/s-4635B/s), io=64.0KiB (65.5kB), run=14137-14137msec The performance is better for both 4K (+7.5%) and THP (+12.5%) cached read. Link: https://lkml.kernel.org/r/20240415171857.19244-5-ryncsn@gmail.com Signed-off-by: Kairui Song <kasong@tencent.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-04-15 17:18:56 +00:00
void *alloced_shadow = NULL;
int alloced_order = 0;
bool huge;
long nr;
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
VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
VM_BUG_ON_FOLIO(folio_test_swapbacked(folio), folio);
mapping_set_update(&xas, mapping);
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/filemap: remove hugetlb special casing in filemap.c Remove special cased hugetlb handling code within the page cache by changing the granularity of ->index to the base page size rather than the huge page size. The motivation of this patch is to reduce complexity within the filemap code while also increasing performance by removing branches that are evaluated on every page cache lookup. To support the change in index, new wrappers for hugetlb page cache interactions are added. These wrappers perform the conversion to a linear index which is now expected by the page cache for huge pages. ========================= PERFORMANCE ====================================== Perf was used to check the performance differences after the patch. Overall the performance is similar to mainline with a very small larger overhead that occurs in __filemap_add_folio() and hugetlb_add_to_page_cache(). This is because of the larger overhead that occurs in xa_load() and xa_store() as the xarray is now using more entries to store hugetlb folios in the page cache. Timing aarch64 2MB Page Size 6.5-rc3 + this patch: [root@sidhakum-ol9-1 hugepages]# time fallocate -l 700GB test.txt real 1m49.568s user 0m0.000s sys 1m49.461s 6.5-rc3: [root]# time fallocate -l 700GB test.txt real 1m47.495s user 0m0.000s sys 1m47.370s 1GB Page Size 6.5-rc3 + this patch: [root@sidhakum-ol9-1 hugepages1G]# time fallocate -l 700GB test.txt real 1m47.024s user 0m0.000s sys 1m46.921s 6.5-rc3: [root@sidhakum-ol9-1 hugepages1G]# time fallocate -l 700GB test.txt real 1m44.551s user 0m0.000s sys 1m44.438s x86 2MB Page Size 6.5-rc3 + this patch: [root@sidhakum-ol9-2 hugepages]# time fallocate -l 100GB test.txt real 0m22.383s user 0m0.000s sys 0m22.255s 6.5-rc3: [opc@sidhakum-ol9-2 hugepages]$ time sudo fallocate -l 100GB /dev/hugepages/test.txt real 0m22.735s user 0m0.038s sys 0m22.567s 1GB Page Size 6.5-rc3 + this patch: [root@sidhakum-ol9-2 hugepages1GB]# time fallocate -l 100GB test.txt real 0m25.786s user 0m0.001s sys 0m25.589s 6.5-rc3: [root@sidhakum-ol9-2 hugepages1G]# time fallocate -l 100GB test.txt real 0m33.454s user 0m0.001s sys 0m33.193s aarch64: workload - fallocate a 700GB file backed by huge pages 6.5-rc3 + this patch: 2MB Page Size: --100.00%--__arm64_sys_fallocate ksys_fallocate vfs_fallocate hugetlbfs_fallocate | |--95.04%--__pi_clear_page | |--3.57%--clear_huge_page | | | |--2.63%--rcu_all_qs | | | --0.91%--__cond_resched | --0.67%--__cond_resched 0.17% 0.00% 0 fallocate [kernel.vmlinux] [k] hugetlb_add_to_page_cache 0.14% 0.10% 11 fallocate [kernel.vmlinux] [k] __filemap_add_folio 6.5-rc3 2MB Page Size: --100.00%--__arm64_sys_fallocate ksys_fallocate vfs_fallocate hugetlbfs_fallocate | |--94.91%--__pi_clear_page | |--4.11%--clear_huge_page | | | |--3.00%--rcu_all_qs | | | --1.10%--__cond_resched | --0.59%--__cond_resched 0.08% 0.01% 1 fallocate [kernel.kallsyms] [k] hugetlb_add_to_page_cache 0.05% 0.03% 3 fallocate [kernel.kallsyms] [k] __filemap_add_folio x86 workload - fallocate a 100GB file backed by huge pages 6.5-rc3 + this patch: 2MB Page Size: hugetlbfs_fallocate | --99.57%--clear_huge_page | --98.47%--clear_page_erms | --0.53%--asm_sysvec_apic_timer_interrupt 0.04% 0.04% 1 fallocate [kernel.kallsyms] [k] xa_load 0.04% 0.00% 0 fallocate [kernel.kallsyms] [k] hugetlb_add_to_page_cache 0.04% 0.00% 0 fallocate [kernel.kallsyms] [k] __filemap_add_folio 0.04% 0.00% 0 fallocate [kernel.kallsyms] [k] xas_store 6.5-rc3 2MB Page Size: --99.93%--__x64_sys_fallocate vfs_fallocate hugetlbfs_fallocate | --99.38%--clear_huge_page | |--98.40%--clear_page_erms | --0.59%--__cond_resched 0.03% 0.03% 1 fallocate [kernel.kallsyms] [k] __filemap_add_folio ========================= TESTING ====================================== This patch passes libhugetlbfs tests and LTP hugetlb tests ********** TEST SUMMARY * 2M * 32-bit 64-bit * Total testcases: 110 113 * Skipped: 0 0 * PASS: 107 113 * FAIL: 0 0 * Killed by signal: 3 0 * Bad configuration: 0 0 * Expected FAIL: 0 0 * Unexpected PASS: 0 0 * Test not present: 0 0 * Strange test result: 0 0 ********** Done executing testcases. LTP Version: 20220527-178-g2761a81c4 page migration was also tested using Mike Kravetz's test program.[8] [dan.carpenter@linaro.org: fix an NULL vs IS_ERR() bug] Link: https://lkml.kernel.org/r/1772c296-1417-486f-8eef-171af2192681@moroto.mountain Link: https://lkml.kernel.org/r/20230926192017.98183-1-sidhartha.kumar@oracle.com Signed-off-by: Sidhartha Kumar <sidhartha.kumar@oracle.com> Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org> Reported-and-tested-by: syzbot+c225dea486da4d5592bd@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=c225dea486da4d5592bd Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Muchun Song <songmuchun@bytedance.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-09-26 19:20:17 +00:00
VM_BUG_ON_FOLIO(index & (folio_nr_pages(folio) - 1), folio);
xas_set_order(&xas, index, folio_order(folio));
mm/filemap: optimize filemap folio adding Instead of doing multiple tree walks, do one optimism range check with lock hold, and exit if raced with another insertion. If a shadow exists, check it with a new xas_get_order helper before releasing the lock to avoid redundant tree walks for getting its order. Drop the lock and do the allocation only if a split is needed. In the best case, it only need to walk the tree once. If it needs to alloc and split, 3 walks are issued (One for first ranged conflict check and order retrieving, one for the second check after allocation, one for the insert after split). Testing with 4K pages, in an 8G cgroup, with 16G brd as block device: echo 3 > /proc/sys/vm/drop_caches fio -name=cached --numjobs=16 --filename=/mnt/test.img \ --buffered=1 --ioengine=mmap --rw=randread --time_based \ --ramp_time=30s --runtime=5m --group_reporting Before: bw ( MiB/s): min= 1027, max= 3520, per=100.00%, avg=2445.02, stdev=18.90, samples=8691 iops : min=263001, max=901288, avg=625924.36, stdev=4837.28, samples=8691 After (+7.3%): bw ( MiB/s): min= 493, max= 3947, per=100.00%, avg=2625.56, stdev=25.74, samples=8651 iops : min=126454, max=1010681, avg=672142.61, stdev=6590.48, samples=8651 Test result with THP (do a THP randread then switch to 4K page in hope it issues a lot of splitting): echo 3 > /proc/sys/vm/drop_caches fio -name=cached --numjobs=16 --filename=/mnt/test.img \ --buffered=1 --ioengine=mmap -thp=1 --readonly \ --rw=randread --time_based --ramp_time=30s --runtime=10m \ --group_reporting fio -name=cached --numjobs=16 --filename=/mnt/test.img \ --buffered=1 --ioengine=mmap \ --rw=randread --time_based --runtime=5s --group_reporting Before: bw ( KiB/s): min= 4141, max=14202, per=100.00%, avg=7935.51, stdev=96.85, samples=18976 iops : min= 1029, max= 3548, avg=1979.52, stdev=24.23, samples=18976· READ: bw=4545B/s (4545B/s), 4545B/s-4545B/s (4545B/s-4545B/s), io=64.0KiB (65.5kB), run=14419-14419msec After (+12.5%): bw ( KiB/s): min= 4611, max=15370, per=100.00%, avg=8928.74, stdev=105.17, samples=19146 iops : min= 1151, max= 3842, avg=2231.27, stdev=26.29, samples=19146 READ: bw=4635B/s (4635B/s), 4635B/s-4635B/s (4635B/s-4635B/s), io=64.0KiB (65.5kB), run=14137-14137msec The performance is better for both 4K (+7.5%) and THP (+12.5%) cached read. Link: https://lkml.kernel.org/r/20240415171857.19244-5-ryncsn@gmail.com Signed-off-by: Kairui Song <kasong@tencent.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-04-15 17:18:56 +00:00
huge = folio_test_hugetlb(folio);
mm/filemap: remove hugetlb special casing in filemap.c Remove special cased hugetlb handling code within the page cache by changing the granularity of ->index to the base page size rather than the huge page size. The motivation of this patch is to reduce complexity within the filemap code while also increasing performance by removing branches that are evaluated on every page cache lookup. To support the change in index, new wrappers for hugetlb page cache interactions are added. These wrappers perform the conversion to a linear index which is now expected by the page cache for huge pages. ========================= PERFORMANCE ====================================== Perf was used to check the performance differences after the patch. Overall the performance is similar to mainline with a very small larger overhead that occurs in __filemap_add_folio() and hugetlb_add_to_page_cache(). This is because of the larger overhead that occurs in xa_load() and xa_store() as the xarray is now using more entries to store hugetlb folios in the page cache. Timing aarch64 2MB Page Size 6.5-rc3 + this patch: [root@sidhakum-ol9-1 hugepages]# time fallocate -l 700GB test.txt real 1m49.568s user 0m0.000s sys 1m49.461s 6.5-rc3: [root]# time fallocate -l 700GB test.txt real 1m47.495s user 0m0.000s sys 1m47.370s 1GB Page Size 6.5-rc3 + this patch: [root@sidhakum-ol9-1 hugepages1G]# time fallocate -l 700GB test.txt real 1m47.024s user 0m0.000s sys 1m46.921s 6.5-rc3: [root@sidhakum-ol9-1 hugepages1G]# time fallocate -l 700GB test.txt real 1m44.551s user 0m0.000s sys 1m44.438s x86 2MB Page Size 6.5-rc3 + this patch: [root@sidhakum-ol9-2 hugepages]# time fallocate -l 100GB test.txt real 0m22.383s user 0m0.000s sys 0m22.255s 6.5-rc3: [opc@sidhakum-ol9-2 hugepages]$ time sudo fallocate -l 100GB /dev/hugepages/test.txt real 0m22.735s user 0m0.038s sys 0m22.567s 1GB Page Size 6.5-rc3 + this patch: [root@sidhakum-ol9-2 hugepages1GB]# time fallocate -l 100GB test.txt real 0m25.786s user 0m0.001s sys 0m25.589s 6.5-rc3: [root@sidhakum-ol9-2 hugepages1G]# time fallocate -l 100GB test.txt real 0m33.454s user 0m0.001s sys 0m33.193s aarch64: workload - fallocate a 700GB file backed by huge pages 6.5-rc3 + this patch: 2MB Page Size: --100.00%--__arm64_sys_fallocate ksys_fallocate vfs_fallocate hugetlbfs_fallocate | |--95.04%--__pi_clear_page | |--3.57%--clear_huge_page | | | |--2.63%--rcu_all_qs | | | --0.91%--__cond_resched | --0.67%--__cond_resched 0.17% 0.00% 0 fallocate [kernel.vmlinux] [k] hugetlb_add_to_page_cache 0.14% 0.10% 11 fallocate [kernel.vmlinux] [k] __filemap_add_folio 6.5-rc3 2MB Page Size: --100.00%--__arm64_sys_fallocate ksys_fallocate vfs_fallocate hugetlbfs_fallocate | |--94.91%--__pi_clear_page | |--4.11%--clear_huge_page | | | |--3.00%--rcu_all_qs | | | --1.10%--__cond_resched | --0.59%--__cond_resched 0.08% 0.01% 1 fallocate [kernel.kallsyms] [k] hugetlb_add_to_page_cache 0.05% 0.03% 3 fallocate [kernel.kallsyms] [k] __filemap_add_folio x86 workload - fallocate a 100GB file backed by huge pages 6.5-rc3 + this patch: 2MB Page Size: hugetlbfs_fallocate | --99.57%--clear_huge_page | --98.47%--clear_page_erms | --0.53%--asm_sysvec_apic_timer_interrupt 0.04% 0.04% 1 fallocate [kernel.kallsyms] [k] xa_load 0.04% 0.00% 0 fallocate [kernel.kallsyms] [k] hugetlb_add_to_page_cache 0.04% 0.00% 0 fallocate [kernel.kallsyms] [k] __filemap_add_folio 0.04% 0.00% 0 fallocate [kernel.kallsyms] [k] xas_store 6.5-rc3 2MB Page Size: --99.93%--__x64_sys_fallocate vfs_fallocate hugetlbfs_fallocate | --99.38%--clear_huge_page | |--98.40%--clear_page_erms | --0.59%--__cond_resched 0.03% 0.03% 1 fallocate [kernel.kallsyms] [k] __filemap_add_folio ========================= TESTING ====================================== This patch passes libhugetlbfs tests and LTP hugetlb tests ********** TEST SUMMARY * 2M * 32-bit 64-bit * Total testcases: 110 113 * Skipped: 0 0 * PASS: 107 113 * FAIL: 0 0 * Killed by signal: 3 0 * Bad configuration: 0 0 * Expected FAIL: 0 0 * Unexpected PASS: 0 0 * Test not present: 0 0 * Strange test result: 0 0 ********** Done executing testcases. LTP Version: 20220527-178-g2761a81c4 page migration was also tested using Mike Kravetz's test program.[8] [dan.carpenter@linaro.org: fix an NULL vs IS_ERR() bug] Link: https://lkml.kernel.org/r/1772c296-1417-486f-8eef-171af2192681@moroto.mountain Link: https://lkml.kernel.org/r/20230926192017.98183-1-sidhartha.kumar@oracle.com Signed-off-by: Sidhartha Kumar <sidhartha.kumar@oracle.com> Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org> Reported-and-tested-by: syzbot+c225dea486da4d5592bd@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=c225dea486da4d5592bd Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Muchun Song <songmuchun@bytedance.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-09-26 19:20:17 +00:00
nr = folio_nr_pages(folio);
gfp &= GFP_RECLAIM_MASK;
folio_ref_add(folio, nr);
folio->mapping = mapping;
folio->index = xas.xa_index;
mm/filemap: optimize filemap folio adding Instead of doing multiple tree walks, do one optimism range check with lock hold, and exit if raced with another insertion. If a shadow exists, check it with a new xas_get_order helper before releasing the lock to avoid redundant tree walks for getting its order. Drop the lock and do the allocation only if a split is needed. In the best case, it only need to walk the tree once. If it needs to alloc and split, 3 walks are issued (One for first ranged conflict check and order retrieving, one for the second check after allocation, one for the insert after split). Testing with 4K pages, in an 8G cgroup, with 16G brd as block device: echo 3 > /proc/sys/vm/drop_caches fio -name=cached --numjobs=16 --filename=/mnt/test.img \ --buffered=1 --ioengine=mmap --rw=randread --time_based \ --ramp_time=30s --runtime=5m --group_reporting Before: bw ( MiB/s): min= 1027, max= 3520, per=100.00%, avg=2445.02, stdev=18.90, samples=8691 iops : min=263001, max=901288, avg=625924.36, stdev=4837.28, samples=8691 After (+7.3%): bw ( MiB/s): min= 493, max= 3947, per=100.00%, avg=2625.56, stdev=25.74, samples=8651 iops : min=126454, max=1010681, avg=672142.61, stdev=6590.48, samples=8651 Test result with THP (do a THP randread then switch to 4K page in hope it issues a lot of splitting): echo 3 > /proc/sys/vm/drop_caches fio -name=cached --numjobs=16 --filename=/mnt/test.img \ --buffered=1 --ioengine=mmap -thp=1 --readonly \ --rw=randread --time_based --ramp_time=30s --runtime=10m \ --group_reporting fio -name=cached --numjobs=16 --filename=/mnt/test.img \ --buffered=1 --ioengine=mmap \ --rw=randread --time_based --runtime=5s --group_reporting Before: bw ( KiB/s): min= 4141, max=14202, per=100.00%, avg=7935.51, stdev=96.85, samples=18976 iops : min= 1029, max= 3548, avg=1979.52, stdev=24.23, samples=18976· READ: bw=4545B/s (4545B/s), 4545B/s-4545B/s (4545B/s-4545B/s), io=64.0KiB (65.5kB), run=14419-14419msec After (+12.5%): bw ( KiB/s): min= 4611, max=15370, per=100.00%, avg=8928.74, stdev=105.17, samples=19146 iops : min= 1151, max= 3842, avg=2231.27, stdev=26.29, samples=19146 READ: bw=4635B/s (4635B/s), 4635B/s-4635B/s (4635B/s-4635B/s), io=64.0KiB (65.5kB), run=14137-14137msec The performance is better for both 4K (+7.5%) and THP (+12.5%) cached read. Link: https://lkml.kernel.org/r/20240415171857.19244-5-ryncsn@gmail.com Signed-off-by: Kairui Song <kasong@tencent.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-04-15 17:18:56 +00:00
for (;;) {
int order = -1, split_order = 0;
void *entry, *old = NULL;
xas_lock_irq(&xas);
xas_for_each_conflict(&xas, entry) {
old = entry;
if (!xa_is_value(entry)) {
xas_set_err(&xas, -EEXIST);
goto unlock;
}
mm/filemap: optimize filemap folio adding Instead of doing multiple tree walks, do one optimism range check with lock hold, and exit if raced with another insertion. If a shadow exists, check it with a new xas_get_order helper before releasing the lock to avoid redundant tree walks for getting its order. Drop the lock and do the allocation only if a split is needed. In the best case, it only need to walk the tree once. If it needs to alloc and split, 3 walks are issued (One for first ranged conflict check and order retrieving, one for the second check after allocation, one for the insert after split). Testing with 4K pages, in an 8G cgroup, with 16G brd as block device: echo 3 > /proc/sys/vm/drop_caches fio -name=cached --numjobs=16 --filename=/mnt/test.img \ --buffered=1 --ioengine=mmap --rw=randread --time_based \ --ramp_time=30s --runtime=5m --group_reporting Before: bw ( MiB/s): min= 1027, max= 3520, per=100.00%, avg=2445.02, stdev=18.90, samples=8691 iops : min=263001, max=901288, avg=625924.36, stdev=4837.28, samples=8691 After (+7.3%): bw ( MiB/s): min= 493, max= 3947, per=100.00%, avg=2625.56, stdev=25.74, samples=8651 iops : min=126454, max=1010681, avg=672142.61, stdev=6590.48, samples=8651 Test result with THP (do a THP randread then switch to 4K page in hope it issues a lot of splitting): echo 3 > /proc/sys/vm/drop_caches fio -name=cached --numjobs=16 --filename=/mnt/test.img \ --buffered=1 --ioengine=mmap -thp=1 --readonly \ --rw=randread --time_based --ramp_time=30s --runtime=10m \ --group_reporting fio -name=cached --numjobs=16 --filename=/mnt/test.img \ --buffered=1 --ioengine=mmap \ --rw=randread --time_based --runtime=5s --group_reporting Before: bw ( KiB/s): min= 4141, max=14202, per=100.00%, avg=7935.51, stdev=96.85, samples=18976 iops : min= 1029, max= 3548, avg=1979.52, stdev=24.23, samples=18976· READ: bw=4545B/s (4545B/s), 4545B/s-4545B/s (4545B/s-4545B/s), io=64.0KiB (65.5kB), run=14419-14419msec After (+12.5%): bw ( KiB/s): min= 4611, max=15370, per=100.00%, avg=8928.74, stdev=105.17, samples=19146 iops : min= 1151, max= 3842, avg=2231.27, stdev=26.29, samples=19146 READ: bw=4635B/s (4635B/s), 4635B/s-4635B/s (4635B/s-4635B/s), io=64.0KiB (65.5kB), run=14137-14137msec The performance is better for both 4K (+7.5%) and THP (+12.5%) cached read. Link: https://lkml.kernel.org/r/20240415171857.19244-5-ryncsn@gmail.com Signed-off-by: Kairui Song <kasong@tencent.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-04-15 17:18:56 +00:00
/*
* If a larger entry exists,
* it will be the first and only entry iterated.
*/
if (order == -1)
order = xas_get_order(&xas);
}
/* entry may have changed before we re-acquire the lock */
if (alloced_order && (old != alloced_shadow || order != alloced_order)) {
xas_destroy(&xas);
alloced_order = 0;
}
if (old) {
mm/filemap: optimize filemap folio adding Instead of doing multiple tree walks, do one optimism range check with lock hold, and exit if raced with another insertion. If a shadow exists, check it with a new xas_get_order helper before releasing the lock to avoid redundant tree walks for getting its order. Drop the lock and do the allocation only if a split is needed. In the best case, it only need to walk the tree once. If it needs to alloc and split, 3 walks are issued (One for first ranged conflict check and order retrieving, one for the second check after allocation, one for the insert after split). Testing with 4K pages, in an 8G cgroup, with 16G brd as block device: echo 3 > /proc/sys/vm/drop_caches fio -name=cached --numjobs=16 --filename=/mnt/test.img \ --buffered=1 --ioengine=mmap --rw=randread --time_based \ --ramp_time=30s --runtime=5m --group_reporting Before: bw ( MiB/s): min= 1027, max= 3520, per=100.00%, avg=2445.02, stdev=18.90, samples=8691 iops : min=263001, max=901288, avg=625924.36, stdev=4837.28, samples=8691 After (+7.3%): bw ( MiB/s): min= 493, max= 3947, per=100.00%, avg=2625.56, stdev=25.74, samples=8651 iops : min=126454, max=1010681, avg=672142.61, stdev=6590.48, samples=8651 Test result with THP (do a THP randread then switch to 4K page in hope it issues a lot of splitting): echo 3 > /proc/sys/vm/drop_caches fio -name=cached --numjobs=16 --filename=/mnt/test.img \ --buffered=1 --ioengine=mmap -thp=1 --readonly \ --rw=randread --time_based --ramp_time=30s --runtime=10m \ --group_reporting fio -name=cached --numjobs=16 --filename=/mnt/test.img \ --buffered=1 --ioengine=mmap \ --rw=randread --time_based --runtime=5s --group_reporting Before: bw ( KiB/s): min= 4141, max=14202, per=100.00%, avg=7935.51, stdev=96.85, samples=18976 iops : min= 1029, max= 3548, avg=1979.52, stdev=24.23, samples=18976· READ: bw=4545B/s (4545B/s), 4545B/s-4545B/s (4545B/s-4545B/s), io=64.0KiB (65.5kB), run=14419-14419msec After (+12.5%): bw ( KiB/s): min= 4611, max=15370, per=100.00%, avg=8928.74, stdev=105.17, samples=19146 iops : min= 1151, max= 3842, avg=2231.27, stdev=26.29, samples=19146 READ: bw=4635B/s (4635B/s), 4635B/s-4635B/s (4635B/s-4635B/s), io=64.0KiB (65.5kB), run=14137-14137msec The performance is better for both 4K (+7.5%) and THP (+12.5%) cached read. Link: https://lkml.kernel.org/r/20240415171857.19244-5-ryncsn@gmail.com Signed-off-by: Kairui Song <kasong@tencent.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-04-15 17:18:56 +00:00
if (order > 0 && order > folio_order(folio)) {
/* How to handle large swap entries? */
BUG_ON(shmem_mapping(mapping));
mm/filemap: optimize filemap folio adding Instead of doing multiple tree walks, do one optimism range check with lock hold, and exit if raced with another insertion. If a shadow exists, check it with a new xas_get_order helper before releasing the lock to avoid redundant tree walks for getting its order. Drop the lock and do the allocation only if a split is needed. In the best case, it only need to walk the tree once. If it needs to alloc and split, 3 walks are issued (One for first ranged conflict check and order retrieving, one for the second check after allocation, one for the insert after split). Testing with 4K pages, in an 8G cgroup, with 16G brd as block device: echo 3 > /proc/sys/vm/drop_caches fio -name=cached --numjobs=16 --filename=/mnt/test.img \ --buffered=1 --ioengine=mmap --rw=randread --time_based \ --ramp_time=30s --runtime=5m --group_reporting Before: bw ( MiB/s): min= 1027, max= 3520, per=100.00%, avg=2445.02, stdev=18.90, samples=8691 iops : min=263001, max=901288, avg=625924.36, stdev=4837.28, samples=8691 After (+7.3%): bw ( MiB/s): min= 493, max= 3947, per=100.00%, avg=2625.56, stdev=25.74, samples=8651 iops : min=126454, max=1010681, avg=672142.61, stdev=6590.48, samples=8651 Test result with THP (do a THP randread then switch to 4K page in hope it issues a lot of splitting): echo 3 > /proc/sys/vm/drop_caches fio -name=cached --numjobs=16 --filename=/mnt/test.img \ --buffered=1 --ioengine=mmap -thp=1 --readonly \ --rw=randread --time_based --ramp_time=30s --runtime=10m \ --group_reporting fio -name=cached --numjobs=16 --filename=/mnt/test.img \ --buffered=1 --ioengine=mmap \ --rw=randread --time_based --runtime=5s --group_reporting Before: bw ( KiB/s): min= 4141, max=14202, per=100.00%, avg=7935.51, stdev=96.85, samples=18976 iops : min= 1029, max= 3548, avg=1979.52, stdev=24.23, samples=18976· READ: bw=4545B/s (4545B/s), 4545B/s-4545B/s (4545B/s-4545B/s), io=64.0KiB (65.5kB), run=14419-14419msec After (+12.5%): bw ( KiB/s): min= 4611, max=15370, per=100.00%, avg=8928.74, stdev=105.17, samples=19146 iops : min= 1151, max= 3842, avg=2231.27, stdev=26.29, samples=19146 READ: bw=4635B/s (4635B/s), 4635B/s-4635B/s (4635B/s-4635B/s), io=64.0KiB (65.5kB), run=14137-14137msec The performance is better for both 4K (+7.5%) and THP (+12.5%) cached read. Link: https://lkml.kernel.org/r/20240415171857.19244-5-ryncsn@gmail.com Signed-off-by: Kairui Song <kasong@tencent.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-04-15 17:18:56 +00:00
if (!alloced_order) {
split_order = order;
goto unlock;
}
xas_split(&xas, old, order);
xas_reset(&xas);
}
mm/filemap: optimize filemap folio adding Instead of doing multiple tree walks, do one optimism range check with lock hold, and exit if raced with another insertion. If a shadow exists, check it with a new xas_get_order helper before releasing the lock to avoid redundant tree walks for getting its order. Drop the lock and do the allocation only if a split is needed. In the best case, it only need to walk the tree once. If it needs to alloc and split, 3 walks are issued (One for first ranged conflict check and order retrieving, one for the second check after allocation, one for the insert after split). Testing with 4K pages, in an 8G cgroup, with 16G brd as block device: echo 3 > /proc/sys/vm/drop_caches fio -name=cached --numjobs=16 --filename=/mnt/test.img \ --buffered=1 --ioengine=mmap --rw=randread --time_based \ --ramp_time=30s --runtime=5m --group_reporting Before: bw ( MiB/s): min= 1027, max= 3520, per=100.00%, avg=2445.02, stdev=18.90, samples=8691 iops : min=263001, max=901288, avg=625924.36, stdev=4837.28, samples=8691 After (+7.3%): bw ( MiB/s): min= 493, max= 3947, per=100.00%, avg=2625.56, stdev=25.74, samples=8651 iops : min=126454, max=1010681, avg=672142.61, stdev=6590.48, samples=8651 Test result with THP (do a THP randread then switch to 4K page in hope it issues a lot of splitting): echo 3 > /proc/sys/vm/drop_caches fio -name=cached --numjobs=16 --filename=/mnt/test.img \ --buffered=1 --ioengine=mmap -thp=1 --readonly \ --rw=randread --time_based --ramp_time=30s --runtime=10m \ --group_reporting fio -name=cached --numjobs=16 --filename=/mnt/test.img \ --buffered=1 --ioengine=mmap \ --rw=randread --time_based --runtime=5s --group_reporting Before: bw ( KiB/s): min= 4141, max=14202, per=100.00%, avg=7935.51, stdev=96.85, samples=18976 iops : min= 1029, max= 3548, avg=1979.52, stdev=24.23, samples=18976· READ: bw=4545B/s (4545B/s), 4545B/s-4545B/s (4545B/s-4545B/s), io=64.0KiB (65.5kB), run=14419-14419msec After (+12.5%): bw ( KiB/s): min= 4611, max=15370, per=100.00%, avg=8928.74, stdev=105.17, samples=19146 iops : min= 1151, max= 3842, avg=2231.27, stdev=26.29, samples=19146 READ: bw=4635B/s (4635B/s), 4635B/s-4635B/s (4635B/s-4635B/s), io=64.0KiB (65.5kB), run=14137-14137msec The performance is better for both 4K (+7.5%) and THP (+12.5%) cached read. Link: https://lkml.kernel.org/r/20240415171857.19244-5-ryncsn@gmail.com Signed-off-by: Kairui Song <kasong@tencent.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-04-15 17:18:56 +00:00
if (shadowp)
*shadowp = old;
}
xas_store(&xas, folio);
if (xas_error(&xas))
goto unlock;
mapping->nrpages += nr;
/* hugetlb pages do not participate in page cache accounting */
if (!huge) {
__lruvec_stat_mod_folio(folio, NR_FILE_PAGES, nr);
if (folio_test_pmd_mappable(folio))
__lruvec_stat_mod_folio(folio,
NR_FILE_THPS, nr);
}
mm/filemap: optimize filemap folio adding Instead of doing multiple tree walks, do one optimism range check with lock hold, and exit if raced with another insertion. If a shadow exists, check it with a new xas_get_order helper before releasing the lock to avoid redundant tree walks for getting its order. Drop the lock and do the allocation only if a split is needed. In the best case, it only need to walk the tree once. If it needs to alloc and split, 3 walks are issued (One for first ranged conflict check and order retrieving, one for the second check after allocation, one for the insert after split). Testing with 4K pages, in an 8G cgroup, with 16G brd as block device: echo 3 > /proc/sys/vm/drop_caches fio -name=cached --numjobs=16 --filename=/mnt/test.img \ --buffered=1 --ioengine=mmap --rw=randread --time_based \ --ramp_time=30s --runtime=5m --group_reporting Before: bw ( MiB/s): min= 1027, max= 3520, per=100.00%, avg=2445.02, stdev=18.90, samples=8691 iops : min=263001, max=901288, avg=625924.36, stdev=4837.28, samples=8691 After (+7.3%): bw ( MiB/s): min= 493, max= 3947, per=100.00%, avg=2625.56, stdev=25.74, samples=8651 iops : min=126454, max=1010681, avg=672142.61, stdev=6590.48, samples=8651 Test result with THP (do a THP randread then switch to 4K page in hope it issues a lot of splitting): echo 3 > /proc/sys/vm/drop_caches fio -name=cached --numjobs=16 --filename=/mnt/test.img \ --buffered=1 --ioengine=mmap -thp=1 --readonly \ --rw=randread --time_based --ramp_time=30s --runtime=10m \ --group_reporting fio -name=cached --numjobs=16 --filename=/mnt/test.img \ --buffered=1 --ioengine=mmap \ --rw=randread --time_based --runtime=5s --group_reporting Before: bw ( KiB/s): min= 4141, max=14202, per=100.00%, avg=7935.51, stdev=96.85, samples=18976 iops : min= 1029, max= 3548, avg=1979.52, stdev=24.23, samples=18976· READ: bw=4545B/s (4545B/s), 4545B/s-4545B/s (4545B/s-4545B/s), io=64.0KiB (65.5kB), run=14419-14419msec After (+12.5%): bw ( KiB/s): min= 4611, max=15370, per=100.00%, avg=8928.74, stdev=105.17, samples=19146 iops : min= 1151, max= 3842, avg=2231.27, stdev=26.29, samples=19146 READ: bw=4635B/s (4635B/s), 4635B/s-4635B/s (4635B/s-4635B/s), io=64.0KiB (65.5kB), run=14137-14137msec The performance is better for both 4K (+7.5%) and THP (+12.5%) cached read. Link: https://lkml.kernel.org/r/20240415171857.19244-5-ryncsn@gmail.com Signed-off-by: Kairui Song <kasong@tencent.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-04-15 17:18:56 +00:00
unlock:
xas_unlock_irq(&xas);
mm/filemap: optimize filemap folio adding Instead of doing multiple tree walks, do one optimism range check with lock hold, and exit if raced with another insertion. If a shadow exists, check it with a new xas_get_order helper before releasing the lock to avoid redundant tree walks for getting its order. Drop the lock and do the allocation only if a split is needed. In the best case, it only need to walk the tree once. If it needs to alloc and split, 3 walks are issued (One for first ranged conflict check and order retrieving, one for the second check after allocation, one for the insert after split). Testing with 4K pages, in an 8G cgroup, with 16G brd as block device: echo 3 > /proc/sys/vm/drop_caches fio -name=cached --numjobs=16 --filename=/mnt/test.img \ --buffered=1 --ioengine=mmap --rw=randread --time_based \ --ramp_time=30s --runtime=5m --group_reporting Before: bw ( MiB/s): min= 1027, max= 3520, per=100.00%, avg=2445.02, stdev=18.90, samples=8691 iops : min=263001, max=901288, avg=625924.36, stdev=4837.28, samples=8691 After (+7.3%): bw ( MiB/s): min= 493, max= 3947, per=100.00%, avg=2625.56, stdev=25.74, samples=8651 iops : min=126454, max=1010681, avg=672142.61, stdev=6590.48, samples=8651 Test result with THP (do a THP randread then switch to 4K page in hope it issues a lot of splitting): echo 3 > /proc/sys/vm/drop_caches fio -name=cached --numjobs=16 --filename=/mnt/test.img \ --buffered=1 --ioengine=mmap -thp=1 --readonly \ --rw=randread --time_based --ramp_time=30s --runtime=10m \ --group_reporting fio -name=cached --numjobs=16 --filename=/mnt/test.img \ --buffered=1 --ioengine=mmap \ --rw=randread --time_based --runtime=5s --group_reporting Before: bw ( KiB/s): min= 4141, max=14202, per=100.00%, avg=7935.51, stdev=96.85, samples=18976 iops : min= 1029, max= 3548, avg=1979.52, stdev=24.23, samples=18976· READ: bw=4545B/s (4545B/s), 4545B/s-4545B/s (4545B/s-4545B/s), io=64.0KiB (65.5kB), run=14419-14419msec After (+12.5%): bw ( KiB/s): min= 4611, max=15370, per=100.00%, avg=8928.74, stdev=105.17, samples=19146 iops : min= 1151, max= 3842, avg=2231.27, stdev=26.29, samples=19146 READ: bw=4635B/s (4635B/s), 4635B/s-4635B/s (4635B/s-4635B/s), io=64.0KiB (65.5kB), run=14137-14137msec The performance is better for both 4K (+7.5%) and THP (+12.5%) cached read. Link: https://lkml.kernel.org/r/20240415171857.19244-5-ryncsn@gmail.com Signed-off-by: Kairui Song <kasong@tencent.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-04-15 17:18:56 +00:00
/* split needed, alloc here and retry. */
if (split_order) {
xas_split_alloc(&xas, old, split_order, gfp);
if (xas_error(&xas))
goto error;
alloced_shadow = old;
alloced_order = split_order;
xas_reset(&xas);
continue;
}
if (!xas_nomem(&xas, gfp))
break;
}
if (xas_error(&xas))
goto error;
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
trace_mm_filemap_add_to_page_cache(folio);
return 0;
error:
folio->mapping = NULL;
/* Leave page->index set: truncation relies upon it */
folio_put_refs(folio, nr);
return xas_error(&xas);
}
ALLOW_ERROR_INJECTION(__filemap_add_folio, ERRNO);
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
int filemap_add_folio(struct address_space *mapping, struct folio *folio,
pgoff_t index, gfp_t gfp)
{
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;
ret = mem_cgroup_charge(folio, NULL, gfp);
if (ret)
return ret;
__folio_set_locked(folio);
ret = __filemap_add_folio(mapping, folio, index, gfp, &shadow);
if (unlikely(ret)) {
mem_cgroup_uncharge(folio);
__folio_clear_locked(folio);
} else {
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
/*
* The folio might have been evicted from cache only
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
* recently, in which case it should be activated like
* any other repeatedly accessed folio.
* The exception is folios getting rewritten; evicting other
mm: workingset: only do workingset activations on reads This is a follow-up to http://www.spinics.net/lists/linux-mm/msg101739.html where Andres reported his database workingset being pushed out by the minimum size enforcement of the inactive file list - currently 50% of cache - as well as repeatedly written file pages that are never actually read. Two changes fell out of the discussions. The first change observes that pages that are only ever written don't benefit from caching beyond what the writeback cache does for partial page writes, and so we shouldn't promote them to the active file list where they compete with pages whose cached data is actually accessed repeatedly. This change comes in two patches - one for in-cache write accesses and one for refaults triggered by writes, neither of which should promote a cache page. Second, with the refault detection we don't need to set 50% of the cache aside for used-once cache anymore since we can detect frequently used pages even when they are evicted between accesses. We can allow the active list to be bigger and thus protect a bigger workingset that isn't challenged by streamers. Depending on the access patterns, this can increase major faults during workingset transitions for better performance during stable phases. This patch (of 3): When rewriting a page, the data in that page is replaced with new data. This means that evicting something else from the active file list, in order to cache data that will be replaced by something else, is likely to be a waste of memory. It is better to save the active list for frequently read pages, because reads actually use the data that is in the page. This patch ignores partial writes, because it is unclear whether the complexity of identifying those is worth any potential performance gain obtained from better caching pages that see repeated partial writes at large enough intervals to not get caught by the use-twice promotion code used for the inactive file list. Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reported-by: Andres Freund <andres@anarazel.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-05-20 23:56:25 +00:00
* data from the working set, only to cache data that will
* get overwritten with something else, is a waste of memory.
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
*/
WARN_ON_ONCE(folio_test_active(folio));
if (!(gfp & __GFP_WRITE) && shadow)
workingset_refault(folio, shadow);
folio_add_lru(folio);
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
}
return ret;
}
EXPORT_SYMBOL_GPL(filemap_add_folio);
#ifdef CONFIG_NUMA
struct folio *filemap_alloc_folio_noprof(gfp_t gfp, unsigned int order)
{
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 folio *folio;
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
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();
folio = __folio_alloc_node_noprof(gfp, order, n);
} while (!folio && 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
return folio;
}
return folio_alloc_noprof(gfp, order);
}
EXPORT_SYMBOL(filemap_alloc_folio_noprof);
#endif
/*
* filemap_invalidate_lock_two - lock invalidate_lock for two mappings
*
* Lock exclusively invalidate_lock of any passed mapping that is not NULL.
*
* @mapping1: the first mapping to lock
* @mapping2: the second mapping to lock
*/
void filemap_invalidate_lock_two(struct address_space *mapping1,
struct address_space *mapping2)
{
if (mapping1 > mapping2)
swap(mapping1, mapping2);
if (mapping1)
down_write(&mapping1->invalidate_lock);
if (mapping2 && mapping1 != mapping2)
down_write_nested(&mapping2->invalidate_lock, 1);
}
EXPORT_SYMBOL(filemap_invalidate_lock_two);
/*
* filemap_invalidate_unlock_two - unlock invalidate_lock for two mappings
*
* Unlock exclusive invalidate_lock of any passed mapping that is not NULL.
*
* @mapping1: the first mapping to unlock
* @mapping2: the second mapping to unlock
*/
void filemap_invalidate_unlock_two(struct address_space *mapping1,
struct address_space *mapping2)
{
if (mapping1)
up_write(&mapping1->invalidate_lock);
if (mapping2 && mapping1 != mapping2)
up_write(&mapping2->invalidate_lock);
}
EXPORT_SYMBOL(filemap_invalidate_unlock_two);
/*
* 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.
*/
2016-12-25 03:00:30 +00:00
#define PAGE_WAIT_TABLE_BITS 8
#define PAGE_WAIT_TABLE_SIZE (1 << PAGE_WAIT_TABLE_BITS)
static wait_queue_head_t folio_wait_table[PAGE_WAIT_TABLE_SIZE] __cacheline_aligned;
2016-12-25 03:00:30 +00:00
static wait_queue_head_t *folio_waitqueue(struct folio *folio)
{
return &folio_wait_table[hash_ptr(folio, PAGE_WAIT_TABLE_BITS)];
}
2016-12-25 03:00:30 +00:00
void __init pagecache_init(void)
{
2016-12-25 03:00:30 +00:00
int i;
2016-12-25 03:00:30 +00:00
for (i = 0; i < PAGE_WAIT_TABLE_SIZE; i++)
init_waitqueue_head(&folio_wait_table[i]);
2016-12-25 03:00:30 +00:00
page_writeback_init();
}
mm: allow a controlled amount of unfairness in the page lock Commit 2a9127fcf229 ("mm: rewrite wait_on_page_bit_common() logic") made the page locking entirely fair, in that if a waiter came in while the lock was held, the lock would be transferred to the lockers strictly in order. That was intended to finally get rid of the long-reported watchdog failures that involved the page lock under extreme load, where a process could end up waiting essentially forever, as other page lockers stole the lock from under it. It also improved some benchmarks, but it ended up causing huge performance regressions on others, simply because fair lock behavior doesn't end up giving out the lock as aggressively, causing better worst-case latency, but potentially much worse average latencies and throughput. Instead of reverting that change entirely, this introduces a controlled amount of unfairness, with a sysctl knob to tune it if somebody needs to. But the default value should hopefully be good for any normal load, allowing a few rounds of lock stealing, but enforcing the strict ordering before the lock has been stolen too many times. There is also a hint from Matthieu Baerts that the fair page coloring may end up exposing an ABBA deadlock that is hidden by the usual optimistic lock stealing, and while the unfairness doesn't fix the fundamental issue (and I'm still looking at that), it avoids it in practice. The amount of unfairness can be modified by writing a new value to the 'sysctl_page_lock_unfairness' variable (default value of 5, exposed through /proc/sys/vm/page_lock_unfairness), but that is hopefully something we'd use mainly for debugging rather than being necessary for any deep system tuning. This whole issue has exposed just how critical the page lock can be, and how contended it gets under certain locks. And the main contention doesn't really seem to be anything related to IO (which was the origin of this lock), but for things like just verifying that the page file mapping is stable while faulting in the page into a page table. Link: https://lore.kernel.org/linux-fsdevel/ed8442fd-6f54-dd84-cd4a-941e8b7ee603@MichaelLarabel.com/ Link: https://www.phoronix.com/scan.php?page=article&item=linux-50-59&num=1 Link: https://lore.kernel.org/linux-fsdevel/c560a38d-8313-51fb-b1ec-e904bd8836bc@tessares.net/ Reported-and-tested-by: Michael Larabel <Michael@michaellarabel.com> Tested-by: Matthieu Baerts <matthieu.baerts@tessares.net> Cc: Dave Chinner <david@fromorbit.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Chris Mason <clm@fb.com> Cc: Jan Kara <jack@suse.cz> Cc: Amir Goldstein <amir73il@gmail.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-09-13 21:05:35 +00:00
/*
* The page wait code treats the "wait->flags" somewhat unusually, because
* we have multiple different kinds of waits, not just the usual "exclusive"
mm: allow a controlled amount of unfairness in the page lock Commit 2a9127fcf229 ("mm: rewrite wait_on_page_bit_common() logic") made the page locking entirely fair, in that if a waiter came in while the lock was held, the lock would be transferred to the lockers strictly in order. That was intended to finally get rid of the long-reported watchdog failures that involved the page lock under extreme load, where a process could end up waiting essentially forever, as other page lockers stole the lock from under it. It also improved some benchmarks, but it ended up causing huge performance regressions on others, simply because fair lock behavior doesn't end up giving out the lock as aggressively, causing better worst-case latency, but potentially much worse average latencies and throughput. Instead of reverting that change entirely, this introduces a controlled amount of unfairness, with a sysctl knob to tune it if somebody needs to. But the default value should hopefully be good for any normal load, allowing a few rounds of lock stealing, but enforcing the strict ordering before the lock has been stolen too many times. There is also a hint from Matthieu Baerts that the fair page coloring may end up exposing an ABBA deadlock that is hidden by the usual optimistic lock stealing, and while the unfairness doesn't fix the fundamental issue (and I'm still looking at that), it avoids it in practice. The amount of unfairness can be modified by writing a new value to the 'sysctl_page_lock_unfairness' variable (default value of 5, exposed through /proc/sys/vm/page_lock_unfairness), but that is hopefully something we'd use mainly for debugging rather than being necessary for any deep system tuning. This whole issue has exposed just how critical the page lock can be, and how contended it gets under certain locks. And the main contention doesn't really seem to be anything related to IO (which was the origin of this lock), but for things like just verifying that the page file mapping is stable while faulting in the page into a page table. Link: https://lore.kernel.org/linux-fsdevel/ed8442fd-6f54-dd84-cd4a-941e8b7ee603@MichaelLarabel.com/ Link: https://www.phoronix.com/scan.php?page=article&item=linux-50-59&num=1 Link: https://lore.kernel.org/linux-fsdevel/c560a38d-8313-51fb-b1ec-e904bd8836bc@tessares.net/ Reported-and-tested-by: Michael Larabel <Michael@michaellarabel.com> Tested-by: Matthieu Baerts <matthieu.baerts@tessares.net> Cc: Dave Chinner <david@fromorbit.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Chris Mason <clm@fb.com> Cc: Jan Kara <jack@suse.cz> Cc: Amir Goldstein <amir73il@gmail.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-09-13 21:05:35 +00:00
* one.
*
* We have:
*
* (a) no special bits set:
*
* We're just waiting for the bit to be released, and when a waker
* calls the wakeup function, we set WQ_FLAG_WOKEN and wake it up,
* and remove it from the wait queue.
*
* Simple and straightforward.
*
* (b) WQ_FLAG_EXCLUSIVE:
*
* The waiter is waiting to get the lock, and only one waiter should
* be woken up to avoid any thundering herd behavior. We'll set the
* WQ_FLAG_WOKEN bit, wake it up, and remove it from the wait queue.
*
* This is the traditional exclusive wait.
*
* (c) WQ_FLAG_EXCLUSIVE | WQ_FLAG_CUSTOM:
mm: allow a controlled amount of unfairness in the page lock Commit 2a9127fcf229 ("mm: rewrite wait_on_page_bit_common() logic") made the page locking entirely fair, in that if a waiter came in while the lock was held, the lock would be transferred to the lockers strictly in order. That was intended to finally get rid of the long-reported watchdog failures that involved the page lock under extreme load, where a process could end up waiting essentially forever, as other page lockers stole the lock from under it. It also improved some benchmarks, but it ended up causing huge performance regressions on others, simply because fair lock behavior doesn't end up giving out the lock as aggressively, causing better worst-case latency, but potentially much worse average latencies and throughput. Instead of reverting that change entirely, this introduces a controlled amount of unfairness, with a sysctl knob to tune it if somebody needs to. But the default value should hopefully be good for any normal load, allowing a few rounds of lock stealing, but enforcing the strict ordering before the lock has been stolen too many times. There is also a hint from Matthieu Baerts that the fair page coloring may end up exposing an ABBA deadlock that is hidden by the usual optimistic lock stealing, and while the unfairness doesn't fix the fundamental issue (and I'm still looking at that), it avoids it in practice. The amount of unfairness can be modified by writing a new value to the 'sysctl_page_lock_unfairness' variable (default value of 5, exposed through /proc/sys/vm/page_lock_unfairness), but that is hopefully something we'd use mainly for debugging rather than being necessary for any deep system tuning. This whole issue has exposed just how critical the page lock can be, and how contended it gets under certain locks. And the main contention doesn't really seem to be anything related to IO (which was the origin of this lock), but for things like just verifying that the page file mapping is stable while faulting in the page into a page table. Link: https://lore.kernel.org/linux-fsdevel/ed8442fd-6f54-dd84-cd4a-941e8b7ee603@MichaelLarabel.com/ Link: https://www.phoronix.com/scan.php?page=article&item=linux-50-59&num=1 Link: https://lore.kernel.org/linux-fsdevel/c560a38d-8313-51fb-b1ec-e904bd8836bc@tessares.net/ Reported-and-tested-by: Michael Larabel <Michael@michaellarabel.com> Tested-by: Matthieu Baerts <matthieu.baerts@tessares.net> Cc: Dave Chinner <david@fromorbit.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Chris Mason <clm@fb.com> Cc: Jan Kara <jack@suse.cz> Cc: Amir Goldstein <amir73il@gmail.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-09-13 21:05:35 +00:00
*
* The waiter is waiting to get the bit, and additionally wants the
* lock to be transferred to it for fair lock behavior. If the lock
* cannot be taken, we stop walking the wait queue without waking
* the waiter.
*
* This is the "fair lock handoff" case, and in addition to setting
* WQ_FLAG_WOKEN, we set WQ_FLAG_DONE to let the waiter easily see
* that it now has the lock.
*/
static int wake_page_function(wait_queue_entry_t *wait, unsigned mode, int sync, void *arg)
{
mm: allow a controlled amount of unfairness in the page lock Commit 2a9127fcf229 ("mm: rewrite wait_on_page_bit_common() logic") made the page locking entirely fair, in that if a waiter came in while the lock was held, the lock would be transferred to the lockers strictly in order. That was intended to finally get rid of the long-reported watchdog failures that involved the page lock under extreme load, where a process could end up waiting essentially forever, as other page lockers stole the lock from under it. It also improved some benchmarks, but it ended up causing huge performance regressions on others, simply because fair lock behavior doesn't end up giving out the lock as aggressively, causing better worst-case latency, but potentially much worse average latencies and throughput. Instead of reverting that change entirely, this introduces a controlled amount of unfairness, with a sysctl knob to tune it if somebody needs to. But the default value should hopefully be good for any normal load, allowing a few rounds of lock stealing, but enforcing the strict ordering before the lock has been stolen too many times. There is also a hint from Matthieu Baerts that the fair page coloring may end up exposing an ABBA deadlock that is hidden by the usual optimistic lock stealing, and while the unfairness doesn't fix the fundamental issue (and I'm still looking at that), it avoids it in practice. The amount of unfairness can be modified by writing a new value to the 'sysctl_page_lock_unfairness' variable (default value of 5, exposed through /proc/sys/vm/page_lock_unfairness), but that is hopefully something we'd use mainly for debugging rather than being necessary for any deep system tuning. This whole issue has exposed just how critical the page lock can be, and how contended it gets under certain locks. And the main contention doesn't really seem to be anything related to IO (which was the origin of this lock), but for things like just verifying that the page file mapping is stable while faulting in the page into a page table. Link: https://lore.kernel.org/linux-fsdevel/ed8442fd-6f54-dd84-cd4a-941e8b7ee603@MichaelLarabel.com/ Link: https://www.phoronix.com/scan.php?page=article&item=linux-50-59&num=1 Link: https://lore.kernel.org/linux-fsdevel/c560a38d-8313-51fb-b1ec-e904bd8836bc@tessares.net/ Reported-and-tested-by: Michael Larabel <Michael@michaellarabel.com> Tested-by: Matthieu Baerts <matthieu.baerts@tessares.net> Cc: Dave Chinner <david@fromorbit.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Chris Mason <clm@fb.com> Cc: Jan Kara <jack@suse.cz> Cc: Amir Goldstein <amir73il@gmail.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-09-13 21:05:35 +00:00
unsigned int flags;
2016-12-25 03:00:30 +00:00
struct wait_page_key *key = arg;
struct wait_page_queue *wait_page
= container_of(wait, struct wait_page_queue, wait);
for-5.9/io_uring-20200802 -----BEGIN PGP SIGNATURE----- iQJEBAABCAAuFiEEwPw5LcreJtl1+l5K99NY+ylx4KYFAl8m7asQHGF4Ym9lQGtl cm5lbC5kawAKCRD301j7KXHgplrCD/0S17kio+k4cOJDGwl88WoJw+QiYmM5019k decZ1JymQvV1HXRmlcZiEAu0hHDD0FoovSRrw7II3gw3GouETmYQM62f6ZTpDeMD CED/fidnfULAkPaI6h+bj3jyI0cEuujG/R47rGSQEkIIr3RttqKZUzVkB9KN+KMw +OBuXZtMIoFFEVJ91qwC2dm2qHLqOn1/5MlT59knso/xbPOYOXsFQpGiACJqF97x 6qSSI8uGE+HZqvL2OLWPDBbLEJhrq+dzCgxln5VlvLele4UcRhOdonUb7nUwEKCe zwvtXzz16u1D1b8bJL4Kg5bGqyUAQUCSShsfBJJxh6vTTULiHyCX5sQaai1OEB16 4dpBL9E+nOUUix4wo9XBY0/KIYaPWg5L1CoEwkAXqkXPhFvNUucsC0u6KvmzZR3V 1OogVTjl6GhS8uEVQjTKNshkTIC9QHEMXDUOHtINDCb/sLU+ANXU5UpvsuzZ9+kt KGc4mdyCwaKBq4YW9sVwhhq/RHLD4AUtWZiUVfOE+0cltCLJUNMbQsJ+XrcYaQnm W4zz22Rep+SJuQNVcCW/w7N2zN3yB6gC1qeroSLvzw4b5el2TdFp+BcgVlLHK+uh xjsGNCq++fyzNk7vvMZ5hVq4JGXYjza7AiP5HlQ8nqdiPUKUPatWCBqUm9i9Cz/B n+0dlYbRwQ== =2vmy -----END PGP SIGNATURE----- Merge tag 'for-5.9/io_uring-20200802' of git://git.kernel.dk/linux-block Pull io_uring updates from Jens Axboe: "Lots of cleanups in here, hardening the code and/or making it easier to read and fixing bugs, but a core feature/change too adding support for real async buffered reads. With the latter in place, we just need buffered write async support and we're done relying on kthreads for the fast path. In detail: - Cleanup how memory accounting is done on ring setup/free (Bijan) - sq array offset calculation fixup (Dmitry) - Consistently handle blocking off O_DIRECT submission path (me) - Support proper async buffered reads, instead of relying on kthread offload for that. This uses the page waitqueue to drive retries from task_work, like we handle poll based retry. (me) - IO completion optimizations (me) - Fix race with accounting and ring fd install (me) - Support EPOLLEXCLUSIVE (Jiufei) - Get rid of the io_kiocb unionizing, made possible by shrinking other bits (Pavel) - Completion side cleanups (Pavel) - Cleanup REQ_F_ flags handling, and kill off many of them (Pavel) - Request environment grabbing cleanups (Pavel) - File and socket read/write cleanups (Pavel) - Improve kiocb_set_rw_flags() (Pavel) - Tons of fixes and cleanups (Pavel) - IORING_SQ_NEED_WAKEUP clear fix (Xiaoguang)" * tag 'for-5.9/io_uring-20200802' of git://git.kernel.dk/linux-block: (127 commits) io_uring: flip if handling after io_setup_async_rw fs: optimise kiocb_set_rw_flags() io_uring: don't touch 'ctx' after installing file descriptor io_uring: get rid of atomic FAA for cq_timeouts io_uring: consolidate *_check_overflow accounting io_uring: fix stalled deferred requests io_uring: fix racy overflow count reporting io_uring: deduplicate __io_complete_rw() io_uring: de-unionise io_kiocb io-wq: update hash bits io_uring: fix missing io_queue_linked_timeout() io_uring: mark ->work uninitialised after cleanup io_uring: deduplicate io_grab_files() calls io_uring: don't do opcode prep twice io_uring: clear IORING_SQ_NEED_WAKEUP after executing task works io_uring: batch put_task_struct() tasks: add put_task_struct_many() io_uring: return locked and pinned page accounting io_uring: don't miscount pinned memory io_uring: don't open-code recv kbuf managment ...
2020-08-03 20:01:22 +00:00
if (!wake_page_match(wait_page, key))
2016-12-25 03:00:30 +00:00
return 0;
Minor page waitqueue cleanups Tim Chen and Kan Liang have been battling a customer load that shows extremely long page wakeup lists. The cause seems to be constant NUMA migration of a hot page that is shared across a lot of threads, but the actual root cause for the exact behavior has not been found. Tim has a patch that batches the wait list traversal at wakeup time, so that we at least don't get long uninterruptible cases where we traverse and wake up thousands of processes and get nasty latency spikes. That is likely 4.14 material, but we're still discussing the page waitqueue specific parts of it. In the meantime, I've tried to look at making the page wait queues less expensive, and failing miserably. If you have thousands of threads waiting for the same page, it will be painful. We'll need to try to figure out the NUMA balancing issue some day, in addition to avoiding the excessive spinlock hold times. That said, having tried to rewrite the page wait queues, I can at least fix up some of the braindamage in the current situation. In particular: (a) we don't want to continue walking the page wait list if the bit we're waiting for already got set again (which seems to be one of the patterns of the bad load). That makes no progress and just causes pointless cache pollution chasing the pointers. (b) we don't want to put the non-locking waiters always on the front of the queue, and the locking waiters always on the back. Not only is that unfair, it means that we wake up thousands of reading threads that will just end up being blocked by the writer later anyway. Also add a comment about the layout of 'struct wait_page_key' - there is an external user of it in the cachefiles code that means that it has to match the layout of 'struct wait_bit_key' in the two first members. It so happens to match, because 'struct page *' and 'unsigned long *' end up having the same values simply because the page flags are the first member in struct page. Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: Christopher Lameter <cl@linux.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-08-27 20:55:12 +00:00
mm: put_and_wait_on_page_locked() while page is migrated Waiting on a page migration entry has used wait_on_page_locked() all along since 2006: but you cannot safely wait_on_page_locked() without holding a reference to the page, and that extra reference is enough to make migrate_page_move_mapping() fail with -EAGAIN, when a racing task faults on the entry before migrate_page_move_mapping() gets there. And that failure is retried nine times, amplifying the pain when trying to migrate a popular page. With a single persistent faulter, migration sometimes succeeds; with two or three concurrent faulters, success becomes much less likely (and the more the page was mapped, the worse the overhead of unmapping and remapping it on each try). This is especially a problem for memory offlining, where the outer level retries forever (or until terminated from userspace), because a heavy refault workload can trigger an endless loop of migration failures. wait_on_page_locked() is the wrong tool for the job. David Herrmann (but was he the first?) noticed this issue in 2014: https://marc.info/?l=linux-mm&m=140110465608116&w=2 Tim Chen started a thread in August 2017 which appears relevant: https://marc.info/?l=linux-mm&m=150275941014915&w=2 where Kan Liang went on to implicate __migration_entry_wait(): https://marc.info/?l=linux-mm&m=150300268411980&w=2 and the thread ended up with the v4.14 commits: 2554db916586 ("sched/wait: Break up long wake list walk") 11a19c7b099f ("sched/wait: Introduce wakeup boomark in wake_up_page_bit") Baoquan He reported "Memory hotplug softlock issue" 14 November 2018: https://marc.info/?l=linux-mm&m=154217936431300&w=2 We have all assumed that it is essential to hold a page reference while waiting on a page lock: partly to guarantee that there is still a struct page when MEMORY_HOTREMOVE is configured, but also to protect against reuse of the struct page going to someone who then holds the page locked indefinitely, when the waiter can reasonably expect timely unlocking. But in fact, so long as wait_on_page_bit_common() does the put_page(), and is careful not to rely on struct page contents thereafter, there is no need to hold a reference to the page while waiting on it. That does mean that this case cannot go back through the loop: but that's fine for the page migration case, and even if used more widely, is limited by the "Stop walking if it's locked" optimization in wake_page_function(). Add interface put_and_wait_on_page_locked() to do this, using "behavior" enum in place of "lock" arg to wait_on_page_bit_common() to implement it. No interruptible or killable variant needed yet, but they might follow: I have a vague notion that reporting -EINTR should take precedence over return from wait_on_page_bit_common() without knowing the page state, so arrange it accordingly - but that may be nothing but pedantic. __migration_entry_wait() still has to take a brief reference to the page, prior to calling put_and_wait_on_page_locked(): but now that it is dropped before waiting, the chance of impeding page migration is very much reduced. Should we perhaps disable preemption across this? shrink_page_list()'s __ClearPageLocked(): that was a surprise! This survived a lot of testing before that showed up. PageWaiters may have been set by wait_on_page_bit_common(), and the reference dropped, just before shrink_page_list() succeeds in freezing its last page reference: in such a case, unlock_page() must be used. Follow the suggestion from Michal Hocko, just revert a978d6f52106 ("mm: unlockless reclaim") now: that optimization predates PageWaiters, and won't buy much these days; but we can reinstate it for the !PageWaiters case if anyone notices. It does raise the question: should vmscan.c's is_page_cache_freeable() and __remove_mapping() now treat a PageWaiters page as if an extra reference were held? Perhaps, but I don't think it matters much, since shrink_page_list() already had to win its trylock_page(), so waiters are not very common there: I noticed no difference when trying the bigger change, and it's surely not needed while put_and_wait_on_page_locked() is only used for page migration. [willy@infradead.org: add put_and_wait_on_page_locked() kerneldoc] Link: http://lkml.kernel.org/r/alpine.LSU.2.11.1811261121330.1116@eggly.anvils Signed-off-by: Hugh Dickins <hughd@google.com> Reported-by: Baoquan He <bhe@redhat.com> Tested-by: Baoquan He <bhe@redhat.com> Reviewed-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Michal Hocko <mhocko@suse.com> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Matthew Wilcox <willy@infradead.org> Cc: Baoquan He <bhe@redhat.com> Cc: David Hildenbrand <david@redhat.com> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: David Herrmann <dh.herrmann@gmail.com> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Christoph Lameter <cl@linux.com> Cc: Nick Piggin <npiggin@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-12-28 08:36:14 +00:00
/*
mm: allow a controlled amount of unfairness in the page lock Commit 2a9127fcf229 ("mm: rewrite wait_on_page_bit_common() logic") made the page locking entirely fair, in that if a waiter came in while the lock was held, the lock would be transferred to the lockers strictly in order. That was intended to finally get rid of the long-reported watchdog failures that involved the page lock under extreme load, where a process could end up waiting essentially forever, as other page lockers stole the lock from under it. It also improved some benchmarks, but it ended up causing huge performance regressions on others, simply because fair lock behavior doesn't end up giving out the lock as aggressively, causing better worst-case latency, but potentially much worse average latencies and throughput. Instead of reverting that change entirely, this introduces a controlled amount of unfairness, with a sysctl knob to tune it if somebody needs to. But the default value should hopefully be good for any normal load, allowing a few rounds of lock stealing, but enforcing the strict ordering before the lock has been stolen too many times. There is also a hint from Matthieu Baerts that the fair page coloring may end up exposing an ABBA deadlock that is hidden by the usual optimistic lock stealing, and while the unfairness doesn't fix the fundamental issue (and I'm still looking at that), it avoids it in practice. The amount of unfairness can be modified by writing a new value to the 'sysctl_page_lock_unfairness' variable (default value of 5, exposed through /proc/sys/vm/page_lock_unfairness), but that is hopefully something we'd use mainly for debugging rather than being necessary for any deep system tuning. This whole issue has exposed just how critical the page lock can be, and how contended it gets under certain locks. And the main contention doesn't really seem to be anything related to IO (which was the origin of this lock), but for things like just verifying that the page file mapping is stable while faulting in the page into a page table. Link: https://lore.kernel.org/linux-fsdevel/ed8442fd-6f54-dd84-cd4a-941e8b7ee603@MichaelLarabel.com/ Link: https://www.phoronix.com/scan.php?page=article&item=linux-50-59&num=1 Link: https://lore.kernel.org/linux-fsdevel/c560a38d-8313-51fb-b1ec-e904bd8836bc@tessares.net/ Reported-and-tested-by: Michael Larabel <Michael@michaellarabel.com> Tested-by: Matthieu Baerts <matthieu.baerts@tessares.net> Cc: Dave Chinner <david@fromorbit.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Chris Mason <clm@fb.com> Cc: Jan Kara <jack@suse.cz> Cc: Amir Goldstein <amir73il@gmail.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-09-13 21:05:35 +00:00
* If it's a lock handoff wait, we get the bit for it, and
* stop walking (and do not wake it up) if we can't.
mm: put_and_wait_on_page_locked() while page is migrated Waiting on a page migration entry has used wait_on_page_locked() all along since 2006: but you cannot safely wait_on_page_locked() without holding a reference to the page, and that extra reference is enough to make migrate_page_move_mapping() fail with -EAGAIN, when a racing task faults on the entry before migrate_page_move_mapping() gets there. And that failure is retried nine times, amplifying the pain when trying to migrate a popular page. With a single persistent faulter, migration sometimes succeeds; with two or three concurrent faulters, success becomes much less likely (and the more the page was mapped, the worse the overhead of unmapping and remapping it on each try). This is especially a problem for memory offlining, where the outer level retries forever (or until terminated from userspace), because a heavy refault workload can trigger an endless loop of migration failures. wait_on_page_locked() is the wrong tool for the job. David Herrmann (but was he the first?) noticed this issue in 2014: https://marc.info/?l=linux-mm&m=140110465608116&w=2 Tim Chen started a thread in August 2017 which appears relevant: https://marc.info/?l=linux-mm&m=150275941014915&w=2 where Kan Liang went on to implicate __migration_entry_wait(): https://marc.info/?l=linux-mm&m=150300268411980&w=2 and the thread ended up with the v4.14 commits: 2554db916586 ("sched/wait: Break up long wake list walk") 11a19c7b099f ("sched/wait: Introduce wakeup boomark in wake_up_page_bit") Baoquan He reported "Memory hotplug softlock issue" 14 November 2018: https://marc.info/?l=linux-mm&m=154217936431300&w=2 We have all assumed that it is essential to hold a page reference while waiting on a page lock: partly to guarantee that there is still a struct page when MEMORY_HOTREMOVE is configured, but also to protect against reuse of the struct page going to someone who then holds the page locked indefinitely, when the waiter can reasonably expect timely unlocking. But in fact, so long as wait_on_page_bit_common() does the put_page(), and is careful not to rely on struct page contents thereafter, there is no need to hold a reference to the page while waiting on it. That does mean that this case cannot go back through the loop: but that's fine for the page migration case, and even if used more widely, is limited by the "Stop walking if it's locked" optimization in wake_page_function(). Add interface put_and_wait_on_page_locked() to do this, using "behavior" enum in place of "lock" arg to wait_on_page_bit_common() to implement it. No interruptible or killable variant needed yet, but they might follow: I have a vague notion that reporting -EINTR should take precedence over return from wait_on_page_bit_common() without knowing the page state, so arrange it accordingly - but that may be nothing but pedantic. __migration_entry_wait() still has to take a brief reference to the page, prior to calling put_and_wait_on_page_locked(): but now that it is dropped before waiting, the chance of impeding page migration is very much reduced. Should we perhaps disable preemption across this? shrink_page_list()'s __ClearPageLocked(): that was a surprise! This survived a lot of testing before that showed up. PageWaiters may have been set by wait_on_page_bit_common(), and the reference dropped, just before shrink_page_list() succeeds in freezing its last page reference: in such a case, unlock_page() must be used. Follow the suggestion from Michal Hocko, just revert a978d6f52106 ("mm: unlockless reclaim") now: that optimization predates PageWaiters, and won't buy much these days; but we can reinstate it for the !PageWaiters case if anyone notices. It does raise the question: should vmscan.c's is_page_cache_freeable() and __remove_mapping() now treat a PageWaiters page as if an extra reference were held? Perhaps, but I don't think it matters much, since shrink_page_list() already had to win its trylock_page(), so waiters are not very common there: I noticed no difference when trying the bigger change, and it's surely not needed while put_and_wait_on_page_locked() is only used for page migration. [willy@infradead.org: add put_and_wait_on_page_locked() kerneldoc] Link: http://lkml.kernel.org/r/alpine.LSU.2.11.1811261121330.1116@eggly.anvils Signed-off-by: Hugh Dickins <hughd@google.com> Reported-by: Baoquan He <bhe@redhat.com> Tested-by: Baoquan He <bhe@redhat.com> Reviewed-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Michal Hocko <mhocko@suse.com> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Matthew Wilcox <willy@infradead.org> Cc: Baoquan He <bhe@redhat.com> Cc: David Hildenbrand <david@redhat.com> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: David Herrmann <dh.herrmann@gmail.com> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Christoph Lameter <cl@linux.com> Cc: Nick Piggin <npiggin@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-12-28 08:36:14 +00:00
*/
mm: allow a controlled amount of unfairness in the page lock Commit 2a9127fcf229 ("mm: rewrite wait_on_page_bit_common() logic") made the page locking entirely fair, in that if a waiter came in while the lock was held, the lock would be transferred to the lockers strictly in order. That was intended to finally get rid of the long-reported watchdog failures that involved the page lock under extreme load, where a process could end up waiting essentially forever, as other page lockers stole the lock from under it. It also improved some benchmarks, but it ended up causing huge performance regressions on others, simply because fair lock behavior doesn't end up giving out the lock as aggressively, causing better worst-case latency, but potentially much worse average latencies and throughput. Instead of reverting that change entirely, this introduces a controlled amount of unfairness, with a sysctl knob to tune it if somebody needs to. But the default value should hopefully be good for any normal load, allowing a few rounds of lock stealing, but enforcing the strict ordering before the lock has been stolen too many times. There is also a hint from Matthieu Baerts that the fair page coloring may end up exposing an ABBA deadlock that is hidden by the usual optimistic lock stealing, and while the unfairness doesn't fix the fundamental issue (and I'm still looking at that), it avoids it in practice. The amount of unfairness can be modified by writing a new value to the 'sysctl_page_lock_unfairness' variable (default value of 5, exposed through /proc/sys/vm/page_lock_unfairness), but that is hopefully something we'd use mainly for debugging rather than being necessary for any deep system tuning. This whole issue has exposed just how critical the page lock can be, and how contended it gets under certain locks. And the main contention doesn't really seem to be anything related to IO (which was the origin of this lock), but for things like just verifying that the page file mapping is stable while faulting in the page into a page table. Link: https://lore.kernel.org/linux-fsdevel/ed8442fd-6f54-dd84-cd4a-941e8b7ee603@MichaelLarabel.com/ Link: https://www.phoronix.com/scan.php?page=article&item=linux-50-59&num=1 Link: https://lore.kernel.org/linux-fsdevel/c560a38d-8313-51fb-b1ec-e904bd8836bc@tessares.net/ Reported-and-tested-by: Michael Larabel <Michael@michaellarabel.com> Tested-by: Matthieu Baerts <matthieu.baerts@tessares.net> Cc: Dave Chinner <david@fromorbit.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Chris Mason <clm@fb.com> Cc: Jan Kara <jack@suse.cz> Cc: Amir Goldstein <amir73il@gmail.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-09-13 21:05:35 +00:00
flags = wait->flags;
if (flags & WQ_FLAG_EXCLUSIVE) {
if (test_bit(key->bit_nr, &key->folio->flags))
return -1;
mm: allow a controlled amount of unfairness in the page lock Commit 2a9127fcf229 ("mm: rewrite wait_on_page_bit_common() logic") made the page locking entirely fair, in that if a waiter came in while the lock was held, the lock would be transferred to the lockers strictly in order. That was intended to finally get rid of the long-reported watchdog failures that involved the page lock under extreme load, where a process could end up waiting essentially forever, as other page lockers stole the lock from under it. It also improved some benchmarks, but it ended up causing huge performance regressions on others, simply because fair lock behavior doesn't end up giving out the lock as aggressively, causing better worst-case latency, but potentially much worse average latencies and throughput. Instead of reverting that change entirely, this introduces a controlled amount of unfairness, with a sysctl knob to tune it if somebody needs to. But the default value should hopefully be good for any normal load, allowing a few rounds of lock stealing, but enforcing the strict ordering before the lock has been stolen too many times. There is also a hint from Matthieu Baerts that the fair page coloring may end up exposing an ABBA deadlock that is hidden by the usual optimistic lock stealing, and while the unfairness doesn't fix the fundamental issue (and I'm still looking at that), it avoids it in practice. The amount of unfairness can be modified by writing a new value to the 'sysctl_page_lock_unfairness' variable (default value of 5, exposed through /proc/sys/vm/page_lock_unfairness), but that is hopefully something we'd use mainly for debugging rather than being necessary for any deep system tuning. This whole issue has exposed just how critical the page lock can be, and how contended it gets under certain locks. And the main contention doesn't really seem to be anything related to IO (which was the origin of this lock), but for things like just verifying that the page file mapping is stable while faulting in the page into a page table. Link: https://lore.kernel.org/linux-fsdevel/ed8442fd-6f54-dd84-cd4a-941e8b7ee603@MichaelLarabel.com/ Link: https://www.phoronix.com/scan.php?page=article&item=linux-50-59&num=1 Link: https://lore.kernel.org/linux-fsdevel/c560a38d-8313-51fb-b1ec-e904bd8836bc@tessares.net/ Reported-and-tested-by: Michael Larabel <Michael@michaellarabel.com> Tested-by: Matthieu Baerts <matthieu.baerts@tessares.net> Cc: Dave Chinner <david@fromorbit.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Chris Mason <clm@fb.com> Cc: Jan Kara <jack@suse.cz> Cc: Amir Goldstein <amir73il@gmail.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-09-13 21:05:35 +00:00
if (flags & WQ_FLAG_CUSTOM) {
if (test_and_set_bit(key->bit_nr, &key->folio->flags))
mm: allow a controlled amount of unfairness in the page lock Commit 2a9127fcf229 ("mm: rewrite wait_on_page_bit_common() logic") made the page locking entirely fair, in that if a waiter came in while the lock was held, the lock would be transferred to the lockers strictly in order. That was intended to finally get rid of the long-reported watchdog failures that involved the page lock under extreme load, where a process could end up waiting essentially forever, as other page lockers stole the lock from under it. It also improved some benchmarks, but it ended up causing huge performance regressions on others, simply because fair lock behavior doesn't end up giving out the lock as aggressively, causing better worst-case latency, but potentially much worse average latencies and throughput. Instead of reverting that change entirely, this introduces a controlled amount of unfairness, with a sysctl knob to tune it if somebody needs to. But the default value should hopefully be good for any normal load, allowing a few rounds of lock stealing, but enforcing the strict ordering before the lock has been stolen too many times. There is also a hint from Matthieu Baerts that the fair page coloring may end up exposing an ABBA deadlock that is hidden by the usual optimistic lock stealing, and while the unfairness doesn't fix the fundamental issue (and I'm still looking at that), it avoids it in practice. The amount of unfairness can be modified by writing a new value to the 'sysctl_page_lock_unfairness' variable (default value of 5, exposed through /proc/sys/vm/page_lock_unfairness), but that is hopefully something we'd use mainly for debugging rather than being necessary for any deep system tuning. This whole issue has exposed just how critical the page lock can be, and how contended it gets under certain locks. And the main contention doesn't really seem to be anything related to IO (which was the origin of this lock), but for things like just verifying that the page file mapping is stable while faulting in the page into a page table. Link: https://lore.kernel.org/linux-fsdevel/ed8442fd-6f54-dd84-cd4a-941e8b7ee603@MichaelLarabel.com/ Link: https://www.phoronix.com/scan.php?page=article&item=linux-50-59&num=1 Link: https://lore.kernel.org/linux-fsdevel/c560a38d-8313-51fb-b1ec-e904bd8836bc@tessares.net/ Reported-and-tested-by: Michael Larabel <Michael@michaellarabel.com> Tested-by: Matthieu Baerts <matthieu.baerts@tessares.net> Cc: Dave Chinner <david@fromorbit.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Chris Mason <clm@fb.com> Cc: Jan Kara <jack@suse.cz> Cc: Amir Goldstein <amir73il@gmail.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-09-13 21:05:35 +00:00
return -1;
flags |= WQ_FLAG_DONE;
}
}
mm: allow a controlled amount of unfairness in the page lock Commit 2a9127fcf229 ("mm: rewrite wait_on_page_bit_common() logic") made the page locking entirely fair, in that if a waiter came in while the lock was held, the lock would be transferred to the lockers strictly in order. That was intended to finally get rid of the long-reported watchdog failures that involved the page lock under extreme load, where a process could end up waiting essentially forever, as other page lockers stole the lock from under it. It also improved some benchmarks, but it ended up causing huge performance regressions on others, simply because fair lock behavior doesn't end up giving out the lock as aggressively, causing better worst-case latency, but potentially much worse average latencies and throughput. Instead of reverting that change entirely, this introduces a controlled amount of unfairness, with a sysctl knob to tune it if somebody needs to. But the default value should hopefully be good for any normal load, allowing a few rounds of lock stealing, but enforcing the strict ordering before the lock has been stolen too many times. There is also a hint from Matthieu Baerts that the fair page coloring may end up exposing an ABBA deadlock that is hidden by the usual optimistic lock stealing, and while the unfairness doesn't fix the fundamental issue (and I'm still looking at that), it avoids it in practice. The amount of unfairness can be modified by writing a new value to the 'sysctl_page_lock_unfairness' variable (default value of 5, exposed through /proc/sys/vm/page_lock_unfairness), but that is hopefully something we'd use mainly for debugging rather than being necessary for any deep system tuning. This whole issue has exposed just how critical the page lock can be, and how contended it gets under certain locks. And the main contention doesn't really seem to be anything related to IO (which was the origin of this lock), but for things like just verifying that the page file mapping is stable while faulting in the page into a page table. Link: https://lore.kernel.org/linux-fsdevel/ed8442fd-6f54-dd84-cd4a-941e8b7ee603@MichaelLarabel.com/ Link: https://www.phoronix.com/scan.php?page=article&item=linux-50-59&num=1 Link: https://lore.kernel.org/linux-fsdevel/c560a38d-8313-51fb-b1ec-e904bd8836bc@tessares.net/ Reported-and-tested-by: Michael Larabel <Michael@michaellarabel.com> Tested-by: Matthieu Baerts <matthieu.baerts@tessares.net> Cc: Dave Chinner <david@fromorbit.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Chris Mason <clm@fb.com> Cc: Jan Kara <jack@suse.cz> Cc: Amir Goldstein <amir73il@gmail.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-09-13 21:05:35 +00:00
/*
* We are holding the wait-queue lock, but the waiter that
* is waiting for this will be checking the flags without
* any locking.
*
* So update the flags atomically, and wake up the waiter
* afterwards to avoid any races. This store-release pairs
* with the load-acquire in folio_wait_bit_common().
mm: allow a controlled amount of unfairness in the page lock Commit 2a9127fcf229 ("mm: rewrite wait_on_page_bit_common() logic") made the page locking entirely fair, in that if a waiter came in while the lock was held, the lock would be transferred to the lockers strictly in order. That was intended to finally get rid of the long-reported watchdog failures that involved the page lock under extreme load, where a process could end up waiting essentially forever, as other page lockers stole the lock from under it. It also improved some benchmarks, but it ended up causing huge performance regressions on others, simply because fair lock behavior doesn't end up giving out the lock as aggressively, causing better worst-case latency, but potentially much worse average latencies and throughput. Instead of reverting that change entirely, this introduces a controlled amount of unfairness, with a sysctl knob to tune it if somebody needs to. But the default value should hopefully be good for any normal load, allowing a few rounds of lock stealing, but enforcing the strict ordering before the lock has been stolen too many times. There is also a hint from Matthieu Baerts that the fair page coloring may end up exposing an ABBA deadlock that is hidden by the usual optimistic lock stealing, and while the unfairness doesn't fix the fundamental issue (and I'm still looking at that), it avoids it in practice. The amount of unfairness can be modified by writing a new value to the 'sysctl_page_lock_unfairness' variable (default value of 5, exposed through /proc/sys/vm/page_lock_unfairness), but that is hopefully something we'd use mainly for debugging rather than being necessary for any deep system tuning. This whole issue has exposed just how critical the page lock can be, and how contended it gets under certain locks. And the main contention doesn't really seem to be anything related to IO (which was the origin of this lock), but for things like just verifying that the page file mapping is stable while faulting in the page into a page table. Link: https://lore.kernel.org/linux-fsdevel/ed8442fd-6f54-dd84-cd4a-941e8b7ee603@MichaelLarabel.com/ Link: https://www.phoronix.com/scan.php?page=article&item=linux-50-59&num=1 Link: https://lore.kernel.org/linux-fsdevel/c560a38d-8313-51fb-b1ec-e904bd8836bc@tessares.net/ Reported-and-tested-by: Michael Larabel <Michael@michaellarabel.com> Tested-by: Matthieu Baerts <matthieu.baerts@tessares.net> Cc: Dave Chinner <david@fromorbit.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Chris Mason <clm@fb.com> Cc: Jan Kara <jack@suse.cz> Cc: Amir Goldstein <amir73il@gmail.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-09-13 21:05:35 +00:00
*/
smp_store_release(&wait->flags, flags | WQ_FLAG_WOKEN);
wake_up_state(wait->private, mode);
/*
* Ok, we have successfully done what we're waiting for,
* and we can unconditionally remove the wait entry.
*
mm: allow a controlled amount of unfairness in the page lock Commit 2a9127fcf229 ("mm: rewrite wait_on_page_bit_common() logic") made the page locking entirely fair, in that if a waiter came in while the lock was held, the lock would be transferred to the lockers strictly in order. That was intended to finally get rid of the long-reported watchdog failures that involved the page lock under extreme load, where a process could end up waiting essentially forever, as other page lockers stole the lock from under it. It also improved some benchmarks, but it ended up causing huge performance regressions on others, simply because fair lock behavior doesn't end up giving out the lock as aggressively, causing better worst-case latency, but potentially much worse average latencies and throughput. Instead of reverting that change entirely, this introduces a controlled amount of unfairness, with a sysctl knob to tune it if somebody needs to. But the default value should hopefully be good for any normal load, allowing a few rounds of lock stealing, but enforcing the strict ordering before the lock has been stolen too many times. There is also a hint from Matthieu Baerts that the fair page coloring may end up exposing an ABBA deadlock that is hidden by the usual optimistic lock stealing, and while the unfairness doesn't fix the fundamental issue (and I'm still looking at that), it avoids it in practice. The amount of unfairness can be modified by writing a new value to the 'sysctl_page_lock_unfairness' variable (default value of 5, exposed through /proc/sys/vm/page_lock_unfairness), but that is hopefully something we'd use mainly for debugging rather than being necessary for any deep system tuning. This whole issue has exposed just how critical the page lock can be, and how contended it gets under certain locks. And the main contention doesn't really seem to be anything related to IO (which was the origin of this lock), but for things like just verifying that the page file mapping is stable while faulting in the page into a page table. Link: https://lore.kernel.org/linux-fsdevel/ed8442fd-6f54-dd84-cd4a-941e8b7ee603@MichaelLarabel.com/ Link: https://www.phoronix.com/scan.php?page=article&item=linux-50-59&num=1 Link: https://lore.kernel.org/linux-fsdevel/c560a38d-8313-51fb-b1ec-e904bd8836bc@tessares.net/ Reported-and-tested-by: Michael Larabel <Michael@michaellarabel.com> Tested-by: Matthieu Baerts <matthieu.baerts@tessares.net> Cc: Dave Chinner <david@fromorbit.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Chris Mason <clm@fb.com> Cc: Jan Kara <jack@suse.cz> Cc: Amir Goldstein <amir73il@gmail.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-09-13 21:05:35 +00:00
* Note that this pairs with the "finish_wait()" in the
* waiter, and has to be the absolute last thing we do.
* After this list_del_init(&wait->entry) the wait entry
* might be de-allocated and the process might even have
* exited.
*/
list_del_init_careful(&wait->entry);
mm: allow a controlled amount of unfairness in the page lock Commit 2a9127fcf229 ("mm: rewrite wait_on_page_bit_common() logic") made the page locking entirely fair, in that if a waiter came in while the lock was held, the lock would be transferred to the lockers strictly in order. That was intended to finally get rid of the long-reported watchdog failures that involved the page lock under extreme load, where a process could end up waiting essentially forever, as other page lockers stole the lock from under it. It also improved some benchmarks, but it ended up causing huge performance regressions on others, simply because fair lock behavior doesn't end up giving out the lock as aggressively, causing better worst-case latency, but potentially much worse average latencies and throughput. Instead of reverting that change entirely, this introduces a controlled amount of unfairness, with a sysctl knob to tune it if somebody needs to. But the default value should hopefully be good for any normal load, allowing a few rounds of lock stealing, but enforcing the strict ordering before the lock has been stolen too many times. There is also a hint from Matthieu Baerts that the fair page coloring may end up exposing an ABBA deadlock that is hidden by the usual optimistic lock stealing, and while the unfairness doesn't fix the fundamental issue (and I'm still looking at that), it avoids it in practice. The amount of unfairness can be modified by writing a new value to the 'sysctl_page_lock_unfairness' variable (default value of 5, exposed through /proc/sys/vm/page_lock_unfairness), but that is hopefully something we'd use mainly for debugging rather than being necessary for any deep system tuning. This whole issue has exposed just how critical the page lock can be, and how contended it gets under certain locks. And the main contention doesn't really seem to be anything related to IO (which was the origin of this lock), but for things like just verifying that the page file mapping is stable while faulting in the page into a page table. Link: https://lore.kernel.org/linux-fsdevel/ed8442fd-6f54-dd84-cd4a-941e8b7ee603@MichaelLarabel.com/ Link: https://www.phoronix.com/scan.php?page=article&item=linux-50-59&num=1 Link: https://lore.kernel.org/linux-fsdevel/c560a38d-8313-51fb-b1ec-e904bd8836bc@tessares.net/ Reported-and-tested-by: Michael Larabel <Michael@michaellarabel.com> Tested-by: Matthieu Baerts <matthieu.baerts@tessares.net> Cc: Dave Chinner <david@fromorbit.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Chris Mason <clm@fb.com> Cc: Jan Kara <jack@suse.cz> Cc: Amir Goldstein <amir73il@gmail.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-09-13 21:05:35 +00:00
return (flags & WQ_FLAG_EXCLUSIVE) != 0;
}
static void folio_wake_bit(struct folio *folio, int bit_nr)
{
wait_queue_head_t *q = folio_waitqueue(folio);
2016-12-25 03:00:30 +00:00
struct wait_page_key key;
unsigned long flags;
key.folio = folio;
2016-12-25 03:00:30 +00:00
key.bit_nr = bit_nr;
key.page_match = 0;
spin_lock_irqsave(&q->lock, flags);
__wake_up_locked_key(q, TASK_NORMAL, &key);
2016-12-25 03:00:30 +00:00
/*
* It's possible to miss clearing waiters here, when we woke our page
* waiters, but the hashed waitqueue has waiters for other pages on it.
* That's okay, it's a rare case. The next waker will clear it.
2016-12-25 03:00:30 +00:00
*
* Note that, depending on the page pool (buddy, hugetlb, ZONE_DEVICE,
* other), the flag may be cleared in the course of freeing the page;
* but that is not required for correctness.
2016-12-25 03:00:30 +00:00
*/
if (!waitqueue_active(q) || !key.page_match)
folio_clear_waiters(folio);
2016-12-25 03:00:30 +00:00
spin_unlock_irqrestore(&q->lock, flags);
}
mm: put_and_wait_on_page_locked() while page is migrated Waiting on a page migration entry has used wait_on_page_locked() all along since 2006: but you cannot safely wait_on_page_locked() without holding a reference to the page, and that extra reference is enough to make migrate_page_move_mapping() fail with -EAGAIN, when a racing task faults on the entry before migrate_page_move_mapping() gets there. And that failure is retried nine times, amplifying the pain when trying to migrate a popular page. With a single persistent faulter, migration sometimes succeeds; with two or three concurrent faulters, success becomes much less likely (and the more the page was mapped, the worse the overhead of unmapping and remapping it on each try). This is especially a problem for memory offlining, where the outer level retries forever (or until terminated from userspace), because a heavy refault workload can trigger an endless loop of migration failures. wait_on_page_locked() is the wrong tool for the job. David Herrmann (but was he the first?) noticed this issue in 2014: https://marc.info/?l=linux-mm&m=140110465608116&w=2 Tim Chen started a thread in August 2017 which appears relevant: https://marc.info/?l=linux-mm&m=150275941014915&w=2 where Kan Liang went on to implicate __migration_entry_wait(): https://marc.info/?l=linux-mm&m=150300268411980&w=2 and the thread ended up with the v4.14 commits: 2554db916586 ("sched/wait: Break up long wake list walk") 11a19c7b099f ("sched/wait: Introduce wakeup boomark in wake_up_page_bit") Baoquan He reported "Memory hotplug softlock issue" 14 November 2018: https://marc.info/?l=linux-mm&m=154217936431300&w=2 We have all assumed that it is essential to hold a page reference while waiting on a page lock: partly to guarantee that there is still a struct page when MEMORY_HOTREMOVE is configured, but also to protect against reuse of the struct page going to someone who then holds the page locked indefinitely, when the waiter can reasonably expect timely unlocking. But in fact, so long as wait_on_page_bit_common() does the put_page(), and is careful not to rely on struct page contents thereafter, there is no need to hold a reference to the page while waiting on it. That does mean that this case cannot go back through the loop: but that's fine for the page migration case, and even if used more widely, is limited by the "Stop walking if it's locked" optimization in wake_page_function(). Add interface put_and_wait_on_page_locked() to do this, using "behavior" enum in place of "lock" arg to wait_on_page_bit_common() to implement it. No interruptible or killable variant needed yet, but they might follow: I have a vague notion that reporting -EINTR should take precedence over return from wait_on_page_bit_common() without knowing the page state, so arrange it accordingly - but that may be nothing but pedantic. __migration_entry_wait() still has to take a brief reference to the page, prior to calling put_and_wait_on_page_locked(): but now that it is dropped before waiting, the chance of impeding page migration is very much reduced. Should we perhaps disable preemption across this? shrink_page_list()'s __ClearPageLocked(): that was a surprise! This survived a lot of testing before that showed up. PageWaiters may have been set by wait_on_page_bit_common(), and the reference dropped, just before shrink_page_list() succeeds in freezing its last page reference: in such a case, unlock_page() must be used. Follow the suggestion from Michal Hocko, just revert a978d6f52106 ("mm: unlockless reclaim") now: that optimization predates PageWaiters, and won't buy much these days; but we can reinstate it for the !PageWaiters case if anyone notices. It does raise the question: should vmscan.c's is_page_cache_freeable() and __remove_mapping() now treat a PageWaiters page as if an extra reference were held? Perhaps, but I don't think it matters much, since shrink_page_list() already had to win its trylock_page(), so waiters are not very common there: I noticed no difference when trying the bigger change, and it's surely not needed while put_and_wait_on_page_locked() is only used for page migration. [willy@infradead.org: add put_and_wait_on_page_locked() kerneldoc] Link: http://lkml.kernel.org/r/alpine.LSU.2.11.1811261121330.1116@eggly.anvils Signed-off-by: Hugh Dickins <hughd@google.com> Reported-by: Baoquan He <bhe@redhat.com> Tested-by: Baoquan He <bhe@redhat.com> Reviewed-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Michal Hocko <mhocko@suse.com> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Matthew Wilcox <willy@infradead.org> Cc: Baoquan He <bhe@redhat.com> Cc: David Hildenbrand <david@redhat.com> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: David Herrmann <dh.herrmann@gmail.com> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Christoph Lameter <cl@linux.com> Cc: Nick Piggin <npiggin@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-12-28 08:36:14 +00:00
/*
* A choice of three behaviors for folio_wait_bit_common():
mm: put_and_wait_on_page_locked() while page is migrated Waiting on a page migration entry has used wait_on_page_locked() all along since 2006: but you cannot safely wait_on_page_locked() without holding a reference to the page, and that extra reference is enough to make migrate_page_move_mapping() fail with -EAGAIN, when a racing task faults on the entry before migrate_page_move_mapping() gets there. And that failure is retried nine times, amplifying the pain when trying to migrate a popular page. With a single persistent faulter, migration sometimes succeeds; with two or three concurrent faulters, success becomes much less likely (and the more the page was mapped, the worse the overhead of unmapping and remapping it on each try). This is especially a problem for memory offlining, where the outer level retries forever (or until terminated from userspace), because a heavy refault workload can trigger an endless loop of migration failures. wait_on_page_locked() is the wrong tool for the job. David Herrmann (but was he the first?) noticed this issue in 2014: https://marc.info/?l=linux-mm&m=140110465608116&w=2 Tim Chen started a thread in August 2017 which appears relevant: https://marc.info/?l=linux-mm&m=150275941014915&w=2 where Kan Liang went on to implicate __migration_entry_wait(): https://marc.info/?l=linux-mm&m=150300268411980&w=2 and the thread ended up with the v4.14 commits: 2554db916586 ("sched/wait: Break up long wake list walk") 11a19c7b099f ("sched/wait: Introduce wakeup boomark in wake_up_page_bit") Baoquan He reported "Memory hotplug softlock issue" 14 November 2018: https://marc.info/?l=linux-mm&m=154217936431300&w=2 We have all assumed that it is essential to hold a page reference while waiting on a page lock: partly to guarantee that there is still a struct page when MEMORY_HOTREMOVE is configured, but also to protect against reuse of the struct page going to someone who then holds the page locked indefinitely, when the waiter can reasonably expect timely unlocking. But in fact, so long as wait_on_page_bit_common() does the put_page(), and is careful not to rely on struct page contents thereafter, there is no need to hold a reference to the page while waiting on it. That does mean that this case cannot go back through the loop: but that's fine for the page migration case, and even if used more widely, is limited by the "Stop walking if it's locked" optimization in wake_page_function(). Add interface put_and_wait_on_page_locked() to do this, using "behavior" enum in place of "lock" arg to wait_on_page_bit_common() to implement it. No interruptible or killable variant needed yet, but they might follow: I have a vague notion that reporting -EINTR should take precedence over return from wait_on_page_bit_common() without knowing the page state, so arrange it accordingly - but that may be nothing but pedantic. __migration_entry_wait() still has to take a brief reference to the page, prior to calling put_and_wait_on_page_locked(): but now that it is dropped before waiting, the chance of impeding page migration is very much reduced. Should we perhaps disable preemption across this? shrink_page_list()'s __ClearPageLocked(): that was a surprise! This survived a lot of testing before that showed up. PageWaiters may have been set by wait_on_page_bit_common(), and the reference dropped, just before shrink_page_list() succeeds in freezing its last page reference: in such a case, unlock_page() must be used. Follow the suggestion from Michal Hocko, just revert a978d6f52106 ("mm: unlockless reclaim") now: that optimization predates PageWaiters, and won't buy much these days; but we can reinstate it for the !PageWaiters case if anyone notices. It does raise the question: should vmscan.c's is_page_cache_freeable() and __remove_mapping() now treat a PageWaiters page as if an extra reference were held? Perhaps, but I don't think it matters much, since shrink_page_list() already had to win its trylock_page(), so waiters are not very common there: I noticed no difference when trying the bigger change, and it's surely not needed while put_and_wait_on_page_locked() is only used for page migration. [willy@infradead.org: add put_and_wait_on_page_locked() kerneldoc] Link: http://lkml.kernel.org/r/alpine.LSU.2.11.1811261121330.1116@eggly.anvils Signed-off-by: Hugh Dickins <hughd@google.com> Reported-by: Baoquan He <bhe@redhat.com> Tested-by: Baoquan He <bhe@redhat.com> Reviewed-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Michal Hocko <mhocko@suse.com> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Matthew Wilcox <willy@infradead.org> Cc: Baoquan He <bhe@redhat.com> Cc: David Hildenbrand <david@redhat.com> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: David Herrmann <dh.herrmann@gmail.com> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Christoph Lameter <cl@linux.com> Cc: Nick Piggin <npiggin@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-12-28 08:36:14 +00:00
*/
enum behavior {
EXCLUSIVE, /* Hold ref to page and take the bit when woken, like
* __folio_lock() waiting on then setting PG_locked.
mm: put_and_wait_on_page_locked() while page is migrated Waiting on a page migration entry has used wait_on_page_locked() all along since 2006: but you cannot safely wait_on_page_locked() without holding a reference to the page, and that extra reference is enough to make migrate_page_move_mapping() fail with -EAGAIN, when a racing task faults on the entry before migrate_page_move_mapping() gets there. And that failure is retried nine times, amplifying the pain when trying to migrate a popular page. With a single persistent faulter, migration sometimes succeeds; with two or three concurrent faulters, success becomes much less likely (and the more the page was mapped, the worse the overhead of unmapping and remapping it on each try). This is especially a problem for memory offlining, where the outer level retries forever (or until terminated from userspace), because a heavy refault workload can trigger an endless loop of migration failures. wait_on_page_locked() is the wrong tool for the job. David Herrmann (but was he the first?) noticed this issue in 2014: https://marc.info/?l=linux-mm&m=140110465608116&w=2 Tim Chen started a thread in August 2017 which appears relevant: https://marc.info/?l=linux-mm&m=150275941014915&w=2 where Kan Liang went on to implicate __migration_entry_wait(): https://marc.info/?l=linux-mm&m=150300268411980&w=2 and the thread ended up with the v4.14 commits: 2554db916586 ("sched/wait: Break up long wake list walk") 11a19c7b099f ("sched/wait: Introduce wakeup boomark in wake_up_page_bit") Baoquan He reported "Memory hotplug softlock issue" 14 November 2018: https://marc.info/?l=linux-mm&m=154217936431300&w=2 We have all assumed that it is essential to hold a page reference while waiting on a page lock: partly to guarantee that there is still a struct page when MEMORY_HOTREMOVE is configured, but also to protect against reuse of the struct page going to someone who then holds the page locked indefinitely, when the waiter can reasonably expect timely unlocking. But in fact, so long as wait_on_page_bit_common() does the put_page(), and is careful not to rely on struct page contents thereafter, there is no need to hold a reference to the page while waiting on it. That does mean that this case cannot go back through the loop: but that's fine for the page migration case, and even if used more widely, is limited by the "Stop walking if it's locked" optimization in wake_page_function(). Add interface put_and_wait_on_page_locked() to do this, using "behavior" enum in place of "lock" arg to wait_on_page_bit_common() to implement it. No interruptible or killable variant needed yet, but they might follow: I have a vague notion that reporting -EINTR should take precedence over return from wait_on_page_bit_common() without knowing the page state, so arrange it accordingly - but that may be nothing but pedantic. __migration_entry_wait() still has to take a brief reference to the page, prior to calling put_and_wait_on_page_locked(): but now that it is dropped before waiting, the chance of impeding page migration is very much reduced. Should we perhaps disable preemption across this? shrink_page_list()'s __ClearPageLocked(): that was a surprise! This survived a lot of testing before that showed up. PageWaiters may have been set by wait_on_page_bit_common(), and the reference dropped, just before shrink_page_list() succeeds in freezing its last page reference: in such a case, unlock_page() must be used. Follow the suggestion from Michal Hocko, just revert a978d6f52106 ("mm: unlockless reclaim") now: that optimization predates PageWaiters, and won't buy much these days; but we can reinstate it for the !PageWaiters case if anyone notices. It does raise the question: should vmscan.c's is_page_cache_freeable() and __remove_mapping() now treat a PageWaiters page as if an extra reference were held? Perhaps, but I don't think it matters much, since shrink_page_list() already had to win its trylock_page(), so waiters are not very common there: I noticed no difference when trying the bigger change, and it's surely not needed while put_and_wait_on_page_locked() is only used for page migration. [willy@infradead.org: add put_and_wait_on_page_locked() kerneldoc] Link: http://lkml.kernel.org/r/alpine.LSU.2.11.1811261121330.1116@eggly.anvils Signed-off-by: Hugh Dickins <hughd@google.com> Reported-by: Baoquan He <bhe@redhat.com> Tested-by: Baoquan He <bhe@redhat.com> Reviewed-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Michal Hocko <mhocko@suse.com> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Matthew Wilcox <willy@infradead.org> Cc: Baoquan He <bhe@redhat.com> Cc: David Hildenbrand <david@redhat.com> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: David Herrmann <dh.herrmann@gmail.com> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Christoph Lameter <cl@linux.com> Cc: Nick Piggin <npiggin@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-12-28 08:36:14 +00:00
*/
SHARED, /* Hold ref to page and check the bit when woken, like
* folio_wait_writeback() waiting on PG_writeback.
mm: put_and_wait_on_page_locked() while page is migrated Waiting on a page migration entry has used wait_on_page_locked() all along since 2006: but you cannot safely wait_on_page_locked() without holding a reference to the page, and that extra reference is enough to make migrate_page_move_mapping() fail with -EAGAIN, when a racing task faults on the entry before migrate_page_move_mapping() gets there. And that failure is retried nine times, amplifying the pain when trying to migrate a popular page. With a single persistent faulter, migration sometimes succeeds; with two or three concurrent faulters, success becomes much less likely (and the more the page was mapped, the worse the overhead of unmapping and remapping it on each try). This is especially a problem for memory offlining, where the outer level retries forever (or until terminated from userspace), because a heavy refault workload can trigger an endless loop of migration failures. wait_on_page_locked() is the wrong tool for the job. David Herrmann (but was he the first?) noticed this issue in 2014: https://marc.info/?l=linux-mm&m=140110465608116&w=2 Tim Chen started a thread in August 2017 which appears relevant: https://marc.info/?l=linux-mm&m=150275941014915&w=2 where Kan Liang went on to implicate __migration_entry_wait(): https://marc.info/?l=linux-mm&m=150300268411980&w=2 and the thread ended up with the v4.14 commits: 2554db916586 ("sched/wait: Break up long wake list walk") 11a19c7b099f ("sched/wait: Introduce wakeup boomark in wake_up_page_bit") Baoquan He reported "Memory hotplug softlock issue" 14 November 2018: https://marc.info/?l=linux-mm&m=154217936431300&w=2 We have all assumed that it is essential to hold a page reference while waiting on a page lock: partly to guarantee that there is still a struct page when MEMORY_HOTREMOVE is configured, but also to protect against reuse of the struct page going to someone who then holds the page locked indefinitely, when the waiter can reasonably expect timely unlocking. But in fact, so long as wait_on_page_bit_common() does the put_page(), and is careful not to rely on struct page contents thereafter, there is no need to hold a reference to the page while waiting on it. That does mean that this case cannot go back through the loop: but that's fine for the page migration case, and even if used more widely, is limited by the "Stop walking if it's locked" optimization in wake_page_function(). Add interface put_and_wait_on_page_locked() to do this, using "behavior" enum in place of "lock" arg to wait_on_page_bit_common() to implement it. No interruptible or killable variant needed yet, but they might follow: I have a vague notion that reporting -EINTR should take precedence over return from wait_on_page_bit_common() without knowing the page state, so arrange it accordingly - but that may be nothing but pedantic. __migration_entry_wait() still has to take a brief reference to the page, prior to calling put_and_wait_on_page_locked(): but now that it is dropped before waiting, the chance of impeding page migration is very much reduced. Should we perhaps disable preemption across this? shrink_page_list()'s __ClearPageLocked(): that was a surprise! This survived a lot of testing before that showed up. PageWaiters may have been set by wait_on_page_bit_common(), and the reference dropped, just before shrink_page_list() succeeds in freezing its last page reference: in such a case, unlock_page() must be used. Follow the suggestion from Michal Hocko, just revert a978d6f52106 ("mm: unlockless reclaim") now: that optimization predates PageWaiters, and won't buy much these days; but we can reinstate it for the !PageWaiters case if anyone notices. It does raise the question: should vmscan.c's is_page_cache_freeable() and __remove_mapping() now treat a PageWaiters page as if an extra reference were held? Perhaps, but I don't think it matters much, since shrink_page_list() already had to win its trylock_page(), so waiters are not very common there: I noticed no difference when trying the bigger change, and it's surely not needed while put_and_wait_on_page_locked() is only used for page migration. [willy@infradead.org: add put_and_wait_on_page_locked() kerneldoc] Link: http://lkml.kernel.org/r/alpine.LSU.2.11.1811261121330.1116@eggly.anvils Signed-off-by: Hugh Dickins <hughd@google.com> Reported-by: Baoquan He <bhe@redhat.com> Tested-by: Baoquan He <bhe@redhat.com> Reviewed-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Michal Hocko <mhocko@suse.com> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Matthew Wilcox <willy@infradead.org> Cc: Baoquan He <bhe@redhat.com> Cc: David Hildenbrand <david@redhat.com> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: David Herrmann <dh.herrmann@gmail.com> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Christoph Lameter <cl@linux.com> Cc: Nick Piggin <npiggin@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-12-28 08:36:14 +00:00
*/
DROP, /* Drop ref to page before wait, no check when woken,
* like folio_put_wait_locked() on PG_locked.
mm: put_and_wait_on_page_locked() while page is migrated Waiting on a page migration entry has used wait_on_page_locked() all along since 2006: but you cannot safely wait_on_page_locked() without holding a reference to the page, and that extra reference is enough to make migrate_page_move_mapping() fail with -EAGAIN, when a racing task faults on the entry before migrate_page_move_mapping() gets there. And that failure is retried nine times, amplifying the pain when trying to migrate a popular page. With a single persistent faulter, migration sometimes succeeds; with two or three concurrent faulters, success becomes much less likely (and the more the page was mapped, the worse the overhead of unmapping and remapping it on each try). This is especially a problem for memory offlining, where the outer level retries forever (or until terminated from userspace), because a heavy refault workload can trigger an endless loop of migration failures. wait_on_page_locked() is the wrong tool for the job. David Herrmann (but was he the first?) noticed this issue in 2014: https://marc.info/?l=linux-mm&m=140110465608116&w=2 Tim Chen started a thread in August 2017 which appears relevant: https://marc.info/?l=linux-mm&m=150275941014915&w=2 where Kan Liang went on to implicate __migration_entry_wait(): https://marc.info/?l=linux-mm&m=150300268411980&w=2 and the thread ended up with the v4.14 commits: 2554db916586 ("sched/wait: Break up long wake list walk") 11a19c7b099f ("sched/wait: Introduce wakeup boomark in wake_up_page_bit") Baoquan He reported "Memory hotplug softlock issue" 14 November 2018: https://marc.info/?l=linux-mm&m=154217936431300&w=2 We have all assumed that it is essential to hold a page reference while waiting on a page lock: partly to guarantee that there is still a struct page when MEMORY_HOTREMOVE is configured, but also to protect against reuse of the struct page going to someone who then holds the page locked indefinitely, when the waiter can reasonably expect timely unlocking. But in fact, so long as wait_on_page_bit_common() does the put_page(), and is careful not to rely on struct page contents thereafter, there is no need to hold a reference to the page while waiting on it. That does mean that this case cannot go back through the loop: but that's fine for the page migration case, and even if used more widely, is limited by the "Stop walking if it's locked" optimization in wake_page_function(). Add interface put_and_wait_on_page_locked() to do this, using "behavior" enum in place of "lock" arg to wait_on_page_bit_common() to implement it. No interruptible or killable variant needed yet, but they might follow: I have a vague notion that reporting -EINTR should take precedence over return from wait_on_page_bit_common() without knowing the page state, so arrange it accordingly - but that may be nothing but pedantic. __migration_entry_wait() still has to take a brief reference to the page, prior to calling put_and_wait_on_page_locked(): but now that it is dropped before waiting, the chance of impeding page migration is very much reduced. Should we perhaps disable preemption across this? shrink_page_list()'s __ClearPageLocked(): that was a surprise! This survived a lot of testing before that showed up. PageWaiters may have been set by wait_on_page_bit_common(), and the reference dropped, just before shrink_page_list() succeeds in freezing its last page reference: in such a case, unlock_page() must be used. Follow the suggestion from Michal Hocko, just revert a978d6f52106 ("mm: unlockless reclaim") now: that optimization predates PageWaiters, and won't buy much these days; but we can reinstate it for the !PageWaiters case if anyone notices. It does raise the question: should vmscan.c's is_page_cache_freeable() and __remove_mapping() now treat a PageWaiters page as if an extra reference were held? Perhaps, but I don't think it matters much, since shrink_page_list() already had to win its trylock_page(), so waiters are not very common there: I noticed no difference when trying the bigger change, and it's surely not needed while put_and_wait_on_page_locked() is only used for page migration. [willy@infradead.org: add put_and_wait_on_page_locked() kerneldoc] Link: http://lkml.kernel.org/r/alpine.LSU.2.11.1811261121330.1116@eggly.anvils Signed-off-by: Hugh Dickins <hughd@google.com> Reported-by: Baoquan He <bhe@redhat.com> Tested-by: Baoquan He <bhe@redhat.com> Reviewed-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Michal Hocko <mhocko@suse.com> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Matthew Wilcox <willy@infradead.org> Cc: Baoquan He <bhe@redhat.com> Cc: David Hildenbrand <david@redhat.com> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: David Herrmann <dh.herrmann@gmail.com> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Christoph Lameter <cl@linux.com> Cc: Nick Piggin <npiggin@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-12-28 08:36:14 +00:00
*/
};
/*
* Attempt to check (or get) the folio flag, and mark us done
mm: allow a controlled amount of unfairness in the page lock Commit 2a9127fcf229 ("mm: rewrite wait_on_page_bit_common() logic") made the page locking entirely fair, in that if a waiter came in while the lock was held, the lock would be transferred to the lockers strictly in order. That was intended to finally get rid of the long-reported watchdog failures that involved the page lock under extreme load, where a process could end up waiting essentially forever, as other page lockers stole the lock from under it. It also improved some benchmarks, but it ended up causing huge performance regressions on others, simply because fair lock behavior doesn't end up giving out the lock as aggressively, causing better worst-case latency, but potentially much worse average latencies and throughput. Instead of reverting that change entirely, this introduces a controlled amount of unfairness, with a sysctl knob to tune it if somebody needs to. But the default value should hopefully be good for any normal load, allowing a few rounds of lock stealing, but enforcing the strict ordering before the lock has been stolen too many times. There is also a hint from Matthieu Baerts that the fair page coloring may end up exposing an ABBA deadlock that is hidden by the usual optimistic lock stealing, and while the unfairness doesn't fix the fundamental issue (and I'm still looking at that), it avoids it in practice. The amount of unfairness can be modified by writing a new value to the 'sysctl_page_lock_unfairness' variable (default value of 5, exposed through /proc/sys/vm/page_lock_unfairness), but that is hopefully something we'd use mainly for debugging rather than being necessary for any deep system tuning. This whole issue has exposed just how critical the page lock can be, and how contended it gets under certain locks. And the main contention doesn't really seem to be anything related to IO (which was the origin of this lock), but for things like just verifying that the page file mapping is stable while faulting in the page into a page table. Link: https://lore.kernel.org/linux-fsdevel/ed8442fd-6f54-dd84-cd4a-941e8b7ee603@MichaelLarabel.com/ Link: https://www.phoronix.com/scan.php?page=article&item=linux-50-59&num=1 Link: https://lore.kernel.org/linux-fsdevel/c560a38d-8313-51fb-b1ec-e904bd8836bc@tessares.net/ Reported-and-tested-by: Michael Larabel <Michael@michaellarabel.com> Tested-by: Matthieu Baerts <matthieu.baerts@tessares.net> Cc: Dave Chinner <david@fromorbit.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Chris Mason <clm@fb.com> Cc: Jan Kara <jack@suse.cz> Cc: Amir Goldstein <amir73il@gmail.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-09-13 21:05:35 +00:00
* if successful.
*/
static inline bool folio_trylock_flag(struct folio *folio, int bit_nr,
struct wait_queue_entry *wait)
{
if (wait->flags & WQ_FLAG_EXCLUSIVE) {
if (test_and_set_bit(bit_nr, &folio->flags))
return false;
} else if (test_bit(bit_nr, &folio->flags))
return false;
mm: allow a controlled amount of unfairness in the page lock Commit 2a9127fcf229 ("mm: rewrite wait_on_page_bit_common() logic") made the page locking entirely fair, in that if a waiter came in while the lock was held, the lock would be transferred to the lockers strictly in order. That was intended to finally get rid of the long-reported watchdog failures that involved the page lock under extreme load, where a process could end up waiting essentially forever, as other page lockers stole the lock from under it. It also improved some benchmarks, but it ended up causing huge performance regressions on others, simply because fair lock behavior doesn't end up giving out the lock as aggressively, causing better worst-case latency, but potentially much worse average latencies and throughput. Instead of reverting that change entirely, this introduces a controlled amount of unfairness, with a sysctl knob to tune it if somebody needs to. But the default value should hopefully be good for any normal load, allowing a few rounds of lock stealing, but enforcing the strict ordering before the lock has been stolen too many times. There is also a hint from Matthieu Baerts that the fair page coloring may end up exposing an ABBA deadlock that is hidden by the usual optimistic lock stealing, and while the unfairness doesn't fix the fundamental issue (and I'm still looking at that), it avoids it in practice. The amount of unfairness can be modified by writing a new value to the 'sysctl_page_lock_unfairness' variable (default value of 5, exposed through /proc/sys/vm/page_lock_unfairness), but that is hopefully something we'd use mainly for debugging rather than being necessary for any deep system tuning. This whole issue has exposed just how critical the page lock can be, and how contended it gets under certain locks. And the main contention doesn't really seem to be anything related to IO (which was the origin of this lock), but for things like just verifying that the page file mapping is stable while faulting in the page into a page table. Link: https://lore.kernel.org/linux-fsdevel/ed8442fd-6f54-dd84-cd4a-941e8b7ee603@MichaelLarabel.com/ Link: https://www.phoronix.com/scan.php?page=article&item=linux-50-59&num=1 Link: https://lore.kernel.org/linux-fsdevel/c560a38d-8313-51fb-b1ec-e904bd8836bc@tessares.net/ Reported-and-tested-by: Michael Larabel <Michael@michaellarabel.com> Tested-by: Matthieu Baerts <matthieu.baerts@tessares.net> Cc: Dave Chinner <david@fromorbit.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Chris Mason <clm@fb.com> Cc: Jan Kara <jack@suse.cz> Cc: Amir Goldstein <amir73il@gmail.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-09-13 21:05:35 +00:00
wait->flags |= WQ_FLAG_WOKEN | WQ_FLAG_DONE;
return true;
}
mm: allow a controlled amount of unfairness in the page lock Commit 2a9127fcf229 ("mm: rewrite wait_on_page_bit_common() logic") made the page locking entirely fair, in that if a waiter came in while the lock was held, the lock would be transferred to the lockers strictly in order. That was intended to finally get rid of the long-reported watchdog failures that involved the page lock under extreme load, where a process could end up waiting essentially forever, as other page lockers stole the lock from under it. It also improved some benchmarks, but it ended up causing huge performance regressions on others, simply because fair lock behavior doesn't end up giving out the lock as aggressively, causing better worst-case latency, but potentially much worse average latencies and throughput. Instead of reverting that change entirely, this introduces a controlled amount of unfairness, with a sysctl knob to tune it if somebody needs to. But the default value should hopefully be good for any normal load, allowing a few rounds of lock stealing, but enforcing the strict ordering before the lock has been stolen too many times. There is also a hint from Matthieu Baerts that the fair page coloring may end up exposing an ABBA deadlock that is hidden by the usual optimistic lock stealing, and while the unfairness doesn't fix the fundamental issue (and I'm still looking at that), it avoids it in practice. The amount of unfairness can be modified by writing a new value to the 'sysctl_page_lock_unfairness' variable (default value of 5, exposed through /proc/sys/vm/page_lock_unfairness), but that is hopefully something we'd use mainly for debugging rather than being necessary for any deep system tuning. This whole issue has exposed just how critical the page lock can be, and how contended it gets under certain locks. And the main contention doesn't really seem to be anything related to IO (which was the origin of this lock), but for things like just verifying that the page file mapping is stable while faulting in the page into a page table. Link: https://lore.kernel.org/linux-fsdevel/ed8442fd-6f54-dd84-cd4a-941e8b7ee603@MichaelLarabel.com/ Link: https://www.phoronix.com/scan.php?page=article&item=linux-50-59&num=1 Link: https://lore.kernel.org/linux-fsdevel/c560a38d-8313-51fb-b1ec-e904bd8836bc@tessares.net/ Reported-and-tested-by: Michael Larabel <Michael@michaellarabel.com> Tested-by: Matthieu Baerts <matthieu.baerts@tessares.net> Cc: Dave Chinner <david@fromorbit.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Chris Mason <clm@fb.com> Cc: Jan Kara <jack@suse.cz> Cc: Amir Goldstein <amir73il@gmail.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-09-13 21:05:35 +00:00
/* How many times do we accept lock stealing from under a waiter? */
int sysctl_page_lock_unfairness = 5;
static inline int folio_wait_bit_common(struct folio *folio, int bit_nr,
int state, enum behavior behavior)
2016-12-25 03:00:30 +00:00
{
wait_queue_head_t *q = folio_waitqueue(folio);
mm: allow a controlled amount of unfairness in the page lock Commit 2a9127fcf229 ("mm: rewrite wait_on_page_bit_common() logic") made the page locking entirely fair, in that if a waiter came in while the lock was held, the lock would be transferred to the lockers strictly in order. That was intended to finally get rid of the long-reported watchdog failures that involved the page lock under extreme load, where a process could end up waiting essentially forever, as other page lockers stole the lock from under it. It also improved some benchmarks, but it ended up causing huge performance regressions on others, simply because fair lock behavior doesn't end up giving out the lock as aggressively, causing better worst-case latency, but potentially much worse average latencies and throughput. Instead of reverting that change entirely, this introduces a controlled amount of unfairness, with a sysctl knob to tune it if somebody needs to. But the default value should hopefully be good for any normal load, allowing a few rounds of lock stealing, but enforcing the strict ordering before the lock has been stolen too many times. There is also a hint from Matthieu Baerts that the fair page coloring may end up exposing an ABBA deadlock that is hidden by the usual optimistic lock stealing, and while the unfairness doesn't fix the fundamental issue (and I'm still looking at that), it avoids it in practice. The amount of unfairness can be modified by writing a new value to the 'sysctl_page_lock_unfairness' variable (default value of 5, exposed through /proc/sys/vm/page_lock_unfairness), but that is hopefully something we'd use mainly for debugging rather than being necessary for any deep system tuning. This whole issue has exposed just how critical the page lock can be, and how contended it gets under certain locks. And the main contention doesn't really seem to be anything related to IO (which was the origin of this lock), but for things like just verifying that the page file mapping is stable while faulting in the page into a page table. Link: https://lore.kernel.org/linux-fsdevel/ed8442fd-6f54-dd84-cd4a-941e8b7ee603@MichaelLarabel.com/ Link: https://www.phoronix.com/scan.php?page=article&item=linux-50-59&num=1 Link: https://lore.kernel.org/linux-fsdevel/c560a38d-8313-51fb-b1ec-e904bd8836bc@tessares.net/ Reported-and-tested-by: Michael Larabel <Michael@michaellarabel.com> Tested-by: Matthieu Baerts <matthieu.baerts@tessares.net> Cc: Dave Chinner <david@fromorbit.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Chris Mason <clm@fb.com> Cc: Jan Kara <jack@suse.cz> Cc: Amir Goldstein <amir73il@gmail.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-09-13 21:05:35 +00:00
int unfairness = sysctl_page_lock_unfairness;
2016-12-25 03:00:30 +00:00
struct wait_page_queue wait_page;
wait_queue_entry_t *wait = &wait_page.wait;
delayacct: track delays from thrashing cache pages Delay accounting already measures the time a task spends in direct reclaim and waiting for swapin, but in low memory situations tasks spend can spend a significant amount of their time waiting on thrashing page cache. This isn't tracked right now. To know the full impact of memory contention on an individual task, measure the delay when waiting for a recently evicted active cache page to read back into memory. Also update tools/accounting/getdelays.c: [hannes@computer accounting]$ sudo ./getdelays -d -p 1 print delayacct stats ON PID 1 CPU count real total virtual total delay total delay average 50318 745000000 847346785 400533713 0.008ms IO count delay total delay average 435 122601218 0ms SWAP count delay total delay average 0 0 0ms RECLAIM count delay total delay average 0 0 0ms THRASHING count delay total delay average 19 12621439 0ms Link: http://lkml.kernel.org/r/20180828172258.3185-4-hannes@cmpxchg.org Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Tested-by: Daniel Drake <drake@endlessm.com> Tested-by: Suren Baghdasaryan <surenb@google.com> Cc: Christopher Lameter <cl@linux.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Johannes Weiner <jweiner@fb.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Enderborg <peter.enderborg@sony.com> Cc: Randy Dunlap <rdunlap@infradead.org> Cc: Shakeel Butt <shakeelb@google.com> Cc: Tejun Heo <tj@kernel.org> Cc: Vinayak Menon <vinmenon@codeaurora.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-10-26 22:06:08 +00:00
bool thrashing = false;
psi: pressure stall information for CPU, memory, and IO When systems are overcommitted and resources become contended, it's hard to tell exactly the impact this has on workload productivity, or how close the system is to lockups and OOM kills. In particular, when machines work multiple jobs concurrently, the impact of overcommit in terms of latency and throughput on the individual job can be enormous. In order to maximize hardware utilization without sacrificing individual job health or risk complete machine lockups, this patch implements a way to quantify resource pressure in the system. A kernel built with CONFIG_PSI=y creates files in /proc/pressure/ that expose the percentage of time the system is stalled on CPU, memory, or IO, respectively. Stall states are aggregate versions of the per-task delay accounting delays: cpu: some tasks are runnable but not executing on a CPU memory: tasks are reclaiming, or waiting for swapin or thrashing cache io: tasks are waiting for io completions These percentages of walltime can be thought of as pressure percentages, and they give a general sense of system health and productivity loss incurred by resource overcommit. They can also indicate when the system is approaching lockup scenarios and OOMs. To do this, psi keeps track of the task states associated with each CPU and samples the time they spend in stall states. Every 2 seconds, the samples are averaged across CPUs - weighted by the CPUs' non-idle time to eliminate artifacts from unused CPUs - and translated into percentages of walltime. A running average of those percentages is maintained over 10s, 1m, and 5m periods (similar to the loadaverage). [hannes@cmpxchg.org: doc fixlet, per Randy] Link: http://lkml.kernel.org/r/20180828205625.GA14030@cmpxchg.org [hannes@cmpxchg.org: code optimization] Link: http://lkml.kernel.org/r/20180907175015.GA8479@cmpxchg.org [hannes@cmpxchg.org: rename psi_clock() to psi_update_work(), per Peter] Link: http://lkml.kernel.org/r/20180907145404.GB11088@cmpxchg.org [hannes@cmpxchg.org: fix build] Link: http://lkml.kernel.org/r/20180913014222.GA2370@cmpxchg.org Link: http://lkml.kernel.org/r/20180828172258.3185-9-hannes@cmpxchg.org Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Tested-by: Daniel Drake <drake@endlessm.com> Tested-by: Suren Baghdasaryan <surenb@google.com> Cc: Christopher Lameter <cl@linux.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Johannes Weiner <jweiner@fb.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Enderborg <peter.enderborg@sony.com> Cc: Randy Dunlap <rdunlap@infradead.org> Cc: Shakeel Butt <shakeelb@google.com> Cc: Tejun Heo <tj@kernel.org> Cc: Vinayak Menon <vinmenon@codeaurora.org> Cc: Randy Dunlap <rdunlap@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-10-26 22:06:27 +00:00
unsigned long pflags;
bool in_thrashing;
2016-12-25 03:00:30 +00:00
psi: pressure stall information for CPU, memory, and IO When systems are overcommitted and resources become contended, it's hard to tell exactly the impact this has on workload productivity, or how close the system is to lockups and OOM kills. In particular, when machines work multiple jobs concurrently, the impact of overcommit in terms of latency and throughput on the individual job can be enormous. In order to maximize hardware utilization without sacrificing individual job health or risk complete machine lockups, this patch implements a way to quantify resource pressure in the system. A kernel built with CONFIG_PSI=y creates files in /proc/pressure/ that expose the percentage of time the system is stalled on CPU, memory, or IO, respectively. Stall states are aggregate versions of the per-task delay accounting delays: cpu: some tasks are runnable but not executing on a CPU memory: tasks are reclaiming, or waiting for swapin or thrashing cache io: tasks are waiting for io completions These percentages of walltime can be thought of as pressure percentages, and they give a general sense of system health and productivity loss incurred by resource overcommit. They can also indicate when the system is approaching lockup scenarios and OOMs. To do this, psi keeps track of the task states associated with each CPU and samples the time they spend in stall states. Every 2 seconds, the samples are averaged across CPUs - weighted by the CPUs' non-idle time to eliminate artifacts from unused CPUs - and translated into percentages of walltime. A running average of those percentages is maintained over 10s, 1m, and 5m periods (similar to the loadaverage). [hannes@cmpxchg.org: doc fixlet, per Randy] Link: http://lkml.kernel.org/r/20180828205625.GA14030@cmpxchg.org [hannes@cmpxchg.org: code optimization] Link: http://lkml.kernel.org/r/20180907175015.GA8479@cmpxchg.org [hannes@cmpxchg.org: rename psi_clock() to psi_update_work(), per Peter] Link: http://lkml.kernel.org/r/20180907145404.GB11088@cmpxchg.org [hannes@cmpxchg.org: fix build] Link: http://lkml.kernel.org/r/20180913014222.GA2370@cmpxchg.org Link: http://lkml.kernel.org/r/20180828172258.3185-9-hannes@cmpxchg.org Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Tested-by: Daniel Drake <drake@endlessm.com> Tested-by: Suren Baghdasaryan <surenb@google.com> Cc: Christopher Lameter <cl@linux.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Johannes Weiner <jweiner@fb.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Enderborg <peter.enderborg@sony.com> Cc: Randy Dunlap <rdunlap@infradead.org> Cc: Shakeel Butt <shakeelb@google.com> Cc: Tejun Heo <tj@kernel.org> Cc: Vinayak Menon <vinmenon@codeaurora.org> Cc: Randy Dunlap <rdunlap@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-10-26 22:06:27 +00:00
if (bit_nr == PG_locked &&
!folio_test_uptodate(folio) && folio_test_workingset(folio)) {
delayacct_thrashing_start(&in_thrashing);
psi: pressure stall information for CPU, memory, and IO When systems are overcommitted and resources become contended, it's hard to tell exactly the impact this has on workload productivity, or how close the system is to lockups and OOM kills. In particular, when machines work multiple jobs concurrently, the impact of overcommit in terms of latency and throughput on the individual job can be enormous. In order to maximize hardware utilization without sacrificing individual job health or risk complete machine lockups, this patch implements a way to quantify resource pressure in the system. A kernel built with CONFIG_PSI=y creates files in /proc/pressure/ that expose the percentage of time the system is stalled on CPU, memory, or IO, respectively. Stall states are aggregate versions of the per-task delay accounting delays: cpu: some tasks are runnable but not executing on a CPU memory: tasks are reclaiming, or waiting for swapin or thrashing cache io: tasks are waiting for io completions These percentages of walltime can be thought of as pressure percentages, and they give a general sense of system health and productivity loss incurred by resource overcommit. They can also indicate when the system is approaching lockup scenarios and OOMs. To do this, psi keeps track of the task states associated with each CPU and samples the time they spend in stall states. Every 2 seconds, the samples are averaged across CPUs - weighted by the CPUs' non-idle time to eliminate artifacts from unused CPUs - and translated into percentages of walltime. A running average of those percentages is maintained over 10s, 1m, and 5m periods (similar to the loadaverage). [hannes@cmpxchg.org: doc fixlet, per Randy] Link: http://lkml.kernel.org/r/20180828205625.GA14030@cmpxchg.org [hannes@cmpxchg.org: code optimization] Link: http://lkml.kernel.org/r/20180907175015.GA8479@cmpxchg.org [hannes@cmpxchg.org: rename psi_clock() to psi_update_work(), per Peter] Link: http://lkml.kernel.org/r/20180907145404.GB11088@cmpxchg.org [hannes@cmpxchg.org: fix build] Link: http://lkml.kernel.org/r/20180913014222.GA2370@cmpxchg.org Link: http://lkml.kernel.org/r/20180828172258.3185-9-hannes@cmpxchg.org Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Tested-by: Daniel Drake <drake@endlessm.com> Tested-by: Suren Baghdasaryan <surenb@google.com> Cc: Christopher Lameter <cl@linux.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Johannes Weiner <jweiner@fb.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Enderborg <peter.enderborg@sony.com> Cc: Randy Dunlap <rdunlap@infradead.org> Cc: Shakeel Butt <shakeelb@google.com> Cc: Tejun Heo <tj@kernel.org> Cc: Vinayak Menon <vinmenon@codeaurora.org> Cc: Randy Dunlap <rdunlap@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-10-26 22:06:27 +00:00
psi_memstall_enter(&pflags);
delayacct: track delays from thrashing cache pages Delay accounting already measures the time a task spends in direct reclaim and waiting for swapin, but in low memory situations tasks spend can spend a significant amount of their time waiting on thrashing page cache. This isn't tracked right now. To know the full impact of memory contention on an individual task, measure the delay when waiting for a recently evicted active cache page to read back into memory. Also update tools/accounting/getdelays.c: [hannes@computer accounting]$ sudo ./getdelays -d -p 1 print delayacct stats ON PID 1 CPU count real total virtual total delay total delay average 50318 745000000 847346785 400533713 0.008ms IO count delay total delay average 435 122601218 0ms SWAP count delay total delay average 0 0 0ms RECLAIM count delay total delay average 0 0 0ms THRASHING count delay total delay average 19 12621439 0ms Link: http://lkml.kernel.org/r/20180828172258.3185-4-hannes@cmpxchg.org Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Tested-by: Daniel Drake <drake@endlessm.com> Tested-by: Suren Baghdasaryan <surenb@google.com> Cc: Christopher Lameter <cl@linux.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Johannes Weiner <jweiner@fb.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Enderborg <peter.enderborg@sony.com> Cc: Randy Dunlap <rdunlap@infradead.org> Cc: Shakeel Butt <shakeelb@google.com> Cc: Tejun Heo <tj@kernel.org> Cc: Vinayak Menon <vinmenon@codeaurora.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-10-26 22:06:08 +00:00
thrashing = true;
}
2016-12-25 03:00:30 +00:00
init_wait(wait);
wait->func = wake_page_function;
wait_page.folio = folio;
2016-12-25 03:00:30 +00:00
wait_page.bit_nr = bit_nr;
mm: allow a controlled amount of unfairness in the page lock Commit 2a9127fcf229 ("mm: rewrite wait_on_page_bit_common() logic") made the page locking entirely fair, in that if a waiter came in while the lock was held, the lock would be transferred to the lockers strictly in order. That was intended to finally get rid of the long-reported watchdog failures that involved the page lock under extreme load, where a process could end up waiting essentially forever, as other page lockers stole the lock from under it. It also improved some benchmarks, but it ended up causing huge performance regressions on others, simply because fair lock behavior doesn't end up giving out the lock as aggressively, causing better worst-case latency, but potentially much worse average latencies and throughput. Instead of reverting that change entirely, this introduces a controlled amount of unfairness, with a sysctl knob to tune it if somebody needs to. But the default value should hopefully be good for any normal load, allowing a few rounds of lock stealing, but enforcing the strict ordering before the lock has been stolen too many times. There is also a hint from Matthieu Baerts that the fair page coloring may end up exposing an ABBA deadlock that is hidden by the usual optimistic lock stealing, and while the unfairness doesn't fix the fundamental issue (and I'm still looking at that), it avoids it in practice. The amount of unfairness can be modified by writing a new value to the 'sysctl_page_lock_unfairness' variable (default value of 5, exposed through /proc/sys/vm/page_lock_unfairness), but that is hopefully something we'd use mainly for debugging rather than being necessary for any deep system tuning. This whole issue has exposed just how critical the page lock can be, and how contended it gets under certain locks. And the main contention doesn't really seem to be anything related to IO (which was the origin of this lock), but for things like just verifying that the page file mapping is stable while faulting in the page into a page table. Link: https://lore.kernel.org/linux-fsdevel/ed8442fd-6f54-dd84-cd4a-941e8b7ee603@MichaelLarabel.com/ Link: https://www.phoronix.com/scan.php?page=article&item=linux-50-59&num=1 Link: https://lore.kernel.org/linux-fsdevel/c560a38d-8313-51fb-b1ec-e904bd8836bc@tessares.net/ Reported-and-tested-by: Michael Larabel <Michael@michaellarabel.com> Tested-by: Matthieu Baerts <matthieu.baerts@tessares.net> Cc: Dave Chinner <david@fromorbit.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Chris Mason <clm@fb.com> Cc: Jan Kara <jack@suse.cz> Cc: Amir Goldstein <amir73il@gmail.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-09-13 21:05:35 +00:00
repeat:
wait->flags = 0;
if (behavior == EXCLUSIVE) {
wait->flags = WQ_FLAG_EXCLUSIVE;
if (--unfairness < 0)
wait->flags |= WQ_FLAG_CUSTOM;
}
/*
* Do one last check whether we can get the
* page bit synchronously.
*
* Do the folio_set_waiters() marking before that
* to let any waker we _just_ missed know they
* need to wake us up (otherwise they'll never
* even go to the slow case that looks at the
* page queue), and add ourselves to the wait
* queue if we need to sleep.
*
* This part needs to be done under the queue
* lock to avoid races.
*/
spin_lock_irq(&q->lock);
folio_set_waiters(folio);
if (!folio_trylock_flag(folio, bit_nr, wait))
__add_wait_queue_entry_tail(q, wait);
spin_unlock_irq(&q->lock);
2016-12-25 03:00:30 +00:00
/*
* From now on, all the logic will be based on
mm: allow a controlled amount of unfairness in the page lock Commit 2a9127fcf229 ("mm: rewrite wait_on_page_bit_common() logic") made the page locking entirely fair, in that if a waiter came in while the lock was held, the lock would be transferred to the lockers strictly in order. That was intended to finally get rid of the long-reported watchdog failures that involved the page lock under extreme load, where a process could end up waiting essentially forever, as other page lockers stole the lock from under it. It also improved some benchmarks, but it ended up causing huge performance regressions on others, simply because fair lock behavior doesn't end up giving out the lock as aggressively, causing better worst-case latency, but potentially much worse average latencies and throughput. Instead of reverting that change entirely, this introduces a controlled amount of unfairness, with a sysctl knob to tune it if somebody needs to. But the default value should hopefully be good for any normal load, allowing a few rounds of lock stealing, but enforcing the strict ordering before the lock has been stolen too many times. There is also a hint from Matthieu Baerts that the fair page coloring may end up exposing an ABBA deadlock that is hidden by the usual optimistic lock stealing, and while the unfairness doesn't fix the fundamental issue (and I'm still looking at that), it avoids it in practice. The amount of unfairness can be modified by writing a new value to the 'sysctl_page_lock_unfairness' variable (default value of 5, exposed through /proc/sys/vm/page_lock_unfairness), but that is hopefully something we'd use mainly for debugging rather than being necessary for any deep system tuning. This whole issue has exposed just how critical the page lock can be, and how contended it gets under certain locks. And the main contention doesn't really seem to be anything related to IO (which was the origin of this lock), but for things like just verifying that the page file mapping is stable while faulting in the page into a page table. Link: https://lore.kernel.org/linux-fsdevel/ed8442fd-6f54-dd84-cd4a-941e8b7ee603@MichaelLarabel.com/ Link: https://www.phoronix.com/scan.php?page=article&item=linux-50-59&num=1 Link: https://lore.kernel.org/linux-fsdevel/c560a38d-8313-51fb-b1ec-e904bd8836bc@tessares.net/ Reported-and-tested-by: Michael Larabel <Michael@michaellarabel.com> Tested-by: Matthieu Baerts <matthieu.baerts@tessares.net> Cc: Dave Chinner <david@fromorbit.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Chris Mason <clm@fb.com> Cc: Jan Kara <jack@suse.cz> Cc: Amir Goldstein <amir73il@gmail.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-09-13 21:05:35 +00:00
* the WQ_FLAG_WOKEN and WQ_FLAG_DONE flag, to
* see whether the page bit testing has already
* been done by the wake function.
*
* We can drop our reference to the folio.
*/
if (behavior == DROP)
folio_put(folio);
2016-12-25 03:00:30 +00:00
mm: allow a controlled amount of unfairness in the page lock Commit 2a9127fcf229 ("mm: rewrite wait_on_page_bit_common() logic") made the page locking entirely fair, in that if a waiter came in while the lock was held, the lock would be transferred to the lockers strictly in order. That was intended to finally get rid of the long-reported watchdog failures that involved the page lock under extreme load, where a process could end up waiting essentially forever, as other page lockers stole the lock from under it. It also improved some benchmarks, but it ended up causing huge performance regressions on others, simply because fair lock behavior doesn't end up giving out the lock as aggressively, causing better worst-case latency, but potentially much worse average latencies and throughput. Instead of reverting that change entirely, this introduces a controlled amount of unfairness, with a sysctl knob to tune it if somebody needs to. But the default value should hopefully be good for any normal load, allowing a few rounds of lock stealing, but enforcing the strict ordering before the lock has been stolen too many times. There is also a hint from Matthieu Baerts that the fair page coloring may end up exposing an ABBA deadlock that is hidden by the usual optimistic lock stealing, and while the unfairness doesn't fix the fundamental issue (and I'm still looking at that), it avoids it in practice. The amount of unfairness can be modified by writing a new value to the 'sysctl_page_lock_unfairness' variable (default value of 5, exposed through /proc/sys/vm/page_lock_unfairness), but that is hopefully something we'd use mainly for debugging rather than being necessary for any deep system tuning. This whole issue has exposed just how critical the page lock can be, and how contended it gets under certain locks. And the main contention doesn't really seem to be anything related to IO (which was the origin of this lock), but for things like just verifying that the page file mapping is stable while faulting in the page into a page table. Link: https://lore.kernel.org/linux-fsdevel/ed8442fd-6f54-dd84-cd4a-941e8b7ee603@MichaelLarabel.com/ Link: https://www.phoronix.com/scan.php?page=article&item=linux-50-59&num=1 Link: https://lore.kernel.org/linux-fsdevel/c560a38d-8313-51fb-b1ec-e904bd8836bc@tessares.net/ Reported-and-tested-by: Michael Larabel <Michael@michaellarabel.com> Tested-by: Matthieu Baerts <matthieu.baerts@tessares.net> Cc: Dave Chinner <david@fromorbit.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Chris Mason <clm@fb.com> Cc: Jan Kara <jack@suse.cz> Cc: Amir Goldstein <amir73il@gmail.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-09-13 21:05:35 +00:00
/*
* Note that until the "finish_wait()", or until
* we see the WQ_FLAG_WOKEN flag, we need to
* be very careful with the 'wait->flags', because
* we may race with a waker that sets them.
*/
for (;;) {
mm: allow a controlled amount of unfairness in the page lock Commit 2a9127fcf229 ("mm: rewrite wait_on_page_bit_common() logic") made the page locking entirely fair, in that if a waiter came in while the lock was held, the lock would be transferred to the lockers strictly in order. That was intended to finally get rid of the long-reported watchdog failures that involved the page lock under extreme load, where a process could end up waiting essentially forever, as other page lockers stole the lock from under it. It also improved some benchmarks, but it ended up causing huge performance regressions on others, simply because fair lock behavior doesn't end up giving out the lock as aggressively, causing better worst-case latency, but potentially much worse average latencies and throughput. Instead of reverting that change entirely, this introduces a controlled amount of unfairness, with a sysctl knob to tune it if somebody needs to. But the default value should hopefully be good for any normal load, allowing a few rounds of lock stealing, but enforcing the strict ordering before the lock has been stolen too many times. There is also a hint from Matthieu Baerts that the fair page coloring may end up exposing an ABBA deadlock that is hidden by the usual optimistic lock stealing, and while the unfairness doesn't fix the fundamental issue (and I'm still looking at that), it avoids it in practice. The amount of unfairness can be modified by writing a new value to the 'sysctl_page_lock_unfairness' variable (default value of 5, exposed through /proc/sys/vm/page_lock_unfairness), but that is hopefully something we'd use mainly for debugging rather than being necessary for any deep system tuning. This whole issue has exposed just how critical the page lock can be, and how contended it gets under certain locks. And the main contention doesn't really seem to be anything related to IO (which was the origin of this lock), but for things like just verifying that the page file mapping is stable while faulting in the page into a page table. Link: https://lore.kernel.org/linux-fsdevel/ed8442fd-6f54-dd84-cd4a-941e8b7ee603@MichaelLarabel.com/ Link: https://www.phoronix.com/scan.php?page=article&item=linux-50-59&num=1 Link: https://lore.kernel.org/linux-fsdevel/c560a38d-8313-51fb-b1ec-e904bd8836bc@tessares.net/ Reported-and-tested-by: Michael Larabel <Michael@michaellarabel.com> Tested-by: Matthieu Baerts <matthieu.baerts@tessares.net> Cc: Dave Chinner <david@fromorbit.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Chris Mason <clm@fb.com> Cc: Jan Kara <jack@suse.cz> Cc: Amir Goldstein <amir73il@gmail.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-09-13 21:05:35 +00:00
unsigned int flags;
2016-12-25 03:00:30 +00:00
set_current_state(state);
mm: allow a controlled amount of unfairness in the page lock Commit 2a9127fcf229 ("mm: rewrite wait_on_page_bit_common() logic") made the page locking entirely fair, in that if a waiter came in while the lock was held, the lock would be transferred to the lockers strictly in order. That was intended to finally get rid of the long-reported watchdog failures that involved the page lock under extreme load, where a process could end up waiting essentially forever, as other page lockers stole the lock from under it. It also improved some benchmarks, but it ended up causing huge performance regressions on others, simply because fair lock behavior doesn't end up giving out the lock as aggressively, causing better worst-case latency, but potentially much worse average latencies and throughput. Instead of reverting that change entirely, this introduces a controlled amount of unfairness, with a sysctl knob to tune it if somebody needs to. But the default value should hopefully be good for any normal load, allowing a few rounds of lock stealing, but enforcing the strict ordering before the lock has been stolen too many times. There is also a hint from Matthieu Baerts that the fair page coloring may end up exposing an ABBA deadlock that is hidden by the usual optimistic lock stealing, and while the unfairness doesn't fix the fundamental issue (and I'm still looking at that), it avoids it in practice. The amount of unfairness can be modified by writing a new value to the 'sysctl_page_lock_unfairness' variable (default value of 5, exposed through /proc/sys/vm/page_lock_unfairness), but that is hopefully something we'd use mainly for debugging rather than being necessary for any deep system tuning. This whole issue has exposed just how critical the page lock can be, and how contended it gets under certain locks. And the main contention doesn't really seem to be anything related to IO (which was the origin of this lock), but for things like just verifying that the page file mapping is stable while faulting in the page into a page table. Link: https://lore.kernel.org/linux-fsdevel/ed8442fd-6f54-dd84-cd4a-941e8b7ee603@MichaelLarabel.com/ Link: https://www.phoronix.com/scan.php?page=article&item=linux-50-59&num=1 Link: https://lore.kernel.org/linux-fsdevel/c560a38d-8313-51fb-b1ec-e904bd8836bc@tessares.net/ Reported-and-tested-by: Michael Larabel <Michael@michaellarabel.com> Tested-by: Matthieu Baerts <matthieu.baerts@tessares.net> Cc: Dave Chinner <david@fromorbit.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Chris Mason <clm@fb.com> Cc: Jan Kara <jack@suse.cz> Cc: Amir Goldstein <amir73il@gmail.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-09-13 21:05:35 +00:00
/* Loop until we've been woken or interrupted */
flags = smp_load_acquire(&wait->flags);
if (!(flags & WQ_FLAG_WOKEN)) {
if (signal_pending_state(state, current))
break;
io_schedule();
continue;
}
/* If we were non-exclusive, we're done */
if (behavior != EXCLUSIVE)
2017-08-27 23:25:09 +00:00
break;
mm: put_and_wait_on_page_locked() while page is migrated Waiting on a page migration entry has used wait_on_page_locked() all along since 2006: but you cannot safely wait_on_page_locked() without holding a reference to the page, and that extra reference is enough to make migrate_page_move_mapping() fail with -EAGAIN, when a racing task faults on the entry before migrate_page_move_mapping() gets there. And that failure is retried nine times, amplifying the pain when trying to migrate a popular page. With a single persistent faulter, migration sometimes succeeds; with two or three concurrent faulters, success becomes much less likely (and the more the page was mapped, the worse the overhead of unmapping and remapping it on each try). This is especially a problem for memory offlining, where the outer level retries forever (or until terminated from userspace), because a heavy refault workload can trigger an endless loop of migration failures. wait_on_page_locked() is the wrong tool for the job. David Herrmann (but was he the first?) noticed this issue in 2014: https://marc.info/?l=linux-mm&m=140110465608116&w=2 Tim Chen started a thread in August 2017 which appears relevant: https://marc.info/?l=linux-mm&m=150275941014915&w=2 where Kan Liang went on to implicate __migration_entry_wait(): https://marc.info/?l=linux-mm&m=150300268411980&w=2 and the thread ended up with the v4.14 commits: 2554db916586 ("sched/wait: Break up long wake list walk") 11a19c7b099f ("sched/wait: Introduce wakeup boomark in wake_up_page_bit") Baoquan He reported "Memory hotplug softlock issue" 14 November 2018: https://marc.info/?l=linux-mm&m=154217936431300&w=2 We have all assumed that it is essential to hold a page reference while waiting on a page lock: partly to guarantee that there is still a struct page when MEMORY_HOTREMOVE is configured, but also to protect against reuse of the struct page going to someone who then holds the page locked indefinitely, when the waiter can reasonably expect timely unlocking. But in fact, so long as wait_on_page_bit_common() does the put_page(), and is careful not to rely on struct page contents thereafter, there is no need to hold a reference to the page while waiting on it. That does mean that this case cannot go back through the loop: but that's fine for the page migration case, and even if used more widely, is limited by the "Stop walking if it's locked" optimization in wake_page_function(). Add interface put_and_wait_on_page_locked() to do this, using "behavior" enum in place of "lock" arg to wait_on_page_bit_common() to implement it. No interruptible or killable variant needed yet, but they might follow: I have a vague notion that reporting -EINTR should take precedence over return from wait_on_page_bit_common() without knowing the page state, so arrange it accordingly - but that may be nothing but pedantic. __migration_entry_wait() still has to take a brief reference to the page, prior to calling put_and_wait_on_page_locked(): but now that it is dropped before waiting, the chance of impeding page migration is very much reduced. Should we perhaps disable preemption across this? shrink_page_list()'s __ClearPageLocked(): that was a surprise! This survived a lot of testing before that showed up. PageWaiters may have been set by wait_on_page_bit_common(), and the reference dropped, just before shrink_page_list() succeeds in freezing its last page reference: in such a case, unlock_page() must be used. Follow the suggestion from Michal Hocko, just revert a978d6f52106 ("mm: unlockless reclaim") now: that optimization predates PageWaiters, and won't buy much these days; but we can reinstate it for the !PageWaiters case if anyone notices. It does raise the question: should vmscan.c's is_page_cache_freeable() and __remove_mapping() now treat a PageWaiters page as if an extra reference were held? Perhaps, but I don't think it matters much, since shrink_page_list() already had to win its trylock_page(), so waiters are not very common there: I noticed no difference when trying the bigger change, and it's surely not needed while put_and_wait_on_page_locked() is only used for page migration. [willy@infradead.org: add put_and_wait_on_page_locked() kerneldoc] Link: http://lkml.kernel.org/r/alpine.LSU.2.11.1811261121330.1116@eggly.anvils Signed-off-by: Hugh Dickins <hughd@google.com> Reported-by: Baoquan He <bhe@redhat.com> Tested-by: Baoquan He <bhe@redhat.com> Reviewed-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Michal Hocko <mhocko@suse.com> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Matthew Wilcox <willy@infradead.org> Cc: Baoquan He <bhe@redhat.com> Cc: David Hildenbrand <david@redhat.com> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: David Herrmann <dh.herrmann@gmail.com> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Christoph Lameter <cl@linux.com> Cc: Nick Piggin <npiggin@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-12-28 08:36:14 +00:00
mm: allow a controlled amount of unfairness in the page lock Commit 2a9127fcf229 ("mm: rewrite wait_on_page_bit_common() logic") made the page locking entirely fair, in that if a waiter came in while the lock was held, the lock would be transferred to the lockers strictly in order. That was intended to finally get rid of the long-reported watchdog failures that involved the page lock under extreme load, where a process could end up waiting essentially forever, as other page lockers stole the lock from under it. It also improved some benchmarks, but it ended up causing huge performance regressions on others, simply because fair lock behavior doesn't end up giving out the lock as aggressively, causing better worst-case latency, but potentially much worse average latencies and throughput. Instead of reverting that change entirely, this introduces a controlled amount of unfairness, with a sysctl knob to tune it if somebody needs to. But the default value should hopefully be good for any normal load, allowing a few rounds of lock stealing, but enforcing the strict ordering before the lock has been stolen too many times. There is also a hint from Matthieu Baerts that the fair page coloring may end up exposing an ABBA deadlock that is hidden by the usual optimistic lock stealing, and while the unfairness doesn't fix the fundamental issue (and I'm still looking at that), it avoids it in practice. The amount of unfairness can be modified by writing a new value to the 'sysctl_page_lock_unfairness' variable (default value of 5, exposed through /proc/sys/vm/page_lock_unfairness), but that is hopefully something we'd use mainly for debugging rather than being necessary for any deep system tuning. This whole issue has exposed just how critical the page lock can be, and how contended it gets under certain locks. And the main contention doesn't really seem to be anything related to IO (which was the origin of this lock), but for things like just verifying that the page file mapping is stable while faulting in the page into a page table. Link: https://lore.kernel.org/linux-fsdevel/ed8442fd-6f54-dd84-cd4a-941e8b7ee603@MichaelLarabel.com/ Link: https://www.phoronix.com/scan.php?page=article&item=linux-50-59&num=1 Link: https://lore.kernel.org/linux-fsdevel/c560a38d-8313-51fb-b1ec-e904bd8836bc@tessares.net/ Reported-and-tested-by: Michael Larabel <Michael@michaellarabel.com> Tested-by: Matthieu Baerts <matthieu.baerts@tessares.net> Cc: Dave Chinner <david@fromorbit.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Chris Mason <clm@fb.com> Cc: Jan Kara <jack@suse.cz> Cc: Amir Goldstein <amir73il@gmail.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-09-13 21:05:35 +00:00
/* If the waker got the lock for us, we're done */
if (flags & WQ_FLAG_DONE)
mm: put_and_wait_on_page_locked() while page is migrated Waiting on a page migration entry has used wait_on_page_locked() all along since 2006: but you cannot safely wait_on_page_locked() without holding a reference to the page, and that extra reference is enough to make migrate_page_move_mapping() fail with -EAGAIN, when a racing task faults on the entry before migrate_page_move_mapping() gets there. And that failure is retried nine times, amplifying the pain when trying to migrate a popular page. With a single persistent faulter, migration sometimes succeeds; with two or three concurrent faulters, success becomes much less likely (and the more the page was mapped, the worse the overhead of unmapping and remapping it on each try). This is especially a problem for memory offlining, where the outer level retries forever (or until terminated from userspace), because a heavy refault workload can trigger an endless loop of migration failures. wait_on_page_locked() is the wrong tool for the job. David Herrmann (but was he the first?) noticed this issue in 2014: https://marc.info/?l=linux-mm&m=140110465608116&w=2 Tim Chen started a thread in August 2017 which appears relevant: https://marc.info/?l=linux-mm&m=150275941014915&w=2 where Kan Liang went on to implicate __migration_entry_wait(): https://marc.info/?l=linux-mm&m=150300268411980&w=2 and the thread ended up with the v4.14 commits: 2554db916586 ("sched/wait: Break up long wake list walk") 11a19c7b099f ("sched/wait: Introduce wakeup boomark in wake_up_page_bit") Baoquan He reported "Memory hotplug softlock issue" 14 November 2018: https://marc.info/?l=linux-mm&m=154217936431300&w=2 We have all assumed that it is essential to hold a page reference while waiting on a page lock: partly to guarantee that there is still a struct page when MEMORY_HOTREMOVE is configured, but also to protect against reuse of the struct page going to someone who then holds the page locked indefinitely, when the waiter can reasonably expect timely unlocking. But in fact, so long as wait_on_page_bit_common() does the put_page(), and is careful not to rely on struct page contents thereafter, there is no need to hold a reference to the page while waiting on it. That does mean that this case cannot go back through the loop: but that's fine for the page migration case, and even if used more widely, is limited by the "Stop walking if it's locked" optimization in wake_page_function(). Add interface put_and_wait_on_page_locked() to do this, using "behavior" enum in place of "lock" arg to wait_on_page_bit_common() to implement it. No interruptible or killable variant needed yet, but they might follow: I have a vague notion that reporting -EINTR should take precedence over return from wait_on_page_bit_common() without knowing the page state, so arrange it accordingly - but that may be nothing but pedantic. __migration_entry_wait() still has to take a brief reference to the page, prior to calling put_and_wait_on_page_locked(): but now that it is dropped before waiting, the chance of impeding page migration is very much reduced. Should we perhaps disable preemption across this? shrink_page_list()'s __ClearPageLocked(): that was a surprise! This survived a lot of testing before that showed up. PageWaiters may have been set by wait_on_page_bit_common(), and the reference dropped, just before shrink_page_list() succeeds in freezing its last page reference: in such a case, unlock_page() must be used. Follow the suggestion from Michal Hocko, just revert a978d6f52106 ("mm: unlockless reclaim") now: that optimization predates PageWaiters, and won't buy much these days; but we can reinstate it for the !PageWaiters case if anyone notices. It does raise the question: should vmscan.c's is_page_cache_freeable() and __remove_mapping() now treat a PageWaiters page as if an extra reference were held? Perhaps, but I don't think it matters much, since shrink_page_list() already had to win its trylock_page(), so waiters are not very common there: I noticed no difference when trying the bigger change, and it's surely not needed while put_and_wait_on_page_locked() is only used for page migration. [willy@infradead.org: add put_and_wait_on_page_locked() kerneldoc] Link: http://lkml.kernel.org/r/alpine.LSU.2.11.1811261121330.1116@eggly.anvils Signed-off-by: Hugh Dickins <hughd@google.com> Reported-by: Baoquan He <bhe@redhat.com> Tested-by: Baoquan He <bhe@redhat.com> Reviewed-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Michal Hocko <mhocko@suse.com> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Matthew Wilcox <willy@infradead.org> Cc: Baoquan He <bhe@redhat.com> Cc: David Hildenbrand <david@redhat.com> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: David Herrmann <dh.herrmann@gmail.com> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Christoph Lameter <cl@linux.com> Cc: Nick Piggin <npiggin@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-12-28 08:36:14 +00:00
break;
mm: allow a controlled amount of unfairness in the page lock Commit 2a9127fcf229 ("mm: rewrite wait_on_page_bit_common() logic") made the page locking entirely fair, in that if a waiter came in while the lock was held, the lock would be transferred to the lockers strictly in order. That was intended to finally get rid of the long-reported watchdog failures that involved the page lock under extreme load, where a process could end up waiting essentially forever, as other page lockers stole the lock from under it. It also improved some benchmarks, but it ended up causing huge performance regressions on others, simply because fair lock behavior doesn't end up giving out the lock as aggressively, causing better worst-case latency, but potentially much worse average latencies and throughput. Instead of reverting that change entirely, this introduces a controlled amount of unfairness, with a sysctl knob to tune it if somebody needs to. But the default value should hopefully be good for any normal load, allowing a few rounds of lock stealing, but enforcing the strict ordering before the lock has been stolen too many times. There is also a hint from Matthieu Baerts that the fair page coloring may end up exposing an ABBA deadlock that is hidden by the usual optimistic lock stealing, and while the unfairness doesn't fix the fundamental issue (and I'm still looking at that), it avoids it in practice. The amount of unfairness can be modified by writing a new value to the 'sysctl_page_lock_unfairness' variable (default value of 5, exposed through /proc/sys/vm/page_lock_unfairness), but that is hopefully something we'd use mainly for debugging rather than being necessary for any deep system tuning. This whole issue has exposed just how critical the page lock can be, and how contended it gets under certain locks. And the main contention doesn't really seem to be anything related to IO (which was the origin of this lock), but for things like just verifying that the page file mapping is stable while faulting in the page into a page table. Link: https://lore.kernel.org/linux-fsdevel/ed8442fd-6f54-dd84-cd4a-941e8b7ee603@MichaelLarabel.com/ Link: https://www.phoronix.com/scan.php?page=article&item=linux-50-59&num=1 Link: https://lore.kernel.org/linux-fsdevel/c560a38d-8313-51fb-b1ec-e904bd8836bc@tessares.net/ Reported-and-tested-by: Michael Larabel <Michael@michaellarabel.com> Tested-by: Matthieu Baerts <matthieu.baerts@tessares.net> Cc: Dave Chinner <david@fromorbit.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Chris Mason <clm@fb.com> Cc: Jan Kara <jack@suse.cz> Cc: Amir Goldstein <amir73il@gmail.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-09-13 21:05:35 +00:00
/*
* Otherwise, if we're getting the lock, we need to
* try to get it ourselves.
*
* And if that fails, we'll have to retry this all.
*/
if (unlikely(test_and_set_bit(bit_nr, folio_flags(folio, 0))))
mm: allow a controlled amount of unfairness in the page lock Commit 2a9127fcf229 ("mm: rewrite wait_on_page_bit_common() logic") made the page locking entirely fair, in that if a waiter came in while the lock was held, the lock would be transferred to the lockers strictly in order. That was intended to finally get rid of the long-reported watchdog failures that involved the page lock under extreme load, where a process could end up waiting essentially forever, as other page lockers stole the lock from under it. It also improved some benchmarks, but it ended up causing huge performance regressions on others, simply because fair lock behavior doesn't end up giving out the lock as aggressively, causing better worst-case latency, but potentially much worse average latencies and throughput. Instead of reverting that change entirely, this introduces a controlled amount of unfairness, with a sysctl knob to tune it if somebody needs to. But the default value should hopefully be good for any normal load, allowing a few rounds of lock stealing, but enforcing the strict ordering before the lock has been stolen too many times. There is also a hint from Matthieu Baerts that the fair page coloring may end up exposing an ABBA deadlock that is hidden by the usual optimistic lock stealing, and while the unfairness doesn't fix the fundamental issue (and I'm still looking at that), it avoids it in practice. The amount of unfairness can be modified by writing a new value to the 'sysctl_page_lock_unfairness' variable (default value of 5, exposed through /proc/sys/vm/page_lock_unfairness), but that is hopefully something we'd use mainly for debugging rather than being necessary for any deep system tuning. This whole issue has exposed just how critical the page lock can be, and how contended it gets under certain locks. And the main contention doesn't really seem to be anything related to IO (which was the origin of this lock), but for things like just verifying that the page file mapping is stable while faulting in the page into a page table. Link: https://lore.kernel.org/linux-fsdevel/ed8442fd-6f54-dd84-cd4a-941e8b7ee603@MichaelLarabel.com/ Link: https://www.phoronix.com/scan.php?page=article&item=linux-50-59&num=1 Link: https://lore.kernel.org/linux-fsdevel/c560a38d-8313-51fb-b1ec-e904bd8836bc@tessares.net/ Reported-and-tested-by: Michael Larabel <Michael@michaellarabel.com> Tested-by: Matthieu Baerts <matthieu.baerts@tessares.net> Cc: Dave Chinner <david@fromorbit.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Chris Mason <clm@fb.com> Cc: Jan Kara <jack@suse.cz> Cc: Amir Goldstein <amir73il@gmail.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-09-13 21:05:35 +00:00
goto repeat;
wait->flags |= WQ_FLAG_DONE;
break;
2016-12-25 03:00:30 +00:00
}
mm: allow a controlled amount of unfairness in the page lock Commit 2a9127fcf229 ("mm: rewrite wait_on_page_bit_common() logic") made the page locking entirely fair, in that if a waiter came in while the lock was held, the lock would be transferred to the lockers strictly in order. That was intended to finally get rid of the long-reported watchdog failures that involved the page lock under extreme load, where a process could end up waiting essentially forever, as other page lockers stole the lock from under it. It also improved some benchmarks, but it ended up causing huge performance regressions on others, simply because fair lock behavior doesn't end up giving out the lock as aggressively, causing better worst-case latency, but potentially much worse average latencies and throughput. Instead of reverting that change entirely, this introduces a controlled amount of unfairness, with a sysctl knob to tune it if somebody needs to. But the default value should hopefully be good for any normal load, allowing a few rounds of lock stealing, but enforcing the strict ordering before the lock has been stolen too many times. There is also a hint from Matthieu Baerts that the fair page coloring may end up exposing an ABBA deadlock that is hidden by the usual optimistic lock stealing, and while the unfairness doesn't fix the fundamental issue (and I'm still looking at that), it avoids it in practice. The amount of unfairness can be modified by writing a new value to the 'sysctl_page_lock_unfairness' variable (default value of 5, exposed through /proc/sys/vm/page_lock_unfairness), but that is hopefully something we'd use mainly for debugging rather than being necessary for any deep system tuning. This whole issue has exposed just how critical the page lock can be, and how contended it gets under certain locks. And the main contention doesn't really seem to be anything related to IO (which was the origin of this lock), but for things like just verifying that the page file mapping is stable while faulting in the page into a page table. Link: https://lore.kernel.org/linux-fsdevel/ed8442fd-6f54-dd84-cd4a-941e8b7ee603@MichaelLarabel.com/ Link: https://www.phoronix.com/scan.php?page=article&item=linux-50-59&num=1 Link: https://lore.kernel.org/linux-fsdevel/c560a38d-8313-51fb-b1ec-e904bd8836bc@tessares.net/ Reported-and-tested-by: Michael Larabel <Michael@michaellarabel.com> Tested-by: Matthieu Baerts <matthieu.baerts@tessares.net> Cc: Dave Chinner <david@fromorbit.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Chris Mason <clm@fb.com> Cc: Jan Kara <jack@suse.cz> Cc: Amir Goldstein <amir73il@gmail.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-09-13 21:05:35 +00:00
/*
* If a signal happened, this 'finish_wait()' may remove the last
* waiter from the wait-queues, but the folio waiters bit will remain
mm: allow a controlled amount of unfairness in the page lock Commit 2a9127fcf229 ("mm: rewrite wait_on_page_bit_common() logic") made the page locking entirely fair, in that if a waiter came in while the lock was held, the lock would be transferred to the lockers strictly in order. That was intended to finally get rid of the long-reported watchdog failures that involved the page lock under extreme load, where a process could end up waiting essentially forever, as other page lockers stole the lock from under it. It also improved some benchmarks, but it ended up causing huge performance regressions on others, simply because fair lock behavior doesn't end up giving out the lock as aggressively, causing better worst-case latency, but potentially much worse average latencies and throughput. Instead of reverting that change entirely, this introduces a controlled amount of unfairness, with a sysctl knob to tune it if somebody needs to. But the default value should hopefully be good for any normal load, allowing a few rounds of lock stealing, but enforcing the strict ordering before the lock has been stolen too many times. There is also a hint from Matthieu Baerts that the fair page coloring may end up exposing an ABBA deadlock that is hidden by the usual optimistic lock stealing, and while the unfairness doesn't fix the fundamental issue (and I'm still looking at that), it avoids it in practice. The amount of unfairness can be modified by writing a new value to the 'sysctl_page_lock_unfairness' variable (default value of 5, exposed through /proc/sys/vm/page_lock_unfairness), but that is hopefully something we'd use mainly for debugging rather than being necessary for any deep system tuning. This whole issue has exposed just how critical the page lock can be, and how contended it gets under certain locks. And the main contention doesn't really seem to be anything related to IO (which was the origin of this lock), but for things like just verifying that the page file mapping is stable while faulting in the page into a page table. Link: https://lore.kernel.org/linux-fsdevel/ed8442fd-6f54-dd84-cd4a-941e8b7ee603@MichaelLarabel.com/ Link: https://www.phoronix.com/scan.php?page=article&item=linux-50-59&num=1 Link: https://lore.kernel.org/linux-fsdevel/c560a38d-8313-51fb-b1ec-e904bd8836bc@tessares.net/ Reported-and-tested-by: Michael Larabel <Michael@michaellarabel.com> Tested-by: Matthieu Baerts <matthieu.baerts@tessares.net> Cc: Dave Chinner <david@fromorbit.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Chris Mason <clm@fb.com> Cc: Jan Kara <jack@suse.cz> Cc: Amir Goldstein <amir73il@gmail.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-09-13 21:05:35 +00:00
* set. That's ok. The next wakeup will take care of it, and trying
* to do it here would be difficult and prone to races.
*/
2016-12-25 03:00:30 +00:00
finish_wait(q, wait);
psi: pressure stall information for CPU, memory, and IO When systems are overcommitted and resources become contended, it's hard to tell exactly the impact this has on workload productivity, or how close the system is to lockups and OOM kills. In particular, when machines work multiple jobs concurrently, the impact of overcommit in terms of latency and throughput on the individual job can be enormous. In order to maximize hardware utilization without sacrificing individual job health or risk complete machine lockups, this patch implements a way to quantify resource pressure in the system. A kernel built with CONFIG_PSI=y creates files in /proc/pressure/ that expose the percentage of time the system is stalled on CPU, memory, or IO, respectively. Stall states are aggregate versions of the per-task delay accounting delays: cpu: some tasks are runnable but not executing on a CPU memory: tasks are reclaiming, or waiting for swapin or thrashing cache io: tasks are waiting for io completions These percentages of walltime can be thought of as pressure percentages, and they give a general sense of system health and productivity loss incurred by resource overcommit. They can also indicate when the system is approaching lockup scenarios and OOMs. To do this, psi keeps track of the task states associated with each CPU and samples the time they spend in stall states. Every 2 seconds, the samples are averaged across CPUs - weighted by the CPUs' non-idle time to eliminate artifacts from unused CPUs - and translated into percentages of walltime. A running average of those percentages is maintained over 10s, 1m, and 5m periods (similar to the loadaverage). [hannes@cmpxchg.org: doc fixlet, per Randy] Link: http://lkml.kernel.org/r/20180828205625.GA14030@cmpxchg.org [hannes@cmpxchg.org: code optimization] Link: http://lkml.kernel.org/r/20180907175015.GA8479@cmpxchg.org [hannes@cmpxchg.org: rename psi_clock() to psi_update_work(), per Peter] Link: http://lkml.kernel.org/r/20180907145404.GB11088@cmpxchg.org [hannes@cmpxchg.org: fix build] Link: http://lkml.kernel.org/r/20180913014222.GA2370@cmpxchg.org Link: http://lkml.kernel.org/r/20180828172258.3185-9-hannes@cmpxchg.org Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Tested-by: Daniel Drake <drake@endlessm.com> Tested-by: Suren Baghdasaryan <surenb@google.com> Cc: Christopher Lameter <cl@linux.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Johannes Weiner <jweiner@fb.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Enderborg <peter.enderborg@sony.com> Cc: Randy Dunlap <rdunlap@infradead.org> Cc: Shakeel Butt <shakeelb@google.com> Cc: Tejun Heo <tj@kernel.org> Cc: Vinayak Menon <vinmenon@codeaurora.org> Cc: Randy Dunlap <rdunlap@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-10-26 22:06:27 +00:00
if (thrashing) {
delayacct_thrashing_end(&in_thrashing);
psi: pressure stall information for CPU, memory, and IO When systems are overcommitted and resources become contended, it's hard to tell exactly the impact this has on workload productivity, or how close the system is to lockups and OOM kills. In particular, when machines work multiple jobs concurrently, the impact of overcommit in terms of latency and throughput on the individual job can be enormous. In order to maximize hardware utilization without sacrificing individual job health or risk complete machine lockups, this patch implements a way to quantify resource pressure in the system. A kernel built with CONFIG_PSI=y creates files in /proc/pressure/ that expose the percentage of time the system is stalled on CPU, memory, or IO, respectively. Stall states are aggregate versions of the per-task delay accounting delays: cpu: some tasks are runnable but not executing on a CPU memory: tasks are reclaiming, or waiting for swapin or thrashing cache io: tasks are waiting for io completions These percentages of walltime can be thought of as pressure percentages, and they give a general sense of system health and productivity loss incurred by resource overcommit. They can also indicate when the system is approaching lockup scenarios and OOMs. To do this, psi keeps track of the task states associated with each CPU and samples the time they spend in stall states. Every 2 seconds, the samples are averaged across CPUs - weighted by the CPUs' non-idle time to eliminate artifacts from unused CPUs - and translated into percentages of walltime. A running average of those percentages is maintained over 10s, 1m, and 5m periods (similar to the loadaverage). [hannes@cmpxchg.org: doc fixlet, per Randy] Link: http://lkml.kernel.org/r/20180828205625.GA14030@cmpxchg.org [hannes@cmpxchg.org: code optimization] Link: http://lkml.kernel.org/r/20180907175015.GA8479@cmpxchg.org [hannes@cmpxchg.org: rename psi_clock() to psi_update_work(), per Peter] Link: http://lkml.kernel.org/r/20180907145404.GB11088@cmpxchg.org [hannes@cmpxchg.org: fix build] Link: http://lkml.kernel.org/r/20180913014222.GA2370@cmpxchg.org Link: http://lkml.kernel.org/r/20180828172258.3185-9-hannes@cmpxchg.org Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Tested-by: Daniel Drake <drake@endlessm.com> Tested-by: Suren Baghdasaryan <surenb@google.com> Cc: Christopher Lameter <cl@linux.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Johannes Weiner <jweiner@fb.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Enderborg <peter.enderborg@sony.com> Cc: Randy Dunlap <rdunlap@infradead.org> Cc: Shakeel Butt <shakeelb@google.com> Cc: Tejun Heo <tj@kernel.org> Cc: Vinayak Menon <vinmenon@codeaurora.org> Cc: Randy Dunlap <rdunlap@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-10-26 22:06:27 +00:00
psi_memstall_leave(&pflags);
}
delayacct: track delays from thrashing cache pages Delay accounting already measures the time a task spends in direct reclaim and waiting for swapin, but in low memory situations tasks spend can spend a significant amount of their time waiting on thrashing page cache. This isn't tracked right now. To know the full impact of memory contention on an individual task, measure the delay when waiting for a recently evicted active cache page to read back into memory. Also update tools/accounting/getdelays.c: [hannes@computer accounting]$ sudo ./getdelays -d -p 1 print delayacct stats ON PID 1 CPU count real total virtual total delay total delay average 50318 745000000 847346785 400533713 0.008ms IO count delay total delay average 435 122601218 0ms SWAP count delay total delay average 0 0 0ms RECLAIM count delay total delay average 0 0 0ms THRASHING count delay total delay average 19 12621439 0ms Link: http://lkml.kernel.org/r/20180828172258.3185-4-hannes@cmpxchg.org Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Tested-by: Daniel Drake <drake@endlessm.com> Tested-by: Suren Baghdasaryan <surenb@google.com> Cc: Christopher Lameter <cl@linux.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Johannes Weiner <jweiner@fb.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Enderborg <peter.enderborg@sony.com> Cc: Randy Dunlap <rdunlap@infradead.org> Cc: Shakeel Butt <shakeelb@google.com> Cc: Tejun Heo <tj@kernel.org> Cc: Vinayak Menon <vinmenon@codeaurora.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-10-26 22:06:08 +00:00
2016-12-25 03:00:30 +00:00
/*
mm: allow a controlled amount of unfairness in the page lock Commit 2a9127fcf229 ("mm: rewrite wait_on_page_bit_common() logic") made the page locking entirely fair, in that if a waiter came in while the lock was held, the lock would be transferred to the lockers strictly in order. That was intended to finally get rid of the long-reported watchdog failures that involved the page lock under extreme load, where a process could end up waiting essentially forever, as other page lockers stole the lock from under it. It also improved some benchmarks, but it ended up causing huge performance regressions on others, simply because fair lock behavior doesn't end up giving out the lock as aggressively, causing better worst-case latency, but potentially much worse average latencies and throughput. Instead of reverting that change entirely, this introduces a controlled amount of unfairness, with a sysctl knob to tune it if somebody needs to. But the default value should hopefully be good for any normal load, allowing a few rounds of lock stealing, but enforcing the strict ordering before the lock has been stolen too many times. There is also a hint from Matthieu Baerts that the fair page coloring may end up exposing an ABBA deadlock that is hidden by the usual optimistic lock stealing, and while the unfairness doesn't fix the fundamental issue (and I'm still looking at that), it avoids it in practice. The amount of unfairness can be modified by writing a new value to the 'sysctl_page_lock_unfairness' variable (default value of 5, exposed through /proc/sys/vm/page_lock_unfairness), but that is hopefully something we'd use mainly for debugging rather than being necessary for any deep system tuning. This whole issue has exposed just how critical the page lock can be, and how contended it gets under certain locks. And the main contention doesn't really seem to be anything related to IO (which was the origin of this lock), but for things like just verifying that the page file mapping is stable while faulting in the page into a page table. Link: https://lore.kernel.org/linux-fsdevel/ed8442fd-6f54-dd84-cd4a-941e8b7ee603@MichaelLarabel.com/ Link: https://www.phoronix.com/scan.php?page=article&item=linux-50-59&num=1 Link: https://lore.kernel.org/linux-fsdevel/c560a38d-8313-51fb-b1ec-e904bd8836bc@tessares.net/ Reported-and-tested-by: Michael Larabel <Michael@michaellarabel.com> Tested-by: Matthieu Baerts <matthieu.baerts@tessares.net> Cc: Dave Chinner <david@fromorbit.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Chris Mason <clm@fb.com> Cc: Jan Kara <jack@suse.cz> Cc: Amir Goldstein <amir73il@gmail.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-09-13 21:05:35 +00:00
* NOTE! The wait->flags weren't stable until we've done the
* 'finish_wait()', and we could have exited the loop above due
* to a signal, and had a wakeup event happen after the signal
* test but before the 'finish_wait()'.
*
* So only after the finish_wait() can we reliably determine
* if we got woken up or not, so we can now figure out the final
* return value based on that state without races.
*
* Also note that WQ_FLAG_WOKEN is sufficient for a non-exclusive
* waiter, but an exclusive one requires WQ_FLAG_DONE.
2016-12-25 03:00:30 +00:00
*/
mm: allow a controlled amount of unfairness in the page lock Commit 2a9127fcf229 ("mm: rewrite wait_on_page_bit_common() logic") made the page locking entirely fair, in that if a waiter came in while the lock was held, the lock would be transferred to the lockers strictly in order. That was intended to finally get rid of the long-reported watchdog failures that involved the page lock under extreme load, where a process could end up waiting essentially forever, as other page lockers stole the lock from under it. It also improved some benchmarks, but it ended up causing huge performance regressions on others, simply because fair lock behavior doesn't end up giving out the lock as aggressively, causing better worst-case latency, but potentially much worse average latencies and throughput. Instead of reverting that change entirely, this introduces a controlled amount of unfairness, with a sysctl knob to tune it if somebody needs to. But the default value should hopefully be good for any normal load, allowing a few rounds of lock stealing, but enforcing the strict ordering before the lock has been stolen too many times. There is also a hint from Matthieu Baerts that the fair page coloring may end up exposing an ABBA deadlock that is hidden by the usual optimistic lock stealing, and while the unfairness doesn't fix the fundamental issue (and I'm still looking at that), it avoids it in practice. The amount of unfairness can be modified by writing a new value to the 'sysctl_page_lock_unfairness' variable (default value of 5, exposed through /proc/sys/vm/page_lock_unfairness), but that is hopefully something we'd use mainly for debugging rather than being necessary for any deep system tuning. This whole issue has exposed just how critical the page lock can be, and how contended it gets under certain locks. And the main contention doesn't really seem to be anything related to IO (which was the origin of this lock), but for things like just verifying that the page file mapping is stable while faulting in the page into a page table. Link: https://lore.kernel.org/linux-fsdevel/ed8442fd-6f54-dd84-cd4a-941e8b7ee603@MichaelLarabel.com/ Link: https://www.phoronix.com/scan.php?page=article&item=linux-50-59&num=1 Link: https://lore.kernel.org/linux-fsdevel/c560a38d-8313-51fb-b1ec-e904bd8836bc@tessares.net/ Reported-and-tested-by: Michael Larabel <Michael@michaellarabel.com> Tested-by: Matthieu Baerts <matthieu.baerts@tessares.net> Cc: Dave Chinner <david@fromorbit.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Chris Mason <clm@fb.com> Cc: Jan Kara <jack@suse.cz> Cc: Amir Goldstein <amir73il@gmail.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-09-13 21:05:35 +00:00
if (behavior == EXCLUSIVE)
return wait->flags & WQ_FLAG_DONE ? 0 : -EINTR;
2016-12-25 03:00:30 +00:00
return wait->flags & WQ_FLAG_WOKEN ? 0 : -EINTR;
2016-12-25 03:00:30 +00:00
}
mm/migrate.c: rework migration_entry_wait() to not take a pageref This fixes the FIXME in migrate_vma_check_page(). Before migrating a page migration code will take a reference and check there are no unexpected page references, failing the migration if there are. When a thread faults on a migration entry it will take a temporary reference to the page to wait for the page to become unlocked signifying the migration entry has been removed. This reference is dropped just prior to waiting on the page lock, however the extra reference can cause migration failures so it is desirable to avoid taking it. As migration code already has a reference to the migrating page an extra reference to wait on PG_locked is unnecessary so long as the reference can't be dropped whilst setting up the wait. When faulting on a migration entry the ptl is taken to check the migration entry. Removing a migration entry also requires the ptl, and migration code won't drop its page reference until after the migration entry has been removed. Therefore retaining the ptl of a migration entry is sufficient to ensure the page has a reference. Reworking migration_entry_wait() to hold the ptl until the wait setup is complete means the extra page reference is no longer needed. [apopple@nvidia.com: v5] Link: https://lkml.kernel.org/r/20211213033848.1973946-1-apopple@nvidia.com Link: https://lkml.kernel.org/r/20211118020754.954425-1-apopple@nvidia.com Signed-off-by: Alistair Popple <apopple@nvidia.com> Acked-by: David Hildenbrand <david@redhat.com> Cc: David Howells <dhowells@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Ralph Campbell <rcampbell@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-01-22 06:10:46 +00:00
#ifdef CONFIG_MIGRATION
/**
* migration_entry_wait_on_locked - Wait for a migration entry to be removed
* @entry: migration swap entry.
* @ptl: already locked ptl. This function will drop the lock.
*
* Wait for a migration entry referencing the given page to be removed. This is
* equivalent to put_and_wait_on_page_locked(page, TASK_UNINTERRUPTIBLE) except
* this can be called without taking a reference on the page. Instead this
* should be called while holding the ptl for the migration entry referencing
* the page.
*
mm/migrate: remove cruft from migration_entry_wait()s migration_entry_wait_on_locked() does not need to take a mapped pte pointer, its callers can do the unmap first. Annotate it with __releases(ptl) to reduce sparse warnings. Fold __migration_entry_wait_huge() into migration_entry_wait_huge(). Fold __migration_entry_wait() into migration_entry_wait(), preferring the tighter pte_offset_map_lock() to pte_offset_map() and pte_lockptr(). Link: https://lkml.kernel.org/r/b0e2a532-cdf2-561b-e999-f3b13b8d6d3@google.com Signed-off-by: Hugh Dickins <hughd@google.com> Reviewed-by: Alistair Popple <apopple@nvidia.com> Cc: Anshuman Khandual <anshuman.khandual@arm.com> Cc: Axel Rasmussen <axelrasmussen@google.com> Cc: Christophe Leroy <christophe.leroy@csgroup.eu> Cc: Christoph Hellwig <hch@infradead.org> Cc: David Hildenbrand <david@redhat.com> Cc: "Huang, Ying" <ying.huang@intel.com> Cc: Ira Weiny <ira.weiny@intel.com> Cc: Jason Gunthorpe <jgg@ziepe.ca> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Lorenzo Stoakes <lstoakes@gmail.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Mike Rapoport (IBM) <rppt@kernel.org> Cc: Minchan Kim <minchan@kernel.org> Cc: Naoya Horiguchi <naoya.horiguchi@nec.com> Cc: Pavel Tatashin <pasha.tatashin@soleen.com> Cc: Peter Xu <peterx@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Qi Zheng <zhengqi.arch@bytedance.com> Cc: Ralph Campbell <rcampbell@nvidia.com> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: SeongJae Park <sj@kernel.org> Cc: Song Liu <song@kernel.org> Cc: Steven Price <steven.price@arm.com> Cc: Suren Baghdasaryan <surenb@google.com> Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com> Cc: Will Deacon <will@kernel.org> Cc: Yang Shi <shy828301@gmail.com> Cc: Yu Zhao <yuzhao@google.com> Cc: Zack Rusin <zackr@vmware.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-06-09 01:08:20 +00:00
* Returns after unlocking the ptl.
mm/migrate.c: rework migration_entry_wait() to not take a pageref This fixes the FIXME in migrate_vma_check_page(). Before migrating a page migration code will take a reference and check there are no unexpected page references, failing the migration if there are. When a thread faults on a migration entry it will take a temporary reference to the page to wait for the page to become unlocked signifying the migration entry has been removed. This reference is dropped just prior to waiting on the page lock, however the extra reference can cause migration failures so it is desirable to avoid taking it. As migration code already has a reference to the migrating page an extra reference to wait on PG_locked is unnecessary so long as the reference can't be dropped whilst setting up the wait. When faulting on a migration entry the ptl is taken to check the migration entry. Removing a migration entry also requires the ptl, and migration code won't drop its page reference until after the migration entry has been removed. Therefore retaining the ptl of a migration entry is sufficient to ensure the page has a reference. Reworking migration_entry_wait() to hold the ptl until the wait setup is complete means the extra page reference is no longer needed. [apopple@nvidia.com: v5] Link: https://lkml.kernel.org/r/20211213033848.1973946-1-apopple@nvidia.com Link: https://lkml.kernel.org/r/20211118020754.954425-1-apopple@nvidia.com Signed-off-by: Alistair Popple <apopple@nvidia.com> Acked-by: David Hildenbrand <david@redhat.com> Cc: David Howells <dhowells@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Ralph Campbell <rcampbell@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-01-22 06:10:46 +00:00
*
* This follows the same logic as folio_wait_bit_common() so see the comments
* there.
*/
mm/migrate: remove cruft from migration_entry_wait()s migration_entry_wait_on_locked() does not need to take a mapped pte pointer, its callers can do the unmap first. Annotate it with __releases(ptl) to reduce sparse warnings. Fold __migration_entry_wait_huge() into migration_entry_wait_huge(). Fold __migration_entry_wait() into migration_entry_wait(), preferring the tighter pte_offset_map_lock() to pte_offset_map() and pte_lockptr(). Link: https://lkml.kernel.org/r/b0e2a532-cdf2-561b-e999-f3b13b8d6d3@google.com Signed-off-by: Hugh Dickins <hughd@google.com> Reviewed-by: Alistair Popple <apopple@nvidia.com> Cc: Anshuman Khandual <anshuman.khandual@arm.com> Cc: Axel Rasmussen <axelrasmussen@google.com> Cc: Christophe Leroy <christophe.leroy@csgroup.eu> Cc: Christoph Hellwig <hch@infradead.org> Cc: David Hildenbrand <david@redhat.com> Cc: "Huang, Ying" <ying.huang@intel.com> Cc: Ira Weiny <ira.weiny@intel.com> Cc: Jason Gunthorpe <jgg@ziepe.ca> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Lorenzo Stoakes <lstoakes@gmail.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Mike Rapoport (IBM) <rppt@kernel.org> Cc: Minchan Kim <minchan@kernel.org> Cc: Naoya Horiguchi <naoya.horiguchi@nec.com> Cc: Pavel Tatashin <pasha.tatashin@soleen.com> Cc: Peter Xu <peterx@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Qi Zheng <zhengqi.arch@bytedance.com> Cc: Ralph Campbell <rcampbell@nvidia.com> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: SeongJae Park <sj@kernel.org> Cc: Song Liu <song@kernel.org> Cc: Steven Price <steven.price@arm.com> Cc: Suren Baghdasaryan <surenb@google.com> Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com> Cc: Will Deacon <will@kernel.org> Cc: Yang Shi <shy828301@gmail.com> Cc: Yu Zhao <yuzhao@google.com> Cc: Zack Rusin <zackr@vmware.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-06-09 01:08:20 +00:00
void migration_entry_wait_on_locked(swp_entry_t entry, spinlock_t *ptl)
__releases(ptl)
mm/migrate.c: rework migration_entry_wait() to not take a pageref This fixes the FIXME in migrate_vma_check_page(). Before migrating a page migration code will take a reference and check there are no unexpected page references, failing the migration if there are. When a thread faults on a migration entry it will take a temporary reference to the page to wait for the page to become unlocked signifying the migration entry has been removed. This reference is dropped just prior to waiting on the page lock, however the extra reference can cause migration failures so it is desirable to avoid taking it. As migration code already has a reference to the migrating page an extra reference to wait on PG_locked is unnecessary so long as the reference can't be dropped whilst setting up the wait. When faulting on a migration entry the ptl is taken to check the migration entry. Removing a migration entry also requires the ptl, and migration code won't drop its page reference until after the migration entry has been removed. Therefore retaining the ptl of a migration entry is sufficient to ensure the page has a reference. Reworking migration_entry_wait() to hold the ptl until the wait setup is complete means the extra page reference is no longer needed. [apopple@nvidia.com: v5] Link: https://lkml.kernel.org/r/20211213033848.1973946-1-apopple@nvidia.com Link: https://lkml.kernel.org/r/20211118020754.954425-1-apopple@nvidia.com Signed-off-by: Alistair Popple <apopple@nvidia.com> Acked-by: David Hildenbrand <david@redhat.com> Cc: David Howells <dhowells@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Ralph Campbell <rcampbell@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-01-22 06:10:46 +00:00
{
struct wait_page_queue wait_page;
wait_queue_entry_t *wait = &wait_page.wait;
bool thrashing = false;
unsigned long pflags;
bool in_thrashing;
mm/migrate.c: rework migration_entry_wait() to not take a pageref This fixes the FIXME in migrate_vma_check_page(). Before migrating a page migration code will take a reference and check there are no unexpected page references, failing the migration if there are. When a thread faults on a migration entry it will take a temporary reference to the page to wait for the page to become unlocked signifying the migration entry has been removed. This reference is dropped just prior to waiting on the page lock, however the extra reference can cause migration failures so it is desirable to avoid taking it. As migration code already has a reference to the migrating page an extra reference to wait on PG_locked is unnecessary so long as the reference can't be dropped whilst setting up the wait. When faulting on a migration entry the ptl is taken to check the migration entry. Removing a migration entry also requires the ptl, and migration code won't drop its page reference until after the migration entry has been removed. Therefore retaining the ptl of a migration entry is sufficient to ensure the page has a reference. Reworking migration_entry_wait() to hold the ptl until the wait setup is complete means the extra page reference is no longer needed. [apopple@nvidia.com: v5] Link: https://lkml.kernel.org/r/20211213033848.1973946-1-apopple@nvidia.com Link: https://lkml.kernel.org/r/20211118020754.954425-1-apopple@nvidia.com Signed-off-by: Alistair Popple <apopple@nvidia.com> Acked-by: David Hildenbrand <david@redhat.com> Cc: David Howells <dhowells@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Ralph Campbell <rcampbell@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-01-22 06:10:46 +00:00
wait_queue_head_t *q;
struct folio *folio = pfn_swap_entry_folio(entry);
mm/migrate.c: rework migration_entry_wait() to not take a pageref This fixes the FIXME in migrate_vma_check_page(). Before migrating a page migration code will take a reference and check there are no unexpected page references, failing the migration if there are. When a thread faults on a migration entry it will take a temporary reference to the page to wait for the page to become unlocked signifying the migration entry has been removed. This reference is dropped just prior to waiting on the page lock, however the extra reference can cause migration failures so it is desirable to avoid taking it. As migration code already has a reference to the migrating page an extra reference to wait on PG_locked is unnecessary so long as the reference can't be dropped whilst setting up the wait. When faulting on a migration entry the ptl is taken to check the migration entry. Removing a migration entry also requires the ptl, and migration code won't drop its page reference until after the migration entry has been removed. Therefore retaining the ptl of a migration entry is sufficient to ensure the page has a reference. Reworking migration_entry_wait() to hold the ptl until the wait setup is complete means the extra page reference is no longer needed. [apopple@nvidia.com: v5] Link: https://lkml.kernel.org/r/20211213033848.1973946-1-apopple@nvidia.com Link: https://lkml.kernel.org/r/20211118020754.954425-1-apopple@nvidia.com Signed-off-by: Alistair Popple <apopple@nvidia.com> Acked-by: David Hildenbrand <david@redhat.com> Cc: David Howells <dhowells@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Ralph Campbell <rcampbell@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-01-22 06:10:46 +00:00
q = folio_waitqueue(folio);
if (!folio_test_uptodate(folio) && folio_test_workingset(folio)) {
delayacct_thrashing_start(&in_thrashing);
mm/migrate.c: rework migration_entry_wait() to not take a pageref This fixes the FIXME in migrate_vma_check_page(). Before migrating a page migration code will take a reference and check there are no unexpected page references, failing the migration if there are. When a thread faults on a migration entry it will take a temporary reference to the page to wait for the page to become unlocked signifying the migration entry has been removed. This reference is dropped just prior to waiting on the page lock, however the extra reference can cause migration failures so it is desirable to avoid taking it. As migration code already has a reference to the migrating page an extra reference to wait on PG_locked is unnecessary so long as the reference can't be dropped whilst setting up the wait. When faulting on a migration entry the ptl is taken to check the migration entry. Removing a migration entry also requires the ptl, and migration code won't drop its page reference until after the migration entry has been removed. Therefore retaining the ptl of a migration entry is sufficient to ensure the page has a reference. Reworking migration_entry_wait() to hold the ptl until the wait setup is complete means the extra page reference is no longer needed. [apopple@nvidia.com: v5] Link: https://lkml.kernel.org/r/20211213033848.1973946-1-apopple@nvidia.com Link: https://lkml.kernel.org/r/20211118020754.954425-1-apopple@nvidia.com Signed-off-by: Alistair Popple <apopple@nvidia.com> Acked-by: David Hildenbrand <david@redhat.com> Cc: David Howells <dhowells@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Ralph Campbell <rcampbell@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-01-22 06:10:46 +00:00
psi_memstall_enter(&pflags);
thrashing = true;
}
init_wait(wait);
wait->func = wake_page_function;
wait_page.folio = folio;
wait_page.bit_nr = PG_locked;
wait->flags = 0;
spin_lock_irq(&q->lock);
folio_set_waiters(folio);
if (!folio_trylock_flag(folio, PG_locked, wait))
__add_wait_queue_entry_tail(q, wait);
spin_unlock_irq(&q->lock);
/*
* If a migration entry exists for the page the migration path must hold
* a valid reference to the page, and it must take the ptl to remove the
* migration entry. So the page is valid until the ptl is dropped.
*/
mm/migrate: remove cruft from migration_entry_wait()s migration_entry_wait_on_locked() does not need to take a mapped pte pointer, its callers can do the unmap first. Annotate it with __releases(ptl) to reduce sparse warnings. Fold __migration_entry_wait_huge() into migration_entry_wait_huge(). Fold __migration_entry_wait() into migration_entry_wait(), preferring the tighter pte_offset_map_lock() to pte_offset_map() and pte_lockptr(). Link: https://lkml.kernel.org/r/b0e2a532-cdf2-561b-e999-f3b13b8d6d3@google.com Signed-off-by: Hugh Dickins <hughd@google.com> Reviewed-by: Alistair Popple <apopple@nvidia.com> Cc: Anshuman Khandual <anshuman.khandual@arm.com> Cc: Axel Rasmussen <axelrasmussen@google.com> Cc: Christophe Leroy <christophe.leroy@csgroup.eu> Cc: Christoph Hellwig <hch@infradead.org> Cc: David Hildenbrand <david@redhat.com> Cc: "Huang, Ying" <ying.huang@intel.com> Cc: Ira Weiny <ira.weiny@intel.com> Cc: Jason Gunthorpe <jgg@ziepe.ca> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Lorenzo Stoakes <lstoakes@gmail.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Mike Rapoport (IBM) <rppt@kernel.org> Cc: Minchan Kim <minchan@kernel.org> Cc: Naoya Horiguchi <naoya.horiguchi@nec.com> Cc: Pavel Tatashin <pasha.tatashin@soleen.com> Cc: Peter Xu <peterx@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Qi Zheng <zhengqi.arch@bytedance.com> Cc: Ralph Campbell <rcampbell@nvidia.com> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: SeongJae Park <sj@kernel.org> Cc: Song Liu <song@kernel.org> Cc: Steven Price <steven.price@arm.com> Cc: Suren Baghdasaryan <surenb@google.com> Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com> Cc: Will Deacon <will@kernel.org> Cc: Yang Shi <shy828301@gmail.com> Cc: Yu Zhao <yuzhao@google.com> Cc: Zack Rusin <zackr@vmware.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-06-09 01:08:20 +00:00
spin_unlock(ptl);
mm/migrate.c: rework migration_entry_wait() to not take a pageref This fixes the FIXME in migrate_vma_check_page(). Before migrating a page migration code will take a reference and check there are no unexpected page references, failing the migration if there are. When a thread faults on a migration entry it will take a temporary reference to the page to wait for the page to become unlocked signifying the migration entry has been removed. This reference is dropped just prior to waiting on the page lock, however the extra reference can cause migration failures so it is desirable to avoid taking it. As migration code already has a reference to the migrating page an extra reference to wait on PG_locked is unnecessary so long as the reference can't be dropped whilst setting up the wait. When faulting on a migration entry the ptl is taken to check the migration entry. Removing a migration entry also requires the ptl, and migration code won't drop its page reference until after the migration entry has been removed. Therefore retaining the ptl of a migration entry is sufficient to ensure the page has a reference. Reworking migration_entry_wait() to hold the ptl until the wait setup is complete means the extra page reference is no longer needed. [apopple@nvidia.com: v5] Link: https://lkml.kernel.org/r/20211213033848.1973946-1-apopple@nvidia.com Link: https://lkml.kernel.org/r/20211118020754.954425-1-apopple@nvidia.com Signed-off-by: Alistair Popple <apopple@nvidia.com> Acked-by: David Hildenbrand <david@redhat.com> Cc: David Howells <dhowells@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Ralph Campbell <rcampbell@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-01-22 06:10:46 +00:00
for (;;) {
unsigned int flags;
set_current_state(TASK_UNINTERRUPTIBLE);
/* Loop until we've been woken or interrupted */
flags = smp_load_acquire(&wait->flags);
if (!(flags & WQ_FLAG_WOKEN)) {
if (signal_pending_state(TASK_UNINTERRUPTIBLE, current))
break;
io_schedule();
continue;
}
break;
}
finish_wait(q, wait);
if (thrashing) {
delayacct_thrashing_end(&in_thrashing);
mm/migrate.c: rework migration_entry_wait() to not take a pageref This fixes the FIXME in migrate_vma_check_page(). Before migrating a page migration code will take a reference and check there are no unexpected page references, failing the migration if there are. When a thread faults on a migration entry it will take a temporary reference to the page to wait for the page to become unlocked signifying the migration entry has been removed. This reference is dropped just prior to waiting on the page lock, however the extra reference can cause migration failures so it is desirable to avoid taking it. As migration code already has a reference to the migrating page an extra reference to wait on PG_locked is unnecessary so long as the reference can't be dropped whilst setting up the wait. When faulting on a migration entry the ptl is taken to check the migration entry. Removing a migration entry also requires the ptl, and migration code won't drop its page reference until after the migration entry has been removed. Therefore retaining the ptl of a migration entry is sufficient to ensure the page has a reference. Reworking migration_entry_wait() to hold the ptl until the wait setup is complete means the extra page reference is no longer needed. [apopple@nvidia.com: v5] Link: https://lkml.kernel.org/r/20211213033848.1973946-1-apopple@nvidia.com Link: https://lkml.kernel.org/r/20211118020754.954425-1-apopple@nvidia.com Signed-off-by: Alistair Popple <apopple@nvidia.com> Acked-by: David Hildenbrand <david@redhat.com> Cc: David Howells <dhowells@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Ralph Campbell <rcampbell@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-01-22 06:10:46 +00:00
psi_memstall_leave(&pflags);
}
}
#endif
void folio_wait_bit(struct folio *folio, int bit_nr)
2016-12-25 03:00:30 +00:00
{
folio_wait_bit_common(folio, bit_nr, TASK_UNINTERRUPTIBLE, SHARED);
2016-12-25 03:00:30 +00:00
}
EXPORT_SYMBOL(folio_wait_bit);
2016-12-25 03:00:30 +00:00
int folio_wait_bit_killable(struct folio *folio, int bit_nr)
2016-12-25 03:00:30 +00:00
{
return folio_wait_bit_common(folio, bit_nr, TASK_KILLABLE, SHARED);
}
EXPORT_SYMBOL(folio_wait_bit_killable);
mm: put_and_wait_on_page_locked() while page is migrated Waiting on a page migration entry has used wait_on_page_locked() all along since 2006: but you cannot safely wait_on_page_locked() without holding a reference to the page, and that extra reference is enough to make migrate_page_move_mapping() fail with -EAGAIN, when a racing task faults on the entry before migrate_page_move_mapping() gets there. And that failure is retried nine times, amplifying the pain when trying to migrate a popular page. With a single persistent faulter, migration sometimes succeeds; with two or three concurrent faulters, success becomes much less likely (and the more the page was mapped, the worse the overhead of unmapping and remapping it on each try). This is especially a problem for memory offlining, where the outer level retries forever (or until terminated from userspace), because a heavy refault workload can trigger an endless loop of migration failures. wait_on_page_locked() is the wrong tool for the job. David Herrmann (but was he the first?) noticed this issue in 2014: https://marc.info/?l=linux-mm&m=140110465608116&w=2 Tim Chen started a thread in August 2017 which appears relevant: https://marc.info/?l=linux-mm&m=150275941014915&w=2 where Kan Liang went on to implicate __migration_entry_wait(): https://marc.info/?l=linux-mm&m=150300268411980&w=2 and the thread ended up with the v4.14 commits: 2554db916586 ("sched/wait: Break up long wake list walk") 11a19c7b099f ("sched/wait: Introduce wakeup boomark in wake_up_page_bit") Baoquan He reported "Memory hotplug softlock issue" 14 November 2018: https://marc.info/?l=linux-mm&m=154217936431300&w=2 We have all assumed that it is essential to hold a page reference while waiting on a page lock: partly to guarantee that there is still a struct page when MEMORY_HOTREMOVE is configured, but also to protect against reuse of the struct page going to someone who then holds the page locked indefinitely, when the waiter can reasonably expect timely unlocking. But in fact, so long as wait_on_page_bit_common() does the put_page(), and is careful not to rely on struct page contents thereafter, there is no need to hold a reference to the page while waiting on it. That does mean that this case cannot go back through the loop: but that's fine for the page migration case, and even if used more widely, is limited by the "Stop walking if it's locked" optimization in wake_page_function(). Add interface put_and_wait_on_page_locked() to do this, using "behavior" enum in place of "lock" arg to wait_on_page_bit_common() to implement it. No interruptible or killable variant needed yet, but they might follow: I have a vague notion that reporting -EINTR should take precedence over return from wait_on_page_bit_common() without knowing the page state, so arrange it accordingly - but that may be nothing but pedantic. __migration_entry_wait() still has to take a brief reference to the page, prior to calling put_and_wait_on_page_locked(): but now that it is dropped before waiting, the chance of impeding page migration is very much reduced. Should we perhaps disable preemption across this? shrink_page_list()'s __ClearPageLocked(): that was a surprise! This survived a lot of testing before that showed up. PageWaiters may have been set by wait_on_page_bit_common(), and the reference dropped, just before shrink_page_list() succeeds in freezing its last page reference: in such a case, unlock_page() must be used. Follow the suggestion from Michal Hocko, just revert a978d6f52106 ("mm: unlockless reclaim") now: that optimization predates PageWaiters, and won't buy much these days; but we can reinstate it for the !PageWaiters case if anyone notices. It does raise the question: should vmscan.c's is_page_cache_freeable() and __remove_mapping() now treat a PageWaiters page as if an extra reference were held? Perhaps, but I don't think it matters much, since shrink_page_list() already had to win its trylock_page(), so waiters are not very common there: I noticed no difference when trying the bigger change, and it's surely not needed while put_and_wait_on_page_locked() is only used for page migration. [willy@infradead.org: add put_and_wait_on_page_locked() kerneldoc] Link: http://lkml.kernel.org/r/alpine.LSU.2.11.1811261121330.1116@eggly.anvils Signed-off-by: Hugh Dickins <hughd@google.com> Reported-by: Baoquan He <bhe@redhat.com> Tested-by: Baoquan He <bhe@redhat.com> Reviewed-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Michal Hocko <mhocko@suse.com> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Matthew Wilcox <willy@infradead.org> Cc: Baoquan He <bhe@redhat.com> Cc: David Hildenbrand <david@redhat.com> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: David Herrmann <dh.herrmann@gmail.com> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Christoph Lameter <cl@linux.com> Cc: Nick Piggin <npiggin@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-12-28 08:36:14 +00:00
/**
* folio_put_wait_locked - Drop a reference and wait for it to be unlocked
* @folio: The folio to wait for.
* @state: The sleep state (TASK_KILLABLE, TASK_UNINTERRUPTIBLE, etc).
mm: put_and_wait_on_page_locked() while page is migrated Waiting on a page migration entry has used wait_on_page_locked() all along since 2006: but you cannot safely wait_on_page_locked() without holding a reference to the page, and that extra reference is enough to make migrate_page_move_mapping() fail with -EAGAIN, when a racing task faults on the entry before migrate_page_move_mapping() gets there. And that failure is retried nine times, amplifying the pain when trying to migrate a popular page. With a single persistent faulter, migration sometimes succeeds; with two or three concurrent faulters, success becomes much less likely (and the more the page was mapped, the worse the overhead of unmapping and remapping it on each try). This is especially a problem for memory offlining, where the outer level retries forever (or until terminated from userspace), because a heavy refault workload can trigger an endless loop of migration failures. wait_on_page_locked() is the wrong tool for the job. David Herrmann (but was he the first?) noticed this issue in 2014: https://marc.info/?l=linux-mm&m=140110465608116&w=2 Tim Chen started a thread in August 2017 which appears relevant: https://marc.info/?l=linux-mm&m=150275941014915&w=2 where Kan Liang went on to implicate __migration_entry_wait(): https://marc.info/?l=linux-mm&m=150300268411980&w=2 and the thread ended up with the v4.14 commits: 2554db916586 ("sched/wait: Break up long wake list walk") 11a19c7b099f ("sched/wait: Introduce wakeup boomark in wake_up_page_bit") Baoquan He reported "Memory hotplug softlock issue" 14 November 2018: https://marc.info/?l=linux-mm&m=154217936431300&w=2 We have all assumed that it is essential to hold a page reference while waiting on a page lock: partly to guarantee that there is still a struct page when MEMORY_HOTREMOVE is configured, but also to protect against reuse of the struct page going to someone who then holds the page locked indefinitely, when the waiter can reasonably expect timely unlocking. But in fact, so long as wait_on_page_bit_common() does the put_page(), and is careful not to rely on struct page contents thereafter, there is no need to hold a reference to the page while waiting on it. That does mean that this case cannot go back through the loop: but that's fine for the page migration case, and even if used more widely, is limited by the "Stop walking if it's locked" optimization in wake_page_function(). Add interface put_and_wait_on_page_locked() to do this, using "behavior" enum in place of "lock" arg to wait_on_page_bit_common() to implement it. No interruptible or killable variant needed yet, but they might follow: I have a vague notion that reporting -EINTR should take precedence over return from wait_on_page_bit_common() without knowing the page state, so arrange it accordingly - but that may be nothing but pedantic. __migration_entry_wait() still has to take a brief reference to the page, prior to calling put_and_wait_on_page_locked(): but now that it is dropped before waiting, the chance of impeding page migration is very much reduced. Should we perhaps disable preemption across this? shrink_page_list()'s __ClearPageLocked(): that was a surprise! This survived a lot of testing before that showed up. PageWaiters may have been set by wait_on_page_bit_common(), and the reference dropped, just before shrink_page_list() succeeds in freezing its last page reference: in such a case, unlock_page() must be used. Follow the suggestion from Michal Hocko, just revert a978d6f52106 ("mm: unlockless reclaim") now: that optimization predates PageWaiters, and won't buy much these days; but we can reinstate it for the !PageWaiters case if anyone notices. It does raise the question: should vmscan.c's is_page_cache_freeable() and __remove_mapping() now treat a PageWaiters page as if an extra reference were held? Perhaps, but I don't think it matters much, since shrink_page_list() already had to win its trylock_page(), so waiters are not very common there: I noticed no difference when trying the bigger change, and it's surely not needed while put_and_wait_on_page_locked() is only used for page migration. [willy@infradead.org: add put_and_wait_on_page_locked() kerneldoc] Link: http://lkml.kernel.org/r/alpine.LSU.2.11.1811261121330.1116@eggly.anvils Signed-off-by: Hugh Dickins <hughd@google.com> Reported-by: Baoquan He <bhe@redhat.com> Tested-by: Baoquan He <bhe@redhat.com> Reviewed-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Michal Hocko <mhocko@suse.com> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Matthew Wilcox <willy@infradead.org> Cc: Baoquan He <bhe@redhat.com> Cc: David Hildenbrand <david@redhat.com> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: David Herrmann <dh.herrmann@gmail.com> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Christoph Lameter <cl@linux.com> Cc: Nick Piggin <npiggin@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-12-28 08:36:14 +00:00
*
* The caller should hold a reference on @folio. They expect the page to
mm: put_and_wait_on_page_locked() while page is migrated Waiting on a page migration entry has used wait_on_page_locked() all along since 2006: but you cannot safely wait_on_page_locked() without holding a reference to the page, and that extra reference is enough to make migrate_page_move_mapping() fail with -EAGAIN, when a racing task faults on the entry before migrate_page_move_mapping() gets there. And that failure is retried nine times, amplifying the pain when trying to migrate a popular page. With a single persistent faulter, migration sometimes succeeds; with two or three concurrent faulters, success becomes much less likely (and the more the page was mapped, the worse the overhead of unmapping and remapping it on each try). This is especially a problem for memory offlining, where the outer level retries forever (or until terminated from userspace), because a heavy refault workload can trigger an endless loop of migration failures. wait_on_page_locked() is the wrong tool for the job. David Herrmann (but was he the first?) noticed this issue in 2014: https://marc.info/?l=linux-mm&m=140110465608116&w=2 Tim Chen started a thread in August 2017 which appears relevant: https://marc.info/?l=linux-mm&m=150275941014915&w=2 where Kan Liang went on to implicate __migration_entry_wait(): https://marc.info/?l=linux-mm&m=150300268411980&w=2 and the thread ended up with the v4.14 commits: 2554db916586 ("sched/wait: Break up long wake list walk") 11a19c7b099f ("sched/wait: Introduce wakeup boomark in wake_up_page_bit") Baoquan He reported "Memory hotplug softlock issue" 14 November 2018: https://marc.info/?l=linux-mm&m=154217936431300&w=2 We have all assumed that it is essential to hold a page reference while waiting on a page lock: partly to guarantee that there is still a struct page when MEMORY_HOTREMOVE is configured, but also to protect against reuse of the struct page going to someone who then holds the page locked indefinitely, when the waiter can reasonably expect timely unlocking. But in fact, so long as wait_on_page_bit_common() does the put_page(), and is careful not to rely on struct page contents thereafter, there is no need to hold a reference to the page while waiting on it. That does mean that this case cannot go back through the loop: but that's fine for the page migration case, and even if used more widely, is limited by the "Stop walking if it's locked" optimization in wake_page_function(). Add interface put_and_wait_on_page_locked() to do this, using "behavior" enum in place of "lock" arg to wait_on_page_bit_common() to implement it. No interruptible or killable variant needed yet, but they might follow: I have a vague notion that reporting -EINTR should take precedence over return from wait_on_page_bit_common() without knowing the page state, so arrange it accordingly - but that may be nothing but pedantic. __migration_entry_wait() still has to take a brief reference to the page, prior to calling put_and_wait_on_page_locked(): but now that it is dropped before waiting, the chance of impeding page migration is very much reduced. Should we perhaps disable preemption across this? shrink_page_list()'s __ClearPageLocked(): that was a surprise! This survived a lot of testing before that showed up. PageWaiters may have been set by wait_on_page_bit_common(), and the reference dropped, just before shrink_page_list() succeeds in freezing its last page reference: in such a case, unlock_page() must be used. Follow the suggestion from Michal Hocko, just revert a978d6f52106 ("mm: unlockless reclaim") now: that optimization predates PageWaiters, and won't buy much these days; but we can reinstate it for the !PageWaiters case if anyone notices. It does raise the question: should vmscan.c's is_page_cache_freeable() and __remove_mapping() now treat a PageWaiters page as if an extra reference were held? Perhaps, but I don't think it matters much, since shrink_page_list() already had to win its trylock_page(), so waiters are not very common there: I noticed no difference when trying the bigger change, and it's surely not needed while put_and_wait_on_page_locked() is only used for page migration. [willy@infradead.org: add put_and_wait_on_page_locked() kerneldoc] Link: http://lkml.kernel.org/r/alpine.LSU.2.11.1811261121330.1116@eggly.anvils Signed-off-by: Hugh Dickins <hughd@google.com> Reported-by: Baoquan He <bhe@redhat.com> Tested-by: Baoquan He <bhe@redhat.com> Reviewed-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Michal Hocko <mhocko@suse.com> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Matthew Wilcox <willy@infradead.org> Cc: Baoquan He <bhe@redhat.com> Cc: David Hildenbrand <david@redhat.com> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: David Herrmann <dh.herrmann@gmail.com> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Christoph Lameter <cl@linux.com> Cc: Nick Piggin <npiggin@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-12-28 08:36:14 +00:00
* become unlocked relatively soon, but do not wish to hold up migration
* (for example) by holding the reference while waiting for the folio to
mm: put_and_wait_on_page_locked() while page is migrated Waiting on a page migration entry has used wait_on_page_locked() all along since 2006: but you cannot safely wait_on_page_locked() without holding a reference to the page, and that extra reference is enough to make migrate_page_move_mapping() fail with -EAGAIN, when a racing task faults on the entry before migrate_page_move_mapping() gets there. And that failure is retried nine times, amplifying the pain when trying to migrate a popular page. With a single persistent faulter, migration sometimes succeeds; with two or three concurrent faulters, success becomes much less likely (and the more the page was mapped, the worse the overhead of unmapping and remapping it on each try). This is especially a problem for memory offlining, where the outer level retries forever (or until terminated from userspace), because a heavy refault workload can trigger an endless loop of migration failures. wait_on_page_locked() is the wrong tool for the job. David Herrmann (but was he the first?) noticed this issue in 2014: https://marc.info/?l=linux-mm&m=140110465608116&w=2 Tim Chen started a thread in August 2017 which appears relevant: https://marc.info/?l=linux-mm&m=150275941014915&w=2 where Kan Liang went on to implicate __migration_entry_wait(): https://marc.info/?l=linux-mm&m=150300268411980&w=2 and the thread ended up with the v4.14 commits: 2554db916586 ("sched/wait: Break up long wake list walk") 11a19c7b099f ("sched/wait: Introduce wakeup boomark in wake_up_page_bit") Baoquan He reported "Memory hotplug softlock issue" 14 November 2018: https://marc.info/?l=linux-mm&m=154217936431300&w=2 We have all assumed that it is essential to hold a page reference while waiting on a page lock: partly to guarantee that there is still a struct page when MEMORY_HOTREMOVE is configured, but also to protect against reuse of the struct page going to someone who then holds the page locked indefinitely, when the waiter can reasonably expect timely unlocking. But in fact, so long as wait_on_page_bit_common() does the put_page(), and is careful not to rely on struct page contents thereafter, there is no need to hold a reference to the page while waiting on it. That does mean that this case cannot go back through the loop: but that's fine for the page migration case, and even if used more widely, is limited by the "Stop walking if it's locked" optimization in wake_page_function(). Add interface put_and_wait_on_page_locked() to do this, using "behavior" enum in place of "lock" arg to wait_on_page_bit_common() to implement it. No interruptible or killable variant needed yet, but they might follow: I have a vague notion that reporting -EINTR should take precedence over return from wait_on_page_bit_common() without knowing the page state, so arrange it accordingly - but that may be nothing but pedantic. __migration_entry_wait() still has to take a brief reference to the page, prior to calling put_and_wait_on_page_locked(): but now that it is dropped before waiting, the chance of impeding page migration is very much reduced. Should we perhaps disable preemption across this? shrink_page_list()'s __ClearPageLocked(): that was a surprise! This survived a lot of testing before that showed up. PageWaiters may have been set by wait_on_page_bit_common(), and the reference dropped, just before shrink_page_list() succeeds in freezing its last page reference: in such a case, unlock_page() must be used. Follow the suggestion from Michal Hocko, just revert a978d6f52106 ("mm: unlockless reclaim") now: that optimization predates PageWaiters, and won't buy much these days; but we can reinstate it for the !PageWaiters case if anyone notices. It does raise the question: should vmscan.c's is_page_cache_freeable() and __remove_mapping() now treat a PageWaiters page as if an extra reference were held? Perhaps, but I don't think it matters much, since shrink_page_list() already had to win its trylock_page(), so waiters are not very common there: I noticed no difference when trying the bigger change, and it's surely not needed while put_and_wait_on_page_locked() is only used for page migration. [willy@infradead.org: add put_and_wait_on_page_locked() kerneldoc] Link: http://lkml.kernel.org/r/alpine.LSU.2.11.1811261121330.1116@eggly.anvils Signed-off-by: Hugh Dickins <hughd@google.com> Reported-by: Baoquan He <bhe@redhat.com> Tested-by: Baoquan He <bhe@redhat.com> Reviewed-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Michal Hocko <mhocko@suse.com> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Matthew Wilcox <willy@infradead.org> Cc: Baoquan He <bhe@redhat.com> Cc: David Hildenbrand <david@redhat.com> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: David Herrmann <dh.herrmann@gmail.com> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Christoph Lameter <cl@linux.com> Cc: Nick Piggin <npiggin@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-12-28 08:36:14 +00:00
* come unlocked. After this function returns, the caller should not
* dereference @folio.
*
* Return: 0 if the folio was unlocked or -EINTR if interrupted by a signal.
mm: put_and_wait_on_page_locked() while page is migrated Waiting on a page migration entry has used wait_on_page_locked() all along since 2006: but you cannot safely wait_on_page_locked() without holding a reference to the page, and that extra reference is enough to make migrate_page_move_mapping() fail with -EAGAIN, when a racing task faults on the entry before migrate_page_move_mapping() gets there. And that failure is retried nine times, amplifying the pain when trying to migrate a popular page. With a single persistent faulter, migration sometimes succeeds; with two or three concurrent faulters, success becomes much less likely (and the more the page was mapped, the worse the overhead of unmapping and remapping it on each try). This is especially a problem for memory offlining, where the outer level retries forever (or until terminated from userspace), because a heavy refault workload can trigger an endless loop of migration failures. wait_on_page_locked() is the wrong tool for the job. David Herrmann (but was he the first?) noticed this issue in 2014: https://marc.info/?l=linux-mm&m=140110465608116&w=2 Tim Chen started a thread in August 2017 which appears relevant: https://marc.info/?l=linux-mm&m=150275941014915&w=2 where Kan Liang went on to implicate __migration_entry_wait(): https://marc.info/?l=linux-mm&m=150300268411980&w=2 and the thread ended up with the v4.14 commits: 2554db916586 ("sched/wait: Break up long wake list walk") 11a19c7b099f ("sched/wait: Introduce wakeup boomark in wake_up_page_bit") Baoquan He reported "Memory hotplug softlock issue" 14 November 2018: https://marc.info/?l=linux-mm&m=154217936431300&w=2 We have all assumed that it is essential to hold a page reference while waiting on a page lock: partly to guarantee that there is still a struct page when MEMORY_HOTREMOVE is configured, but also to protect against reuse of the struct page going to someone who then holds the page locked indefinitely, when the waiter can reasonably expect timely unlocking. But in fact, so long as wait_on_page_bit_common() does the put_page(), and is careful not to rely on struct page contents thereafter, there is no need to hold a reference to the page while waiting on it. That does mean that this case cannot go back through the loop: but that's fine for the page migration case, and even if used more widely, is limited by the "Stop walking if it's locked" optimization in wake_page_function(). Add interface put_and_wait_on_page_locked() to do this, using "behavior" enum in place of "lock" arg to wait_on_page_bit_common() to implement it. No interruptible or killable variant needed yet, but they might follow: I have a vague notion that reporting -EINTR should take precedence over return from wait_on_page_bit_common() without knowing the page state, so arrange it accordingly - but that may be nothing but pedantic. __migration_entry_wait() still has to take a brief reference to the page, prior to calling put_and_wait_on_page_locked(): but now that it is dropped before waiting, the chance of impeding page migration is very much reduced. Should we perhaps disable preemption across this? shrink_page_list()'s __ClearPageLocked(): that was a surprise! This survived a lot of testing before that showed up. PageWaiters may have been set by wait_on_page_bit_common(), and the reference dropped, just before shrink_page_list() succeeds in freezing its last page reference: in such a case, unlock_page() must be used. Follow the suggestion from Michal Hocko, just revert a978d6f52106 ("mm: unlockless reclaim") now: that optimization predates PageWaiters, and won't buy much these days; but we can reinstate it for the !PageWaiters case if anyone notices. It does raise the question: should vmscan.c's is_page_cache_freeable() and __remove_mapping() now treat a PageWaiters page as if an extra reference were held? Perhaps, but I don't think it matters much, since shrink_page_list() already had to win its trylock_page(), so waiters are not very common there: I noticed no difference when trying the bigger change, and it's surely not needed while put_and_wait_on_page_locked() is only used for page migration. [willy@infradead.org: add put_and_wait_on_page_locked() kerneldoc] Link: http://lkml.kernel.org/r/alpine.LSU.2.11.1811261121330.1116@eggly.anvils Signed-off-by: Hugh Dickins <hughd@google.com> Reported-by: Baoquan He <bhe@redhat.com> Tested-by: Baoquan He <bhe@redhat.com> Reviewed-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Michal Hocko <mhocko@suse.com> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Matthew Wilcox <willy@infradead.org> Cc: Baoquan He <bhe@redhat.com> Cc: David Hildenbrand <david@redhat.com> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: David Herrmann <dh.herrmann@gmail.com> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Christoph Lameter <cl@linux.com> Cc: Nick Piggin <npiggin@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-12-28 08:36:14 +00:00
*/
static int folio_put_wait_locked(struct folio *folio, int state)
mm: put_and_wait_on_page_locked() while page is migrated Waiting on a page migration entry has used wait_on_page_locked() all along since 2006: but you cannot safely wait_on_page_locked() without holding a reference to the page, and that extra reference is enough to make migrate_page_move_mapping() fail with -EAGAIN, when a racing task faults on the entry before migrate_page_move_mapping() gets there. And that failure is retried nine times, amplifying the pain when trying to migrate a popular page. With a single persistent faulter, migration sometimes succeeds; with two or three concurrent faulters, success becomes much less likely (and the more the page was mapped, the worse the overhead of unmapping and remapping it on each try). This is especially a problem for memory offlining, where the outer level retries forever (or until terminated from userspace), because a heavy refault workload can trigger an endless loop of migration failures. wait_on_page_locked() is the wrong tool for the job. David Herrmann (but was he the first?) noticed this issue in 2014: https://marc.info/?l=linux-mm&m=140110465608116&w=2 Tim Chen started a thread in August 2017 which appears relevant: https://marc.info/?l=linux-mm&m=150275941014915&w=2 where Kan Liang went on to implicate __migration_entry_wait(): https://marc.info/?l=linux-mm&m=150300268411980&w=2 and the thread ended up with the v4.14 commits: 2554db916586 ("sched/wait: Break up long wake list walk") 11a19c7b099f ("sched/wait: Introduce wakeup boomark in wake_up_page_bit") Baoquan He reported "Memory hotplug softlock issue" 14 November 2018: https://marc.info/?l=linux-mm&m=154217936431300&w=2 We have all assumed that it is essential to hold a page reference while waiting on a page lock: partly to guarantee that there is still a struct page when MEMORY_HOTREMOVE is configured, but also to protect against reuse of the struct page going to someone who then holds the page locked indefinitely, when the waiter can reasonably expect timely unlocking. But in fact, so long as wait_on_page_bit_common() does the put_page(), and is careful not to rely on struct page contents thereafter, there is no need to hold a reference to the page while waiting on it. That does mean that this case cannot go back through the loop: but that's fine for the page migration case, and even if used more widely, is limited by the "Stop walking if it's locked" optimization in wake_page_function(). Add interface put_and_wait_on_page_locked() to do this, using "behavior" enum in place of "lock" arg to wait_on_page_bit_common() to implement it. No interruptible or killable variant needed yet, but they might follow: I have a vague notion that reporting -EINTR should take precedence over return from wait_on_page_bit_common() without knowing the page state, so arrange it accordingly - but that may be nothing but pedantic. __migration_entry_wait() still has to take a brief reference to the page, prior to calling put_and_wait_on_page_locked(): but now that it is dropped before waiting, the chance of impeding page migration is very much reduced. Should we perhaps disable preemption across this? shrink_page_list()'s __ClearPageLocked(): that was a surprise! This survived a lot of testing before that showed up. PageWaiters may have been set by wait_on_page_bit_common(), and the reference dropped, just before shrink_page_list() succeeds in freezing its last page reference: in such a case, unlock_page() must be used. Follow the suggestion from Michal Hocko, just revert a978d6f52106 ("mm: unlockless reclaim") now: that optimization predates PageWaiters, and won't buy much these days; but we can reinstate it for the !PageWaiters case if anyone notices. It does raise the question: should vmscan.c's is_page_cache_freeable() and __remove_mapping() now treat a PageWaiters page as if an extra reference were held? Perhaps, but I don't think it matters much, since shrink_page_list() already had to win its trylock_page(), so waiters are not very common there: I noticed no difference when trying the bigger change, and it's surely not needed while put_and_wait_on_page_locked() is only used for page migration. [willy@infradead.org: add put_and_wait_on_page_locked() kerneldoc] Link: http://lkml.kernel.org/r/alpine.LSU.2.11.1811261121330.1116@eggly.anvils Signed-off-by: Hugh Dickins <hughd@google.com> Reported-by: Baoquan He <bhe@redhat.com> Tested-by: Baoquan He <bhe@redhat.com> Reviewed-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Michal Hocko <mhocko@suse.com> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Matthew Wilcox <willy@infradead.org> Cc: Baoquan He <bhe@redhat.com> Cc: David Hildenbrand <david@redhat.com> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: David Herrmann <dh.herrmann@gmail.com> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Christoph Lameter <cl@linux.com> Cc: Nick Piggin <npiggin@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-12-28 08:36:14 +00:00
{
return folio_wait_bit_common(folio, PG_locked, state, DROP);
mm: put_and_wait_on_page_locked() while page is migrated Waiting on a page migration entry has used wait_on_page_locked() all along since 2006: but you cannot safely wait_on_page_locked() without holding a reference to the page, and that extra reference is enough to make migrate_page_move_mapping() fail with -EAGAIN, when a racing task faults on the entry before migrate_page_move_mapping() gets there. And that failure is retried nine times, amplifying the pain when trying to migrate a popular page. With a single persistent faulter, migration sometimes succeeds; with two or three concurrent faulters, success becomes much less likely (and the more the page was mapped, the worse the overhead of unmapping and remapping it on each try). This is especially a problem for memory offlining, where the outer level retries forever (or until terminated from userspace), because a heavy refault workload can trigger an endless loop of migration failures. wait_on_page_locked() is the wrong tool for the job. David Herrmann (but was he the first?) noticed this issue in 2014: https://marc.info/?l=linux-mm&m=140110465608116&w=2 Tim Chen started a thread in August 2017 which appears relevant: https://marc.info/?l=linux-mm&m=150275941014915&w=2 where Kan Liang went on to implicate __migration_entry_wait(): https://marc.info/?l=linux-mm&m=150300268411980&w=2 and the thread ended up with the v4.14 commits: 2554db916586 ("sched/wait: Break up long wake list walk") 11a19c7b099f ("sched/wait: Introduce wakeup boomark in wake_up_page_bit") Baoquan He reported "Memory hotplug softlock issue" 14 November 2018: https://marc.info/?l=linux-mm&m=154217936431300&w=2 We have all assumed that it is essential to hold a page reference while waiting on a page lock: partly to guarantee that there is still a struct page when MEMORY_HOTREMOVE is configured, but also to protect against reuse of the struct page going to someone who then holds the page locked indefinitely, when the waiter can reasonably expect timely unlocking. But in fact, so long as wait_on_page_bit_common() does the put_page(), and is careful not to rely on struct page contents thereafter, there is no need to hold a reference to the page while waiting on it. That does mean that this case cannot go back through the loop: but that's fine for the page migration case, and even if used more widely, is limited by the "Stop walking if it's locked" optimization in wake_page_function(). Add interface put_and_wait_on_page_locked() to do this, using "behavior" enum in place of "lock" arg to wait_on_page_bit_common() to implement it. No interruptible or killable variant needed yet, but they might follow: I have a vague notion that reporting -EINTR should take precedence over return from wait_on_page_bit_common() without knowing the page state, so arrange it accordingly - but that may be nothing but pedantic. __migration_entry_wait() still has to take a brief reference to the page, prior to calling put_and_wait_on_page_locked(): but now that it is dropped before waiting, the chance of impeding page migration is very much reduced. Should we perhaps disable preemption across this? shrink_page_list()'s __ClearPageLocked(): that was a surprise! This survived a lot of testing before that showed up. PageWaiters may have been set by wait_on_page_bit_common(), and the reference dropped, just before shrink_page_list() succeeds in freezing its last page reference: in such a case, unlock_page() must be used. Follow the suggestion from Michal Hocko, just revert a978d6f52106 ("mm: unlockless reclaim") now: that optimization predates PageWaiters, and won't buy much these days; but we can reinstate it for the !PageWaiters case if anyone notices. It does raise the question: should vmscan.c's is_page_cache_freeable() and __remove_mapping() now treat a PageWaiters page as if an extra reference were held? Perhaps, but I don't think it matters much, since shrink_page_list() already had to win its trylock_page(), so waiters are not very common there: I noticed no difference when trying the bigger change, and it's surely not needed while put_and_wait_on_page_locked() is only used for page migration. [willy@infradead.org: add put_and_wait_on_page_locked() kerneldoc] Link: http://lkml.kernel.org/r/alpine.LSU.2.11.1811261121330.1116@eggly.anvils Signed-off-by: Hugh Dickins <hughd@google.com> Reported-by: Baoquan He <bhe@redhat.com> Tested-by: Baoquan He <bhe@redhat.com> Reviewed-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Michal Hocko <mhocko@suse.com> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Matthew Wilcox <willy@infradead.org> Cc: Baoquan He <bhe@redhat.com> Cc: David Hildenbrand <david@redhat.com> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: David Herrmann <dh.herrmann@gmail.com> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Christoph Lameter <cl@linux.com> Cc: Nick Piggin <npiggin@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-12-28 08:36:14 +00:00
}
/**
* folio_add_wait_queue - Add an arbitrary waiter to a folio's wait queue
* @folio: Folio defining the wait queue of interest
* @waiter: Waiter to add to the queue
*
* Add an arbitrary @waiter to the wait queue for the nominated @folio.
*/
void folio_add_wait_queue(struct folio *folio, wait_queue_entry_t *waiter)
{
wait_queue_head_t *q = folio_waitqueue(folio);
unsigned long flags;
spin_lock_irqsave(&q->lock, flags);
__add_wait_queue_entry_tail(q, waiter);
folio_set_waiters(folio);
spin_unlock_irqrestore(&q->lock, flags);
}
EXPORT_SYMBOL_GPL(folio_add_wait_queue);
/**
* folio_unlock - Unlock a locked folio.
* @folio: The folio.
*
* Unlocks the folio and wakes up any thread sleeping on the page lock.
*
* Context: May be called from interrupt or process context. May not be
* called from NMI context.
*/
void folio_unlock(struct folio *folio)
{
/* Bit 7 allows x86 to check the byte's sign bit */
mm: optimize PageWaiters bit use for unlock_page() In commit 62906027091f ("mm: add PageWaiters indicating tasks are waiting for a page bit") Nick Piggin made our page locking no longer unconditionally touch the hashed page waitqueue, which not only helps performance in general, but is particularly helpful on NUMA machines where the hashed wait queues can bounce around a lot. However, the "clear lock bit atomically and then test the waiters bit" sequence turns out to be much more expensive than it needs to be, because you get a nasty stall when trying to access the same word that just got updated atomically. On architectures where locking is done with LL/SC, this would be trivial to fix with a new primitive that clears one bit and tests another atomically, but that ends up not working on x86, where the only atomic operations that return the result end up being cmpxchg and xadd. The atomic bit operations return the old value of the same bit we changed, not the value of an unrelated bit. On x86, we could put the lock bit in the high bit of the byte, and use "xadd" with that bit (where the overflow ends up not touching other bits), and look at the other bits of the result. However, an even simpler model is to just use a regular atomic "and" to clear the lock bit, and then the sign bit in eflags will indicate the resulting state of the unrelated bit #7. So by moving the PageWaiters bit up to bit #7, we can atomically clear the lock bit and test the waiters bit on x86 too. And architectures with LL/SC (which is all the usual RISC suspects), the particular bit doesn't matter, so they are fine with this approach too. This avoids the extra access to the same atomic word, and thus avoids the costly stall at page unlock time. The only downside is that the interface ends up being a bit odd and specialized: clear a bit in a byte, and test the sign bit. Nick doesn't love the resulting name of the new primitive, but I'd rather make the name be descriptive and very clear about the limitation imposed by trying to work across all relevant architectures than make it be some generic thing that doesn't make the odd semantics explicit. So this introduces the new architecture primitive clear_bit_unlock_is_negative_byte(); and adds the trivial implementation for x86. We have a generic non-optimized fallback (that just does a "clear_bit()"+"test_bit(7)" combination) which can be overridden by any architecture that can do better. According to Nick, Power has the same hickup x86 has, for example, but some other architectures may not even care. All these optimizations mean that my page locking stress-test (which is just executing a lot of small short-lived shell scripts: "make test" in the git source tree) no longer makes our page locking look horribly bad. Before all these optimizations, just the unlock_page() costs were just over 3% of all CPU overhead on "make test". After this, it's down to 0.66%, so just a quarter of the cost it used to be. (The difference on NUMA is bigger, but there this micro-optimization is likely less noticeable, since the big issue on NUMA was not the accesses to 'struct page', but the waitqueue accesses that were already removed by Nick's earlier commit). Acked-by: Nick Piggin <npiggin@gmail.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Bob Peterson <rpeterso@redhat.com> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Andrew Lutomirski <luto@kernel.org> Cc: Andreas Gruenbacher <agruenba@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Mel Gorman <mgorman@techsingularity.net> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-12-27 19:40:38 +00:00
BUILD_BUG_ON(PG_waiters != 7);
BUILD_BUG_ON(PG_locked > 7);
VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
if (folio_xor_flags_has_waiters(folio, 1 << PG_locked))
folio_wake_bit(folio, PG_locked);
}
EXPORT_SYMBOL(folio_unlock);
/**
* folio_end_read - End read on a folio.
* @folio: The folio.
* @success: True if all reads completed successfully.
*
* When all reads against a folio have completed, filesystems should
* call this function to let the pagecache know that no more reads
* are outstanding. This will unlock the folio and wake up any thread
* sleeping on the lock. The folio will also be marked uptodate if all
* reads succeeded.
*
* Context: May be called from interrupt or process context. May not be
* called from NMI context.
*/
void folio_end_read(struct folio *folio, bool success)
{
unsigned long mask = 1 << PG_locked;
/* Must be in bottom byte for x86 to work */
BUILD_BUG_ON(PG_uptodate > 7);
VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
VM_BUG_ON_FOLIO(folio_test_uptodate(folio), folio);
if (likely(success))
mask |= 1 << PG_uptodate;
if (folio_xor_flags_has_waiters(folio, mask))
folio_wake_bit(folio, PG_locked);
}
EXPORT_SYMBOL(folio_end_read);
mm: Add set/end/wait functions for PG_private_2 Add three functions to manipulate PG_private_2: (*) set_page_private_2() - Set the flag and take an appropriate reference on the flagged page. (*) end_page_private_2() - Clear the flag, drop the reference and wake up any waiters, somewhat analogously with end_page_writeback(). (*) wait_on_page_private_2() - Wait for the flag to be cleared. Wrappers will need to be placed in the netfs lib header in the patch that adds that. [This implements a suggestion by Linus[1] to not mix the terminology of PG_private_2 and PG_fscache in the mm core function] Changes: v7: - Use compound_head() in all the functions to make them THP safe[6]. v5: - Add set and end functions, calling the end function end rather than unlock[3]. - Keep a ref on the page when PG_private_2 is set[4][5]. v4: - Remove extern from the declaration[2]. Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org> Tested-by: Jeff Layton <jlayton@kernel.org> Tested-by: Dave Wysochanski <dwysocha@redhat.com> Tested-By: Marc Dionne <marc.dionne@auristor.com> cc: Alexander Viro <viro@zeniv.linux.org.uk> cc: Christoph Hellwig <hch@lst.de> cc: linux-mm@kvack.org cc: linux-cachefs@redhat.com cc: linux-afs@lists.infradead.org cc: linux-nfs@vger.kernel.org cc: linux-cifs@vger.kernel.org cc: ceph-devel@vger.kernel.org cc: v9fs-developer@lists.sourceforge.net cc: linux-fsdevel@vger.kernel.org Link: https://lore.kernel.org/r/1330473.1612974547@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/CAHk-=wjgA-74ddehziVk=XAEMTKswPu1Yw4uaro1R3ibs27ztw@mail.gmail.com/ [1] Link: https://lore.kernel.org/r/20210216102659.GA27714@lst.de/ [2] Link: https://lore.kernel.org/r/161340387944.1303470.7944159520278177652.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/161539528910.286939.1252328699383291173.stgit@warthog.procyon.org.uk # v4 Link: https://lore.kernel.org/r/20210321105309.GG3420@casper.infradead.org [3] Link: https://lore.kernel.org/r/CAHk-=wh+2gbF7XEjYc=HV9w_2uVzVf7vs60BPz0gFA=+pUm3ww@mail.gmail.com/ [4] Link: https://lore.kernel.org/r/CAHk-=wjSGsRj7xwhSMQ6dAQiz53xA39pOG+XA_WeTgwBBu4uqg@mail.gmail.com/ [5] Link: https://lore.kernel.org/r/20210408145057.GN2531743@casper.infradead.org/ [6] Link: https://lore.kernel.org/r/161653788200.2770958.9517755716374927208.stgit@warthog.procyon.org.uk/ # v5 Link: https://lore.kernel.org/r/161789066013.6155.9816857201817288382.stgit@warthog.procyon.org.uk/ # v6
2020-02-10 10:00:21 +00:00
/**
* folio_end_private_2 - Clear PG_private_2 and wake any waiters.
* @folio: The folio.
mm: Add set/end/wait functions for PG_private_2 Add three functions to manipulate PG_private_2: (*) set_page_private_2() - Set the flag and take an appropriate reference on the flagged page. (*) end_page_private_2() - Clear the flag, drop the reference and wake up any waiters, somewhat analogously with end_page_writeback(). (*) wait_on_page_private_2() - Wait for the flag to be cleared. Wrappers will need to be placed in the netfs lib header in the patch that adds that. [This implements a suggestion by Linus[1] to not mix the terminology of PG_private_2 and PG_fscache in the mm core function] Changes: v7: - Use compound_head() in all the functions to make them THP safe[6]. v5: - Add set and end functions, calling the end function end rather than unlock[3]. - Keep a ref on the page when PG_private_2 is set[4][5]. v4: - Remove extern from the declaration[2]. Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org> Tested-by: Jeff Layton <jlayton@kernel.org> Tested-by: Dave Wysochanski <dwysocha@redhat.com> Tested-By: Marc Dionne <marc.dionne@auristor.com> cc: Alexander Viro <viro@zeniv.linux.org.uk> cc: Christoph Hellwig <hch@lst.de> cc: linux-mm@kvack.org cc: linux-cachefs@redhat.com cc: linux-afs@lists.infradead.org cc: linux-nfs@vger.kernel.org cc: linux-cifs@vger.kernel.org cc: ceph-devel@vger.kernel.org cc: v9fs-developer@lists.sourceforge.net cc: linux-fsdevel@vger.kernel.org Link: https://lore.kernel.org/r/1330473.1612974547@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/CAHk-=wjgA-74ddehziVk=XAEMTKswPu1Yw4uaro1R3ibs27ztw@mail.gmail.com/ [1] Link: https://lore.kernel.org/r/20210216102659.GA27714@lst.de/ [2] Link: https://lore.kernel.org/r/161340387944.1303470.7944159520278177652.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/161539528910.286939.1252328699383291173.stgit@warthog.procyon.org.uk # v4 Link: https://lore.kernel.org/r/20210321105309.GG3420@casper.infradead.org [3] Link: https://lore.kernel.org/r/CAHk-=wh+2gbF7XEjYc=HV9w_2uVzVf7vs60BPz0gFA=+pUm3ww@mail.gmail.com/ [4] Link: https://lore.kernel.org/r/CAHk-=wjSGsRj7xwhSMQ6dAQiz53xA39pOG+XA_WeTgwBBu4uqg@mail.gmail.com/ [5] Link: https://lore.kernel.org/r/20210408145057.GN2531743@casper.infradead.org/ [6] Link: https://lore.kernel.org/r/161653788200.2770958.9517755716374927208.stgit@warthog.procyon.org.uk/ # v5 Link: https://lore.kernel.org/r/161789066013.6155.9816857201817288382.stgit@warthog.procyon.org.uk/ # v6
2020-02-10 10:00:21 +00:00
*
* Clear the PG_private_2 bit on a folio and wake up any sleepers waiting for
* it. The folio reference held for PG_private_2 being set is released.
mm: Add set/end/wait functions for PG_private_2 Add three functions to manipulate PG_private_2: (*) set_page_private_2() - Set the flag and take an appropriate reference on the flagged page. (*) end_page_private_2() - Clear the flag, drop the reference and wake up any waiters, somewhat analogously with end_page_writeback(). (*) wait_on_page_private_2() - Wait for the flag to be cleared. Wrappers will need to be placed in the netfs lib header in the patch that adds that. [This implements a suggestion by Linus[1] to not mix the terminology of PG_private_2 and PG_fscache in the mm core function] Changes: v7: - Use compound_head() in all the functions to make them THP safe[6]. v5: - Add set and end functions, calling the end function end rather than unlock[3]. - Keep a ref on the page when PG_private_2 is set[4][5]. v4: - Remove extern from the declaration[2]. Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org> Tested-by: Jeff Layton <jlayton@kernel.org> Tested-by: Dave Wysochanski <dwysocha@redhat.com> Tested-By: Marc Dionne <marc.dionne@auristor.com> cc: Alexander Viro <viro@zeniv.linux.org.uk> cc: Christoph Hellwig <hch@lst.de> cc: linux-mm@kvack.org cc: linux-cachefs@redhat.com cc: linux-afs@lists.infradead.org cc: linux-nfs@vger.kernel.org cc: linux-cifs@vger.kernel.org cc: ceph-devel@vger.kernel.org cc: v9fs-developer@lists.sourceforge.net cc: linux-fsdevel@vger.kernel.org Link: https://lore.kernel.org/r/1330473.1612974547@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/CAHk-=wjgA-74ddehziVk=XAEMTKswPu1Yw4uaro1R3ibs27ztw@mail.gmail.com/ [1] Link: https://lore.kernel.org/r/20210216102659.GA27714@lst.de/ [2] Link: https://lore.kernel.org/r/161340387944.1303470.7944159520278177652.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/161539528910.286939.1252328699383291173.stgit@warthog.procyon.org.uk # v4 Link: https://lore.kernel.org/r/20210321105309.GG3420@casper.infradead.org [3] Link: https://lore.kernel.org/r/CAHk-=wh+2gbF7XEjYc=HV9w_2uVzVf7vs60BPz0gFA=+pUm3ww@mail.gmail.com/ [4] Link: https://lore.kernel.org/r/CAHk-=wjSGsRj7xwhSMQ6dAQiz53xA39pOG+XA_WeTgwBBu4uqg@mail.gmail.com/ [5] Link: https://lore.kernel.org/r/20210408145057.GN2531743@casper.infradead.org/ [6] Link: https://lore.kernel.org/r/161653788200.2770958.9517755716374927208.stgit@warthog.procyon.org.uk/ # v5 Link: https://lore.kernel.org/r/161789066013.6155.9816857201817288382.stgit@warthog.procyon.org.uk/ # v6
2020-02-10 10:00:21 +00:00
*
* This is, for example, used when a netfs folio is being written to a local
* disk cache, thereby allowing writes to the cache for the same folio to be
mm: Add set/end/wait functions for PG_private_2 Add three functions to manipulate PG_private_2: (*) set_page_private_2() - Set the flag and take an appropriate reference on the flagged page. (*) end_page_private_2() - Clear the flag, drop the reference and wake up any waiters, somewhat analogously with end_page_writeback(). (*) wait_on_page_private_2() - Wait for the flag to be cleared. Wrappers will need to be placed in the netfs lib header in the patch that adds that. [This implements a suggestion by Linus[1] to not mix the terminology of PG_private_2 and PG_fscache in the mm core function] Changes: v7: - Use compound_head() in all the functions to make them THP safe[6]. v5: - Add set and end functions, calling the end function end rather than unlock[3]. - Keep a ref on the page when PG_private_2 is set[4][5]. v4: - Remove extern from the declaration[2]. Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org> Tested-by: Jeff Layton <jlayton@kernel.org> Tested-by: Dave Wysochanski <dwysocha@redhat.com> Tested-By: Marc Dionne <marc.dionne@auristor.com> cc: Alexander Viro <viro@zeniv.linux.org.uk> cc: Christoph Hellwig <hch@lst.de> cc: linux-mm@kvack.org cc: linux-cachefs@redhat.com cc: linux-afs@lists.infradead.org cc: linux-nfs@vger.kernel.org cc: linux-cifs@vger.kernel.org cc: ceph-devel@vger.kernel.org cc: v9fs-developer@lists.sourceforge.net cc: linux-fsdevel@vger.kernel.org Link: https://lore.kernel.org/r/1330473.1612974547@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/CAHk-=wjgA-74ddehziVk=XAEMTKswPu1Yw4uaro1R3ibs27ztw@mail.gmail.com/ [1] Link: https://lore.kernel.org/r/20210216102659.GA27714@lst.de/ [2] Link: https://lore.kernel.org/r/161340387944.1303470.7944159520278177652.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/161539528910.286939.1252328699383291173.stgit@warthog.procyon.org.uk # v4 Link: https://lore.kernel.org/r/20210321105309.GG3420@casper.infradead.org [3] Link: https://lore.kernel.org/r/CAHk-=wh+2gbF7XEjYc=HV9w_2uVzVf7vs60BPz0gFA=+pUm3ww@mail.gmail.com/ [4] Link: https://lore.kernel.org/r/CAHk-=wjSGsRj7xwhSMQ6dAQiz53xA39pOG+XA_WeTgwBBu4uqg@mail.gmail.com/ [5] Link: https://lore.kernel.org/r/20210408145057.GN2531743@casper.infradead.org/ [6] Link: https://lore.kernel.org/r/161653788200.2770958.9517755716374927208.stgit@warthog.procyon.org.uk/ # v5 Link: https://lore.kernel.org/r/161789066013.6155.9816857201817288382.stgit@warthog.procyon.org.uk/ # v6
2020-02-10 10:00:21 +00:00
* serialised.
*/
void folio_end_private_2(struct folio *folio)
mm: Add set/end/wait functions for PG_private_2 Add three functions to manipulate PG_private_2: (*) set_page_private_2() - Set the flag and take an appropriate reference on the flagged page. (*) end_page_private_2() - Clear the flag, drop the reference and wake up any waiters, somewhat analogously with end_page_writeback(). (*) wait_on_page_private_2() - Wait for the flag to be cleared. Wrappers will need to be placed in the netfs lib header in the patch that adds that. [This implements a suggestion by Linus[1] to not mix the terminology of PG_private_2 and PG_fscache in the mm core function] Changes: v7: - Use compound_head() in all the functions to make them THP safe[6]. v5: - Add set and end functions, calling the end function end rather than unlock[3]. - Keep a ref on the page when PG_private_2 is set[4][5]. v4: - Remove extern from the declaration[2]. Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org> Tested-by: Jeff Layton <jlayton@kernel.org> Tested-by: Dave Wysochanski <dwysocha@redhat.com> Tested-By: Marc Dionne <marc.dionne@auristor.com> cc: Alexander Viro <viro@zeniv.linux.org.uk> cc: Christoph Hellwig <hch@lst.de> cc: linux-mm@kvack.org cc: linux-cachefs@redhat.com cc: linux-afs@lists.infradead.org cc: linux-nfs@vger.kernel.org cc: linux-cifs@vger.kernel.org cc: ceph-devel@vger.kernel.org cc: v9fs-developer@lists.sourceforge.net cc: linux-fsdevel@vger.kernel.org Link: https://lore.kernel.org/r/1330473.1612974547@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/CAHk-=wjgA-74ddehziVk=XAEMTKswPu1Yw4uaro1R3ibs27ztw@mail.gmail.com/ [1] Link: https://lore.kernel.org/r/20210216102659.GA27714@lst.de/ [2] Link: https://lore.kernel.org/r/161340387944.1303470.7944159520278177652.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/161539528910.286939.1252328699383291173.stgit@warthog.procyon.org.uk # v4 Link: https://lore.kernel.org/r/20210321105309.GG3420@casper.infradead.org [3] Link: https://lore.kernel.org/r/CAHk-=wh+2gbF7XEjYc=HV9w_2uVzVf7vs60BPz0gFA=+pUm3ww@mail.gmail.com/ [4] Link: https://lore.kernel.org/r/CAHk-=wjSGsRj7xwhSMQ6dAQiz53xA39pOG+XA_WeTgwBBu4uqg@mail.gmail.com/ [5] Link: https://lore.kernel.org/r/20210408145057.GN2531743@casper.infradead.org/ [6] Link: https://lore.kernel.org/r/161653788200.2770958.9517755716374927208.stgit@warthog.procyon.org.uk/ # v5 Link: https://lore.kernel.org/r/161789066013.6155.9816857201817288382.stgit@warthog.procyon.org.uk/ # v6
2020-02-10 10:00:21 +00:00
{
VM_BUG_ON_FOLIO(!folio_test_private_2(folio), folio);
clear_bit_unlock(PG_private_2, folio_flags(folio, 0));
folio_wake_bit(folio, PG_private_2);
folio_put(folio);
mm: Add set/end/wait functions for PG_private_2 Add three functions to manipulate PG_private_2: (*) set_page_private_2() - Set the flag and take an appropriate reference on the flagged page. (*) end_page_private_2() - Clear the flag, drop the reference and wake up any waiters, somewhat analogously with end_page_writeback(). (*) wait_on_page_private_2() - Wait for the flag to be cleared. Wrappers will need to be placed in the netfs lib header in the patch that adds that. [This implements a suggestion by Linus[1] to not mix the terminology of PG_private_2 and PG_fscache in the mm core function] Changes: v7: - Use compound_head() in all the functions to make them THP safe[6]. v5: - Add set and end functions, calling the end function end rather than unlock[3]. - Keep a ref on the page when PG_private_2 is set[4][5]. v4: - Remove extern from the declaration[2]. Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org> Tested-by: Jeff Layton <jlayton@kernel.org> Tested-by: Dave Wysochanski <dwysocha@redhat.com> Tested-By: Marc Dionne <marc.dionne@auristor.com> cc: Alexander Viro <viro@zeniv.linux.org.uk> cc: Christoph Hellwig <hch@lst.de> cc: linux-mm@kvack.org cc: linux-cachefs@redhat.com cc: linux-afs@lists.infradead.org cc: linux-nfs@vger.kernel.org cc: linux-cifs@vger.kernel.org cc: ceph-devel@vger.kernel.org cc: v9fs-developer@lists.sourceforge.net cc: linux-fsdevel@vger.kernel.org Link: https://lore.kernel.org/r/1330473.1612974547@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/CAHk-=wjgA-74ddehziVk=XAEMTKswPu1Yw4uaro1R3ibs27ztw@mail.gmail.com/ [1] Link: https://lore.kernel.org/r/20210216102659.GA27714@lst.de/ [2] Link: https://lore.kernel.org/r/161340387944.1303470.7944159520278177652.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/161539528910.286939.1252328699383291173.stgit@warthog.procyon.org.uk # v4 Link: https://lore.kernel.org/r/20210321105309.GG3420@casper.infradead.org [3] Link: https://lore.kernel.org/r/CAHk-=wh+2gbF7XEjYc=HV9w_2uVzVf7vs60BPz0gFA=+pUm3ww@mail.gmail.com/ [4] Link: https://lore.kernel.org/r/CAHk-=wjSGsRj7xwhSMQ6dAQiz53xA39pOG+XA_WeTgwBBu4uqg@mail.gmail.com/ [5] Link: https://lore.kernel.org/r/20210408145057.GN2531743@casper.infradead.org/ [6] Link: https://lore.kernel.org/r/161653788200.2770958.9517755716374927208.stgit@warthog.procyon.org.uk/ # v5 Link: https://lore.kernel.org/r/161789066013.6155.9816857201817288382.stgit@warthog.procyon.org.uk/ # v6
2020-02-10 10:00:21 +00:00
}
EXPORT_SYMBOL(folio_end_private_2);
mm: Add set/end/wait functions for PG_private_2 Add three functions to manipulate PG_private_2: (*) set_page_private_2() - Set the flag and take an appropriate reference on the flagged page. (*) end_page_private_2() - Clear the flag, drop the reference and wake up any waiters, somewhat analogously with end_page_writeback(). (*) wait_on_page_private_2() - Wait for the flag to be cleared. Wrappers will need to be placed in the netfs lib header in the patch that adds that. [This implements a suggestion by Linus[1] to not mix the terminology of PG_private_2 and PG_fscache in the mm core function] Changes: v7: - Use compound_head() in all the functions to make them THP safe[6]. v5: - Add set and end functions, calling the end function end rather than unlock[3]. - Keep a ref on the page when PG_private_2 is set[4][5]. v4: - Remove extern from the declaration[2]. Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org> Tested-by: Jeff Layton <jlayton@kernel.org> Tested-by: Dave Wysochanski <dwysocha@redhat.com> Tested-By: Marc Dionne <marc.dionne@auristor.com> cc: Alexander Viro <viro@zeniv.linux.org.uk> cc: Christoph Hellwig <hch@lst.de> cc: linux-mm@kvack.org cc: linux-cachefs@redhat.com cc: linux-afs@lists.infradead.org cc: linux-nfs@vger.kernel.org cc: linux-cifs@vger.kernel.org cc: ceph-devel@vger.kernel.org cc: v9fs-developer@lists.sourceforge.net cc: linux-fsdevel@vger.kernel.org Link: https://lore.kernel.org/r/1330473.1612974547@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/CAHk-=wjgA-74ddehziVk=XAEMTKswPu1Yw4uaro1R3ibs27ztw@mail.gmail.com/ [1] Link: https://lore.kernel.org/r/20210216102659.GA27714@lst.de/ [2] Link: https://lore.kernel.org/r/161340387944.1303470.7944159520278177652.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/161539528910.286939.1252328699383291173.stgit@warthog.procyon.org.uk # v4 Link: https://lore.kernel.org/r/20210321105309.GG3420@casper.infradead.org [3] Link: https://lore.kernel.org/r/CAHk-=wh+2gbF7XEjYc=HV9w_2uVzVf7vs60BPz0gFA=+pUm3ww@mail.gmail.com/ [4] Link: https://lore.kernel.org/r/CAHk-=wjSGsRj7xwhSMQ6dAQiz53xA39pOG+XA_WeTgwBBu4uqg@mail.gmail.com/ [5] Link: https://lore.kernel.org/r/20210408145057.GN2531743@casper.infradead.org/ [6] Link: https://lore.kernel.org/r/161653788200.2770958.9517755716374927208.stgit@warthog.procyon.org.uk/ # v5 Link: https://lore.kernel.org/r/161789066013.6155.9816857201817288382.stgit@warthog.procyon.org.uk/ # v6
2020-02-10 10:00:21 +00:00
/**
* folio_wait_private_2 - Wait for PG_private_2 to be cleared on a folio.
* @folio: The folio to wait on.
mm: Add set/end/wait functions for PG_private_2 Add three functions to manipulate PG_private_2: (*) set_page_private_2() - Set the flag and take an appropriate reference on the flagged page. (*) end_page_private_2() - Clear the flag, drop the reference and wake up any waiters, somewhat analogously with end_page_writeback(). (*) wait_on_page_private_2() - Wait for the flag to be cleared. Wrappers will need to be placed in the netfs lib header in the patch that adds that. [This implements a suggestion by Linus[1] to not mix the terminology of PG_private_2 and PG_fscache in the mm core function] Changes: v7: - Use compound_head() in all the functions to make them THP safe[6]. v5: - Add set and end functions, calling the end function end rather than unlock[3]. - Keep a ref on the page when PG_private_2 is set[4][5]. v4: - Remove extern from the declaration[2]. Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org> Tested-by: Jeff Layton <jlayton@kernel.org> Tested-by: Dave Wysochanski <dwysocha@redhat.com> Tested-By: Marc Dionne <marc.dionne@auristor.com> cc: Alexander Viro <viro@zeniv.linux.org.uk> cc: Christoph Hellwig <hch@lst.de> cc: linux-mm@kvack.org cc: linux-cachefs@redhat.com cc: linux-afs@lists.infradead.org cc: linux-nfs@vger.kernel.org cc: linux-cifs@vger.kernel.org cc: ceph-devel@vger.kernel.org cc: v9fs-developer@lists.sourceforge.net cc: linux-fsdevel@vger.kernel.org Link: https://lore.kernel.org/r/1330473.1612974547@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/CAHk-=wjgA-74ddehziVk=XAEMTKswPu1Yw4uaro1R3ibs27ztw@mail.gmail.com/ [1] Link: https://lore.kernel.org/r/20210216102659.GA27714@lst.de/ [2] Link: https://lore.kernel.org/r/161340387944.1303470.7944159520278177652.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/161539528910.286939.1252328699383291173.stgit@warthog.procyon.org.uk # v4 Link: https://lore.kernel.org/r/20210321105309.GG3420@casper.infradead.org [3] Link: https://lore.kernel.org/r/CAHk-=wh+2gbF7XEjYc=HV9w_2uVzVf7vs60BPz0gFA=+pUm3ww@mail.gmail.com/ [4] Link: https://lore.kernel.org/r/CAHk-=wjSGsRj7xwhSMQ6dAQiz53xA39pOG+XA_WeTgwBBu4uqg@mail.gmail.com/ [5] Link: https://lore.kernel.org/r/20210408145057.GN2531743@casper.infradead.org/ [6] Link: https://lore.kernel.org/r/161653788200.2770958.9517755716374927208.stgit@warthog.procyon.org.uk/ # v5 Link: https://lore.kernel.org/r/161789066013.6155.9816857201817288382.stgit@warthog.procyon.org.uk/ # v6
2020-02-10 10:00:21 +00:00
*
* Wait for PG_private_2 to be cleared on a folio.
mm: Add set/end/wait functions for PG_private_2 Add three functions to manipulate PG_private_2: (*) set_page_private_2() - Set the flag and take an appropriate reference on the flagged page. (*) end_page_private_2() - Clear the flag, drop the reference and wake up any waiters, somewhat analogously with end_page_writeback(). (*) wait_on_page_private_2() - Wait for the flag to be cleared. Wrappers will need to be placed in the netfs lib header in the patch that adds that. [This implements a suggestion by Linus[1] to not mix the terminology of PG_private_2 and PG_fscache in the mm core function] Changes: v7: - Use compound_head() in all the functions to make them THP safe[6]. v5: - Add set and end functions, calling the end function end rather than unlock[3]. - Keep a ref on the page when PG_private_2 is set[4][5]. v4: - Remove extern from the declaration[2]. Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org> Tested-by: Jeff Layton <jlayton@kernel.org> Tested-by: Dave Wysochanski <dwysocha@redhat.com> Tested-By: Marc Dionne <marc.dionne@auristor.com> cc: Alexander Viro <viro@zeniv.linux.org.uk> cc: Christoph Hellwig <hch@lst.de> cc: linux-mm@kvack.org cc: linux-cachefs@redhat.com cc: linux-afs@lists.infradead.org cc: linux-nfs@vger.kernel.org cc: linux-cifs@vger.kernel.org cc: ceph-devel@vger.kernel.org cc: v9fs-developer@lists.sourceforge.net cc: linux-fsdevel@vger.kernel.org Link: https://lore.kernel.org/r/1330473.1612974547@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/CAHk-=wjgA-74ddehziVk=XAEMTKswPu1Yw4uaro1R3ibs27ztw@mail.gmail.com/ [1] Link: https://lore.kernel.org/r/20210216102659.GA27714@lst.de/ [2] Link: https://lore.kernel.org/r/161340387944.1303470.7944159520278177652.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/161539528910.286939.1252328699383291173.stgit@warthog.procyon.org.uk # v4 Link: https://lore.kernel.org/r/20210321105309.GG3420@casper.infradead.org [3] Link: https://lore.kernel.org/r/CAHk-=wh+2gbF7XEjYc=HV9w_2uVzVf7vs60BPz0gFA=+pUm3ww@mail.gmail.com/ [4] Link: https://lore.kernel.org/r/CAHk-=wjSGsRj7xwhSMQ6dAQiz53xA39pOG+XA_WeTgwBBu4uqg@mail.gmail.com/ [5] Link: https://lore.kernel.org/r/20210408145057.GN2531743@casper.infradead.org/ [6] Link: https://lore.kernel.org/r/161653788200.2770958.9517755716374927208.stgit@warthog.procyon.org.uk/ # v5 Link: https://lore.kernel.org/r/161789066013.6155.9816857201817288382.stgit@warthog.procyon.org.uk/ # v6
2020-02-10 10:00:21 +00:00
*/
void folio_wait_private_2(struct folio *folio)
mm: Add set/end/wait functions for PG_private_2 Add three functions to manipulate PG_private_2: (*) set_page_private_2() - Set the flag and take an appropriate reference on the flagged page. (*) end_page_private_2() - Clear the flag, drop the reference and wake up any waiters, somewhat analogously with end_page_writeback(). (*) wait_on_page_private_2() - Wait for the flag to be cleared. Wrappers will need to be placed in the netfs lib header in the patch that adds that. [This implements a suggestion by Linus[1] to not mix the terminology of PG_private_2 and PG_fscache in the mm core function] Changes: v7: - Use compound_head() in all the functions to make them THP safe[6]. v5: - Add set and end functions, calling the end function end rather than unlock[3]. - Keep a ref on the page when PG_private_2 is set[4][5]. v4: - Remove extern from the declaration[2]. Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org> Tested-by: Jeff Layton <jlayton@kernel.org> Tested-by: Dave Wysochanski <dwysocha@redhat.com> Tested-By: Marc Dionne <marc.dionne@auristor.com> cc: Alexander Viro <viro@zeniv.linux.org.uk> cc: Christoph Hellwig <hch@lst.de> cc: linux-mm@kvack.org cc: linux-cachefs@redhat.com cc: linux-afs@lists.infradead.org cc: linux-nfs@vger.kernel.org cc: linux-cifs@vger.kernel.org cc: ceph-devel@vger.kernel.org cc: v9fs-developer@lists.sourceforge.net cc: linux-fsdevel@vger.kernel.org Link: https://lore.kernel.org/r/1330473.1612974547@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/CAHk-=wjgA-74ddehziVk=XAEMTKswPu1Yw4uaro1R3ibs27ztw@mail.gmail.com/ [1] Link: https://lore.kernel.org/r/20210216102659.GA27714@lst.de/ [2] Link: https://lore.kernel.org/r/161340387944.1303470.7944159520278177652.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/161539528910.286939.1252328699383291173.stgit@warthog.procyon.org.uk # v4 Link: https://lore.kernel.org/r/20210321105309.GG3420@casper.infradead.org [3] Link: https://lore.kernel.org/r/CAHk-=wh+2gbF7XEjYc=HV9w_2uVzVf7vs60BPz0gFA=+pUm3ww@mail.gmail.com/ [4] Link: https://lore.kernel.org/r/CAHk-=wjSGsRj7xwhSMQ6dAQiz53xA39pOG+XA_WeTgwBBu4uqg@mail.gmail.com/ [5] Link: https://lore.kernel.org/r/20210408145057.GN2531743@casper.infradead.org/ [6] Link: https://lore.kernel.org/r/161653788200.2770958.9517755716374927208.stgit@warthog.procyon.org.uk/ # v5 Link: https://lore.kernel.org/r/161789066013.6155.9816857201817288382.stgit@warthog.procyon.org.uk/ # v6
2020-02-10 10:00:21 +00:00
{
while (folio_test_private_2(folio))
folio_wait_bit(folio, PG_private_2);
mm: Add set/end/wait functions for PG_private_2 Add three functions to manipulate PG_private_2: (*) set_page_private_2() - Set the flag and take an appropriate reference on the flagged page. (*) end_page_private_2() - Clear the flag, drop the reference and wake up any waiters, somewhat analogously with end_page_writeback(). (*) wait_on_page_private_2() - Wait for the flag to be cleared. Wrappers will need to be placed in the netfs lib header in the patch that adds that. [This implements a suggestion by Linus[1] to not mix the terminology of PG_private_2 and PG_fscache in the mm core function] Changes: v7: - Use compound_head() in all the functions to make them THP safe[6]. v5: - Add set and end functions, calling the end function end rather than unlock[3]. - Keep a ref on the page when PG_private_2 is set[4][5]. v4: - Remove extern from the declaration[2]. Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org> Tested-by: Jeff Layton <jlayton@kernel.org> Tested-by: Dave Wysochanski <dwysocha@redhat.com> Tested-By: Marc Dionne <marc.dionne@auristor.com> cc: Alexander Viro <viro@zeniv.linux.org.uk> cc: Christoph Hellwig <hch@lst.de> cc: linux-mm@kvack.org cc: linux-cachefs@redhat.com cc: linux-afs@lists.infradead.org cc: linux-nfs@vger.kernel.org cc: linux-cifs@vger.kernel.org cc: ceph-devel@vger.kernel.org cc: v9fs-developer@lists.sourceforge.net cc: linux-fsdevel@vger.kernel.org Link: https://lore.kernel.org/r/1330473.1612974547@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/CAHk-=wjgA-74ddehziVk=XAEMTKswPu1Yw4uaro1R3ibs27ztw@mail.gmail.com/ [1] Link: https://lore.kernel.org/r/20210216102659.GA27714@lst.de/ [2] Link: https://lore.kernel.org/r/161340387944.1303470.7944159520278177652.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/161539528910.286939.1252328699383291173.stgit@warthog.procyon.org.uk # v4 Link: https://lore.kernel.org/r/20210321105309.GG3420@casper.infradead.org [3] Link: https://lore.kernel.org/r/CAHk-=wh+2gbF7XEjYc=HV9w_2uVzVf7vs60BPz0gFA=+pUm3ww@mail.gmail.com/ [4] Link: https://lore.kernel.org/r/CAHk-=wjSGsRj7xwhSMQ6dAQiz53xA39pOG+XA_WeTgwBBu4uqg@mail.gmail.com/ [5] Link: https://lore.kernel.org/r/20210408145057.GN2531743@casper.infradead.org/ [6] Link: https://lore.kernel.org/r/161653788200.2770958.9517755716374927208.stgit@warthog.procyon.org.uk/ # v5 Link: https://lore.kernel.org/r/161789066013.6155.9816857201817288382.stgit@warthog.procyon.org.uk/ # v6
2020-02-10 10:00:21 +00:00
}
EXPORT_SYMBOL(folio_wait_private_2);
mm: Add set/end/wait functions for PG_private_2 Add three functions to manipulate PG_private_2: (*) set_page_private_2() - Set the flag and take an appropriate reference on the flagged page. (*) end_page_private_2() - Clear the flag, drop the reference and wake up any waiters, somewhat analogously with end_page_writeback(). (*) wait_on_page_private_2() - Wait for the flag to be cleared. Wrappers will need to be placed in the netfs lib header in the patch that adds that. [This implements a suggestion by Linus[1] to not mix the terminology of PG_private_2 and PG_fscache in the mm core function] Changes: v7: - Use compound_head() in all the functions to make them THP safe[6]. v5: - Add set and end functions, calling the end function end rather than unlock[3]. - Keep a ref on the page when PG_private_2 is set[4][5]. v4: - Remove extern from the declaration[2]. Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org> Tested-by: Jeff Layton <jlayton@kernel.org> Tested-by: Dave Wysochanski <dwysocha@redhat.com> Tested-By: Marc Dionne <marc.dionne@auristor.com> cc: Alexander Viro <viro@zeniv.linux.org.uk> cc: Christoph Hellwig <hch@lst.de> cc: linux-mm@kvack.org cc: linux-cachefs@redhat.com cc: linux-afs@lists.infradead.org cc: linux-nfs@vger.kernel.org cc: linux-cifs@vger.kernel.org cc: ceph-devel@vger.kernel.org cc: v9fs-developer@lists.sourceforge.net cc: linux-fsdevel@vger.kernel.org Link: https://lore.kernel.org/r/1330473.1612974547@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/CAHk-=wjgA-74ddehziVk=XAEMTKswPu1Yw4uaro1R3ibs27ztw@mail.gmail.com/ [1] Link: https://lore.kernel.org/r/20210216102659.GA27714@lst.de/ [2] Link: https://lore.kernel.org/r/161340387944.1303470.7944159520278177652.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/161539528910.286939.1252328699383291173.stgit@warthog.procyon.org.uk # v4 Link: https://lore.kernel.org/r/20210321105309.GG3420@casper.infradead.org [3] Link: https://lore.kernel.org/r/CAHk-=wh+2gbF7XEjYc=HV9w_2uVzVf7vs60BPz0gFA=+pUm3ww@mail.gmail.com/ [4] Link: https://lore.kernel.org/r/CAHk-=wjSGsRj7xwhSMQ6dAQiz53xA39pOG+XA_WeTgwBBu4uqg@mail.gmail.com/ [5] Link: https://lore.kernel.org/r/20210408145057.GN2531743@casper.infradead.org/ [6] Link: https://lore.kernel.org/r/161653788200.2770958.9517755716374927208.stgit@warthog.procyon.org.uk/ # v5 Link: https://lore.kernel.org/r/161789066013.6155.9816857201817288382.stgit@warthog.procyon.org.uk/ # v6
2020-02-10 10:00:21 +00:00
/**
* folio_wait_private_2_killable - Wait for PG_private_2 to be cleared on a folio.
* @folio: The folio to wait on.
mm: Add set/end/wait functions for PG_private_2 Add three functions to manipulate PG_private_2: (*) set_page_private_2() - Set the flag and take an appropriate reference on the flagged page. (*) end_page_private_2() - Clear the flag, drop the reference and wake up any waiters, somewhat analogously with end_page_writeback(). (*) wait_on_page_private_2() - Wait for the flag to be cleared. Wrappers will need to be placed in the netfs lib header in the patch that adds that. [This implements a suggestion by Linus[1] to not mix the terminology of PG_private_2 and PG_fscache in the mm core function] Changes: v7: - Use compound_head() in all the functions to make them THP safe[6]. v5: - Add set and end functions, calling the end function end rather than unlock[3]. - Keep a ref on the page when PG_private_2 is set[4][5]. v4: - Remove extern from the declaration[2]. Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org> Tested-by: Jeff Layton <jlayton@kernel.org> Tested-by: Dave Wysochanski <dwysocha@redhat.com> Tested-By: Marc Dionne <marc.dionne@auristor.com> cc: Alexander Viro <viro@zeniv.linux.org.uk> cc: Christoph Hellwig <hch@lst.de> cc: linux-mm@kvack.org cc: linux-cachefs@redhat.com cc: linux-afs@lists.infradead.org cc: linux-nfs@vger.kernel.org cc: linux-cifs@vger.kernel.org cc: ceph-devel@vger.kernel.org cc: v9fs-developer@lists.sourceforge.net cc: linux-fsdevel@vger.kernel.org Link: https://lore.kernel.org/r/1330473.1612974547@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/CAHk-=wjgA-74ddehziVk=XAEMTKswPu1Yw4uaro1R3ibs27ztw@mail.gmail.com/ [1] Link: https://lore.kernel.org/r/20210216102659.GA27714@lst.de/ [2] Link: https://lore.kernel.org/r/161340387944.1303470.7944159520278177652.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/161539528910.286939.1252328699383291173.stgit@warthog.procyon.org.uk # v4 Link: https://lore.kernel.org/r/20210321105309.GG3420@casper.infradead.org [3] Link: https://lore.kernel.org/r/CAHk-=wh+2gbF7XEjYc=HV9w_2uVzVf7vs60BPz0gFA=+pUm3ww@mail.gmail.com/ [4] Link: https://lore.kernel.org/r/CAHk-=wjSGsRj7xwhSMQ6dAQiz53xA39pOG+XA_WeTgwBBu4uqg@mail.gmail.com/ [5] Link: https://lore.kernel.org/r/20210408145057.GN2531743@casper.infradead.org/ [6] Link: https://lore.kernel.org/r/161653788200.2770958.9517755716374927208.stgit@warthog.procyon.org.uk/ # v5 Link: https://lore.kernel.org/r/161789066013.6155.9816857201817288382.stgit@warthog.procyon.org.uk/ # v6
2020-02-10 10:00:21 +00:00
*
* Wait for PG_private_2 to be cleared on a folio or until a fatal signal is
* received by the calling task.
mm: Add set/end/wait functions for PG_private_2 Add three functions to manipulate PG_private_2: (*) set_page_private_2() - Set the flag and take an appropriate reference on the flagged page. (*) end_page_private_2() - Clear the flag, drop the reference and wake up any waiters, somewhat analogously with end_page_writeback(). (*) wait_on_page_private_2() - Wait for the flag to be cleared. Wrappers will need to be placed in the netfs lib header in the patch that adds that. [This implements a suggestion by Linus[1] to not mix the terminology of PG_private_2 and PG_fscache in the mm core function] Changes: v7: - Use compound_head() in all the functions to make them THP safe[6]. v5: - Add set and end functions, calling the end function end rather than unlock[3]. - Keep a ref on the page when PG_private_2 is set[4][5]. v4: - Remove extern from the declaration[2]. Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org> Tested-by: Jeff Layton <jlayton@kernel.org> Tested-by: Dave Wysochanski <dwysocha@redhat.com> Tested-By: Marc Dionne <marc.dionne@auristor.com> cc: Alexander Viro <viro@zeniv.linux.org.uk> cc: Christoph Hellwig <hch@lst.de> cc: linux-mm@kvack.org cc: linux-cachefs@redhat.com cc: linux-afs@lists.infradead.org cc: linux-nfs@vger.kernel.org cc: linux-cifs@vger.kernel.org cc: ceph-devel@vger.kernel.org cc: v9fs-developer@lists.sourceforge.net cc: linux-fsdevel@vger.kernel.org Link: https://lore.kernel.org/r/1330473.1612974547@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/CAHk-=wjgA-74ddehziVk=XAEMTKswPu1Yw4uaro1R3ibs27ztw@mail.gmail.com/ [1] Link: https://lore.kernel.org/r/20210216102659.GA27714@lst.de/ [2] Link: https://lore.kernel.org/r/161340387944.1303470.7944159520278177652.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/161539528910.286939.1252328699383291173.stgit@warthog.procyon.org.uk # v4 Link: https://lore.kernel.org/r/20210321105309.GG3420@casper.infradead.org [3] Link: https://lore.kernel.org/r/CAHk-=wh+2gbF7XEjYc=HV9w_2uVzVf7vs60BPz0gFA=+pUm3ww@mail.gmail.com/ [4] Link: https://lore.kernel.org/r/CAHk-=wjSGsRj7xwhSMQ6dAQiz53xA39pOG+XA_WeTgwBBu4uqg@mail.gmail.com/ [5] Link: https://lore.kernel.org/r/20210408145057.GN2531743@casper.infradead.org/ [6] Link: https://lore.kernel.org/r/161653788200.2770958.9517755716374927208.stgit@warthog.procyon.org.uk/ # v5 Link: https://lore.kernel.org/r/161789066013.6155.9816857201817288382.stgit@warthog.procyon.org.uk/ # v6
2020-02-10 10:00:21 +00:00
*
* Return:
* - 0 if successful.
* - -EINTR if a fatal signal was encountered.
*/
int folio_wait_private_2_killable(struct folio *folio)
mm: Add set/end/wait functions for PG_private_2 Add three functions to manipulate PG_private_2: (*) set_page_private_2() - Set the flag and take an appropriate reference on the flagged page. (*) end_page_private_2() - Clear the flag, drop the reference and wake up any waiters, somewhat analogously with end_page_writeback(). (*) wait_on_page_private_2() - Wait for the flag to be cleared. Wrappers will need to be placed in the netfs lib header in the patch that adds that. [This implements a suggestion by Linus[1] to not mix the terminology of PG_private_2 and PG_fscache in the mm core function] Changes: v7: - Use compound_head() in all the functions to make them THP safe[6]. v5: - Add set and end functions, calling the end function end rather than unlock[3]. - Keep a ref on the page when PG_private_2 is set[4][5]. v4: - Remove extern from the declaration[2]. Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org> Tested-by: Jeff Layton <jlayton@kernel.org> Tested-by: Dave Wysochanski <dwysocha@redhat.com> Tested-By: Marc Dionne <marc.dionne@auristor.com> cc: Alexander Viro <viro@zeniv.linux.org.uk> cc: Christoph Hellwig <hch@lst.de> cc: linux-mm@kvack.org cc: linux-cachefs@redhat.com cc: linux-afs@lists.infradead.org cc: linux-nfs@vger.kernel.org cc: linux-cifs@vger.kernel.org cc: ceph-devel@vger.kernel.org cc: v9fs-developer@lists.sourceforge.net cc: linux-fsdevel@vger.kernel.org Link: https://lore.kernel.org/r/1330473.1612974547@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/CAHk-=wjgA-74ddehziVk=XAEMTKswPu1Yw4uaro1R3ibs27ztw@mail.gmail.com/ [1] Link: https://lore.kernel.org/r/20210216102659.GA27714@lst.de/ [2] Link: https://lore.kernel.org/r/161340387944.1303470.7944159520278177652.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/161539528910.286939.1252328699383291173.stgit@warthog.procyon.org.uk # v4 Link: https://lore.kernel.org/r/20210321105309.GG3420@casper.infradead.org [3] Link: https://lore.kernel.org/r/CAHk-=wh+2gbF7XEjYc=HV9w_2uVzVf7vs60BPz0gFA=+pUm3ww@mail.gmail.com/ [4] Link: https://lore.kernel.org/r/CAHk-=wjSGsRj7xwhSMQ6dAQiz53xA39pOG+XA_WeTgwBBu4uqg@mail.gmail.com/ [5] Link: https://lore.kernel.org/r/20210408145057.GN2531743@casper.infradead.org/ [6] Link: https://lore.kernel.org/r/161653788200.2770958.9517755716374927208.stgit@warthog.procyon.org.uk/ # v5 Link: https://lore.kernel.org/r/161789066013.6155.9816857201817288382.stgit@warthog.procyon.org.uk/ # v6
2020-02-10 10:00:21 +00:00
{
int ret = 0;
while (folio_test_private_2(folio)) {
ret = folio_wait_bit_killable(folio, PG_private_2);
mm: Add set/end/wait functions for PG_private_2 Add three functions to manipulate PG_private_2: (*) set_page_private_2() - Set the flag and take an appropriate reference on the flagged page. (*) end_page_private_2() - Clear the flag, drop the reference and wake up any waiters, somewhat analogously with end_page_writeback(). (*) wait_on_page_private_2() - Wait for the flag to be cleared. Wrappers will need to be placed in the netfs lib header in the patch that adds that. [This implements a suggestion by Linus[1] to not mix the terminology of PG_private_2 and PG_fscache in the mm core function] Changes: v7: - Use compound_head() in all the functions to make them THP safe[6]. v5: - Add set and end functions, calling the end function end rather than unlock[3]. - Keep a ref on the page when PG_private_2 is set[4][5]. v4: - Remove extern from the declaration[2]. Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org> Tested-by: Jeff Layton <jlayton@kernel.org> Tested-by: Dave Wysochanski <dwysocha@redhat.com> Tested-By: Marc Dionne <marc.dionne@auristor.com> cc: Alexander Viro <viro@zeniv.linux.org.uk> cc: Christoph Hellwig <hch@lst.de> cc: linux-mm@kvack.org cc: linux-cachefs@redhat.com cc: linux-afs@lists.infradead.org cc: linux-nfs@vger.kernel.org cc: linux-cifs@vger.kernel.org cc: ceph-devel@vger.kernel.org cc: v9fs-developer@lists.sourceforge.net cc: linux-fsdevel@vger.kernel.org Link: https://lore.kernel.org/r/1330473.1612974547@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/CAHk-=wjgA-74ddehziVk=XAEMTKswPu1Yw4uaro1R3ibs27ztw@mail.gmail.com/ [1] Link: https://lore.kernel.org/r/20210216102659.GA27714@lst.de/ [2] Link: https://lore.kernel.org/r/161340387944.1303470.7944159520278177652.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/161539528910.286939.1252328699383291173.stgit@warthog.procyon.org.uk # v4 Link: https://lore.kernel.org/r/20210321105309.GG3420@casper.infradead.org [3] Link: https://lore.kernel.org/r/CAHk-=wh+2gbF7XEjYc=HV9w_2uVzVf7vs60BPz0gFA=+pUm3ww@mail.gmail.com/ [4] Link: https://lore.kernel.org/r/CAHk-=wjSGsRj7xwhSMQ6dAQiz53xA39pOG+XA_WeTgwBBu4uqg@mail.gmail.com/ [5] Link: https://lore.kernel.org/r/20210408145057.GN2531743@casper.infradead.org/ [6] Link: https://lore.kernel.org/r/161653788200.2770958.9517755716374927208.stgit@warthog.procyon.org.uk/ # v5 Link: https://lore.kernel.org/r/161789066013.6155.9816857201817288382.stgit@warthog.procyon.org.uk/ # v6
2020-02-10 10:00:21 +00:00
if (ret < 0)
break;
}
return ret;
}
EXPORT_SYMBOL(folio_wait_private_2_killable);
mm: Add set/end/wait functions for PG_private_2 Add three functions to manipulate PG_private_2: (*) set_page_private_2() - Set the flag and take an appropriate reference on the flagged page. (*) end_page_private_2() - Clear the flag, drop the reference and wake up any waiters, somewhat analogously with end_page_writeback(). (*) wait_on_page_private_2() - Wait for the flag to be cleared. Wrappers will need to be placed in the netfs lib header in the patch that adds that. [This implements a suggestion by Linus[1] to not mix the terminology of PG_private_2 and PG_fscache in the mm core function] Changes: v7: - Use compound_head() in all the functions to make them THP safe[6]. v5: - Add set and end functions, calling the end function end rather than unlock[3]. - Keep a ref on the page when PG_private_2 is set[4][5]. v4: - Remove extern from the declaration[2]. Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org> Tested-by: Jeff Layton <jlayton@kernel.org> Tested-by: Dave Wysochanski <dwysocha@redhat.com> Tested-By: Marc Dionne <marc.dionne@auristor.com> cc: Alexander Viro <viro@zeniv.linux.org.uk> cc: Christoph Hellwig <hch@lst.de> cc: linux-mm@kvack.org cc: linux-cachefs@redhat.com cc: linux-afs@lists.infradead.org cc: linux-nfs@vger.kernel.org cc: linux-cifs@vger.kernel.org cc: ceph-devel@vger.kernel.org cc: v9fs-developer@lists.sourceforge.net cc: linux-fsdevel@vger.kernel.org Link: https://lore.kernel.org/r/1330473.1612974547@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/CAHk-=wjgA-74ddehziVk=XAEMTKswPu1Yw4uaro1R3ibs27ztw@mail.gmail.com/ [1] Link: https://lore.kernel.org/r/20210216102659.GA27714@lst.de/ [2] Link: https://lore.kernel.org/r/161340387944.1303470.7944159520278177652.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/161539528910.286939.1252328699383291173.stgit@warthog.procyon.org.uk # v4 Link: https://lore.kernel.org/r/20210321105309.GG3420@casper.infradead.org [3] Link: https://lore.kernel.org/r/CAHk-=wh+2gbF7XEjYc=HV9w_2uVzVf7vs60BPz0gFA=+pUm3ww@mail.gmail.com/ [4] Link: https://lore.kernel.org/r/CAHk-=wjSGsRj7xwhSMQ6dAQiz53xA39pOG+XA_WeTgwBBu4uqg@mail.gmail.com/ [5] Link: https://lore.kernel.org/r/20210408145057.GN2531743@casper.infradead.org/ [6] Link: https://lore.kernel.org/r/161653788200.2770958.9517755716374927208.stgit@warthog.procyon.org.uk/ # v5 Link: https://lore.kernel.org/r/161789066013.6155.9816857201817288382.stgit@warthog.procyon.org.uk/ # v6
2020-02-10 10:00:21 +00:00
/**
* folio_end_writeback - End writeback against a folio.
* @folio: The folio.
*
* The folio must actually be under writeback.
*
* Context: May be called from process or interrupt context.
*/
void folio_end_writeback(struct folio *folio)
{
VM_BUG_ON_FOLIO(!folio_test_writeback(folio), folio);
/*
* folio_test_clear_reclaim() could be used here but it is an
* atomic operation and overkill in this particular case. Failing
* to shuffle a folio marked for immediate reclaim is too mild
* a gain to justify taking an atomic operation penalty at the
* end of every folio writeback.
*/
if (folio_test_reclaim(folio)) {
folio_clear_reclaim(folio);
folio_rotate_reclaimable(folio);
}
mm: fix VM_BUG_ON(PageTail) and BUG_ON(PageWriteback) Twice now, when exercising ext4 looped on shmem huge pages, I have crashed on the PF_ONLY_HEAD check inside PageWaiters(): ext4_finish_bio() calling end_page_writeback() calling wake_up_page() on tail of a shmem huge page, no longer an ext4 page at all. The problem is that PageWriteback is not accompanied by a page reference (as the NOTE at the end of test_clear_page_writeback() acknowledges): as soon as TestClearPageWriteback has been done, that page could be removed from page cache, freed, and reused for something else by the time that wake_up_page() is reached. https://lore.kernel.org/linux-mm/20200827122019.GC14765@casper.infradead.org/ Matthew Wilcox suggested avoiding or weakening the PageWaiters() tail check; but I'm paranoid about even looking at an unreferenced struct page, lest its memory might itself have already been reused or hotremoved (and wake_up_page_bit() may modify that memory with its ClearPageWaiters()). Then on crashing a second time, realized there's a stronger reason against that approach. If my testing just occasionally crashes on that check, when the page is reused for part of a compound page, wouldn't it be much more common for the page to get reused as an order-0 page before reaching wake_up_page()? And on rare occasions, might that reused page already be marked PageWriteback by its new user, and already be waited upon? What would that look like? It would look like BUG_ON(PageWriteback) after wait_on_page_writeback() in write_cache_pages() (though I have never seen that crash myself). Matthew Wilcox explaining this to himself: "page is allocated, added to page cache, dirtied, writeback starts, --- thread A --- filesystem calls end_page_writeback() test_clear_page_writeback() --- context switch to thread B --- truncate_inode_pages_range() finds the page, it doesn't have writeback set, we delete it from the page cache. Page gets reallocated, dirtied, writeback starts again. Then we call write_cache_pages(), see PageWriteback() set, call wait_on_page_writeback() --- context switch back to thread A --- wake_up_page(page, PG_writeback); ... thread B is woken, but because the wakeup was for the old use of the page, PageWriteback is still set. Devious" And prior to 2a9127fcf229 ("mm: rewrite wait_on_page_bit_common() logic") this would have been much less likely: before that, wake_page_function()'s non-exclusive case would stop walking and not wake if it found Writeback already set again; whereas now the non-exclusive case proceeds to wake. I have not thought of a fix that does not add a little overhead: the simplest fix is for end_page_writeback() to get_page() before calling test_clear_page_writeback(), then put_page() after wake_up_page(). Was there a chance of missed wakeups before, since a page freed before reaching wake_up_page() would have PageWaiters cleared? I think not, because each waiter does hold a reference on the page. This bug comes when the old use of the page, the one we do TestClearPageWriteback on, had *no* waiters, so no additional page reference beyond the page cache (and whoever racily freed it). The reuse of the page has a waiter holding a reference, and its own PageWriteback set; but the belated wake_up_page() has woken the reuse to hit that BUG_ON(PageWriteback). Reported-by: syzbot+3622cea378100f45d59f@syzkaller.appspotmail.com Reported-by: Qian Cai <cai@lca.pw> Fixes: 2a9127fcf229 ("mm: rewrite wait_on_page_bit_common() logic") Signed-off-by: Hugh Dickins <hughd@google.com> Cc: stable@vger.kernel.org # v5.8+ Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-11-24 16:46:43 +00:00
/*
* Writeback does not hold a folio reference of its own, relying
mm: fix VM_BUG_ON(PageTail) and BUG_ON(PageWriteback) Twice now, when exercising ext4 looped on shmem huge pages, I have crashed on the PF_ONLY_HEAD check inside PageWaiters(): ext4_finish_bio() calling end_page_writeback() calling wake_up_page() on tail of a shmem huge page, no longer an ext4 page at all. The problem is that PageWriteback is not accompanied by a page reference (as the NOTE at the end of test_clear_page_writeback() acknowledges): as soon as TestClearPageWriteback has been done, that page could be removed from page cache, freed, and reused for something else by the time that wake_up_page() is reached. https://lore.kernel.org/linux-mm/20200827122019.GC14765@casper.infradead.org/ Matthew Wilcox suggested avoiding or weakening the PageWaiters() tail check; but I'm paranoid about even looking at an unreferenced struct page, lest its memory might itself have already been reused or hotremoved (and wake_up_page_bit() may modify that memory with its ClearPageWaiters()). Then on crashing a second time, realized there's a stronger reason against that approach. If my testing just occasionally crashes on that check, when the page is reused for part of a compound page, wouldn't it be much more common for the page to get reused as an order-0 page before reaching wake_up_page()? And on rare occasions, might that reused page already be marked PageWriteback by its new user, and already be waited upon? What would that look like? It would look like BUG_ON(PageWriteback) after wait_on_page_writeback() in write_cache_pages() (though I have never seen that crash myself). Matthew Wilcox explaining this to himself: "page is allocated, added to page cache, dirtied, writeback starts, --- thread A --- filesystem calls end_page_writeback() test_clear_page_writeback() --- context switch to thread B --- truncate_inode_pages_range() finds the page, it doesn't have writeback set, we delete it from the page cache. Page gets reallocated, dirtied, writeback starts again. Then we call write_cache_pages(), see PageWriteback() set, call wait_on_page_writeback() --- context switch back to thread A --- wake_up_page(page, PG_writeback); ... thread B is woken, but because the wakeup was for the old use of the page, PageWriteback is still set. Devious" And prior to 2a9127fcf229 ("mm: rewrite wait_on_page_bit_common() logic") this would have been much less likely: before that, wake_page_function()'s non-exclusive case would stop walking and not wake if it found Writeback already set again; whereas now the non-exclusive case proceeds to wake. I have not thought of a fix that does not add a little overhead: the simplest fix is for end_page_writeback() to get_page() before calling test_clear_page_writeback(), then put_page() after wake_up_page(). Was there a chance of missed wakeups before, since a page freed before reaching wake_up_page() would have PageWaiters cleared? I think not, because each waiter does hold a reference on the page. This bug comes when the old use of the page, the one we do TestClearPageWriteback on, had *no* waiters, so no additional page reference beyond the page cache (and whoever racily freed it). The reuse of the page has a waiter holding a reference, and its own PageWriteback set; but the belated wake_up_page() has woken the reuse to hit that BUG_ON(PageWriteback). Reported-by: syzbot+3622cea378100f45d59f@syzkaller.appspotmail.com Reported-by: Qian Cai <cai@lca.pw> Fixes: 2a9127fcf229 ("mm: rewrite wait_on_page_bit_common() logic") Signed-off-by: Hugh Dickins <hughd@google.com> Cc: stable@vger.kernel.org # v5.8+ Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-11-24 16:46:43 +00:00
* on truncation to wait for the clearing of PG_writeback.
* But here we must make sure that the folio is not freed and
* reused before the folio_wake_bit().
mm: fix VM_BUG_ON(PageTail) and BUG_ON(PageWriteback) Twice now, when exercising ext4 looped on shmem huge pages, I have crashed on the PF_ONLY_HEAD check inside PageWaiters(): ext4_finish_bio() calling end_page_writeback() calling wake_up_page() on tail of a shmem huge page, no longer an ext4 page at all. The problem is that PageWriteback is not accompanied by a page reference (as the NOTE at the end of test_clear_page_writeback() acknowledges): as soon as TestClearPageWriteback has been done, that page could be removed from page cache, freed, and reused for something else by the time that wake_up_page() is reached. https://lore.kernel.org/linux-mm/20200827122019.GC14765@casper.infradead.org/ Matthew Wilcox suggested avoiding or weakening the PageWaiters() tail check; but I'm paranoid about even looking at an unreferenced struct page, lest its memory might itself have already been reused or hotremoved (and wake_up_page_bit() may modify that memory with its ClearPageWaiters()). Then on crashing a second time, realized there's a stronger reason against that approach. If my testing just occasionally crashes on that check, when the page is reused for part of a compound page, wouldn't it be much more common for the page to get reused as an order-0 page before reaching wake_up_page()? And on rare occasions, might that reused page already be marked PageWriteback by its new user, and already be waited upon? What would that look like? It would look like BUG_ON(PageWriteback) after wait_on_page_writeback() in write_cache_pages() (though I have never seen that crash myself). Matthew Wilcox explaining this to himself: "page is allocated, added to page cache, dirtied, writeback starts, --- thread A --- filesystem calls end_page_writeback() test_clear_page_writeback() --- context switch to thread B --- truncate_inode_pages_range() finds the page, it doesn't have writeback set, we delete it from the page cache. Page gets reallocated, dirtied, writeback starts again. Then we call write_cache_pages(), see PageWriteback() set, call wait_on_page_writeback() --- context switch back to thread A --- wake_up_page(page, PG_writeback); ... thread B is woken, but because the wakeup was for the old use of the page, PageWriteback is still set. Devious" And prior to 2a9127fcf229 ("mm: rewrite wait_on_page_bit_common() logic") this would have been much less likely: before that, wake_page_function()'s non-exclusive case would stop walking and not wake if it found Writeback already set again; whereas now the non-exclusive case proceeds to wake. I have not thought of a fix that does not add a little overhead: the simplest fix is for end_page_writeback() to get_page() before calling test_clear_page_writeback(), then put_page() after wake_up_page(). Was there a chance of missed wakeups before, since a page freed before reaching wake_up_page() would have PageWaiters cleared? I think not, because each waiter does hold a reference on the page. This bug comes when the old use of the page, the one we do TestClearPageWriteback on, had *no* waiters, so no additional page reference beyond the page cache (and whoever racily freed it). The reuse of the page has a waiter holding a reference, and its own PageWriteback set; but the belated wake_up_page() has woken the reuse to hit that BUG_ON(PageWriteback). Reported-by: syzbot+3622cea378100f45d59f@syzkaller.appspotmail.com Reported-by: Qian Cai <cai@lca.pw> Fixes: 2a9127fcf229 ("mm: rewrite wait_on_page_bit_common() logic") Signed-off-by: Hugh Dickins <hughd@google.com> Cc: stable@vger.kernel.org # v5.8+ Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-11-24 16:46:43 +00:00
*/
folio_get(folio);
if (__folio_end_writeback(folio))
folio_wake_bit(folio, PG_writeback);
Merge branch 'akpm' (patches from Andrew) Merge misc updates from Andrew Morton: "257 patches. Subsystems affected by this patch series: scripts, ocfs2, vfs, and mm (slab-generic, slab, slub, kconfig, dax, kasan, debug, pagecache, gup, swap, memcg, pagemap, mprotect, mremap, iomap, tracing, vmalloc, pagealloc, memory-failure, hugetlb, userfaultfd, vmscan, tools, memblock, oom-kill, hugetlbfs, migration, thp, readahead, nommu, ksm, vmstat, madvise, memory-hotplug, rmap, zsmalloc, highmem, zram, cleanups, kfence, and damon)" * emailed patches from Andrew Morton <akpm@linux-foundation.org>: (257 commits) mm/damon: remove return value from before_terminate callback mm/damon: fix a few spelling mistakes in comments and a pr_debug message mm/damon: simplify stop mechanism Docs/admin-guide/mm/pagemap: wordsmith page flags descriptions Docs/admin-guide/mm/damon/start: simplify the content Docs/admin-guide/mm/damon/start: fix a wrong link Docs/admin-guide/mm/damon/start: fix wrong example commands mm/damon/dbgfs: add adaptive_targets list check before enable monitor_on mm/damon: remove unnecessary variable initialization Documentation/admin-guide/mm/damon: add a document for DAMON_RECLAIM mm/damon: introduce DAMON-based Reclamation (DAMON_RECLAIM) selftests/damon: support watermarks mm/damon/dbgfs: support watermarks mm/damon/schemes: activate schemes based on a watermarks mechanism tools/selftests/damon: update for regions prioritization of schemes mm/damon/dbgfs: support prioritization weights mm/damon/vaddr,paddr: support pageout prioritization mm/damon/schemes: prioritize regions within the quotas mm/damon/selftests: support schemes quotas mm/damon/dbgfs: support quotas of schemes ...
2021-11-06 21:08:17 +00:00
acct_reclaim_writeback(folio);
folio_put(folio);
}
EXPORT_SYMBOL(folio_end_writeback);
/**
* __folio_lock - Get a lock on the folio, assuming we need to sleep to get it.
* @folio: The folio to lock
*/
void __folio_lock(struct folio *folio)
{
folio_wait_bit_common(folio, PG_locked, TASK_UNINTERRUPTIBLE,
mm: put_and_wait_on_page_locked() while page is migrated Waiting on a page migration entry has used wait_on_page_locked() all along since 2006: but you cannot safely wait_on_page_locked() without holding a reference to the page, and that extra reference is enough to make migrate_page_move_mapping() fail with -EAGAIN, when a racing task faults on the entry before migrate_page_move_mapping() gets there. And that failure is retried nine times, amplifying the pain when trying to migrate a popular page. With a single persistent faulter, migration sometimes succeeds; with two or three concurrent faulters, success becomes much less likely (and the more the page was mapped, the worse the overhead of unmapping and remapping it on each try). This is especially a problem for memory offlining, where the outer level retries forever (or until terminated from userspace), because a heavy refault workload can trigger an endless loop of migration failures. wait_on_page_locked() is the wrong tool for the job. David Herrmann (but was he the first?) noticed this issue in 2014: https://marc.info/?l=linux-mm&m=140110465608116&w=2 Tim Chen started a thread in August 2017 which appears relevant: https://marc.info/?l=linux-mm&m=150275941014915&w=2 where Kan Liang went on to implicate __migration_entry_wait(): https://marc.info/?l=linux-mm&m=150300268411980&w=2 and the thread ended up with the v4.14 commits: 2554db916586 ("sched/wait: Break up long wake list walk") 11a19c7b099f ("sched/wait: Introduce wakeup boomark in wake_up_page_bit") Baoquan He reported "Memory hotplug softlock issue" 14 November 2018: https://marc.info/?l=linux-mm&m=154217936431300&w=2 We have all assumed that it is essential to hold a page reference while waiting on a page lock: partly to guarantee that there is still a struct page when MEMORY_HOTREMOVE is configured, but also to protect against reuse of the struct page going to someone who then holds the page locked indefinitely, when the waiter can reasonably expect timely unlocking. But in fact, so long as wait_on_page_bit_common() does the put_page(), and is careful not to rely on struct page contents thereafter, there is no need to hold a reference to the page while waiting on it. That does mean that this case cannot go back through the loop: but that's fine for the page migration case, and even if used more widely, is limited by the "Stop walking if it's locked" optimization in wake_page_function(). Add interface put_and_wait_on_page_locked() to do this, using "behavior" enum in place of "lock" arg to wait_on_page_bit_common() to implement it. No interruptible or killable variant needed yet, but they might follow: I have a vague notion that reporting -EINTR should take precedence over return from wait_on_page_bit_common() without knowing the page state, so arrange it accordingly - but that may be nothing but pedantic. __migration_entry_wait() still has to take a brief reference to the page, prior to calling put_and_wait_on_page_locked(): but now that it is dropped before waiting, the chance of impeding page migration is very much reduced. Should we perhaps disable preemption across this? shrink_page_list()'s __ClearPageLocked(): that was a surprise! This survived a lot of testing before that showed up. PageWaiters may have been set by wait_on_page_bit_common(), and the reference dropped, just before shrink_page_list() succeeds in freezing its last page reference: in such a case, unlock_page() must be used. Follow the suggestion from Michal Hocko, just revert a978d6f52106 ("mm: unlockless reclaim") now: that optimization predates PageWaiters, and won't buy much these days; but we can reinstate it for the !PageWaiters case if anyone notices. It does raise the question: should vmscan.c's is_page_cache_freeable() and __remove_mapping() now treat a PageWaiters page as if an extra reference were held? Perhaps, but I don't think it matters much, since shrink_page_list() already had to win its trylock_page(), so waiters are not very common there: I noticed no difference when trying the bigger change, and it's surely not needed while put_and_wait_on_page_locked() is only used for page migration. [willy@infradead.org: add put_and_wait_on_page_locked() kerneldoc] Link: http://lkml.kernel.org/r/alpine.LSU.2.11.1811261121330.1116@eggly.anvils Signed-off-by: Hugh Dickins <hughd@google.com> Reported-by: Baoquan He <bhe@redhat.com> Tested-by: Baoquan He <bhe@redhat.com> Reviewed-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Michal Hocko <mhocko@suse.com> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Matthew Wilcox <willy@infradead.org> Cc: Baoquan He <bhe@redhat.com> Cc: David Hildenbrand <david@redhat.com> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: David Herrmann <dh.herrmann@gmail.com> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Christoph Lameter <cl@linux.com> Cc: Nick Piggin <npiggin@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-12-28 08:36:14 +00:00
EXCLUSIVE);
}
EXPORT_SYMBOL(__folio_lock);
int __folio_lock_killable(struct folio *folio)
{
return folio_wait_bit_common(folio, PG_locked, TASK_KILLABLE,
mm: put_and_wait_on_page_locked() while page is migrated Waiting on a page migration entry has used wait_on_page_locked() all along since 2006: but you cannot safely wait_on_page_locked() without holding a reference to the page, and that extra reference is enough to make migrate_page_move_mapping() fail with -EAGAIN, when a racing task faults on the entry before migrate_page_move_mapping() gets there. And that failure is retried nine times, amplifying the pain when trying to migrate a popular page. With a single persistent faulter, migration sometimes succeeds; with two or three concurrent faulters, success becomes much less likely (and the more the page was mapped, the worse the overhead of unmapping and remapping it on each try). This is especially a problem for memory offlining, where the outer level retries forever (or until terminated from userspace), because a heavy refault workload can trigger an endless loop of migration failures. wait_on_page_locked() is the wrong tool for the job. David Herrmann (but was he the first?) noticed this issue in 2014: https://marc.info/?l=linux-mm&m=140110465608116&w=2 Tim Chen started a thread in August 2017 which appears relevant: https://marc.info/?l=linux-mm&m=150275941014915&w=2 where Kan Liang went on to implicate __migration_entry_wait(): https://marc.info/?l=linux-mm&m=150300268411980&w=2 and the thread ended up with the v4.14 commits: 2554db916586 ("sched/wait: Break up long wake list walk") 11a19c7b099f ("sched/wait: Introduce wakeup boomark in wake_up_page_bit") Baoquan He reported "Memory hotplug softlock issue" 14 November 2018: https://marc.info/?l=linux-mm&m=154217936431300&w=2 We have all assumed that it is essential to hold a page reference while waiting on a page lock: partly to guarantee that there is still a struct page when MEMORY_HOTREMOVE is configured, but also to protect against reuse of the struct page going to someone who then holds the page locked indefinitely, when the waiter can reasonably expect timely unlocking. But in fact, so long as wait_on_page_bit_common() does the put_page(), and is careful not to rely on struct page contents thereafter, there is no need to hold a reference to the page while waiting on it. That does mean that this case cannot go back through the loop: but that's fine for the page migration case, and even if used more widely, is limited by the "Stop walking if it's locked" optimization in wake_page_function(). Add interface put_and_wait_on_page_locked() to do this, using "behavior" enum in place of "lock" arg to wait_on_page_bit_common() to implement it. No interruptible or killable variant needed yet, but they might follow: I have a vague notion that reporting -EINTR should take precedence over return from wait_on_page_bit_common() without knowing the page state, so arrange it accordingly - but that may be nothing but pedantic. __migration_entry_wait() still has to take a brief reference to the page, prior to calling put_and_wait_on_page_locked(): but now that it is dropped before waiting, the chance of impeding page migration is very much reduced. Should we perhaps disable preemption across this? shrink_page_list()'s __ClearPageLocked(): that was a surprise! This survived a lot of testing before that showed up. PageWaiters may have been set by wait_on_page_bit_common(), and the reference dropped, just before shrink_page_list() succeeds in freezing its last page reference: in such a case, unlock_page() must be used. Follow the suggestion from Michal Hocko, just revert a978d6f52106 ("mm: unlockless reclaim") now: that optimization predates PageWaiters, and won't buy much these days; but we can reinstate it for the !PageWaiters case if anyone notices. It does raise the question: should vmscan.c's is_page_cache_freeable() and __remove_mapping() now treat a PageWaiters page as if an extra reference were held? Perhaps, but I don't think it matters much, since shrink_page_list() already had to win its trylock_page(), so waiters are not very common there: I noticed no difference when trying the bigger change, and it's surely not needed while put_and_wait_on_page_locked() is only used for page migration. [willy@infradead.org: add put_and_wait_on_page_locked() kerneldoc] Link: http://lkml.kernel.org/r/alpine.LSU.2.11.1811261121330.1116@eggly.anvils Signed-off-by: Hugh Dickins <hughd@google.com> Reported-by: Baoquan He <bhe@redhat.com> Tested-by: Baoquan He <bhe@redhat.com> Reviewed-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Michal Hocko <mhocko@suse.com> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Matthew Wilcox <willy@infradead.org> Cc: Baoquan He <bhe@redhat.com> Cc: David Hildenbrand <david@redhat.com> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: David Herrmann <dh.herrmann@gmail.com> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Christoph Lameter <cl@linux.com> Cc: Nick Piggin <npiggin@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-12-28 08:36:14 +00:00
EXCLUSIVE);
}
EXPORT_SYMBOL_GPL(__folio_lock_killable);
static int __folio_lock_async(struct folio *folio, struct wait_page_queue *wait)
{
struct wait_queue_head *q = folio_waitqueue(folio);
int ret;
wait->folio = folio;
wait->bit_nr = PG_locked;
spin_lock_irq(&q->lock);
__add_wait_queue_entry_tail(q, &wait->wait);
folio_set_waiters(folio);
ret = !folio_trylock(folio);
/*
* If we were successful now, we know we're still on the
* waitqueue as we're still under the lock. This means it's
* safe to remove and return success, we know the callback
* isn't going to trigger.
*/
if (!ret)
__remove_wait_queue(q, &wait->wait);
else
ret = -EIOCBQUEUED;
spin_unlock_irq(&q->lock);
return ret;
}
/*
* Return values:
* 0 - folio is locked.
* non-zero - folio is not locked.
mm: handle swap page faults under per-VMA lock When page fault is handled under per-VMA lock protection, all swap page faults are retried with mmap_lock because folio_lock_or_retry has to drop and reacquire mmap_lock if folio could not be immediately locked. Follow the same pattern as mmap_lock to drop per-VMA lock when waiting for folio and retrying once folio is available. With this obstacle removed, enable do_swap_page to operate under per-VMA lock protection. Drivers implementing ops->migrate_to_ram might still rely on mmap_lock, therefore we have to fall back to mmap_lock in that particular case. Note that the only time do_swap_page calls synchronous swap_readpage is when SWP_SYNCHRONOUS_IO is set, which is only set for QUEUE_FLAG_SYNCHRONOUS devices: brd, zram and nvdimms (both btt and pmem). Therefore we don't sleep in this path, and there's no need to drop the mmap or per-VMA lock. Link: https://lkml.kernel.org/r/20230630211957.1341547-6-surenb@google.com Signed-off-by: Suren Baghdasaryan <surenb@google.com> Tested-by: Alistair Popple <apopple@nvidia.com> Reviewed-by: Alistair Popple <apopple@nvidia.com> Acked-by: Peter Xu <peterx@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Christian Brauner <brauner@kernel.org> Cc: Christoph Hellwig <hch@lst.de> Cc: David Hildenbrand <david@redhat.com> Cc: David Howells <dhowells@redhat.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Hillf Danton <hdanton@sina.com> Cc: "Huang, Ying" <ying.huang@intel.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jan Kara <jack@suse.cz> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Josef Bacik <josef@toxicpanda.com> Cc: Laurent Dufour <ldufour@linux.ibm.com> Cc: Liam R. Howlett <Liam.Howlett@oracle.com> Cc: Lorenzo Stoakes <lstoakes@gmail.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Michel Lespinasse <michel@lespinasse.org> Cc: Minchan Kim <minchan@google.com> Cc: Pavel Tatashin <pasha.tatashin@soleen.com> Cc: Punit Agrawal <punit.agrawal@bytedance.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Yu Zhao <yuzhao@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-06-30 21:19:56 +00:00
* mmap_lock or per-VMA lock has been released (mmap_read_unlock() or
* vma_end_read()), unless flags had both FAULT_FLAG_ALLOW_RETRY and
* FAULT_FLAG_RETRY_NOWAIT set, in which case the lock is still held.
*
* If neither ALLOW_RETRY nor KILLABLE are set, will always return 0
mm: handle swap page faults under per-VMA lock When page fault is handled under per-VMA lock protection, all swap page faults are retried with mmap_lock because folio_lock_or_retry has to drop and reacquire mmap_lock if folio could not be immediately locked. Follow the same pattern as mmap_lock to drop per-VMA lock when waiting for folio and retrying once folio is available. With this obstacle removed, enable do_swap_page to operate under per-VMA lock protection. Drivers implementing ops->migrate_to_ram might still rely on mmap_lock, therefore we have to fall back to mmap_lock in that particular case. Note that the only time do_swap_page calls synchronous swap_readpage is when SWP_SYNCHRONOUS_IO is set, which is only set for QUEUE_FLAG_SYNCHRONOUS devices: brd, zram and nvdimms (both btt and pmem). Therefore we don't sleep in this path, and there's no need to drop the mmap or per-VMA lock. Link: https://lkml.kernel.org/r/20230630211957.1341547-6-surenb@google.com Signed-off-by: Suren Baghdasaryan <surenb@google.com> Tested-by: Alistair Popple <apopple@nvidia.com> Reviewed-by: Alistair Popple <apopple@nvidia.com> Acked-by: Peter Xu <peterx@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Christian Brauner <brauner@kernel.org> Cc: Christoph Hellwig <hch@lst.de> Cc: David Hildenbrand <david@redhat.com> Cc: David Howells <dhowells@redhat.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Hillf Danton <hdanton@sina.com> Cc: "Huang, Ying" <ying.huang@intel.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jan Kara <jack@suse.cz> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Josef Bacik <josef@toxicpanda.com> Cc: Laurent Dufour <ldufour@linux.ibm.com> Cc: Liam R. Howlett <Liam.Howlett@oracle.com> Cc: Lorenzo Stoakes <lstoakes@gmail.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Michel Lespinasse <michel@lespinasse.org> Cc: Minchan Kim <minchan@google.com> Cc: Pavel Tatashin <pasha.tatashin@soleen.com> Cc: Punit Agrawal <punit.agrawal@bytedance.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Yu Zhao <yuzhao@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-06-30 21:19:56 +00:00
* with the folio locked and the mmap_lock/per-VMA lock is left unperturbed.
*/
vm_fault_t __folio_lock_or_retry(struct folio *folio, struct vm_fault *vmf)
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
{
unsigned int flags = vmf->flags;
mm: allow VM_FAULT_RETRY for multiple times The idea comes from a discussion between Linus and Andrea [1]. Before this patch we only allow a page fault to retry once. We achieved this by clearing the FAULT_FLAG_ALLOW_RETRY flag when doing handle_mm_fault() the second time. This was majorly used to avoid unexpected starvation of the system by looping over forever to handle the page fault on a single page. However that should hardly happen, and after all for each code path to return a VM_FAULT_RETRY we'll first wait for a condition (during which time we should possibly yield the cpu) to happen before VM_FAULT_RETRY is really returned. This patch removes the restriction by keeping the FAULT_FLAG_ALLOW_RETRY flag when we receive VM_FAULT_RETRY. It means that the page fault handler now can retry the page fault for multiple times if necessary without the need to generate another page fault event. Meanwhile we still keep the FAULT_FLAG_TRIED flag so page fault handler can still identify whether a page fault is the first attempt or not. Then we'll have these combinations of fault flags (only considering ALLOW_RETRY flag and TRIED flag): - ALLOW_RETRY and !TRIED: this means the page fault allows to retry, and this is the first try - ALLOW_RETRY and TRIED: this means the page fault allows to retry, and this is not the first try - !ALLOW_RETRY and !TRIED: this means the page fault does not allow to retry at all - !ALLOW_RETRY and TRIED: this is forbidden and should never be used In existing code we have multiple places that has taken special care of the first condition above by checking against (fault_flags & FAULT_FLAG_ALLOW_RETRY). This patch introduces a simple helper to detect the first retry of a page fault by checking against both (fault_flags & FAULT_FLAG_ALLOW_RETRY) and !(fault_flag & FAULT_FLAG_TRIED) because now even the 2nd try will have the ALLOW_RETRY set, then use that helper in all existing special paths. One example is in __lock_page_or_retry(), now we'll drop the mmap_sem only in the first attempt of page fault and we'll keep it in follow up retries, so old locking behavior will be retained. This will be a nice enhancement for current code [2] at the same time a supporting material for the future userfaultfd-writeprotect work, since in that work there will always be an explicit userfault writeprotect retry for protected pages, and if that cannot resolve the page fault (e.g., when userfaultfd-writeprotect is used in conjunction with swapped pages) then we'll possibly need a 3rd retry of the page fault. It might also benefit other potential users who will have similar requirement like userfault write-protection. GUP code is not touched yet and will be covered in follow up patch. Please read the thread below for more information. [1] https://lore.kernel.org/lkml/20171102193644.GB22686@redhat.com/ [2] https://lore.kernel.org/lkml/20181230154648.GB9832@redhat.com/ Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Suggested-by: Andrea Arcangeli <aarcange@redhat.com> Signed-off-by: Peter Xu <peterx@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Tested-by: Brian Geffon <bgeffon@google.com> Cc: Bobby Powers <bobbypowers@gmail.com> Cc: David Hildenbrand <david@redhat.com> Cc: Denis Plotnikov <dplotnikov@virtuozzo.com> Cc: "Dr . David Alan Gilbert" <dgilbert@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: "Kirill A . Shutemov" <kirill@shutemov.name> Cc: Martin Cracauer <cracauer@cons.org> Cc: Marty McFadden <mcfadden8@llnl.gov> Cc: Matthew Wilcox <willy@infradead.org> Cc: Maya Gokhale <gokhale2@llnl.gov> Cc: Mel Gorman <mgorman@suse.de> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Mike Rapoport <rppt@linux.vnet.ibm.com> Cc: Pavel Emelyanov <xemul@openvz.org> Link: http://lkml.kernel.org/r/20200220160246.9790-1-peterx@redhat.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-04-02 04:08:45 +00:00
if (fault_flag_allow_retry_first(flags)) {
/*
mm: handle swap page faults under per-VMA lock When page fault is handled under per-VMA lock protection, all swap page faults are retried with mmap_lock because folio_lock_or_retry has to drop and reacquire mmap_lock if folio could not be immediately locked. Follow the same pattern as mmap_lock to drop per-VMA lock when waiting for folio and retrying once folio is available. With this obstacle removed, enable do_swap_page to operate under per-VMA lock protection. Drivers implementing ops->migrate_to_ram might still rely on mmap_lock, therefore we have to fall back to mmap_lock in that particular case. Note that the only time do_swap_page calls synchronous swap_readpage is when SWP_SYNCHRONOUS_IO is set, which is only set for QUEUE_FLAG_SYNCHRONOUS devices: brd, zram and nvdimms (both btt and pmem). Therefore we don't sleep in this path, and there's no need to drop the mmap or per-VMA lock. Link: https://lkml.kernel.org/r/20230630211957.1341547-6-surenb@google.com Signed-off-by: Suren Baghdasaryan <surenb@google.com> Tested-by: Alistair Popple <apopple@nvidia.com> Reviewed-by: Alistair Popple <apopple@nvidia.com> Acked-by: Peter Xu <peterx@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Christian Brauner <brauner@kernel.org> Cc: Christoph Hellwig <hch@lst.de> Cc: David Hildenbrand <david@redhat.com> Cc: David Howells <dhowells@redhat.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Hillf Danton <hdanton@sina.com> Cc: "Huang, Ying" <ying.huang@intel.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jan Kara <jack@suse.cz> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Josef Bacik <josef@toxicpanda.com> Cc: Laurent Dufour <ldufour@linux.ibm.com> Cc: Liam R. Howlett <Liam.Howlett@oracle.com> Cc: Lorenzo Stoakes <lstoakes@gmail.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Michel Lespinasse <michel@lespinasse.org> Cc: Minchan Kim <minchan@google.com> Cc: Pavel Tatashin <pasha.tatashin@soleen.com> Cc: Punit Agrawal <punit.agrawal@bytedance.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Yu Zhao <yuzhao@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-06-30 21:19:56 +00:00
* CAUTION! In this case, mmap_lock/per-VMA lock is not
* released even though returning VM_FAULT_RETRY.
*/
if (flags & FAULT_FLAG_RETRY_NOWAIT)
return VM_FAULT_RETRY;
mm: handle swap page faults under per-VMA lock When page fault is handled under per-VMA lock protection, all swap page faults are retried with mmap_lock because folio_lock_or_retry has to drop and reacquire mmap_lock if folio could not be immediately locked. Follow the same pattern as mmap_lock to drop per-VMA lock when waiting for folio and retrying once folio is available. With this obstacle removed, enable do_swap_page to operate under per-VMA lock protection. Drivers implementing ops->migrate_to_ram might still rely on mmap_lock, therefore we have to fall back to mmap_lock in that particular case. Note that the only time do_swap_page calls synchronous swap_readpage is when SWP_SYNCHRONOUS_IO is set, which is only set for QUEUE_FLAG_SYNCHRONOUS devices: brd, zram and nvdimms (both btt and pmem). Therefore we don't sleep in this path, and there's no need to drop the mmap or per-VMA lock. Link: https://lkml.kernel.org/r/20230630211957.1341547-6-surenb@google.com Signed-off-by: Suren Baghdasaryan <surenb@google.com> Tested-by: Alistair Popple <apopple@nvidia.com> Reviewed-by: Alistair Popple <apopple@nvidia.com> Acked-by: Peter Xu <peterx@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Christian Brauner <brauner@kernel.org> Cc: Christoph Hellwig <hch@lst.de> Cc: David Hildenbrand <david@redhat.com> Cc: David Howells <dhowells@redhat.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Hillf Danton <hdanton@sina.com> Cc: "Huang, Ying" <ying.huang@intel.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jan Kara <jack@suse.cz> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Josef Bacik <josef@toxicpanda.com> Cc: Laurent Dufour <ldufour@linux.ibm.com> Cc: Liam R. Howlett <Liam.Howlett@oracle.com> Cc: Lorenzo Stoakes <lstoakes@gmail.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Michel Lespinasse <michel@lespinasse.org> Cc: Minchan Kim <minchan@google.com> Cc: Pavel Tatashin <pasha.tatashin@soleen.com> Cc: Punit Agrawal <punit.agrawal@bytedance.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Yu Zhao <yuzhao@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-06-30 21:19:56 +00:00
release_fault_lock(vmf);
if (flags & FAULT_FLAG_KILLABLE)
folio_wait_locked_killable(folio);
else
folio_wait_locked(folio);
return VM_FAULT_RETRY;
}
if (flags & FAULT_FLAG_KILLABLE) {
bool ret;
ret = __folio_lock_killable(folio);
if (ret) {
mm: handle swap page faults under per-VMA lock When page fault is handled under per-VMA lock protection, all swap page faults are retried with mmap_lock because folio_lock_or_retry has to drop and reacquire mmap_lock if folio could not be immediately locked. Follow the same pattern as mmap_lock to drop per-VMA lock when waiting for folio and retrying once folio is available. With this obstacle removed, enable do_swap_page to operate under per-VMA lock protection. Drivers implementing ops->migrate_to_ram might still rely on mmap_lock, therefore we have to fall back to mmap_lock in that particular case. Note that the only time do_swap_page calls synchronous swap_readpage is when SWP_SYNCHRONOUS_IO is set, which is only set for QUEUE_FLAG_SYNCHRONOUS devices: brd, zram and nvdimms (both btt and pmem). Therefore we don't sleep in this path, and there's no need to drop the mmap or per-VMA lock. Link: https://lkml.kernel.org/r/20230630211957.1341547-6-surenb@google.com Signed-off-by: Suren Baghdasaryan <surenb@google.com> Tested-by: Alistair Popple <apopple@nvidia.com> Reviewed-by: Alistair Popple <apopple@nvidia.com> Acked-by: Peter Xu <peterx@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Christian Brauner <brauner@kernel.org> Cc: Christoph Hellwig <hch@lst.de> Cc: David Hildenbrand <david@redhat.com> Cc: David Howells <dhowells@redhat.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Hillf Danton <hdanton@sina.com> Cc: "Huang, Ying" <ying.huang@intel.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jan Kara <jack@suse.cz> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Josef Bacik <josef@toxicpanda.com> Cc: Laurent Dufour <ldufour@linux.ibm.com> Cc: Liam R. Howlett <Liam.Howlett@oracle.com> Cc: Lorenzo Stoakes <lstoakes@gmail.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Michel Lespinasse <michel@lespinasse.org> Cc: Minchan Kim <minchan@google.com> Cc: Pavel Tatashin <pasha.tatashin@soleen.com> Cc: Punit Agrawal <punit.agrawal@bytedance.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Yu Zhao <yuzhao@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-06-30 21:19:56 +00:00
release_fault_lock(vmf);
return VM_FAULT_RETRY;
}
} else {
__folio_lock(folio);
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;
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_miss() - Find the next gap in the page cache.
* @mapping: Mapping.
* @index: Index.
* @max_scan: Maximum range to search.
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
*
* Search the range [index, min(index + max_scan - 1, ULONG_MAX)] for the
* gap with the lowest index.
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
*
* This function may be called under the rcu_read_lock. However, this will
* not atomically search a snapshot of the cache at a single point in time.
* For example, if a gap is created at index 5, then subsequently a gap is
* created at index 10, page_cache_next_miss covering both indices may
* return 10 if called under the rcu_read_lock.
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
*
* Return: The index of the gap if found, otherwise an index outside the
* range specified (in which case 'return - index >= max_scan' will be true).
* In the rare case of index wrap-around, 0 will be returned.
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
*/
pgoff_t page_cache_next_miss(struct address_space *mapping,
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
pgoff_t index, unsigned long max_scan)
{
XA_STATE(xas, &mapping->i_pages, index);
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
while (max_scan--) {
void *entry = xas_next(&xas);
if (!entry || xa_is_value(entry))
break;
if (xas.xa_index == 0)
break;
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
}
return xas.xa_index;
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
}
EXPORT_SYMBOL(page_cache_next_miss);
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_prev_miss() - Find the previous gap in the page cache.
* @mapping: Mapping.
* @index: Index.
* @max_scan: Maximum range to search.
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
*
* Search the range [max(index - max_scan + 1, 0), index] for the
* gap with the highest index.
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
*
* This function may be called under the rcu_read_lock. However, this will
* not atomically search a snapshot of the cache at a single point in time.
* For example, if a gap is created at index 10, then subsequently a gap is
* created at index 5, page_cache_prev_miss() covering both indices may
* return 5 if called under the rcu_read_lock.
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
*
* Return: The index of the gap if found, otherwise an index outside the
* range specified (in which case 'index - return >= max_scan' will be true).
* In the rare case of wrap-around, ULONG_MAX will be returned.
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
*/
pgoff_t page_cache_prev_miss(struct address_space *mapping,
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
pgoff_t index, unsigned long max_scan)
{
XA_STATE(xas, &mapping->i_pages, index);
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
while (max_scan--) {
void *entry = xas_prev(&xas);
if (!entry || xa_is_value(entry))
break;
if (xas.xa_index == ULONG_MAX)
break;
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
}
return xas.xa_index;
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
}
EXPORT_SYMBOL(page_cache_prev_miss);
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
/*
* Lockless page cache protocol:
* On the lookup side:
* 1. Load the folio from i_pages
* 2. Increment the refcount if it's not zero
* 3. If the folio is not found by xas_reload(), put the refcount and retry
*
* On the removal side:
* A. Freeze the page (by zeroing the refcount if nobody else has a reference)
* B. Remove the page from i_pages
* C. Return the page to the page allocator
*
* This means that any page may have its reference count temporarily
* increased by a speculative page cache (or GUP-fast) lookup as it can
* be allocated by another user before the RCU grace period expires.
* Because the refcount temporarily acquired here may end up being the
* last refcount on the page, any page allocation must be freeable by
* folio_put().
*/
/*
* filemap_get_entry - Get a page cache entry.
* @mapping: the address_space to search
* @index: The page cache index.
2014-04-03 21:47:46 +00:00
*
* Looks up the page cache entry at @mapping & @index. If it is a folio,
* it is returned with an increased refcount. If it is a shadow entry
* of a previously evicted folio, or a swap entry from shmem/tmpfs,
* it is returned without further action.
*
* Return: The folio, swap or shadow entry, %NULL if nothing is found.
*/
void *filemap_get_entry(struct address_space *mapping, pgoff_t index)
{
XA_STATE(xas, &mapping->i_pages, index);
struct folio *folio;
rcu_read_lock();
repeat:
xas_reset(&xas);
folio = xas_load(&xas);
if (xas_retry(&xas, folio))
goto repeat;
/*
* A shadow entry of a recently evicted page, or a swap entry from
* shmem/tmpfs. Return it without attempting to raise page count.
*/
if (!folio || xa_is_value(folio))
goto out;
if (!folio_try_get_rcu(folio))
goto repeat;
if (unlikely(folio != xas_reload(&xas))) {
folio_put(folio);
goto repeat;
}
out:
rcu_read_unlock();
return folio;
}
2014-04-03 21:47:46 +00:00
/**
* __filemap_get_folio - Find and get a reference to a folio.
* @mapping: The address_space to search.
* @index: The page index.
* @fgp_flags: %FGP flags modify how the folio is returned.
* @gfp: Memory allocation flags to use if %FGP_CREAT is specified.
*
* Looks up the page cache entry at @mapping & @index.
2014-04-03 21:47:46 +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.
*
* If this function returns a folio, it is returned with an increased refcount.
*
* Return: The found folio or an ERR_PTR() otherwise.
*/
struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index,
fgf_t fgp_flags, gfp_t gfp)
{
struct folio *folio;
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:
folio = filemap_get_entry(mapping, index);
if (xa_is_value(folio))
folio = NULL;
if (!folio)
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
goto no_page;
if (fgp_flags & FGP_LOCK) {
if (fgp_flags & FGP_NOWAIT) {
if (!folio_trylock(folio)) {
folio_put(folio);
return ERR_PTR(-EAGAIN);
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
}
} else {
folio_lock(folio);
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
}
/* Has the page been truncated? */
if (unlikely(folio->mapping != mapping)) {
folio_unlock(folio);
folio_put(folio);
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
goto repeat;
}
VM_BUG_ON_FOLIO(!folio_contains(folio, index), folio);
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)
folio_mark_accessed(folio);
else if (fgp_flags & FGP_WRITE) {
/* Clear idle flag for buffer write */
if (folio_test_idle(folio))
folio_clear_idle(folio);
}
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_STABLE)
folio_wait_stable(folio);
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
no_page:
if (!folio && (fgp_flags & FGP_CREAT)) {
unsigned order = FGF_GET_ORDER(fgp_flags);
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 err;
if ((fgp_flags & FGP_WRITE) && mapping_can_writeback(mapping))
gfp |= __GFP_WRITE;
if (fgp_flags & FGP_NOFS)
gfp &= ~__GFP_FS;
mm: honor FGP_NOWAIT for page cache page allocation If we're creating a page cache page with FGP_CREAT but FGP_NOWAIT is set, we should dial back the gfp flags to avoid frivolous blocking which is trivial to hit in low memory conditions: [ 10.117661] __schedule+0x8c/0x550 [ 10.118305] schedule+0x58/0xa0 [ 10.118897] schedule_timeout+0x30/0xdc [ 10.119610] __wait_for_common+0x88/0x114 [ 10.120348] wait_for_completion+0x1c/0x24 [ 10.121103] __flush_work.isra.0+0x16c/0x19c [ 10.121896] flush_work+0xc/0x14 [ 10.122496] __drain_all_pages+0x144/0x218 [ 10.123267] drain_all_pages+0x10/0x18 [ 10.123941] __alloc_pages+0x464/0x9e4 [ 10.124633] __folio_alloc+0x18/0x3c [ 10.125294] __filemap_get_folio+0x17c/0x204 [ 10.126084] iomap_write_begin+0xf8/0x428 [ 10.126829] iomap_file_buffered_write+0x144/0x24c [ 10.127710] xfs_file_buffered_write+0xe8/0x248 [ 10.128553] xfs_file_write_iter+0xa8/0x120 [ 10.129324] io_write+0x16c/0x38c [ 10.129940] io_issue_sqe+0x70/0x1cc [ 10.130617] io_queue_sqe+0x18/0xfc [ 10.131277] io_submit_sqes+0x5d4/0x600 [ 10.131946] __arm64_sys_io_uring_enter+0x224/0x600 [ 10.132752] invoke_syscall.constprop.0+0x70/0xc0 [ 10.133616] do_el0_svc+0xd0/0x118 [ 10.134238] el0_svc+0x78/0xa0 Clear IO, FS, and reclaim flags and mark the allocation as GFP_NOWAIT and add __GFP_NOWARN to avoid polluting dmesg with pointless allocations failures. A caller with FGP_NOWAIT must be expected to handle the resulting -EAGAIN return and retry from a suitable context without NOWAIT set. Reviewed-by: Shakeel Butt <shakeelb@google.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2022-07-01 20:04:43 +00:00
if (fgp_flags & FGP_NOWAIT) {
gfp &= ~GFP_KERNEL;
gfp |= GFP_NOWAIT | __GFP_NOWARN;
}
filemap: kill page_cache_read usage in filemap_fault Patch series "drop the mmap_sem when doing IO in the fault path", v6. Now that we have proper isolation in place with cgroups2 we have started going through and fixing the various priority inversions. Most are all gone now, but this one is sort of weird since it's not necessarily a priority inversion that happens within the kernel, but rather because of something userspace does. We have giant applications that we want to protect, and parts of these giant applications do things like watch the system state to determine how healthy the box is for load balancing and such. This involves running 'ps' or other such utilities. These utilities will often walk /proc/<pid>/whatever, and these files can sometimes need to down_read(&task->mmap_sem). Not usually a big deal, but we noticed when we are stress testing that sometimes our protected application has latency spikes trying to get the mmap_sem for tasks that are in lower priority cgroups. This is because any down_write() on a semaphore essentially turns it into a mutex, so even if we currently have it held for reading, any new readers will not be allowed on to keep from starving the writer. This is fine, except a lower priority task could be stuck doing IO because it has been throttled to the point that its IO is taking much longer than normal. But because a higher priority group depends on this completing it is now stuck behind lower priority work. In order to avoid this particular priority inversion we want to use the existing retry mechanism to stop from holding the mmap_sem at all if we are going to do IO. This already exists in the read case sort of, but needed to be extended for more than just grabbing the page lock. With io.latency we throttle at submit_bio() time, so the readahead stuff can block and even page_cache_read can block, so all these paths need to have the mmap_sem dropped. The other big thing is ->page_mkwrite. btrfs is particularly shitty here because we have to reserve space for the dirty page, which can be a very expensive operation. We use the same retry method as the read path, and simply cache the page and verify the page is still setup properly the next pass through ->page_mkwrite(). I've tested these patches with xfstests and there are no regressions. This patch (of 3): If we do not have a page at filemap_fault time we'll do this weird forced page_cache_read thing to populate the page, and then drop it again and loop around and find it. This makes for 2 ways we can read a page in filemap_fault, and it's not really needed. Instead add a FGP_FOR_MMAP flag so that pagecache_get_page() will return a unlocked page that's in pagecache. Then use the normal page locking and readpage logic already in filemap_fault. This simplifies the no page in page cache case significantly. [akpm@linux-foundation.org: fix comment text] [josef@toxicpanda.com: don't unlock null page in FGP_FOR_MMAP case] Link: http://lkml.kernel.org/r/20190312201742.22935-1-josef@toxicpanda.com Link: http://lkml.kernel.org/r/20181211173801.29535-2-josef@toxicpanda.com Signed-off-by: Josef Bacik <josef@toxicpanda.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Jan Kara <jack@suse.cz> Reviewed-by: Andrew Morton <akpm@linux-foundation.org> Cc: Tejun Heo <tj@kernel.org> Cc: Dave Chinner <david@fromorbit.com> Cc: Rik van Riel <riel@redhat.com> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-13 18:44:14 +00:00
if (WARN_ON_ONCE(!(fgp_flags & (FGP_LOCK | FGP_FOR_MMAP))))
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_LOCK;
if (!mapping_large_folio_support(mapping))
order = 0;
if (order > MAX_PAGECACHE_ORDER)
order = MAX_PAGECACHE_ORDER;
/* If we're not aligned, allocate a smaller folio */
if (index & ((1UL << order) - 1))
order = __ffs(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
do {
gfp_t alloc_gfp = gfp;
err = -ENOMEM;
if (order > 0)
alloc_gfp |= __GFP_NORETRY | __GFP_NOWARN;
folio = filemap_alloc_folio(alloc_gfp, order);
if (!folio)
continue;
/* Init accessed so avoid atomic mark_page_accessed later */
if (fgp_flags & FGP_ACCESSED)
__folio_set_referenced(folio);
err = filemap_add_folio(mapping, folio, index, gfp);
if (!err)
break;
folio_put(folio);
folio = NULL;
} while (order-- > 0);
filemap: kill page_cache_read usage in filemap_fault Patch series "drop the mmap_sem when doing IO in the fault path", v6. Now that we have proper isolation in place with cgroups2 we have started going through and fixing the various priority inversions. Most are all gone now, but this one is sort of weird since it's not necessarily a priority inversion that happens within the kernel, but rather because of something userspace does. We have giant applications that we want to protect, and parts of these giant applications do things like watch the system state to determine how healthy the box is for load balancing and such. This involves running 'ps' or other such utilities. These utilities will often walk /proc/<pid>/whatever, and these files can sometimes need to down_read(&task->mmap_sem). Not usually a big deal, but we noticed when we are stress testing that sometimes our protected application has latency spikes trying to get the mmap_sem for tasks that are in lower priority cgroups. This is because any down_write() on a semaphore essentially turns it into a mutex, so even if we currently have it held for reading, any new readers will not be allowed on to keep from starving the writer. This is fine, except a lower priority task could be stuck doing IO because it has been throttled to the point that its IO is taking much longer than normal. But because a higher priority group depends on this completing it is now stuck behind lower priority work. In order to avoid this particular priority inversion we want to use the existing retry mechanism to stop from holding the mmap_sem at all if we are going to do IO. This already exists in the read case sort of, but needed to be extended for more than just grabbing the page lock. With io.latency we throttle at submit_bio() time, so the readahead stuff can block and even page_cache_read can block, so all these paths need to have the mmap_sem dropped. The other big thing is ->page_mkwrite. btrfs is particularly shitty here because we have to reserve space for the dirty page, which can be a very expensive operation. We use the same retry method as the read path, and simply cache the page and verify the page is still setup properly the next pass through ->page_mkwrite(). I've tested these patches with xfstests and there are no regressions. This patch (of 3): If we do not have a page at filemap_fault time we'll do this weird forced page_cache_read thing to populate the page, and then drop it again and loop around and find it. This makes for 2 ways we can read a page in filemap_fault, and it's not really needed. Instead add a FGP_FOR_MMAP flag so that pagecache_get_page() will return a unlocked page that's in pagecache. Then use the normal page locking and readpage logic already in filemap_fault. This simplifies the no page in page cache case significantly. [akpm@linux-foundation.org: fix comment text] [josef@toxicpanda.com: don't unlock null page in FGP_FOR_MMAP case] Link: http://lkml.kernel.org/r/20190312201742.22935-1-josef@toxicpanda.com Link: http://lkml.kernel.org/r/20181211173801.29535-2-josef@toxicpanda.com Signed-off-by: Josef Bacik <josef@toxicpanda.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Jan Kara <jack@suse.cz> Reviewed-by: Andrew Morton <akpm@linux-foundation.org> Cc: Tejun Heo <tj@kernel.org> Cc: Dave Chinner <david@fromorbit.com> Cc: Rik van Riel <riel@redhat.com> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-13 18:44:14 +00:00
if (err == -EEXIST)
goto repeat;
if (err)
return ERR_PTR(err);
filemap: kill page_cache_read usage in filemap_fault Patch series "drop the mmap_sem when doing IO in the fault path", v6. Now that we have proper isolation in place with cgroups2 we have started going through and fixing the various priority inversions. Most are all gone now, but this one is sort of weird since it's not necessarily a priority inversion that happens within the kernel, but rather because of something userspace does. We have giant applications that we want to protect, and parts of these giant applications do things like watch the system state to determine how healthy the box is for load balancing and such. This involves running 'ps' or other such utilities. These utilities will often walk /proc/<pid>/whatever, and these files can sometimes need to down_read(&task->mmap_sem). Not usually a big deal, but we noticed when we are stress testing that sometimes our protected application has latency spikes trying to get the mmap_sem for tasks that are in lower priority cgroups. This is because any down_write() on a semaphore essentially turns it into a mutex, so even if we currently have it held for reading, any new readers will not be allowed on to keep from starving the writer. This is fine, except a lower priority task could be stuck doing IO because it has been throttled to the point that its IO is taking much longer than normal. But because a higher priority group depends on this completing it is now stuck behind lower priority work. In order to avoid this particular priority inversion we want to use the existing retry mechanism to stop from holding the mmap_sem at all if we are going to do IO. This already exists in the read case sort of, but needed to be extended for more than just grabbing the page lock. With io.latency we throttle at submit_bio() time, so the readahead stuff can block and even page_cache_read can block, so all these paths need to have the mmap_sem dropped. The other big thing is ->page_mkwrite. btrfs is particularly shitty here because we have to reserve space for the dirty page, which can be a very expensive operation. We use the same retry method as the read path, and simply cache the page and verify the page is still setup properly the next pass through ->page_mkwrite(). I've tested these patches with xfstests and there are no regressions. This patch (of 3): If we do not have a page at filemap_fault time we'll do this weird forced page_cache_read thing to populate the page, and then drop it again and loop around and find it. This makes for 2 ways we can read a page in filemap_fault, and it's not really needed. Instead add a FGP_FOR_MMAP flag so that pagecache_get_page() will return a unlocked page that's in pagecache. Then use the normal page locking and readpage logic already in filemap_fault. This simplifies the no page in page cache case significantly. [akpm@linux-foundation.org: fix comment text] [josef@toxicpanda.com: don't unlock null page in FGP_FOR_MMAP case] Link: http://lkml.kernel.org/r/20190312201742.22935-1-josef@toxicpanda.com Link: http://lkml.kernel.org/r/20181211173801.29535-2-josef@toxicpanda.com Signed-off-by: Josef Bacik <josef@toxicpanda.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Jan Kara <jack@suse.cz> Reviewed-by: Andrew Morton <akpm@linux-foundation.org> Cc: Tejun Heo <tj@kernel.org> Cc: Dave Chinner <david@fromorbit.com> Cc: Rik van Riel <riel@redhat.com> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-13 18:44:14 +00:00
/*
* filemap_add_folio locks the page, and for mmap
* we expect an unlocked page.
filemap: kill page_cache_read usage in filemap_fault Patch series "drop the mmap_sem when doing IO in the fault path", v6. Now that we have proper isolation in place with cgroups2 we have started going through and fixing the various priority inversions. Most are all gone now, but this one is sort of weird since it's not necessarily a priority inversion that happens within the kernel, but rather because of something userspace does. We have giant applications that we want to protect, and parts of these giant applications do things like watch the system state to determine how healthy the box is for load balancing and such. This involves running 'ps' or other such utilities. These utilities will often walk /proc/<pid>/whatever, and these files can sometimes need to down_read(&task->mmap_sem). Not usually a big deal, but we noticed when we are stress testing that sometimes our protected application has latency spikes trying to get the mmap_sem for tasks that are in lower priority cgroups. This is because any down_write() on a semaphore essentially turns it into a mutex, so even if we currently have it held for reading, any new readers will not be allowed on to keep from starving the writer. This is fine, except a lower priority task could be stuck doing IO because it has been throttled to the point that its IO is taking much longer than normal. But because a higher priority group depends on this completing it is now stuck behind lower priority work. In order to avoid this particular priority inversion we want to use the existing retry mechanism to stop from holding the mmap_sem at all if we are going to do IO. This already exists in the read case sort of, but needed to be extended for more than just grabbing the page lock. With io.latency we throttle at submit_bio() time, so the readahead stuff can block and even page_cache_read can block, so all these paths need to have the mmap_sem dropped. The other big thing is ->page_mkwrite. btrfs is particularly shitty here because we have to reserve space for the dirty page, which can be a very expensive operation. We use the same retry method as the read path, and simply cache the page and verify the page is still setup properly the next pass through ->page_mkwrite(). I've tested these patches with xfstests and there are no regressions. This patch (of 3): If we do not have a page at filemap_fault time we'll do this weird forced page_cache_read thing to populate the page, and then drop it again and loop around and find it. This makes for 2 ways we can read a page in filemap_fault, and it's not really needed. Instead add a FGP_FOR_MMAP flag so that pagecache_get_page() will return a unlocked page that's in pagecache. Then use the normal page locking and readpage logic already in filemap_fault. This simplifies the no page in page cache case significantly. [akpm@linux-foundation.org: fix comment text] [josef@toxicpanda.com: don't unlock null page in FGP_FOR_MMAP case] Link: http://lkml.kernel.org/r/20190312201742.22935-1-josef@toxicpanda.com Link: http://lkml.kernel.org/r/20181211173801.29535-2-josef@toxicpanda.com Signed-off-by: Josef Bacik <josef@toxicpanda.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Jan Kara <jack@suse.cz> Reviewed-by: Andrew Morton <akpm@linux-foundation.org> Cc: Tejun Heo <tj@kernel.org> Cc: Dave Chinner <david@fromorbit.com> Cc: Rik van Riel <riel@redhat.com> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-13 18:44:14 +00:00
*/
if (folio && (fgp_flags & FGP_FOR_MMAP))
folio_unlock(folio);
}
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 (!folio)
return ERR_PTR(-ENOENT);
return folio;
}
EXPORT_SYMBOL(__filemap_get_folio);
static inline struct folio *find_get_entry(struct xa_state *xas, pgoff_t max,
xa_mark_t mark)
{
struct folio *folio;
retry:
if (mark == XA_PRESENT)
folio = xas_find(xas, max);
else
folio = xas_find_marked(xas, max, mark);
if (xas_retry(xas, folio))
goto retry;
/*
* A shadow entry of a recently evicted page, a swap
* entry from shmem/tmpfs or a DAX entry. Return it
* without attempting to raise page count.
*/
if (!folio || xa_is_value(folio))
return folio;
if (!folio_try_get_rcu(folio))
goto reset;
if (unlikely(folio != xas_reload(xas))) {
folio_put(folio);
goto reset;
}
return folio;
reset:
xas_reset(xas);
goto retry;
}
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
* @end: The final page index (inclusive).
* @fbatch: Where the resulting entries are placed.
2014-04-03 21:47:46 +00:00
* @indices: The cache indices corresponding to the entries in @entries
*
* find_get_entries() will search for and return a batch of entries in
* the mapping. The entries are placed in @fbatch. find_get_entries()
* takes a reference on any actual folios it returns.
2014-04-03 21:47:46 +00:00
*
* The entries have ascending indexes. The indices may not be consecutive
* due to not-present entries or large folios.
2014-04-03 21:47:46 +00:00
*
* Any shadow entries of evicted folios, or swap entries from
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
* shmem/tmpfs, are included in the returned array.
2014-04-03 21:47:46 +00:00
*
* Return: The number of entries which were found.
2014-04-03 21:47:46 +00:00
*/
unsigned find_get_entries(struct address_space *mapping, pgoff_t *start,
pgoff_t end, struct folio_batch *fbatch, pgoff_t *indices)
2014-04-03 21:47:46 +00:00
{
XA_STATE(xas, &mapping->i_pages, *start);
struct folio *folio;
2014-04-03 21:47:46 +00:00
rcu_read_lock();
while ((folio = find_get_entry(&xas, end, XA_PRESENT)) != NULL) {
indices[fbatch->nr] = xas.xa_index;
if (!folio_batch_add(fbatch, folio))
2014-04-03 21:47:46 +00:00
break;
}
rcu_read_unlock();
if (folio_batch_count(fbatch)) {
unsigned long nr = 1;
int idx = folio_batch_count(fbatch) - 1;
folio = fbatch->folios[idx];
mm/filemap: remove hugetlb special casing in filemap.c Remove special cased hugetlb handling code within the page cache by changing the granularity of ->index to the base page size rather than the huge page size. The motivation of this patch is to reduce complexity within the filemap code while also increasing performance by removing branches that are evaluated on every page cache lookup. To support the change in index, new wrappers for hugetlb page cache interactions are added. These wrappers perform the conversion to a linear index which is now expected by the page cache for huge pages. ========================= PERFORMANCE ====================================== Perf was used to check the performance differences after the patch. Overall the performance is similar to mainline with a very small larger overhead that occurs in __filemap_add_folio() and hugetlb_add_to_page_cache(). This is because of the larger overhead that occurs in xa_load() and xa_store() as the xarray is now using more entries to store hugetlb folios in the page cache. Timing aarch64 2MB Page Size 6.5-rc3 + this patch: [root@sidhakum-ol9-1 hugepages]# time fallocate -l 700GB test.txt real 1m49.568s user 0m0.000s sys 1m49.461s 6.5-rc3: [root]# time fallocate -l 700GB test.txt real 1m47.495s user 0m0.000s sys 1m47.370s 1GB Page Size 6.5-rc3 + this patch: [root@sidhakum-ol9-1 hugepages1G]# time fallocate -l 700GB test.txt real 1m47.024s user 0m0.000s sys 1m46.921s 6.5-rc3: [root@sidhakum-ol9-1 hugepages1G]# time fallocate -l 700GB test.txt real 1m44.551s user 0m0.000s sys 1m44.438s x86 2MB Page Size 6.5-rc3 + this patch: [root@sidhakum-ol9-2 hugepages]# time fallocate -l 100GB test.txt real 0m22.383s user 0m0.000s sys 0m22.255s 6.5-rc3: [opc@sidhakum-ol9-2 hugepages]$ time sudo fallocate -l 100GB /dev/hugepages/test.txt real 0m22.735s user 0m0.038s sys 0m22.567s 1GB Page Size 6.5-rc3 + this patch: [root@sidhakum-ol9-2 hugepages1GB]# time fallocate -l 100GB test.txt real 0m25.786s user 0m0.001s sys 0m25.589s 6.5-rc3: [root@sidhakum-ol9-2 hugepages1G]# time fallocate -l 100GB test.txt real 0m33.454s user 0m0.001s sys 0m33.193s aarch64: workload - fallocate a 700GB file backed by huge pages 6.5-rc3 + this patch: 2MB Page Size: --100.00%--__arm64_sys_fallocate ksys_fallocate vfs_fallocate hugetlbfs_fallocate | |--95.04%--__pi_clear_page | |--3.57%--clear_huge_page | | | |--2.63%--rcu_all_qs | | | --0.91%--__cond_resched | --0.67%--__cond_resched 0.17% 0.00% 0 fallocate [kernel.vmlinux] [k] hugetlb_add_to_page_cache 0.14% 0.10% 11 fallocate [kernel.vmlinux] [k] __filemap_add_folio 6.5-rc3 2MB Page Size: --100.00%--__arm64_sys_fallocate ksys_fallocate vfs_fallocate hugetlbfs_fallocate | |--94.91%--__pi_clear_page | |--4.11%--clear_huge_page | | | |--3.00%--rcu_all_qs | | | --1.10%--__cond_resched | --0.59%--__cond_resched 0.08% 0.01% 1 fallocate [kernel.kallsyms] [k] hugetlb_add_to_page_cache 0.05% 0.03% 3 fallocate [kernel.kallsyms] [k] __filemap_add_folio x86 workload - fallocate a 100GB file backed by huge pages 6.5-rc3 + this patch: 2MB Page Size: hugetlbfs_fallocate | --99.57%--clear_huge_page | --98.47%--clear_page_erms | --0.53%--asm_sysvec_apic_timer_interrupt 0.04% 0.04% 1 fallocate [kernel.kallsyms] [k] xa_load 0.04% 0.00% 0 fallocate [kernel.kallsyms] [k] hugetlb_add_to_page_cache 0.04% 0.00% 0 fallocate [kernel.kallsyms] [k] __filemap_add_folio 0.04% 0.00% 0 fallocate [kernel.kallsyms] [k] xas_store 6.5-rc3 2MB Page Size: --99.93%--__x64_sys_fallocate vfs_fallocate hugetlbfs_fallocate | --99.38%--clear_huge_page | |--98.40%--clear_page_erms | --0.59%--__cond_resched 0.03% 0.03% 1 fallocate [kernel.kallsyms] [k] __filemap_add_folio ========================= TESTING ====================================== This patch passes libhugetlbfs tests and LTP hugetlb tests ********** TEST SUMMARY * 2M * 32-bit 64-bit * Total testcases: 110 113 * Skipped: 0 0 * PASS: 107 113 * FAIL: 0 0 * Killed by signal: 3 0 * Bad configuration: 0 0 * Expected FAIL: 0 0 * Unexpected PASS: 0 0 * Test not present: 0 0 * Strange test result: 0 0 ********** Done executing testcases. LTP Version: 20220527-178-g2761a81c4 page migration was also tested using Mike Kravetz's test program.[8] [dan.carpenter@linaro.org: fix an NULL vs IS_ERR() bug] Link: https://lkml.kernel.org/r/1772c296-1417-486f-8eef-171af2192681@moroto.mountain Link: https://lkml.kernel.org/r/20230926192017.98183-1-sidhartha.kumar@oracle.com Signed-off-by: Sidhartha Kumar <sidhartha.kumar@oracle.com> Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org> Reported-and-tested-by: syzbot+c225dea486da4d5592bd@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=c225dea486da4d5592bd Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Muchun Song <songmuchun@bytedance.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-09-26 19:20:17 +00:00
if (!xa_is_value(folio))
nr = folio_nr_pages(folio);
*start = indices[idx] + nr;
}
return folio_batch_count(fbatch);
2014-04-03 21:47:46 +00:00
}
/**
* find_lock_entries - Find a batch of pagecache entries.
* @mapping: The address_space to search.
* @start: The starting page cache index.
* @end: The final page index (inclusive).
* @fbatch: Where the resulting entries are placed.
* @indices: The cache indices of the entries in @fbatch.
*
* find_lock_entries() will return a batch of entries from @mapping.
* Swap, shadow and DAX entries are included. Folios are returned
* locked and with an incremented refcount. Folios which are locked
* by somebody else or under writeback are skipped. Folios which are
* partially outside the range are not returned.
*
* The entries have ascending indexes. The indices may not be consecutive
* due to not-present entries, large folios, folios which could not be
* locked or folios under writeback.
*
* Return: The number of entries which were found.
*/
filemap: find_lock_entries() now updates start offset Patch series "Rework find_get_entries() and find_lock_entries()", v3. Originally the callers of find_get_entries() and find_lock_entries() were keeping track of the start index themselves as they traverse the search range. This resulted in hacky code such as in shmem_undo_range(): index = folio->index + folio_nr_pages(folio) - 1; where the - 1 is only present to stay in the right spot after incrementing index later. This sort of calculation was also being done on every folio despite not even using index later within that function. These patches change find_get_entries() and find_lock_entries() to calculate the new index instead of leaving it to the callers so we can avoid all these complications. This patch (of 2): Initially, find_lock_entries() was being passed in the start offset as a value. That left the calculation of the offset to the callers. This led to complexity in the callers trying to keep track of the index. Now find_lock_entries() takes in a pointer to the start offset and updates the value to be directly after the last entry found. If no entry is found, the offset is not changed. This gets rid of multiple hacky calculations that kept track of the start offset. Link: https://lkml.kernel.org/r/20221017161800.2003-1-vishal.moola@gmail.com Link: https://lkml.kernel.org/r/20221017161800.2003-2-vishal.moola@gmail.com Signed-off-by: Vishal Moola (Oracle) <vishal.moola@gmail.com> Cc: Hugh Dickins <hughd@google.com> Cc: Matthew Wilcox <willy@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-10-17 16:17:59 +00:00
unsigned find_lock_entries(struct address_space *mapping, pgoff_t *start,
pgoff_t end, struct folio_batch *fbatch, pgoff_t *indices)
{
filemap: find_lock_entries() now updates start offset Patch series "Rework find_get_entries() and find_lock_entries()", v3. Originally the callers of find_get_entries() and find_lock_entries() were keeping track of the start index themselves as they traverse the search range. This resulted in hacky code such as in shmem_undo_range(): index = folio->index + folio_nr_pages(folio) - 1; where the - 1 is only present to stay in the right spot after incrementing index later. This sort of calculation was also being done on every folio despite not even using index later within that function. These patches change find_get_entries() and find_lock_entries() to calculate the new index instead of leaving it to the callers so we can avoid all these complications. This patch (of 2): Initially, find_lock_entries() was being passed in the start offset as a value. That left the calculation of the offset to the callers. This led to complexity in the callers trying to keep track of the index. Now find_lock_entries() takes in a pointer to the start offset and updates the value to be directly after the last entry found. If no entry is found, the offset is not changed. This gets rid of multiple hacky calculations that kept track of the start offset. Link: https://lkml.kernel.org/r/20221017161800.2003-1-vishal.moola@gmail.com Link: https://lkml.kernel.org/r/20221017161800.2003-2-vishal.moola@gmail.com Signed-off-by: Vishal Moola (Oracle) <vishal.moola@gmail.com> Cc: Hugh Dickins <hughd@google.com> Cc: Matthew Wilcox <willy@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-10-17 16:17:59 +00:00
XA_STATE(xas, &mapping->i_pages, *start);
struct folio *folio;
rcu_read_lock();
while ((folio = find_get_entry(&xas, end, XA_PRESENT))) {
if (!xa_is_value(folio)) {
filemap: find_lock_entries() now updates start offset Patch series "Rework find_get_entries() and find_lock_entries()", v3. Originally the callers of find_get_entries() and find_lock_entries() were keeping track of the start index themselves as they traverse the search range. This resulted in hacky code such as in shmem_undo_range(): index = folio->index + folio_nr_pages(folio) - 1; where the - 1 is only present to stay in the right spot after incrementing index later. This sort of calculation was also being done on every folio despite not even using index later within that function. These patches change find_get_entries() and find_lock_entries() to calculate the new index instead of leaving it to the callers so we can avoid all these complications. This patch (of 2): Initially, find_lock_entries() was being passed in the start offset as a value. That left the calculation of the offset to the callers. This led to complexity in the callers trying to keep track of the index. Now find_lock_entries() takes in a pointer to the start offset and updates the value to be directly after the last entry found. If no entry is found, the offset is not changed. This gets rid of multiple hacky calculations that kept track of the start offset. Link: https://lkml.kernel.org/r/20221017161800.2003-1-vishal.moola@gmail.com Link: https://lkml.kernel.org/r/20221017161800.2003-2-vishal.moola@gmail.com Signed-off-by: Vishal Moola (Oracle) <vishal.moola@gmail.com> Cc: Hugh Dickins <hughd@google.com> Cc: Matthew Wilcox <willy@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-10-17 16:17:59 +00:00
if (folio->index < *start)
goto put;
if (folio_next_index(folio) - 1 > end)
goto put;
if (!folio_trylock(folio))
goto put;
if (folio->mapping != mapping ||
folio_test_writeback(folio))
goto unlock;
VM_BUG_ON_FOLIO(!folio_contains(folio, xas.xa_index),
folio);
}
indices[fbatch->nr] = xas.xa_index;
if (!folio_batch_add(fbatch, folio))
break;
continue;
unlock:
folio_unlock(folio);
put:
folio_put(folio);
}
rcu_read_unlock();
filemap: find_lock_entries() now updates start offset Patch series "Rework find_get_entries() and find_lock_entries()", v3. Originally the callers of find_get_entries() and find_lock_entries() were keeping track of the start index themselves as they traverse the search range. This resulted in hacky code such as in shmem_undo_range(): index = folio->index + folio_nr_pages(folio) - 1; where the - 1 is only present to stay in the right spot after incrementing index later. This sort of calculation was also being done on every folio despite not even using index later within that function. These patches change find_get_entries() and find_lock_entries() to calculate the new index instead of leaving it to the callers so we can avoid all these complications. This patch (of 2): Initially, find_lock_entries() was being passed in the start offset as a value. That left the calculation of the offset to the callers. This led to complexity in the callers trying to keep track of the index. Now find_lock_entries() takes in a pointer to the start offset and updates the value to be directly after the last entry found. If no entry is found, the offset is not changed. This gets rid of multiple hacky calculations that kept track of the start offset. Link: https://lkml.kernel.org/r/20221017161800.2003-1-vishal.moola@gmail.com Link: https://lkml.kernel.org/r/20221017161800.2003-2-vishal.moola@gmail.com Signed-off-by: Vishal Moola (Oracle) <vishal.moola@gmail.com> Cc: Hugh Dickins <hughd@google.com> Cc: Matthew Wilcox <willy@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-10-17 16:17:59 +00:00
if (folio_batch_count(fbatch)) {
unsigned long nr = 1;
int idx = folio_batch_count(fbatch) - 1;
folio = fbatch->folios[idx];
mm/filemap: remove hugetlb special casing in filemap.c Remove special cased hugetlb handling code within the page cache by changing the granularity of ->index to the base page size rather than the huge page size. The motivation of this patch is to reduce complexity within the filemap code while also increasing performance by removing branches that are evaluated on every page cache lookup. To support the change in index, new wrappers for hugetlb page cache interactions are added. These wrappers perform the conversion to a linear index which is now expected by the page cache for huge pages. ========================= PERFORMANCE ====================================== Perf was used to check the performance differences after the patch. Overall the performance is similar to mainline with a very small larger overhead that occurs in __filemap_add_folio() and hugetlb_add_to_page_cache(). This is because of the larger overhead that occurs in xa_load() and xa_store() as the xarray is now using more entries to store hugetlb folios in the page cache. Timing aarch64 2MB Page Size 6.5-rc3 + this patch: [root@sidhakum-ol9-1 hugepages]# time fallocate -l 700GB test.txt real 1m49.568s user 0m0.000s sys 1m49.461s 6.5-rc3: [root]# time fallocate -l 700GB test.txt real 1m47.495s user 0m0.000s sys 1m47.370s 1GB Page Size 6.5-rc3 + this patch: [root@sidhakum-ol9-1 hugepages1G]# time fallocate -l 700GB test.txt real 1m47.024s user 0m0.000s sys 1m46.921s 6.5-rc3: [root@sidhakum-ol9-1 hugepages1G]# time fallocate -l 700GB test.txt real 1m44.551s user 0m0.000s sys 1m44.438s x86 2MB Page Size 6.5-rc3 + this patch: [root@sidhakum-ol9-2 hugepages]# time fallocate -l 100GB test.txt real 0m22.383s user 0m0.000s sys 0m22.255s 6.5-rc3: [opc@sidhakum-ol9-2 hugepages]$ time sudo fallocate -l 100GB /dev/hugepages/test.txt real 0m22.735s user 0m0.038s sys 0m22.567s 1GB Page Size 6.5-rc3 + this patch: [root@sidhakum-ol9-2 hugepages1GB]# time fallocate -l 100GB test.txt real 0m25.786s user 0m0.001s sys 0m25.589s 6.5-rc3: [root@sidhakum-ol9-2 hugepages1G]# time fallocate -l 100GB test.txt real 0m33.454s user 0m0.001s sys 0m33.193s aarch64: workload - fallocate a 700GB file backed by huge pages 6.5-rc3 + this patch: 2MB Page Size: --100.00%--__arm64_sys_fallocate ksys_fallocate vfs_fallocate hugetlbfs_fallocate | |--95.04%--__pi_clear_page | |--3.57%--clear_huge_page | | | |--2.63%--rcu_all_qs | | | --0.91%--__cond_resched | --0.67%--__cond_resched 0.17% 0.00% 0 fallocate [kernel.vmlinux] [k] hugetlb_add_to_page_cache 0.14% 0.10% 11 fallocate [kernel.vmlinux] [k] __filemap_add_folio 6.5-rc3 2MB Page Size: --100.00%--__arm64_sys_fallocate ksys_fallocate vfs_fallocate hugetlbfs_fallocate | |--94.91%--__pi_clear_page | |--4.11%--clear_huge_page | | | |--3.00%--rcu_all_qs | | | --1.10%--__cond_resched | --0.59%--__cond_resched 0.08% 0.01% 1 fallocate [kernel.kallsyms] [k] hugetlb_add_to_page_cache 0.05% 0.03% 3 fallocate [kernel.kallsyms] [k] __filemap_add_folio x86 workload - fallocate a 100GB file backed by huge pages 6.5-rc3 + this patch: 2MB Page Size: hugetlbfs_fallocate | --99.57%--clear_huge_page | --98.47%--clear_page_erms | --0.53%--asm_sysvec_apic_timer_interrupt 0.04% 0.04% 1 fallocate [kernel.kallsyms] [k] xa_load 0.04% 0.00% 0 fallocate [kernel.kallsyms] [k] hugetlb_add_to_page_cache 0.04% 0.00% 0 fallocate [kernel.kallsyms] [k] __filemap_add_folio 0.04% 0.00% 0 fallocate [kernel.kallsyms] [k] xas_store 6.5-rc3 2MB Page Size: --99.93%--__x64_sys_fallocate vfs_fallocate hugetlbfs_fallocate | --99.38%--clear_huge_page | |--98.40%--clear_page_erms | --0.59%--__cond_resched 0.03% 0.03% 1 fallocate [kernel.kallsyms] [k] __filemap_add_folio ========================= TESTING ====================================== This patch passes libhugetlbfs tests and LTP hugetlb tests ********** TEST SUMMARY * 2M * 32-bit 64-bit * Total testcases: 110 113 * Skipped: 0 0 * PASS: 107 113 * FAIL: 0 0 * Killed by signal: 3 0 * Bad configuration: 0 0 * Expected FAIL: 0 0 * Unexpected PASS: 0 0 * Test not present: 0 0 * Strange test result: 0 0 ********** Done executing testcases. LTP Version: 20220527-178-g2761a81c4 page migration was also tested using Mike Kravetz's test program.[8] [dan.carpenter@linaro.org: fix an NULL vs IS_ERR() bug] Link: https://lkml.kernel.org/r/1772c296-1417-486f-8eef-171af2192681@moroto.mountain Link: https://lkml.kernel.org/r/20230926192017.98183-1-sidhartha.kumar@oracle.com Signed-off-by: Sidhartha Kumar <sidhartha.kumar@oracle.com> Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org> Reported-and-tested-by: syzbot+c225dea486da4d5592bd@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=c225dea486da4d5592bd Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Muchun Song <songmuchun@bytedance.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-09-26 19:20:17 +00:00
if (!xa_is_value(folio))
filemap: find_lock_entries() now updates start offset Patch series "Rework find_get_entries() and find_lock_entries()", v3. Originally the callers of find_get_entries() and find_lock_entries() were keeping track of the start index themselves as they traverse the search range. This resulted in hacky code such as in shmem_undo_range(): index = folio->index + folio_nr_pages(folio) - 1; where the - 1 is only present to stay in the right spot after incrementing index later. This sort of calculation was also being done on every folio despite not even using index later within that function. These patches change find_get_entries() and find_lock_entries() to calculate the new index instead of leaving it to the callers so we can avoid all these complications. This patch (of 2): Initially, find_lock_entries() was being passed in the start offset as a value. That left the calculation of the offset to the callers. This led to complexity in the callers trying to keep track of the index. Now find_lock_entries() takes in a pointer to the start offset and updates the value to be directly after the last entry found. If no entry is found, the offset is not changed. This gets rid of multiple hacky calculations that kept track of the start offset. Link: https://lkml.kernel.org/r/20221017161800.2003-1-vishal.moola@gmail.com Link: https://lkml.kernel.org/r/20221017161800.2003-2-vishal.moola@gmail.com Signed-off-by: Vishal Moola (Oracle) <vishal.moola@gmail.com> Cc: Hugh Dickins <hughd@google.com> Cc: Matthew Wilcox <willy@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-10-17 16:17:59 +00:00
nr = folio_nr_pages(folio);
*start = indices[idx] + nr;
}
return folio_batch_count(fbatch);
}
/**
* filemap_get_folios - Get a batch of folios
* @mapping: The address_space to search
* @start: The starting page index
* @end: The final page index (inclusive)
* @fbatch: The batch to fill.
*
* Search for and return a batch of folios in the mapping starting at
* index @start and up to index @end (inclusive). The folios are returned
* in @fbatch with an elevated reference count.
*
* Return: The number of folios which were found.
* We also update @start to index the next folio for the traversal.
*/
unsigned filemap_get_folios(struct address_space *mapping, pgoff_t *start,
pgoff_t end, struct folio_batch *fbatch)
{
return filemap_get_folios_tag(mapping, start, end, XA_PRESENT, fbatch);
}
EXPORT_SYMBOL(filemap_get_folios);
/**
* filemap_get_folios_contig - Get a batch of contiguous folios
* @mapping: The address_space to search
* @start: The starting page index
* @end: The final page index (inclusive)
* @fbatch: The batch to fill
*
* filemap_get_folios_contig() works exactly like filemap_get_folios(),
* except the returned folios are guaranteed to be contiguous. This may
* not return all contiguous folios if the batch gets filled up.
*
* Return: The number of folios found.
* Also update @start to be positioned for traversal of the next folio.
*/
unsigned filemap_get_folios_contig(struct address_space *mapping,
pgoff_t *start, pgoff_t end, struct folio_batch *fbatch)
{
XA_STATE(xas, &mapping->i_pages, *start);
unsigned long nr;
struct folio *folio;
rcu_read_lock();
for (folio = xas_load(&xas); folio && xas.xa_index <= end;
folio = xas_next(&xas)) {
if (xas_retry(&xas, folio))
continue;
/*
* If the entry has been swapped out, we can stop looking.
* No current caller is looking for DAX entries.
*/
if (xa_is_value(folio))
goto update_start;
if (!folio_try_get_rcu(folio))
goto retry;
if (unlikely(folio != xas_reload(&xas)))
goto put_folio;
if (!folio_batch_add(fbatch, folio)) {
nr = folio_nr_pages(folio);
*start = folio->index + nr;
goto out;
}
continue;
put_folio:
folio_put(folio);
retry:
xas_reset(&xas);
}
update_start:
nr = folio_batch_count(fbatch);
if (nr) {
folio = fbatch->folios[nr - 1];
*start = folio_next_index(folio);
}
out:
rcu_read_unlock();
return folio_batch_count(fbatch);
}
EXPORT_SYMBOL(filemap_get_folios_contig);
/**
* filemap_get_folios_tag - Get a batch of folios matching @tag
* @mapping: The address_space to search
* @start: The starting page index
* @end: The final page index (inclusive)
* @tag: The tag index
* @fbatch: The batch to fill
*
* The first folio may start before @start; if it does, it will contain
* @start. The final folio may extend beyond @end; if it does, it will
* contain @end. The folios have ascending indices. There may be gaps
* between the folios if there are indices which have no folio in the
* page cache. If folios are added to or removed from the page cache
* while this is running, they may or may not be found by this call.
* Only returns folios that are tagged with @tag.
*
* Return: The number of folios found.
* Also update @start to index the next folio for traversal.
*/
unsigned filemap_get_folios_tag(struct address_space *mapping, pgoff_t *start,
pgoff_t end, xa_mark_t tag, struct folio_batch *fbatch)
{
XA_STATE(xas, &mapping->i_pages, *start);
struct folio *folio;
rcu_read_lock();
while ((folio = find_get_entry(&xas, end, tag)) != NULL) {
/*
* Shadow entries should never be tagged, but this iteration
* is lockless so there is a window for page reclaim to evict
* a page we saw tagged. Skip over it.
*/
if (xa_is_value(folio))
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;
if (!folio_batch_add(fbatch, folio)) {
unsigned long nr = folio_nr_pages(folio);
*start = folio->index + nr;
goto out;
}
}
/*
* We come here when there is no page beyond @end. We take care to not
* overflow the index @start as it confuses some of the callers. This
* breaks the iteration when there is a page at index -1 but that is
* already broke anyway.
*/
if (end == (pgoff_t)-1)
*start = (pgoff_t)-1;
else
*start = end + 1;
out:
rcu_read_unlock();
return folio_batch_count(fbatch);
}
EXPORT_SYMBOL(filemap_get_folios_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_ra_state *ra)
[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
{
ra->ra_pages /= 4;
}
/*
* filemap_get_read_batch - Get a batch of folios for read
*
* Get a batch of folios which represent a contiguous range of bytes in
* the file. No exceptional entries will be returned. If @index is in
* the middle of a folio, the entire folio will be returned. The last
* folio in the batch may have the readahead flag set or the uptodate flag
* clear so that the caller can take the appropriate action.
*/
static void filemap_get_read_batch(struct address_space *mapping,
pgoff_t index, pgoff_t max, struct folio_batch *fbatch)
{
XA_STATE(xas, &mapping->i_pages, index);
struct folio *folio;
rcu_read_lock();
for (folio = xas_load(&xas); folio; folio = xas_next(&xas)) {
if (xas_retry(&xas, folio))
continue;
if (xas.xa_index > max || xa_is_value(folio))
break;
if (xa_is_sibling(folio))
break;
if (!folio_try_get_rcu(folio))
goto retry;
if (unlikely(folio != xas_reload(&xas)))
goto put_folio;
if (!folio_batch_add(fbatch, folio))
break;
if (!folio_test_uptodate(folio))
break;
if (folio_test_readahead(folio))
break;
xas_advance(&xas, folio_next_index(folio) - 1);
continue;
put_folio:
folio_put(folio);
retry:
xas_reset(&xas);
}
rcu_read_unlock();
}
static int filemap_read_folio(struct file *file, filler_t filler,
struct folio *folio)
{
bool workingset = folio_test_workingset(folio);
unsigned long pflags;
int error;
/*
* A previous I/O error may have been due to temporary failures,
* eg. multipath errors. PG_error will be set again if read_folio
* fails.
*/
folio_clear_error(folio);
/* Start the actual read. The read will unlock the page. */
if (unlikely(workingset))
psi_memstall_enter(&pflags);
error = filler(file, folio);
if (unlikely(workingset))
psi_memstall_leave(&pflags);
if (error)
return error;
error = folio_wait_locked_killable(folio);
if (error)
return error;
if (folio_test_uptodate(folio))
return 0;
if (file)
shrink_readahead_size_eio(&file->f_ra);
return -EIO;
}
static bool filemap_range_uptodate(struct address_space *mapping,
loff_t pos, size_t count, struct folio *folio,
bool need_uptodate)
{
if (folio_test_uptodate(folio))
return true;
/* pipes can't handle partially uptodate pages */
if (need_uptodate)
return false;
if (!mapping->a_ops->is_partially_uptodate)
return false;
if (mapping->host->i_blkbits >= folio_shift(folio))
return false;
if (folio_pos(folio) > pos) {
count -= folio_pos(folio) - pos;
pos = 0;
} else {
pos -= folio_pos(folio);
}
return mapping->a_ops->is_partially_uptodate(folio, pos, count);
}
static int filemap_update_page(struct kiocb *iocb,
struct address_space *mapping, size_t count,
struct folio *folio, bool need_uptodate)
{
int error;
if (iocb->ki_flags & IOCB_NOWAIT) {
if (!filemap_invalidate_trylock_shared(mapping))
return -EAGAIN;
} else {
filemap_invalidate_lock_shared(mapping);
}
if (!folio_trylock(folio)) {
error = -EAGAIN;
if (iocb->ki_flags & (IOCB_NOWAIT | IOCB_NOIO))
goto unlock_mapping;
if (!(iocb->ki_flags & IOCB_WAITQ)) {
filemap_invalidate_unlock_shared(mapping);
/*
* This is where we usually end up waiting for a
* previously submitted readahead to finish.
*/
folio_put_wait_locked(folio, TASK_KILLABLE);
return AOP_TRUNCATED_PAGE;
}
error = __folio_lock_async(folio, iocb->ki_waitq);
if (error)
goto unlock_mapping;
}
error = AOP_TRUNCATED_PAGE;
if (!folio->mapping)
goto unlock;
error = 0;
if (filemap_range_uptodate(mapping, iocb->ki_pos, count, folio,
need_uptodate))
goto unlock;
error = -EAGAIN;
if (iocb->ki_flags & (IOCB_NOIO | IOCB_NOWAIT | IOCB_WAITQ))
goto unlock;
error = filemap_read_folio(iocb->ki_filp, mapping->a_ops->read_folio,
folio);
goto unlock_mapping;
unlock:
folio_unlock(folio);
unlock_mapping:
filemap_invalidate_unlock_shared(mapping);
if (error == AOP_TRUNCATED_PAGE)
folio_put(folio);
return error;
}
static int filemap_create_folio(struct file *file,
struct address_space *mapping, pgoff_t index,
struct folio_batch *fbatch)
{
struct folio *folio;
int error;
folio = filemap_alloc_folio(mapping_gfp_mask(mapping), 0);
if (!folio)
return -ENOMEM;
/*
* Protect against truncate / hole punch. Grabbing invalidate_lock
* here assures we cannot instantiate and bring uptodate new
* pagecache folios after evicting page cache during truncate
* and before actually freeing blocks. Note that we could
* release invalidate_lock after inserting the folio into
* the page cache as the locked folio would then be enough to
* synchronize with hole punching. But there are code paths
* such as filemap_update_page() filling in partially uptodate
* pages or ->readahead() that need to hold invalidate_lock
* while mapping blocks for IO so let's hold the lock here as
* well to keep locking rules simple.
*/
filemap_invalidate_lock_shared(mapping);
error = filemap_add_folio(mapping, folio, index,
mapping_gfp_constraint(mapping, GFP_KERNEL));
if (error == -EEXIST)
error = AOP_TRUNCATED_PAGE;
if (error)
goto error;
error = filemap_read_folio(file, mapping->a_ops->read_folio, folio);
if (error)
goto error;
filemap_invalidate_unlock_shared(mapping);
folio_batch_add(fbatch, folio);
return 0;
error:
filemap_invalidate_unlock_shared(mapping);
folio_put(folio);
return error;
}
static int filemap_readahead(struct kiocb *iocb, struct file *file,
struct address_space *mapping, struct folio *folio,
pgoff_t last_index)
{
DEFINE_READAHEAD(ractl, file, &file->f_ra, mapping, folio->index);
if (iocb->ki_flags & IOCB_NOIO)
return -EAGAIN;
page_cache_async_ra(&ractl, folio, last_index - folio->index);
return 0;
}
static int filemap_get_pages(struct kiocb *iocb, size_t count,
struct folio_batch *fbatch, bool need_uptodate)
{
struct file *filp = iocb->ki_filp;
struct address_space *mapping = filp->f_mapping;
struct file_ra_state *ra = &filp->f_ra;
pgoff_t index = iocb->ki_pos >> PAGE_SHIFT;
pgoff_t last_index;
struct folio *folio;
int err = 0;
/* "last_index" is the index of the page beyond the end of the read */
last_index = DIV_ROUND_UP(iocb->ki_pos + count, PAGE_SIZE);
retry:
if (fatal_signal_pending(current))
return -EINTR;
filemap_get_read_batch(mapping, index, last_index - 1, fbatch);
if (!folio_batch_count(fbatch)) {
if (iocb->ki_flags & IOCB_NOIO)
return -EAGAIN;
page_cache_sync_readahead(mapping, ra, filp, index,
last_index - index);
filemap_get_read_batch(mapping, index, last_index - 1, fbatch);
}
if (!folio_batch_count(fbatch)) {
if (iocb->ki_flags & (IOCB_NOWAIT | IOCB_WAITQ))
return -EAGAIN;
err = filemap_create_folio(filp, mapping,
iocb->ki_pos >> PAGE_SHIFT, fbatch);
if (err == AOP_TRUNCATED_PAGE)
goto retry;
return err;
}
folio = fbatch->folios[folio_batch_count(fbatch) - 1];
if (folio_test_readahead(folio)) {
err = filemap_readahead(iocb, filp, mapping, folio, last_index);
if (err)
goto err;
}
if (!folio_test_uptodate(folio)) {
if ((iocb->ki_flags & IOCB_WAITQ) &&
folio_batch_count(fbatch) > 1)
iocb->ki_flags |= IOCB_NOWAIT;
err = filemap_update_page(iocb, mapping, count, folio,
need_uptodate);
if (err)
goto err;
}
return 0;
err:
if (err < 0)
folio_put(folio);
if (likely(--fbatch->nr))
return 0;
if (err == AOP_TRUNCATED_PAGE)
goto retry;
return err;
}
static inline bool pos_same_folio(loff_t pos1, loff_t pos2, struct folio *folio)
{
unsigned int shift = folio_shift(folio);
return (pos1 >> shift == pos2 >> shift);
}
/**
* filemap_read - Read data from the page cache.
* @iocb: The iocb to read.
* @iter: Destination for the data.
* @already_read: Number of bytes already read by the caller.
*
* Copies data from the page cache. If the data is not currently present,
* uses the readahead and read_folio address_space operations to fetch it.
*
* Return: Total number of bytes copied, including those already read by
* the caller. If an error happens before any bytes are copied, returns
* a negative error number.
*/
ssize_t filemap_read(struct kiocb *iocb, struct iov_iter *iter,
ssize_t already_read)
{
struct file *filp = iocb->ki_filp;
struct file_ra_state *ra = &filp->f_ra;
struct address_space *mapping = filp->f_mapping;
struct inode *inode = mapping->host;
struct folio_batch fbatch;
int i, error = 0;
bool writably_mapped;
loff_t isize, end_offset;
mm/filemap.c: fix update prev_pos after one read request done ra->prev_pos tracks the last visited byte in the previous read request. It is used to check whether it is sequential read in ondemand_readahead and thus affects the readahead window. After commit 06c0444290ce ("mm/filemap.c: generic_file_buffered_read() now uses find_get_pages_contig"), update logic of prev_pos is changed. It updates prev_pos after each return from filemap_get_pages(). But the read request from user may be not fully completed at this point. The updated prev_pos impacts the subsequent readahead window. The real problem is performance drop of fsck_msdos between linux-5.4 and linux-5.15(also linux-6.4). Comparing to linux-5.4,It spends about 110% time and read 140% pages. The read pattern of fsck_msdos is not fully sequential. Simplified read pattern of fsck_msdos likes below: 1.read at page offset 0xa,size 0x1000 2.read at other page offset like 0x20,size 0x1000 3.read at page offset 0xa,size 0x4000 4.read at page offset 0xe,size 0x1000 Here is the read status on linux-6.4: 1.after read at page offset 0xa,size 0x1000 ->page ofs 0xa go into pagecache 2.after read at page offset 0x20,size 0x1000 ->page ofs 0x20 go into pagecache 3.read at page offset 0xa,size 0x4000 ->filemap_get_pages read ofs 0xa from pagecache and returns ->prev_pos is updated to 0xb and goto next loop ->filemap_get_pages tends to read ofs 0xb,size 0x3000 ->initial_readahead case in ondemand_readahead since prev_pos is the same as request ofs. ->read 8 pages while async size is 5 pages (PageReadahead flag at page 0xe) 4.read at page offset 0xe,size 0x1000 ->hit page 0xe with PageReadahead flag set,double the ra_size. read 16 pages while async size is 16 pages Now it reads 24 pages while actually uses 5 pages on linux-5.4: 1.the same as 6.4 2.the same as 6.4 3.read at page offset 0xa,size 0x4000 ->read ofs 0xa from pagecache ->read ofs 0xb,size 0x3000 using page_cache_sync_readahead read 3 pages ->prev_pos is updated to 0xd before generic_file_buffered_read returns 4.read at page offset 0xe,size 0x1000 ->initial_readahead case in ondemand_readahead since request ofs-prev_pos==1 ->read 4 pages while async size is 3 pages Now it reads 7 pages while actually uses 5 pages. In above demo, the initial_readahead case is triggered by offset of user request on linux-5.4. While it may be triggered by update logic of prev_pos on linux-6.4. To fix the performance drop, update prev_pos after finishing one read request. Link: https://lkml.kernel.org/r/20230628110220.120134-1-haibo.li@mediatek.com Signed-off-by: Haibo Li <haibo.li@mediatek.com> Reviewed-by: Jan Kara <jack@suse.cz> Cc: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Matthias Brugger <matthias.bgg@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-06-28 11:02:20 +00:00
loff_t last_pos = ra->prev_pos;
if (unlikely(iocb->ki_pos >= inode->i_sb->s_maxbytes))
return 0;
if (unlikely(!iov_iter_count(iter)))
return 0;
vfs,mm: fix a dead loop in truncate_inode_pages_range() We triggered a deadloop in truncate_inode_pages_range() on 32 bits architecture with the test case bellow: ... fd = open(); write(fd, buf, 4096); preadv64(fd, &iovec, 1, 0xffffffff000); ftruncate(fd, 0); ... Then ftruncate() will not return forever. The filesystem used in this case is ubifs, but it can be triggered on many other filesystems. When preadv64() is called with offset=0xffffffff000, a page with index=0xffffffff will be added to the radix tree of ->mapping. Then this page can be found in ->mapping with pagevec_lookup(). After that, truncate_inode_pages_range(), which is called in ftruncate(), will fall into an infinite loop: - find a page with index=0xffffffff, since index>=end, this page won't be truncated - index++, and index become 0 - the page with index=0xffffffff will be found again The data type of index is unsigned long, so index won't overflow to 0 on 64 bits architecture in this case, and the dead loop won't happen. Since truncate_inode_pages_range() is executed with holding lock of inode->i_rwsem, any operation related with this lock will be blocked, and a hung task will happen, e.g.: INFO: task truncate_test:3364 blocked for more than 120 seconds. ... call_rwsem_down_write_failed+0x17/0x30 generic_file_write_iter+0x32/0x1c0 ubifs_write_iter+0xcc/0x170 __vfs_write+0xc4/0x120 vfs_write+0xb2/0x1b0 SyS_write+0x46/0xa0 The page with index=0xffffffff added to ->mapping is useless. Fix this by checking the read position before allocating pages. Link: http://lkml.kernel.org/r/1475151010-40166-1-git-send-email-fangwei1@huawei.com Signed-off-by: Wei Fang <fangwei1@huawei.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Dave Chinner <david@fromorbit.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-08 00:01:52 +00:00
iov_iter_truncate(iter, inode->i_sb->s_maxbytes);
folio_batch_init(&fbatch);
vfs,mm: fix a dead loop in truncate_inode_pages_range() We triggered a deadloop in truncate_inode_pages_range() on 32 bits architecture with the test case bellow: ... fd = open(); write(fd, buf, 4096); preadv64(fd, &iovec, 1, 0xffffffff000); ftruncate(fd, 0); ... Then ftruncate() will not return forever. The filesystem used in this case is ubifs, but it can be triggered on many other filesystems. When preadv64() is called with offset=0xffffffff000, a page with index=0xffffffff will be added to the radix tree of ->mapping. Then this page can be found in ->mapping with pagevec_lookup(). After that, truncate_inode_pages_range(), which is called in ftruncate(), will fall into an infinite loop: - find a page with index=0xffffffff, since index>=end, this page won't be truncated - index++, and index become 0 - the page with index=0xffffffff will be found again The data type of index is unsigned long, so index won't overflow to 0 on 64 bits architecture in this case, and the dead loop won't happen. Since truncate_inode_pages_range() is executed with holding lock of inode->i_rwsem, any operation related with this lock will be blocked, and a hung task will happen, e.g.: INFO: task truncate_test:3364 blocked for more than 120 seconds. ... call_rwsem_down_write_failed+0x17/0x30 generic_file_write_iter+0x32/0x1c0 ubifs_write_iter+0xcc/0x170 __vfs_write+0xc4/0x120 vfs_write+0xb2/0x1b0 SyS_write+0x46/0xa0 The page with index=0xffffffff added to ->mapping is useless. Fix this by checking the read position before allocating pages. Link: http://lkml.kernel.org/r/1475151010-40166-1-git-send-email-fangwei1@huawei.com Signed-off-by: Wei Fang <fangwei1@huawei.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Dave Chinner <david@fromorbit.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-08 00:01:52 +00:00
do {
cond_resched();
/*
* If we've already successfully copied some data, then we
* can no longer safely return -EIOCBQUEUED. Hence mark
* an async read NOWAIT at that point.
*/
if ((iocb->ki_flags & IOCB_WAITQ) && already_read)
iocb->ki_flags |= IOCB_NOWAIT;
if (unlikely(iocb->ki_pos >= i_size_read(inode)))
break;
error = filemap_get_pages(iocb, iter->count, &fbatch, false);
if (error < 0)
break;
/*
* i_size must be checked after we know the pages are 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);
if (unlikely(iocb->ki_pos >= isize))
goto put_folios;
end_offset = min_t(loff_t, isize, iocb->ki_pos + iter->count);
/*
* Once we start copying data, we don't want to be touching any
* cachelines that might be contended:
*/
writably_mapped = mapping_writably_mapped(mapping);
/*
* When a read accesses the same folio several times, only
* mark it as accessed the first time.
*/
mm/filemap.c: fix update prev_pos after one read request done ra->prev_pos tracks the last visited byte in the previous read request. It is used to check whether it is sequential read in ondemand_readahead and thus affects the readahead window. After commit 06c0444290ce ("mm/filemap.c: generic_file_buffered_read() now uses find_get_pages_contig"), update logic of prev_pos is changed. It updates prev_pos after each return from filemap_get_pages(). But the read request from user may be not fully completed at this point. The updated prev_pos impacts the subsequent readahead window. The real problem is performance drop of fsck_msdos between linux-5.4 and linux-5.15(also linux-6.4). Comparing to linux-5.4,It spends about 110% time and read 140% pages. The read pattern of fsck_msdos is not fully sequential. Simplified read pattern of fsck_msdos likes below: 1.read at page offset 0xa,size 0x1000 2.read at other page offset like 0x20,size 0x1000 3.read at page offset 0xa,size 0x4000 4.read at page offset 0xe,size 0x1000 Here is the read status on linux-6.4: 1.after read at page offset 0xa,size 0x1000 ->page ofs 0xa go into pagecache 2.after read at page offset 0x20,size 0x1000 ->page ofs 0x20 go into pagecache 3.read at page offset 0xa,size 0x4000 ->filemap_get_pages read ofs 0xa from pagecache and returns ->prev_pos is updated to 0xb and goto next loop ->filemap_get_pages tends to read ofs 0xb,size 0x3000 ->initial_readahead case in ondemand_readahead since prev_pos is the same as request ofs. ->read 8 pages while async size is 5 pages (PageReadahead flag at page 0xe) 4.read at page offset 0xe,size 0x1000 ->hit page 0xe with PageReadahead flag set,double the ra_size. read 16 pages while async size is 16 pages Now it reads 24 pages while actually uses 5 pages on linux-5.4: 1.the same as 6.4 2.the same as 6.4 3.read at page offset 0xa,size 0x4000 ->read ofs 0xa from pagecache ->read ofs 0xb,size 0x3000 using page_cache_sync_readahead read 3 pages ->prev_pos is updated to 0xd before generic_file_buffered_read returns 4.read at page offset 0xe,size 0x1000 ->initial_readahead case in ondemand_readahead since request ofs-prev_pos==1 ->read 4 pages while async size is 3 pages Now it reads 7 pages while actually uses 5 pages. In above demo, the initial_readahead case is triggered by offset of user request on linux-5.4. While it may be triggered by update logic of prev_pos on linux-6.4. To fix the performance drop, update prev_pos after finishing one read request. Link: https://lkml.kernel.org/r/20230628110220.120134-1-haibo.li@mediatek.com Signed-off-by: Haibo Li <haibo.li@mediatek.com> Reviewed-by: Jan Kara <jack@suse.cz> Cc: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Matthias Brugger <matthias.bgg@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-06-28 11:02:20 +00:00
if (!pos_same_folio(iocb->ki_pos, last_pos - 1,
fbatch.folios[0]))
folio_mark_accessed(fbatch.folios[0]);
for (i = 0; i < folio_batch_count(&fbatch); i++) {
struct folio *folio = fbatch.folios[i];
size_t fsize = folio_size(folio);
size_t offset = iocb->ki_pos & (fsize - 1);
size_t bytes = min_t(loff_t, end_offset - iocb->ki_pos,
fsize - offset);
size_t copied;
if (end_offset < folio_pos(folio))
break;
if (i > 0)
folio_mark_accessed(folio);
/*
* If users can be writing to this folio using arbitrary
* virtual addresses, take care of potential aliasing
* before reading the folio on the kernel side.
*/
if (writably_mapped)
flush_dcache_folio(folio);
copied = copy_folio_to_iter(folio, offset, bytes, iter);
already_read += copied;
iocb->ki_pos += copied;
mm/filemap.c: fix update prev_pos after one read request done ra->prev_pos tracks the last visited byte in the previous read request. It is used to check whether it is sequential read in ondemand_readahead and thus affects the readahead window. After commit 06c0444290ce ("mm/filemap.c: generic_file_buffered_read() now uses find_get_pages_contig"), update logic of prev_pos is changed. It updates prev_pos after each return from filemap_get_pages(). But the read request from user may be not fully completed at this point. The updated prev_pos impacts the subsequent readahead window. The real problem is performance drop of fsck_msdos between linux-5.4 and linux-5.15(also linux-6.4). Comparing to linux-5.4,It spends about 110% time and read 140% pages. The read pattern of fsck_msdos is not fully sequential. Simplified read pattern of fsck_msdos likes below: 1.read at page offset 0xa,size 0x1000 2.read at other page offset like 0x20,size 0x1000 3.read at page offset 0xa,size 0x4000 4.read at page offset 0xe,size 0x1000 Here is the read status on linux-6.4: 1.after read at page offset 0xa,size 0x1000 ->page ofs 0xa go into pagecache 2.after read at page offset 0x20,size 0x1000 ->page ofs 0x20 go into pagecache 3.read at page offset 0xa,size 0x4000 ->filemap_get_pages read ofs 0xa from pagecache and returns ->prev_pos is updated to 0xb and goto next loop ->filemap_get_pages tends to read ofs 0xb,size 0x3000 ->initial_readahead case in ondemand_readahead since prev_pos is the same as request ofs. ->read 8 pages while async size is 5 pages (PageReadahead flag at page 0xe) 4.read at page offset 0xe,size 0x1000 ->hit page 0xe with PageReadahead flag set,double the ra_size. read 16 pages while async size is 16 pages Now it reads 24 pages while actually uses 5 pages on linux-5.4: 1.the same as 6.4 2.the same as 6.4 3.read at page offset 0xa,size 0x4000 ->read ofs 0xa from pagecache ->read ofs 0xb,size 0x3000 using page_cache_sync_readahead read 3 pages ->prev_pos is updated to 0xd before generic_file_buffered_read returns 4.read at page offset 0xe,size 0x1000 ->initial_readahead case in ondemand_readahead since request ofs-prev_pos==1 ->read 4 pages while async size is 3 pages Now it reads 7 pages while actually uses 5 pages. In above demo, the initial_readahead case is triggered by offset of user request on linux-5.4. While it may be triggered by update logic of prev_pos on linux-6.4. To fix the performance drop, update prev_pos after finishing one read request. Link: https://lkml.kernel.org/r/20230628110220.120134-1-haibo.li@mediatek.com Signed-off-by: Haibo Li <haibo.li@mediatek.com> Reviewed-by: Jan Kara <jack@suse.cz> Cc: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Matthias Brugger <matthias.bgg@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-06-28 11:02:20 +00:00
last_pos = iocb->ki_pos;
if (copied < bytes) {
error = -EFAULT;
break;
}
}
put_folios:
for (i = 0; i < folio_batch_count(&fbatch); i++)
folio_put(fbatch.folios[i]);
folio_batch_init(&fbatch);
} while (iov_iter_count(iter) && iocb->ki_pos < isize && !error);
file_accessed(filp);
mm/filemap.c: fix update prev_pos after one read request done ra->prev_pos tracks the last visited byte in the previous read request. It is used to check whether it is sequential read in ondemand_readahead and thus affects the readahead window. After commit 06c0444290ce ("mm/filemap.c: generic_file_buffered_read() now uses find_get_pages_contig"), update logic of prev_pos is changed. It updates prev_pos after each return from filemap_get_pages(). But the read request from user may be not fully completed at this point. The updated prev_pos impacts the subsequent readahead window. The real problem is performance drop of fsck_msdos between linux-5.4 and linux-5.15(also linux-6.4). Comparing to linux-5.4,It spends about 110% time and read 140% pages. The read pattern of fsck_msdos is not fully sequential. Simplified read pattern of fsck_msdos likes below: 1.read at page offset 0xa,size 0x1000 2.read at other page offset like 0x20,size 0x1000 3.read at page offset 0xa,size 0x4000 4.read at page offset 0xe,size 0x1000 Here is the read status on linux-6.4: 1.after read at page offset 0xa,size 0x1000 ->page ofs 0xa go into pagecache 2.after read at page offset 0x20,size 0x1000 ->page ofs 0x20 go into pagecache 3.read at page offset 0xa,size 0x4000 ->filemap_get_pages read ofs 0xa from pagecache and returns ->prev_pos is updated to 0xb and goto next loop ->filemap_get_pages tends to read ofs 0xb,size 0x3000 ->initial_readahead case in ondemand_readahead since prev_pos is the same as request ofs. ->read 8 pages while async size is 5 pages (PageReadahead flag at page 0xe) 4.read at page offset 0xe,size 0x1000 ->hit page 0xe with PageReadahead flag set,double the ra_size. read 16 pages while async size is 16 pages Now it reads 24 pages while actually uses 5 pages on linux-5.4: 1.the same as 6.4 2.the same as 6.4 3.read at page offset 0xa,size 0x4000 ->read ofs 0xa from pagecache ->read ofs 0xb,size 0x3000 using page_cache_sync_readahead read 3 pages ->prev_pos is updated to 0xd before generic_file_buffered_read returns 4.read at page offset 0xe,size 0x1000 ->initial_readahead case in ondemand_readahead since request ofs-prev_pos==1 ->read 4 pages while async size is 3 pages Now it reads 7 pages while actually uses 5 pages. In above demo, the initial_readahead case is triggered by offset of user request on linux-5.4. While it may be triggered by update logic of prev_pos on linux-6.4. To fix the performance drop, update prev_pos after finishing one read request. Link: https://lkml.kernel.org/r/20230628110220.120134-1-haibo.li@mediatek.com Signed-off-by: Haibo Li <haibo.li@mediatek.com> Reviewed-by: Jan Kara <jack@suse.cz> Cc: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Matthias Brugger <matthias.bgg@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-06-28 11:02:20 +00:00
ra->prev_pos = last_pos;
return already_read ? already_read : error;
}
EXPORT_SYMBOL_GPL(filemap_read);
int kiocb_write_and_wait(struct kiocb *iocb, size_t count)
{
struct address_space *mapping = iocb->ki_filp->f_mapping;
loff_t pos = iocb->ki_pos;
loff_t end = pos + count - 1;
if (iocb->ki_flags & IOCB_NOWAIT) {
if (filemap_range_needs_writeback(mapping, pos, end))
return -EAGAIN;
return 0;
}
return filemap_write_and_wait_range(mapping, pos, end);
}
EXPORT_SYMBOL_GPL(kiocb_write_and_wait);
int kiocb_invalidate_pages(struct kiocb *iocb, size_t count)
{
struct address_space *mapping = iocb->ki_filp->f_mapping;
loff_t pos = iocb->ki_pos;
loff_t end = pos + count - 1;
int ret;
if (iocb->ki_flags & IOCB_NOWAIT) {
/* we could block if there are any pages in the range */
if (filemap_range_has_page(mapping, pos, end))
return -EAGAIN;
} else {
ret = filemap_write_and_wait_range(mapping, pos, end);
if (ret)
return ret;
}
/*
* 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
* without clobbering -EIOCBQUEUED from ->direct_IO().
*/
return invalidate_inode_pages2_range(mapping, pos >> PAGE_SHIFT,
end >> PAGE_SHIFT);
}
EXPORT_SYMBOL_GPL(kiocb_invalidate_pages);
/**
* 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.
*
* The IOCB_NOWAIT flag in iocb->ki_flags indicates that -EAGAIN shall
* be returned when no data can be read without waiting for I/O requests
* to complete; it doesn't prevent readahead.
*
* The IOCB_NOIO flag in iocb->ki_flags indicates that no new I/O
* requests shall be made for the read or for readahead. When no data
* can be read, -EAGAIN shall be returned. When readahead would be
* triggered, a partial, possibly empty read shall be returned.
*
* Return:
* * number of bytes copied, even for partial reads
* * negative error code (or 0 if IOCB_NOIO) if nothing was read
*/
ssize_t
generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
{
mm/filemap: generic_file_read_iter(): check for zero reads unconditionally If - generic_file_read_iter() gets called with a zero read length, - the read offset is at a page boundary, - IOCB_DIRECT is not set - and the page in question hasn't made it into the page cache yet, then do_generic_file_read() will trigger a readahead with a req_size hint of zero. Since roundup_pow_of_two(0) is undefined, UBSAN reports UBSAN: Undefined behaviour in include/linux/log2.h:63:13 shift exponent 64 is too large for 64-bit type 'long unsigned int' CPU: 3 PID: 1017 Comm: sa1 Tainted: G L 4.5.0-next-20160318+ #14 [...] Call Trace: [...] [<ffffffff813ef61a>] ondemand_readahead+0x3aa/0x3d0 [<ffffffff813ef61a>] ? ondemand_readahead+0x3aa/0x3d0 [<ffffffff813c73bd>] ? find_get_entry+0x2d/0x210 [<ffffffff813ef9c3>] page_cache_sync_readahead+0x63/0xa0 [<ffffffff813cc04d>] do_generic_file_read+0x80d/0xf90 [<ffffffff813cc955>] generic_file_read_iter+0x185/0x420 [...] [<ffffffff81510b06>] __vfs_read+0x256/0x3d0 [...] when get_init_ra_size() gets called from ondemand_readahead(). The net effect is that the initial readahead size is arch dependent for requested read lengths of zero: for example, since 1UL << (sizeof(unsigned long) * 8) evaluates to 1 on x86 while its result is 0 on ARMv7, the initial readahead size becomes 4 on the former and 0 on the latter. What's more, whether or not the file access timestamp is updated for zero length reads is decided differently for the two cases of IOCB_DIRECT being set or cleared: in the first case, generic_file_read_iter() explicitly skips updating that timestamp while in the latter case, it is always updated through the call to do_generic_file_read(). According to POSIX, zero length reads "do not modify the last data access timestamp" and thus, the IOCB_DIRECT behaviour is POSIXly correct. Let generic_file_read_iter() unconditionally check the requested read length at its entry and return immediately with success if it is zero. Signed-off-by: Nicolai Stange <nicstange@gmail.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Reviewed-by: Jan Kara <jack@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-03-25 21:22:14 +00:00
size_t count = iov_iter_count(iter);
ssize_t retval = 0;
mm/filemap: generic_file_read_iter(): check for zero reads unconditionally If - generic_file_read_iter() gets called with a zero read length, - the read offset is at a page boundary, - IOCB_DIRECT is not set - and the page in question hasn't made it into the page cache yet, then do_generic_file_read() will trigger a readahead with a req_size hint of zero. Since roundup_pow_of_two(0) is undefined, UBSAN reports UBSAN: Undefined behaviour in include/linux/log2.h:63:13 shift exponent 64 is too large for 64-bit type 'long unsigned int' CPU: 3 PID: 1017 Comm: sa1 Tainted: G L 4.5.0-next-20160318+ #14 [...] Call Trace: [...] [<ffffffff813ef61a>] ondemand_readahead+0x3aa/0x3d0 [<ffffffff813ef61a>] ? ondemand_readahead+0x3aa/0x3d0 [<ffffffff813c73bd>] ? find_get_entry+0x2d/0x210 [<ffffffff813ef9c3>] page_cache_sync_readahead+0x63/0xa0 [<ffffffff813cc04d>] do_generic_file_read+0x80d/0xf90 [<ffffffff813cc955>] generic_file_read_iter+0x185/0x420 [...] [<ffffffff81510b06>] __vfs_read+0x256/0x3d0 [...] when get_init_ra_size() gets called from ondemand_readahead(). The net effect is that the initial readahead size is arch dependent for requested read lengths of zero: for example, since 1UL << (sizeof(unsigned long) * 8) evaluates to 1 on x86 while its result is 0 on ARMv7, the initial readahead size becomes 4 on the former and 0 on the latter. What's more, whether or not the file access timestamp is updated for zero length reads is decided differently for the two cases of IOCB_DIRECT being set or cleared: in the first case, generic_file_read_iter() explicitly skips updating that timestamp while in the latter case, it is always updated through the call to do_generic_file_read(). According to POSIX, zero length reads "do not modify the last data access timestamp" and thus, the IOCB_DIRECT behaviour is POSIXly correct. Let generic_file_read_iter() unconditionally check the requested read length at its entry and return immediately with success if it is zero. Signed-off-by: Nicolai Stange <nicstange@gmail.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Reviewed-by: Jan Kara <jack@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-03-25 21:22:14 +00:00
if (!count)
return 0; /* skip atime */
if (iocb->ki_flags & IOCB_DIRECT) {
struct file *file = iocb->ki_filp;
struct address_space *mapping = file->f_mapping;
struct inode *inode = mapping->host;
retval = kiocb_write_and_wait(iocb, count);
if (retval < 0)
return retval;
file_accessed(file);
retval = mapping->a_ops->direct_IO(iocb, iter);
if (retval >= 0) {
iocb->ki_pos += retval;
count -= 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
}
if (retval != -EIOCBQUEUED)
iov_iter_revert(iter, count - iov_iter_count(iter));
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 || !count || IS_DAX(inode))
return retval;
if (iocb->ki_pos >= i_size_read(inode))
return retval;
}
return filemap_read(iocb, iter, retval);
}
EXPORT_SYMBOL(generic_file_read_iter);
/*
* Splice subpages from a folio into a pipe.
*/
size_t splice_folio_into_pipe(struct pipe_inode_info *pipe,
struct folio *folio, loff_t fpos, size_t size)
{
struct page *page;
size_t spliced = 0, offset = offset_in_folio(folio, fpos);
page = folio_page(folio, offset / PAGE_SIZE);
size = min(size, folio_size(folio) - offset);
offset %= PAGE_SIZE;
while (spliced < size &&
!pipe_full(pipe->head, pipe->tail, pipe->max_usage)) {
struct pipe_buffer *buf = pipe_head_buf(pipe);
size_t part = min_t(size_t, PAGE_SIZE - offset, size - spliced);
*buf = (struct pipe_buffer) {
.ops = &page_cache_pipe_buf_ops,
.page = page,
.offset = offset,
.len = part,
};
folio_get(folio);
pipe->head++;
page++;
spliced += part;
offset = 0;
}
return spliced;
}
/**
* filemap_splice_read - Splice data from a file's pagecache into a pipe
* @in: The file to read from
* @ppos: Pointer to the file position to read from
* @pipe: The pipe to splice into
* @len: The amount to splice
* @flags: The SPLICE_F_* flags
*
* This function gets folios from a file's pagecache and splices them into the
* pipe. Readahead will be called as necessary to fill more folios. This may
* be used for blockdevs also.
*
* Return: On success, the number of bytes read will be returned and *@ppos
* will be updated if appropriate; 0 will be returned if there is no more data
* to be read; -EAGAIN will be returned if the pipe had no space, and some
* other negative error code will be returned on error. A short read may occur
* if the pipe has insufficient space, we reach the end of the data or we hit a
* hole.
*/
ssize_t filemap_splice_read(struct file *in, loff_t *ppos,
struct pipe_inode_info *pipe,
size_t len, unsigned int flags)
{
struct folio_batch fbatch;
struct kiocb iocb;
size_t total_spliced = 0, used, npages;
loff_t isize, end_offset;
bool writably_mapped;
int i, error = 0;
if (unlikely(*ppos >= in->f_mapping->host->i_sb->s_maxbytes))
return 0;
init_sync_kiocb(&iocb, in);
iocb.ki_pos = *ppos;
/* Work out how much data we can actually add into the pipe */
used = pipe_occupancy(pipe->head, pipe->tail);
npages = max_t(ssize_t, pipe->max_usage - used, 0);
len = min_t(size_t, len, npages * PAGE_SIZE);
folio_batch_init(&fbatch);
do {
cond_resched();
if (*ppos >= i_size_read(in->f_mapping->host))
break;
iocb.ki_pos = *ppos;
error = filemap_get_pages(&iocb, len, &fbatch, true);
if (error < 0)
break;
/*
* i_size must be checked after we know the pages are 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(in->f_mapping->host);
if (unlikely(*ppos >= isize))
break;
end_offset = min_t(loff_t, isize, *ppos + len);
/*
* Once we start copying data, we don't want to be touching any
* cachelines that might be contended:
*/
writably_mapped = mapping_writably_mapped(in->f_mapping);
for (i = 0; i < folio_batch_count(&fbatch); i++) {
struct folio *folio = fbatch.folios[i];
size_t n;
if (folio_pos(folio) >= end_offset)
goto out;
folio_mark_accessed(folio);
/*
* If users can be writing to this folio using arbitrary
* virtual addresses, take care of potential aliasing
* before reading the folio on the kernel side.
*/
if (writably_mapped)
flush_dcache_folio(folio);
n = min_t(loff_t, len, isize - *ppos);
n = splice_folio_into_pipe(pipe, folio, *ppos, n);
if (!n)
goto out;
len -= n;
total_spliced += n;
*ppos += n;
in->f_ra.prev_pos = *ppos;
if (pipe_full(pipe->head, pipe->tail, pipe->max_usage))
goto out;
}
folio_batch_release(&fbatch);
} while (len);
out:
folio_batch_release(&fbatch);
file_accessed(in);
return total_spliced ? total_spliced : error;
}
EXPORT_SYMBOL(filemap_splice_read);
static inline loff_t folio_seek_hole_data(struct xa_state *xas,
struct address_space *mapping, struct folio *folio,
loff_t start, loff_t end, bool seek_data)
{
const struct address_space_operations *ops = mapping->a_ops;
size_t offset, bsz = i_blocksize(mapping->host);
if (xa_is_value(folio) || folio_test_uptodate(folio))
return seek_data ? start : end;
if (!ops->is_partially_uptodate)
return seek_data ? end : start;
xas_pause(xas);
rcu_read_unlock();
folio_lock(folio);
if (unlikely(folio->mapping != mapping))
goto unlock;
offset = offset_in_folio(folio, start) & ~(bsz - 1);
do {
if (ops->is_partially_uptodate(folio, offset, bsz) ==
seek_data)
break;
start = (start + bsz) & ~(bsz - 1);
offset += bsz;
} while (offset < folio_size(folio));
unlock:
folio_unlock(folio);
rcu_read_lock();
return start;
}
static inline size_t seek_folio_size(struct xa_state *xas, struct folio *folio)
{
if (xa_is_value(folio))
return PAGE_SIZE << xa_get_order(xas->xa, xas->xa_index);
return folio_size(folio);
}
/**
* mapping_seek_hole_data - Seek for SEEK_DATA / SEEK_HOLE in the page cache.
* @mapping: Address space to search.
* @start: First byte to consider.
* @end: Limit of search (exclusive).
* @whence: Either SEEK_HOLE or SEEK_DATA.
*
* If the page cache knows which blocks contain holes and which blocks
* contain data, your filesystem can use this function to implement
* SEEK_HOLE and SEEK_DATA. This is useful for filesystems which are
* entirely memory-based such as tmpfs, and filesystems which support
* unwritten extents.
*
* Return: The requested offset on success, or -ENXIO if @whence specifies
* SEEK_DATA and there is no data after @start. There is an implicit hole
* after @end - 1, so SEEK_HOLE returns @end if all the bytes between @start
* and @end contain data.
*/
loff_t mapping_seek_hole_data(struct address_space *mapping, loff_t start,
loff_t end, int whence)
{
XA_STATE(xas, &mapping->i_pages, start >> PAGE_SHIFT);
mm/filemap: fix mapping_seek_hole_data on THP & 32-bit No problem on 64-bit, or without huge pages, but xfstests generic/285 and other SEEK_HOLE/SEEK_DATA tests have regressed on huge tmpfs, and on 32-bit architectures, with the new mapping_seek_hole_data(). Several different bugs turned out to need fixing. u64 cast to stop losing bits when converting unsigned long to loff_t (and let's use shifts throughout, rather than mixed with * and /). Use round_up() when advancing pos, to stop assuming that pos was already THP-aligned when advancing it by THP-size. (This use of round_up() assumes that any THP has THP-aligned index: true at present and true going forward, but could be recoded to avoid the assumption.) Use xas_set() when iterating away from a THP, so that xa_index stays in synch with start, instead of drifting away to return bogus offset. Check start against end to avoid wrapping 32-bit xa_index to 0 (and to handle these additional cases, seek_data or not, it's easier to break the loop than goto: so rearrange exit from the function). [hughd@google.com: remove unneeded u64 casts, per Matthew] Link: https://lkml.kernel.org/r/alpine.LSU.2.11.2104221347240.1170@eggly.anvils Link: https://lkml.kernel.org/r/alpine.LSU.2.11.2104211737410.3299@eggly.anvils Fixes: 41139aa4c3a3 ("mm/filemap: add mapping_seek_hole_data") Signed-off-by: Hugh Dickins <hughd@google.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Dave Chinner <dchinner@redhat.com> Cc: Jan Kara <jack@suse.cz> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: William Kucharski <william.kucharski@oracle.com> Cc: Yang Shi <yang.shi@linux.alibaba.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-04-23 21:29:00 +00:00
pgoff_t max = (end - 1) >> PAGE_SHIFT;
bool seek_data = (whence == SEEK_DATA);
struct folio *folio;
if (end <= start)
return -ENXIO;
rcu_read_lock();
while ((folio = find_get_entry(&xas, max, XA_PRESENT))) {
mm/filemap: fix mapping_seek_hole_data on THP & 32-bit No problem on 64-bit, or without huge pages, but xfstests generic/285 and other SEEK_HOLE/SEEK_DATA tests have regressed on huge tmpfs, and on 32-bit architectures, with the new mapping_seek_hole_data(). Several different bugs turned out to need fixing. u64 cast to stop losing bits when converting unsigned long to loff_t (and let's use shifts throughout, rather than mixed with * and /). Use round_up() when advancing pos, to stop assuming that pos was already THP-aligned when advancing it by THP-size. (This use of round_up() assumes that any THP has THP-aligned index: true at present and true going forward, but could be recoded to avoid the assumption.) Use xas_set() when iterating away from a THP, so that xa_index stays in synch with start, instead of drifting away to return bogus offset. Check start against end to avoid wrapping 32-bit xa_index to 0 (and to handle these additional cases, seek_data or not, it's easier to break the loop than goto: so rearrange exit from the function). [hughd@google.com: remove unneeded u64 casts, per Matthew] Link: https://lkml.kernel.org/r/alpine.LSU.2.11.2104221347240.1170@eggly.anvils Link: https://lkml.kernel.org/r/alpine.LSU.2.11.2104211737410.3299@eggly.anvils Fixes: 41139aa4c3a3 ("mm/filemap: add mapping_seek_hole_data") Signed-off-by: Hugh Dickins <hughd@google.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Dave Chinner <dchinner@redhat.com> Cc: Jan Kara <jack@suse.cz> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: William Kucharski <william.kucharski@oracle.com> Cc: Yang Shi <yang.shi@linux.alibaba.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-04-23 21:29:00 +00:00
loff_t pos = (u64)xas.xa_index << PAGE_SHIFT;
size_t seek_size;
if (start < pos) {
if (!seek_data)
goto unlock;
start = pos;
}
seek_size = seek_folio_size(&xas, folio);
pos = round_up((u64)pos + 1, seek_size);
start = folio_seek_hole_data(&xas, mapping, folio, start, pos,
seek_data);
if (start < pos)
goto unlock;
mm/filemap: fix mapping_seek_hole_data on THP & 32-bit No problem on 64-bit, or without huge pages, but xfstests generic/285 and other SEEK_HOLE/SEEK_DATA tests have regressed on huge tmpfs, and on 32-bit architectures, with the new mapping_seek_hole_data(). Several different bugs turned out to need fixing. u64 cast to stop losing bits when converting unsigned long to loff_t (and let's use shifts throughout, rather than mixed with * and /). Use round_up() when advancing pos, to stop assuming that pos was already THP-aligned when advancing it by THP-size. (This use of round_up() assumes that any THP has THP-aligned index: true at present and true going forward, but could be recoded to avoid the assumption.) Use xas_set() when iterating away from a THP, so that xa_index stays in synch with start, instead of drifting away to return bogus offset. Check start against end to avoid wrapping 32-bit xa_index to 0 (and to handle these additional cases, seek_data or not, it's easier to break the loop than goto: so rearrange exit from the function). [hughd@google.com: remove unneeded u64 casts, per Matthew] Link: https://lkml.kernel.org/r/alpine.LSU.2.11.2104221347240.1170@eggly.anvils Link: https://lkml.kernel.org/r/alpine.LSU.2.11.2104211737410.3299@eggly.anvils Fixes: 41139aa4c3a3 ("mm/filemap: add mapping_seek_hole_data") Signed-off-by: Hugh Dickins <hughd@google.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Dave Chinner <dchinner@redhat.com> Cc: Jan Kara <jack@suse.cz> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: William Kucharski <william.kucharski@oracle.com> Cc: Yang Shi <yang.shi@linux.alibaba.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-04-23 21:29:00 +00:00
if (start >= end)
break;
if (seek_size > PAGE_SIZE)
xas_set(&xas, pos >> PAGE_SHIFT);
if (!xa_is_value(folio))
folio_put(folio);
}
if (seek_data)
mm/filemap: fix mapping_seek_hole_data on THP & 32-bit No problem on 64-bit, or without huge pages, but xfstests generic/285 and other SEEK_HOLE/SEEK_DATA tests have regressed on huge tmpfs, and on 32-bit architectures, with the new mapping_seek_hole_data(). Several different bugs turned out to need fixing. u64 cast to stop losing bits when converting unsigned long to loff_t (and let's use shifts throughout, rather than mixed with * and /). Use round_up() when advancing pos, to stop assuming that pos was already THP-aligned when advancing it by THP-size. (This use of round_up() assumes that any THP has THP-aligned index: true at present and true going forward, but could be recoded to avoid the assumption.) Use xas_set() when iterating away from a THP, so that xa_index stays in synch with start, instead of drifting away to return bogus offset. Check start against end to avoid wrapping 32-bit xa_index to 0 (and to handle these additional cases, seek_data or not, it's easier to break the loop than goto: so rearrange exit from the function). [hughd@google.com: remove unneeded u64 casts, per Matthew] Link: https://lkml.kernel.org/r/alpine.LSU.2.11.2104221347240.1170@eggly.anvils Link: https://lkml.kernel.org/r/alpine.LSU.2.11.2104211737410.3299@eggly.anvils Fixes: 41139aa4c3a3 ("mm/filemap: add mapping_seek_hole_data") Signed-off-by: Hugh Dickins <hughd@google.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Dave Chinner <dchinner@redhat.com> Cc: Jan Kara <jack@suse.cz> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: William Kucharski <william.kucharski@oracle.com> Cc: Yang Shi <yang.shi@linux.alibaba.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-04-23 21:29:00 +00:00
start = -ENXIO;
unlock:
rcu_read_unlock();
if (folio && !xa_is_value(folio))
folio_put(folio);
if (start > end)
return end;
return start;
}
#ifdef CONFIG_MMU
#define MMAP_LOTSAMISS (100)
filemap: drop the mmap_sem for all blocking operations Currently we only drop the mmap_sem if there is contention on the page lock. The idea is that we issue readahead and then go to lock the page while it is under IO and we want to not hold the mmap_sem during the IO. The problem with this is the assumption that the readahead does anything. In the case that the box is under extreme memory or IO pressure we may end up not reading anything at all for readahead, which means we will end up reading in the page under the mmap_sem. Even if the readahead does something, it could get throttled because of io pressure on the system and the process is in a lower priority cgroup. Holding the mmap_sem while doing IO is problematic because it can cause system-wide priority inversions. Consider some large company that does a lot of web traffic. This large company has load balancing logic in it's core web server, cause some engineer thought this was a brilliant plan. This load balancing logic gets statistics from /proc about the system, which trip over processes mmap_sem for various reasons. Now the web server application is in a protected cgroup, but these other processes may not be, and if they are being throttled while their mmap_sem is held we'll stall, and cause this nice death spiral. Instead rework filemap fault path to drop the mmap sem at any point that we may do IO or block for an extended period of time. This includes while issuing readahead, locking the page, or needing to call ->readpage because readahead did not occur. Then once we have a fully uptodate page we can return with VM_FAULT_RETRY and come back again to find our nicely in-cache page that was gotten outside of the mmap_sem. This patch also adds a new helper for locking the page with the mmap_sem dropped. This doesn't make sense currently as generally speaking if the page is already locked it'll have been read in (unless there was an error) before it was unlocked. However a forthcoming patchset will change this with the ability to abort read-ahead bio's if necessary, making it more likely that we could contend for a page lock and still have a not uptodate page. This allows us to deal with this case by grabbing the lock and issuing the IO without the mmap_sem held, and then returning VM_FAULT_RETRY to come back around. [josef@toxicpanda.com: v6] Link: http://lkml.kernel.org/r/20181212152757.10017-1-josef@toxicpanda.com [kirill@shutemov.name: fix race in filemap_fault()] Link: http://lkml.kernel.org/r/20181228235106.okk3oastsnpxusxs@kshutemo-mobl1 [akpm@linux-foundation.org: coding style fixes] Link: http://lkml.kernel.org/r/20181211173801.29535-4-josef@toxicpanda.com Signed-off-by: Josef Bacik <josef@toxicpanda.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Jan Kara <jack@suse.cz> Tested-by: syzbot+b437b5a429d680cf2217@syzkaller.appspotmail.com Cc: Dave Chinner <david@fromorbit.com> Cc: Rik van Riel <riel@redhat.com> Cc: Tejun Heo <tj@kernel.org> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-13 18:44:22 +00:00
/*
* lock_folio_maybe_drop_mmap - lock the page, possibly dropping the mmap_lock
filemap: drop the mmap_sem for all blocking operations Currently we only drop the mmap_sem if there is contention on the page lock. The idea is that we issue readahead and then go to lock the page while it is under IO and we want to not hold the mmap_sem during the IO. The problem with this is the assumption that the readahead does anything. In the case that the box is under extreme memory or IO pressure we may end up not reading anything at all for readahead, which means we will end up reading in the page under the mmap_sem. Even if the readahead does something, it could get throttled because of io pressure on the system and the process is in a lower priority cgroup. Holding the mmap_sem while doing IO is problematic because it can cause system-wide priority inversions. Consider some large company that does a lot of web traffic. This large company has load balancing logic in it's core web server, cause some engineer thought this was a brilliant plan. This load balancing logic gets statistics from /proc about the system, which trip over processes mmap_sem for various reasons. Now the web server application is in a protected cgroup, but these other processes may not be, and if they are being throttled while their mmap_sem is held we'll stall, and cause this nice death spiral. Instead rework filemap fault path to drop the mmap sem at any point that we may do IO or block for an extended period of time. This includes while issuing readahead, locking the page, or needing to call ->readpage because readahead did not occur. Then once we have a fully uptodate page we can return with VM_FAULT_RETRY and come back again to find our nicely in-cache page that was gotten outside of the mmap_sem. This patch also adds a new helper for locking the page with the mmap_sem dropped. This doesn't make sense currently as generally speaking if the page is already locked it'll have been read in (unless there was an error) before it was unlocked. However a forthcoming patchset will change this with the ability to abort read-ahead bio's if necessary, making it more likely that we could contend for a page lock and still have a not uptodate page. This allows us to deal with this case by grabbing the lock and issuing the IO without the mmap_sem held, and then returning VM_FAULT_RETRY to come back around. [josef@toxicpanda.com: v6] Link: http://lkml.kernel.org/r/20181212152757.10017-1-josef@toxicpanda.com [kirill@shutemov.name: fix race in filemap_fault()] Link: http://lkml.kernel.org/r/20181228235106.okk3oastsnpxusxs@kshutemo-mobl1 [akpm@linux-foundation.org: coding style fixes] Link: http://lkml.kernel.org/r/20181211173801.29535-4-josef@toxicpanda.com Signed-off-by: Josef Bacik <josef@toxicpanda.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Jan Kara <jack@suse.cz> Tested-by: syzbot+b437b5a429d680cf2217@syzkaller.appspotmail.com Cc: Dave Chinner <david@fromorbit.com> Cc: Rik van Riel <riel@redhat.com> Cc: Tejun Heo <tj@kernel.org> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-13 18:44:22 +00:00
* @vmf - the vm_fault for this fault.
* @folio - the folio to lock.
filemap: drop the mmap_sem for all blocking operations Currently we only drop the mmap_sem if there is contention on the page lock. The idea is that we issue readahead and then go to lock the page while it is under IO and we want to not hold the mmap_sem during the IO. The problem with this is the assumption that the readahead does anything. In the case that the box is under extreme memory or IO pressure we may end up not reading anything at all for readahead, which means we will end up reading in the page under the mmap_sem. Even if the readahead does something, it could get throttled because of io pressure on the system and the process is in a lower priority cgroup. Holding the mmap_sem while doing IO is problematic because it can cause system-wide priority inversions. Consider some large company that does a lot of web traffic. This large company has load balancing logic in it's core web server, cause some engineer thought this was a brilliant plan. This load balancing logic gets statistics from /proc about the system, which trip over processes mmap_sem for various reasons. Now the web server application is in a protected cgroup, but these other processes may not be, and if they are being throttled while their mmap_sem is held we'll stall, and cause this nice death spiral. Instead rework filemap fault path to drop the mmap sem at any point that we may do IO or block for an extended period of time. This includes while issuing readahead, locking the page, or needing to call ->readpage because readahead did not occur. Then once we have a fully uptodate page we can return with VM_FAULT_RETRY and come back again to find our nicely in-cache page that was gotten outside of the mmap_sem. This patch also adds a new helper for locking the page with the mmap_sem dropped. This doesn't make sense currently as generally speaking if the page is already locked it'll have been read in (unless there was an error) before it was unlocked. However a forthcoming patchset will change this with the ability to abort read-ahead bio's if necessary, making it more likely that we could contend for a page lock and still have a not uptodate page. This allows us to deal with this case by grabbing the lock and issuing the IO without the mmap_sem held, and then returning VM_FAULT_RETRY to come back around. [josef@toxicpanda.com: v6] Link: http://lkml.kernel.org/r/20181212152757.10017-1-josef@toxicpanda.com [kirill@shutemov.name: fix race in filemap_fault()] Link: http://lkml.kernel.org/r/20181228235106.okk3oastsnpxusxs@kshutemo-mobl1 [akpm@linux-foundation.org: coding style fixes] Link: http://lkml.kernel.org/r/20181211173801.29535-4-josef@toxicpanda.com Signed-off-by: Josef Bacik <josef@toxicpanda.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Jan Kara <jack@suse.cz> Tested-by: syzbot+b437b5a429d680cf2217@syzkaller.appspotmail.com Cc: Dave Chinner <david@fromorbit.com> Cc: Rik van Riel <riel@redhat.com> Cc: Tejun Heo <tj@kernel.org> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-13 18:44:22 +00:00
* @fpin - the pointer to the file we may pin (or is already pinned).
*
* This works similar to lock_folio_or_retry in that it can drop the
* mmap_lock. It differs in that it actually returns the folio locked
* if it returns 1 and 0 if it couldn't lock the folio. If we did have
* to drop the mmap_lock then fpin will point to the pinned file and
* needs to be fput()'ed at a later point.
filemap: drop the mmap_sem for all blocking operations Currently we only drop the mmap_sem if there is contention on the page lock. The idea is that we issue readahead and then go to lock the page while it is under IO and we want to not hold the mmap_sem during the IO. The problem with this is the assumption that the readahead does anything. In the case that the box is under extreme memory or IO pressure we may end up not reading anything at all for readahead, which means we will end up reading in the page under the mmap_sem. Even if the readahead does something, it could get throttled because of io pressure on the system and the process is in a lower priority cgroup. Holding the mmap_sem while doing IO is problematic because it can cause system-wide priority inversions. Consider some large company that does a lot of web traffic. This large company has load balancing logic in it's core web server, cause some engineer thought this was a brilliant plan. This load balancing logic gets statistics from /proc about the system, which trip over processes mmap_sem for various reasons. Now the web server application is in a protected cgroup, but these other processes may not be, and if they are being throttled while their mmap_sem is held we'll stall, and cause this nice death spiral. Instead rework filemap fault path to drop the mmap sem at any point that we may do IO or block for an extended period of time. This includes while issuing readahead, locking the page, or needing to call ->readpage because readahead did not occur. Then once we have a fully uptodate page we can return with VM_FAULT_RETRY and come back again to find our nicely in-cache page that was gotten outside of the mmap_sem. This patch also adds a new helper for locking the page with the mmap_sem dropped. This doesn't make sense currently as generally speaking if the page is already locked it'll have been read in (unless there was an error) before it was unlocked. However a forthcoming patchset will change this with the ability to abort read-ahead bio's if necessary, making it more likely that we could contend for a page lock and still have a not uptodate page. This allows us to deal with this case by grabbing the lock and issuing the IO without the mmap_sem held, and then returning VM_FAULT_RETRY to come back around. [josef@toxicpanda.com: v6] Link: http://lkml.kernel.org/r/20181212152757.10017-1-josef@toxicpanda.com [kirill@shutemov.name: fix race in filemap_fault()] Link: http://lkml.kernel.org/r/20181228235106.okk3oastsnpxusxs@kshutemo-mobl1 [akpm@linux-foundation.org: coding style fixes] Link: http://lkml.kernel.org/r/20181211173801.29535-4-josef@toxicpanda.com Signed-off-by: Josef Bacik <josef@toxicpanda.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Jan Kara <jack@suse.cz> Tested-by: syzbot+b437b5a429d680cf2217@syzkaller.appspotmail.com Cc: Dave Chinner <david@fromorbit.com> Cc: Rik van Riel <riel@redhat.com> Cc: Tejun Heo <tj@kernel.org> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-13 18:44:22 +00:00
*/
static int lock_folio_maybe_drop_mmap(struct vm_fault *vmf, struct folio *folio,
filemap: drop the mmap_sem for all blocking operations Currently we only drop the mmap_sem if there is contention on the page lock. The idea is that we issue readahead and then go to lock the page while it is under IO and we want to not hold the mmap_sem during the IO. The problem with this is the assumption that the readahead does anything. In the case that the box is under extreme memory or IO pressure we may end up not reading anything at all for readahead, which means we will end up reading in the page under the mmap_sem. Even if the readahead does something, it could get throttled because of io pressure on the system and the process is in a lower priority cgroup. Holding the mmap_sem while doing IO is problematic because it can cause system-wide priority inversions. Consider some large company that does a lot of web traffic. This large company has load balancing logic in it's core web server, cause some engineer thought this was a brilliant plan. This load balancing logic gets statistics from /proc about the system, which trip over processes mmap_sem for various reasons. Now the web server application is in a protected cgroup, but these other processes may not be, and if they are being throttled while their mmap_sem is held we'll stall, and cause this nice death spiral. Instead rework filemap fault path to drop the mmap sem at any point that we may do IO or block for an extended period of time. This includes while issuing readahead, locking the page, or needing to call ->readpage because readahead did not occur. Then once we have a fully uptodate page we can return with VM_FAULT_RETRY and come back again to find our nicely in-cache page that was gotten outside of the mmap_sem. This patch also adds a new helper for locking the page with the mmap_sem dropped. This doesn't make sense currently as generally speaking if the page is already locked it'll have been read in (unless there was an error) before it was unlocked. However a forthcoming patchset will change this with the ability to abort read-ahead bio's if necessary, making it more likely that we could contend for a page lock and still have a not uptodate page. This allows us to deal with this case by grabbing the lock and issuing the IO without the mmap_sem held, and then returning VM_FAULT_RETRY to come back around. [josef@toxicpanda.com: v6] Link: http://lkml.kernel.org/r/20181212152757.10017-1-josef@toxicpanda.com [kirill@shutemov.name: fix race in filemap_fault()] Link: http://lkml.kernel.org/r/20181228235106.okk3oastsnpxusxs@kshutemo-mobl1 [akpm@linux-foundation.org: coding style fixes] Link: http://lkml.kernel.org/r/20181211173801.29535-4-josef@toxicpanda.com Signed-off-by: Josef Bacik <josef@toxicpanda.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Jan Kara <jack@suse.cz> Tested-by: syzbot+b437b5a429d680cf2217@syzkaller.appspotmail.com Cc: Dave Chinner <david@fromorbit.com> Cc: Rik van Riel <riel@redhat.com> Cc: Tejun Heo <tj@kernel.org> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-13 18:44:22 +00:00
struct file **fpin)
{
if (folio_trylock(folio))
filemap: drop the mmap_sem for all blocking operations Currently we only drop the mmap_sem if there is contention on the page lock. The idea is that we issue readahead and then go to lock the page while it is under IO and we want to not hold the mmap_sem during the IO. The problem with this is the assumption that the readahead does anything. In the case that the box is under extreme memory or IO pressure we may end up not reading anything at all for readahead, which means we will end up reading in the page under the mmap_sem. Even if the readahead does something, it could get throttled because of io pressure on the system and the process is in a lower priority cgroup. Holding the mmap_sem while doing IO is problematic because it can cause system-wide priority inversions. Consider some large company that does a lot of web traffic. This large company has load balancing logic in it's core web server, cause some engineer thought this was a brilliant plan. This load balancing logic gets statistics from /proc about the system, which trip over processes mmap_sem for various reasons. Now the web server application is in a protected cgroup, but these other processes may not be, and if they are being throttled while their mmap_sem is held we'll stall, and cause this nice death spiral. Instead rework filemap fault path to drop the mmap sem at any point that we may do IO or block for an extended period of time. This includes while issuing readahead, locking the page, or needing to call ->readpage because readahead did not occur. Then once we have a fully uptodate page we can return with VM_FAULT_RETRY and come back again to find our nicely in-cache page that was gotten outside of the mmap_sem. This patch also adds a new helper for locking the page with the mmap_sem dropped. This doesn't make sense currently as generally speaking if the page is already locked it'll have been read in (unless there was an error) before it was unlocked. However a forthcoming patchset will change this with the ability to abort read-ahead bio's if necessary, making it more likely that we could contend for a page lock and still have a not uptodate page. This allows us to deal with this case by grabbing the lock and issuing the IO without the mmap_sem held, and then returning VM_FAULT_RETRY to come back around. [josef@toxicpanda.com: v6] Link: http://lkml.kernel.org/r/20181212152757.10017-1-josef@toxicpanda.com [kirill@shutemov.name: fix race in filemap_fault()] Link: http://lkml.kernel.org/r/20181228235106.okk3oastsnpxusxs@kshutemo-mobl1 [akpm@linux-foundation.org: coding style fixes] Link: http://lkml.kernel.org/r/20181211173801.29535-4-josef@toxicpanda.com Signed-off-by: Josef Bacik <josef@toxicpanda.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Jan Kara <jack@suse.cz> Tested-by: syzbot+b437b5a429d680cf2217@syzkaller.appspotmail.com Cc: Dave Chinner <david@fromorbit.com> Cc: Rik van Riel <riel@redhat.com> Cc: Tejun Heo <tj@kernel.org> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-13 18:44:22 +00:00
return 1;
/*
* NOTE! This will make us return with VM_FAULT_RETRY, but with
mm: make lock_folio_maybe_drop_mmap() VMA lock aware Patch series "Handle more faults under the VMA lock", v2. At this point, we're handling the majority of file-backed page faults under the VMA lock, using the ->map_pages entry point. This patch set attempts to expand that for the following siutations: - We have to do a read. This could be because we've hit the point in the readahead window where we need to kick off the next readahead, or because the page is simply not present in cache. - We're handling a write fault. Most applications don't do I/O by writes to shared mmaps for very good reasons, but some do, and it'd be nice to not make that slow unnecessarily. - We're doing a COW of a private mapping (both PTE already present and PTE not-present). These are two different codepaths and I handle both of them in this patch set. There is no support in this patch set for drivers to mark themselves as being VMA lock friendly; they could implement the ->map_pages vm_operation, but if they do, they would be the first. This is probably something we want to change at some point in the future, and I've marked where to make that change in the code. There is very little performance change in the benchmarks we've run; mostly because the vast majority of page faults are handled through the other paths. I still think this patch series is useful for workloads that may take these paths more often, and just for cleaning up the fault path in general (it's now clearer why we have to retry in these cases). This patch (of 6): Drop the VMA lock instead of the mmap_lock if that's the one which is held. Link: https://lkml.kernel.org/r/20231006195318.4087158-1-willy@infradead.org Link: https://lkml.kernel.org/r/20231006195318.4087158-2-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org> Reviewed-by: Suren Baghdasaryan <surenb@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-10-06 19:53:13 +00:00
* the fault lock still held. That's how FAULT_FLAG_RETRY_NOWAIT
* is supposed to work. We have way too many special cases..
*/
filemap: drop the mmap_sem for all blocking operations Currently we only drop the mmap_sem if there is contention on the page lock. The idea is that we issue readahead and then go to lock the page while it is under IO and we want to not hold the mmap_sem during the IO. The problem with this is the assumption that the readahead does anything. In the case that the box is under extreme memory or IO pressure we may end up not reading anything at all for readahead, which means we will end up reading in the page under the mmap_sem. Even if the readahead does something, it could get throttled because of io pressure on the system and the process is in a lower priority cgroup. Holding the mmap_sem while doing IO is problematic because it can cause system-wide priority inversions. Consider some large company that does a lot of web traffic. This large company has load balancing logic in it's core web server, cause some engineer thought this was a brilliant plan. This load balancing logic gets statistics from /proc about the system, which trip over processes mmap_sem for various reasons. Now the web server application is in a protected cgroup, but these other processes may not be, and if they are being throttled while their mmap_sem is held we'll stall, and cause this nice death spiral. Instead rework filemap fault path to drop the mmap sem at any point that we may do IO or block for an extended period of time. This includes while issuing readahead, locking the page, or needing to call ->readpage because readahead did not occur. Then once we have a fully uptodate page we can return with VM_FAULT_RETRY and come back again to find our nicely in-cache page that was gotten outside of the mmap_sem. This patch also adds a new helper for locking the page with the mmap_sem dropped. This doesn't make sense currently as generally speaking if the page is already locked it'll have been read in (unless there was an error) before it was unlocked. However a forthcoming patchset will change this with the ability to abort read-ahead bio's if necessary, making it more likely that we could contend for a page lock and still have a not uptodate page. This allows us to deal with this case by grabbing the lock and issuing the IO without the mmap_sem held, and then returning VM_FAULT_RETRY to come back around. [josef@toxicpanda.com: v6] Link: http://lkml.kernel.org/r/20181212152757.10017-1-josef@toxicpanda.com [kirill@shutemov.name: fix race in filemap_fault()] Link: http://lkml.kernel.org/r/20181228235106.okk3oastsnpxusxs@kshutemo-mobl1 [akpm@linux-foundation.org: coding style fixes] Link: http://lkml.kernel.org/r/20181211173801.29535-4-josef@toxicpanda.com Signed-off-by: Josef Bacik <josef@toxicpanda.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Jan Kara <jack@suse.cz> Tested-by: syzbot+b437b5a429d680cf2217@syzkaller.appspotmail.com Cc: Dave Chinner <david@fromorbit.com> Cc: Rik van Riel <riel@redhat.com> Cc: Tejun Heo <tj@kernel.org> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-13 18:44:22 +00:00
if (vmf->flags & FAULT_FLAG_RETRY_NOWAIT)
return 0;
*fpin = maybe_unlock_mmap_for_io(vmf, *fpin);
if (vmf->flags & FAULT_FLAG_KILLABLE) {
if (__folio_lock_killable(folio)) {
filemap: drop the mmap_sem for all blocking operations Currently we only drop the mmap_sem if there is contention on the page lock. The idea is that we issue readahead and then go to lock the page while it is under IO and we want to not hold the mmap_sem during the IO. The problem with this is the assumption that the readahead does anything. In the case that the box is under extreme memory or IO pressure we may end up not reading anything at all for readahead, which means we will end up reading in the page under the mmap_sem. Even if the readahead does something, it could get throttled because of io pressure on the system and the process is in a lower priority cgroup. Holding the mmap_sem while doing IO is problematic because it can cause system-wide priority inversions. Consider some large company that does a lot of web traffic. This large company has load balancing logic in it's core web server, cause some engineer thought this was a brilliant plan. This load balancing logic gets statistics from /proc about the system, which trip over processes mmap_sem for various reasons. Now the web server application is in a protected cgroup, but these other processes may not be, and if they are being throttled while their mmap_sem is held we'll stall, and cause this nice death spiral. Instead rework filemap fault path to drop the mmap sem at any point that we may do IO or block for an extended period of time. This includes while issuing readahead, locking the page, or needing to call ->readpage because readahead did not occur. Then once we have a fully uptodate page we can return with VM_FAULT_RETRY and come back again to find our nicely in-cache page that was gotten outside of the mmap_sem. This patch also adds a new helper for locking the page with the mmap_sem dropped. This doesn't make sense currently as generally speaking if the page is already locked it'll have been read in (unless there was an error) before it was unlocked. However a forthcoming patchset will change this with the ability to abort read-ahead bio's if necessary, making it more likely that we could contend for a page lock and still have a not uptodate page. This allows us to deal with this case by grabbing the lock and issuing the IO without the mmap_sem held, and then returning VM_FAULT_RETRY to come back around. [josef@toxicpanda.com: v6] Link: http://lkml.kernel.org/r/20181212152757.10017-1-josef@toxicpanda.com [kirill@shutemov.name: fix race in filemap_fault()] Link: http://lkml.kernel.org/r/20181228235106.okk3oastsnpxusxs@kshutemo-mobl1 [akpm@linux-foundation.org: coding style fixes] Link: http://lkml.kernel.org/r/20181211173801.29535-4-josef@toxicpanda.com Signed-off-by: Josef Bacik <josef@toxicpanda.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Jan Kara <jack@suse.cz> Tested-by: syzbot+b437b5a429d680cf2217@syzkaller.appspotmail.com Cc: Dave Chinner <david@fromorbit.com> Cc: Rik van Riel <riel@redhat.com> Cc: Tejun Heo <tj@kernel.org> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-13 18:44:22 +00:00
/*
mm: make lock_folio_maybe_drop_mmap() VMA lock aware Patch series "Handle more faults under the VMA lock", v2. At this point, we're handling the majority of file-backed page faults under the VMA lock, using the ->map_pages entry point. This patch set attempts to expand that for the following siutations: - We have to do a read. This could be because we've hit the point in the readahead window where we need to kick off the next readahead, or because the page is simply not present in cache. - We're handling a write fault. Most applications don't do I/O by writes to shared mmaps for very good reasons, but some do, and it'd be nice to not make that slow unnecessarily. - We're doing a COW of a private mapping (both PTE already present and PTE not-present). These are two different codepaths and I handle both of them in this patch set. There is no support in this patch set for drivers to mark themselves as being VMA lock friendly; they could implement the ->map_pages vm_operation, but if they do, they would be the first. This is probably something we want to change at some point in the future, and I've marked where to make that change in the code. There is very little performance change in the benchmarks we've run; mostly because the vast majority of page faults are handled through the other paths. I still think this patch series is useful for workloads that may take these paths more often, and just for cleaning up the fault path in general (it's now clearer why we have to retry in these cases). This patch (of 6): Drop the VMA lock instead of the mmap_lock if that's the one which is held. Link: https://lkml.kernel.org/r/20231006195318.4087158-1-willy@infradead.org Link: https://lkml.kernel.org/r/20231006195318.4087158-2-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org> Reviewed-by: Suren Baghdasaryan <surenb@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-10-06 19:53:13 +00:00
* We didn't have the right flags to drop the
* fault lock, but all fault_handlers only check
* for fatal signals if we return VM_FAULT_RETRY,
* so we need to drop the fault lock here and
* return 0 if we don't have a fpin.
filemap: drop the mmap_sem for all blocking operations Currently we only drop the mmap_sem if there is contention on the page lock. The idea is that we issue readahead and then go to lock the page while it is under IO and we want to not hold the mmap_sem during the IO. The problem with this is the assumption that the readahead does anything. In the case that the box is under extreme memory or IO pressure we may end up not reading anything at all for readahead, which means we will end up reading in the page under the mmap_sem. Even if the readahead does something, it could get throttled because of io pressure on the system and the process is in a lower priority cgroup. Holding the mmap_sem while doing IO is problematic because it can cause system-wide priority inversions. Consider some large company that does a lot of web traffic. This large company has load balancing logic in it's core web server, cause some engineer thought this was a brilliant plan. This load balancing logic gets statistics from /proc about the system, which trip over processes mmap_sem for various reasons. Now the web server application is in a protected cgroup, but these other processes may not be, and if they are being throttled while their mmap_sem is held we'll stall, and cause this nice death spiral. Instead rework filemap fault path to drop the mmap sem at any point that we may do IO or block for an extended period of time. This includes while issuing readahead, locking the page, or needing to call ->readpage because readahead did not occur. Then once we have a fully uptodate page we can return with VM_FAULT_RETRY and come back again to find our nicely in-cache page that was gotten outside of the mmap_sem. This patch also adds a new helper for locking the page with the mmap_sem dropped. This doesn't make sense currently as generally speaking if the page is already locked it'll have been read in (unless there was an error) before it was unlocked. However a forthcoming patchset will change this with the ability to abort read-ahead bio's if necessary, making it more likely that we could contend for a page lock and still have a not uptodate page. This allows us to deal with this case by grabbing the lock and issuing the IO without the mmap_sem held, and then returning VM_FAULT_RETRY to come back around. [josef@toxicpanda.com: v6] Link: http://lkml.kernel.org/r/20181212152757.10017-1-josef@toxicpanda.com [kirill@shutemov.name: fix race in filemap_fault()] Link: http://lkml.kernel.org/r/20181228235106.okk3oastsnpxusxs@kshutemo-mobl1 [akpm@linux-foundation.org: coding style fixes] Link: http://lkml.kernel.org/r/20181211173801.29535-4-josef@toxicpanda.com Signed-off-by: Josef Bacik <josef@toxicpanda.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Jan Kara <jack@suse.cz> Tested-by: syzbot+b437b5a429d680cf2217@syzkaller.appspotmail.com Cc: Dave Chinner <david@fromorbit.com> Cc: Rik van Riel <riel@redhat.com> Cc: Tejun Heo <tj@kernel.org> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-13 18:44:22 +00:00
*/
if (*fpin == NULL)
mm: make lock_folio_maybe_drop_mmap() VMA lock aware Patch series "Handle more faults under the VMA lock", v2. At this point, we're handling the majority of file-backed page faults under the VMA lock, using the ->map_pages entry point. This patch set attempts to expand that for the following siutations: - We have to do a read. This could be because we've hit the point in the readahead window where we need to kick off the next readahead, or because the page is simply not present in cache. - We're handling a write fault. Most applications don't do I/O by writes to shared mmaps for very good reasons, but some do, and it'd be nice to not make that slow unnecessarily. - We're doing a COW of a private mapping (both PTE already present and PTE not-present). These are two different codepaths and I handle both of them in this patch set. There is no support in this patch set for drivers to mark themselves as being VMA lock friendly; they could implement the ->map_pages vm_operation, but if they do, they would be the first. This is probably something we want to change at some point in the future, and I've marked where to make that change in the code. There is very little performance change in the benchmarks we've run; mostly because the vast majority of page faults are handled through the other paths. I still think this patch series is useful for workloads that may take these paths more often, and just for cleaning up the fault path in general (it's now clearer why we have to retry in these cases). This patch (of 6): Drop the VMA lock instead of the mmap_lock if that's the one which is held. Link: https://lkml.kernel.org/r/20231006195318.4087158-1-willy@infradead.org Link: https://lkml.kernel.org/r/20231006195318.4087158-2-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org> Reviewed-by: Suren Baghdasaryan <surenb@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-10-06 19:53:13 +00:00
release_fault_lock(vmf);
filemap: drop the mmap_sem for all blocking operations Currently we only drop the mmap_sem if there is contention on the page lock. The idea is that we issue readahead and then go to lock the page while it is under IO and we want to not hold the mmap_sem during the IO. The problem with this is the assumption that the readahead does anything. In the case that the box is under extreme memory or IO pressure we may end up not reading anything at all for readahead, which means we will end up reading in the page under the mmap_sem. Even if the readahead does something, it could get throttled because of io pressure on the system and the process is in a lower priority cgroup. Holding the mmap_sem while doing IO is problematic because it can cause system-wide priority inversions. Consider some large company that does a lot of web traffic. This large company has load balancing logic in it's core web server, cause some engineer thought this was a brilliant plan. This load balancing logic gets statistics from /proc about the system, which trip over processes mmap_sem for various reasons. Now the web server application is in a protected cgroup, but these other processes may not be, and if they are being throttled while their mmap_sem is held we'll stall, and cause this nice death spiral. Instead rework filemap fault path to drop the mmap sem at any point that we may do IO or block for an extended period of time. This includes while issuing readahead, locking the page, or needing to call ->readpage because readahead did not occur. Then once we have a fully uptodate page we can return with VM_FAULT_RETRY and come back again to find our nicely in-cache page that was gotten outside of the mmap_sem. This patch also adds a new helper for locking the page with the mmap_sem dropped. This doesn't make sense currently as generally speaking if the page is already locked it'll have been read in (unless there was an error) before it was unlocked. However a forthcoming patchset will change this with the ability to abort read-ahead bio's if necessary, making it more likely that we could contend for a page lock and still have a not uptodate page. This allows us to deal with this case by grabbing the lock and issuing the IO without the mmap_sem held, and then returning VM_FAULT_RETRY to come back around. [josef@toxicpanda.com: v6] Link: http://lkml.kernel.org/r/20181212152757.10017-1-josef@toxicpanda.com [kirill@shutemov.name: fix race in filemap_fault()] Link: http://lkml.kernel.org/r/20181228235106.okk3oastsnpxusxs@kshutemo-mobl1 [akpm@linux-foundation.org: coding style fixes] Link: http://lkml.kernel.org/r/20181211173801.29535-4-josef@toxicpanda.com Signed-off-by: Josef Bacik <josef@toxicpanda.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Jan Kara <jack@suse.cz> Tested-by: syzbot+b437b5a429d680cf2217@syzkaller.appspotmail.com Cc: Dave Chinner <david@fromorbit.com> Cc: Rik van Riel <riel@redhat.com> Cc: Tejun Heo <tj@kernel.org> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-13 18:44:22 +00:00
return 0;
}
} else
__folio_lock(folio);
filemap: drop the mmap_sem for all blocking operations Currently we only drop the mmap_sem if there is contention on the page lock. The idea is that we issue readahead and then go to lock the page while it is under IO and we want to not hold the mmap_sem during the IO. The problem with this is the assumption that the readahead does anything. In the case that the box is under extreme memory or IO pressure we may end up not reading anything at all for readahead, which means we will end up reading in the page under the mmap_sem. Even if the readahead does something, it could get throttled because of io pressure on the system and the process is in a lower priority cgroup. Holding the mmap_sem while doing IO is problematic because it can cause system-wide priority inversions. Consider some large company that does a lot of web traffic. This large company has load balancing logic in it's core web server, cause some engineer thought this was a brilliant plan. This load balancing logic gets statistics from /proc about the system, which trip over processes mmap_sem for various reasons. Now the web server application is in a protected cgroup, but these other processes may not be, and if they are being throttled while their mmap_sem is held we'll stall, and cause this nice death spiral. Instead rework filemap fault path to drop the mmap sem at any point that we may do IO or block for an extended period of time. This includes while issuing readahead, locking the page, or needing to call ->readpage because readahead did not occur. Then once we have a fully uptodate page we can return with VM_FAULT_RETRY and come back again to find our nicely in-cache page that was gotten outside of the mmap_sem. This patch also adds a new helper for locking the page with the mmap_sem dropped. This doesn't make sense currently as generally speaking if the page is already locked it'll have been read in (unless there was an error) before it was unlocked. However a forthcoming patchset will change this with the ability to abort read-ahead bio's if necessary, making it more likely that we could contend for a page lock and still have a not uptodate page. This allows us to deal with this case by grabbing the lock and issuing the IO without the mmap_sem held, and then returning VM_FAULT_RETRY to come back around. [josef@toxicpanda.com: v6] Link: http://lkml.kernel.org/r/20181212152757.10017-1-josef@toxicpanda.com [kirill@shutemov.name: fix race in filemap_fault()] Link: http://lkml.kernel.org/r/20181228235106.okk3oastsnpxusxs@kshutemo-mobl1 [akpm@linux-foundation.org: coding style fixes] Link: http://lkml.kernel.org/r/20181211173801.29535-4-josef@toxicpanda.com Signed-off-by: Josef Bacik <josef@toxicpanda.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Jan Kara <jack@suse.cz> Tested-by: syzbot+b437b5a429d680cf2217@syzkaller.appspotmail.com Cc: Dave Chinner <david@fromorbit.com> Cc: Rik van Riel <riel@redhat.com> Cc: Tejun Heo <tj@kernel.org> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-13 18:44:22 +00:00
return 1;
}
/*
filemap: drop the mmap_sem for all blocking operations Currently we only drop the mmap_sem if there is contention on the page lock. The idea is that we issue readahead and then go to lock the page while it is under IO and we want to not hold the mmap_sem during the IO. The problem with this is the assumption that the readahead does anything. In the case that the box is under extreme memory or IO pressure we may end up not reading anything at all for readahead, which means we will end up reading in the page under the mmap_sem. Even if the readahead does something, it could get throttled because of io pressure on the system and the process is in a lower priority cgroup. Holding the mmap_sem while doing IO is problematic because it can cause system-wide priority inversions. Consider some large company that does a lot of web traffic. This large company has load balancing logic in it's core web server, cause some engineer thought this was a brilliant plan. This load balancing logic gets statistics from /proc about the system, which trip over processes mmap_sem for various reasons. Now the web server application is in a protected cgroup, but these other processes may not be, and if they are being throttled while their mmap_sem is held we'll stall, and cause this nice death spiral. Instead rework filemap fault path to drop the mmap sem at any point that we may do IO or block for an extended period of time. This includes while issuing readahead, locking the page, or needing to call ->readpage because readahead did not occur. Then once we have a fully uptodate page we can return with VM_FAULT_RETRY and come back again to find our nicely in-cache page that was gotten outside of the mmap_sem. This patch also adds a new helper for locking the page with the mmap_sem dropped. This doesn't make sense currently as generally speaking if the page is already locked it'll have been read in (unless there was an error) before it was unlocked. However a forthcoming patchset will change this with the ability to abort read-ahead bio's if necessary, making it more likely that we could contend for a page lock and still have a not uptodate page. This allows us to deal with this case by grabbing the lock and issuing the IO without the mmap_sem held, and then returning VM_FAULT_RETRY to come back around. [josef@toxicpanda.com: v6] Link: http://lkml.kernel.org/r/20181212152757.10017-1-josef@toxicpanda.com [kirill@shutemov.name: fix race in filemap_fault()] Link: http://lkml.kernel.org/r/20181228235106.okk3oastsnpxusxs@kshutemo-mobl1 [akpm@linux-foundation.org: coding style fixes] Link: http://lkml.kernel.org/r/20181211173801.29535-4-josef@toxicpanda.com Signed-off-by: Josef Bacik <josef@toxicpanda.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Jan Kara <jack@suse.cz> Tested-by: syzbot+b437b5a429d680cf2217@syzkaller.appspotmail.com Cc: Dave Chinner <david@fromorbit.com> Cc: Rik van Riel <riel@redhat.com> Cc: Tejun Heo <tj@kernel.org> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-13 18:44:22 +00:00
* Synchronous readahead happens when we don't even find a page in the page
* cache at all. We don't want to perform IO under the mmap sem, so if we have
* to drop the mmap sem we return the file that was pinned in order for us to do
* that. If we didn't pin a file then we return NULL. The file that is
* returned needs to be fput()'ed when we're done with it.
*/
filemap: drop the mmap_sem for all blocking operations Currently we only drop the mmap_sem if there is contention on the page lock. The idea is that we issue readahead and then go to lock the page while it is under IO and we want to not hold the mmap_sem during the IO. The problem with this is the assumption that the readahead does anything. In the case that the box is under extreme memory or IO pressure we may end up not reading anything at all for readahead, which means we will end up reading in the page under the mmap_sem. Even if the readahead does something, it could get throttled because of io pressure on the system and the process is in a lower priority cgroup. Holding the mmap_sem while doing IO is problematic because it can cause system-wide priority inversions. Consider some large company that does a lot of web traffic. This large company has load balancing logic in it's core web server, cause some engineer thought this was a brilliant plan. This load balancing logic gets statistics from /proc about the system, which trip over processes mmap_sem for various reasons. Now the web server application is in a protected cgroup, but these other processes may not be, and if they are being throttled while their mmap_sem is held we'll stall, and cause this nice death spiral. Instead rework filemap fault path to drop the mmap sem at any point that we may do IO or block for an extended period of time. This includes while issuing readahead, locking the page, or needing to call ->readpage because readahead did not occur. Then once we have a fully uptodate page we can return with VM_FAULT_RETRY and come back again to find our nicely in-cache page that was gotten outside of the mmap_sem. This patch also adds a new helper for locking the page with the mmap_sem dropped. This doesn't make sense currently as generally speaking if the page is already locked it'll have been read in (unless there was an error) before it was unlocked. However a forthcoming patchset will change this with the ability to abort read-ahead bio's if necessary, making it more likely that we could contend for a page lock and still have a not uptodate page. This allows us to deal with this case by grabbing the lock and issuing the IO without the mmap_sem held, and then returning VM_FAULT_RETRY to come back around. [josef@toxicpanda.com: v6] Link: http://lkml.kernel.org/r/20181212152757.10017-1-josef@toxicpanda.com [kirill@shutemov.name: fix race in filemap_fault()] Link: http://lkml.kernel.org/r/20181228235106.okk3oastsnpxusxs@kshutemo-mobl1 [akpm@linux-foundation.org: coding style fixes] Link: http://lkml.kernel.org/r/20181211173801.29535-4-josef@toxicpanda.com Signed-off-by: Josef Bacik <josef@toxicpanda.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Jan Kara <jack@suse.cz> Tested-by: syzbot+b437b5a429d680cf2217@syzkaller.appspotmail.com Cc: Dave Chinner <david@fromorbit.com> Cc: Rik van Riel <riel@redhat.com> Cc: Tejun Heo <tj@kernel.org> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-13 18:44:22 +00:00
static struct file *do_sync_mmap_readahead(struct vm_fault *vmf)
{
struct file *file = vmf->vma->vm_file;
struct file_ra_state *ra = &file->f_ra;
struct address_space *mapping = file->f_mapping;
DEFINE_READAHEAD(ractl, file, ra, mapping, vmf->pgoff);
filemap: drop the mmap_sem for all blocking operations Currently we only drop the mmap_sem if there is contention on the page lock. The idea is that we issue readahead and then go to lock the page while it is under IO and we want to not hold the mmap_sem during the IO. The problem with this is the assumption that the readahead does anything. In the case that the box is under extreme memory or IO pressure we may end up not reading anything at all for readahead, which means we will end up reading in the page under the mmap_sem. Even if the readahead does something, it could get throttled because of io pressure on the system and the process is in a lower priority cgroup. Holding the mmap_sem while doing IO is problematic because it can cause system-wide priority inversions. Consider some large company that does a lot of web traffic. This large company has load balancing logic in it's core web server, cause some engineer thought this was a brilliant plan. This load balancing logic gets statistics from /proc about the system, which trip over processes mmap_sem for various reasons. Now the web server application is in a protected cgroup, but these other processes may not be, and if they are being throttled while their mmap_sem is held we'll stall, and cause this nice death spiral. Instead rework filemap fault path to drop the mmap sem at any point that we may do IO or block for an extended period of time. This includes while issuing readahead, locking the page, or needing to call ->readpage because readahead did not occur. Then once we have a fully uptodate page we can return with VM_FAULT_RETRY and come back again to find our nicely in-cache page that was gotten outside of the mmap_sem. This patch also adds a new helper for locking the page with the mmap_sem dropped. This doesn't make sense currently as generally speaking if the page is already locked it'll have been read in (unless there was an error) before it was unlocked. However a forthcoming patchset will change this with the ability to abort read-ahead bio's if necessary, making it more likely that we could contend for a page lock and still have a not uptodate page. This allows us to deal with this case by grabbing the lock and issuing the IO without the mmap_sem held, and then returning VM_FAULT_RETRY to come back around. [josef@toxicpanda.com: v6] Link: http://lkml.kernel.org/r/20181212152757.10017-1-josef@toxicpanda.com [kirill@shutemov.name: fix race in filemap_fault()] Link: http://lkml.kernel.org/r/20181228235106.okk3oastsnpxusxs@kshutemo-mobl1 [akpm@linux-foundation.org: coding style fixes] Link: http://lkml.kernel.org/r/20181211173801.29535-4-josef@toxicpanda.com Signed-off-by: Josef Bacik <josef@toxicpanda.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Jan Kara <jack@suse.cz> Tested-by: syzbot+b437b5a429d680cf2217@syzkaller.appspotmail.com Cc: Dave Chinner <david@fromorbit.com> Cc: Rik van Riel <riel@redhat.com> Cc: Tejun Heo <tj@kernel.org> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-13 18:44:22 +00:00
struct file *fpin = NULL;
unsigned long vm_flags = vmf->vma->vm_flags;
mm/filemap.c: fix a data race in filemap_fault() struct file_ra_state ra.mmap_miss could be accessed concurrently during page faults as noticed by KCSAN, BUG: KCSAN: data-race in filemap_fault / filemap_map_pages write to 0xffff9b1700a2c1b4 of 4 bytes by task 3292 on cpu 30: filemap_fault+0x920/0xfc0 do_sync_mmap_readahead at mm/filemap.c:2384 (inlined by) filemap_fault at mm/filemap.c:2486 __xfs_filemap_fault+0x112/0x3e0 [xfs] xfs_filemap_fault+0x74/0x90 [xfs] __do_fault+0x9e/0x220 do_fault+0x4a0/0x920 __handle_mm_fault+0xc69/0xd00 handle_mm_fault+0xfc/0x2f0 do_page_fault+0x263/0x6f9 page_fault+0x34/0x40 read to 0xffff9b1700a2c1b4 of 4 bytes by task 3313 on cpu 32: filemap_map_pages+0xc2e/0xd80 filemap_map_pages at mm/filemap.c:2625 do_fault+0x3da/0x920 __handle_mm_fault+0xc69/0xd00 handle_mm_fault+0xfc/0x2f0 do_page_fault+0x263/0x6f9 page_fault+0x34/0x40 Reported by Kernel Concurrency Sanitizer on: CPU: 32 PID: 3313 Comm: systemd-udevd Tainted: G W L 5.5.0-next-20200210+ #1 Hardware name: HPE ProLiant DL385 Gen10/ProLiant DL385 Gen10, BIOS A40 07/10/2019 ra.mmap_miss is used to contribute the readahead decisions, a data race could be undesirable. Both the read and write is only under non-exclusive mmap_sem, two concurrent writers could even underflow the counter. Fix the underflow by writing to a local variable before committing a final store to ra.mmap_miss given a small inaccuracy of the counter should be acceptable. Signed-off-by: Kirill A. Shutemov <kirill@shutemov.name> Signed-off-by: Qian Cai <cai@lca.pw> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Tested-by: Qian Cai <cai@lca.pw> Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Marco Elver <elver@google.com> Link: http://lkml.kernel.org/r/20200211030134.1847-1-cai@lca.pw Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-08-15 00:31:27 +00:00
unsigned int mmap_miss;
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
/* Use the readahead code, even if readahead is disabled */
if (vm_flags & VM_HUGEPAGE) {
fpin = maybe_unlock_mmap_for_io(vmf, fpin);
ractl._index &= ~((unsigned long)HPAGE_PMD_NR - 1);
ra->size = HPAGE_PMD_NR;
/*
* Fetch two PMD folios, so we get the chance to actually
* readahead, unless we've been told not to.
*/
if (!(vm_flags & VM_RAND_READ))
ra->size *= 2;
ra->async_size = HPAGE_PMD_NR;
page_cache_ra_order(&ractl, ra, HPAGE_PMD_ORDER);
return fpin;
}
#endif
/* If we don't want any read-ahead, don't bother */
if (vm_flags & VM_RAND_READ)
filemap: drop the mmap_sem for all blocking operations Currently we only drop the mmap_sem if there is contention on the page lock. The idea is that we issue readahead and then go to lock the page while it is under IO and we want to not hold the mmap_sem during the IO. The problem with this is the assumption that the readahead does anything. In the case that the box is under extreme memory or IO pressure we may end up not reading anything at all for readahead, which means we will end up reading in the page under the mmap_sem. Even if the readahead does something, it could get throttled because of io pressure on the system and the process is in a lower priority cgroup. Holding the mmap_sem while doing IO is problematic because it can cause system-wide priority inversions. Consider some large company that does a lot of web traffic. This large company has load balancing logic in it's core web server, cause some engineer thought this was a brilliant plan. This load balancing logic gets statistics from /proc about the system, which trip over processes mmap_sem for various reasons. Now the web server application is in a protected cgroup, but these other processes may not be, and if they are being throttled while their mmap_sem is held we'll stall, and cause this nice death spiral. Instead rework filemap fault path to drop the mmap sem at any point that we may do IO or block for an extended period of time. This includes while issuing readahead, locking the page, or needing to call ->readpage because readahead did not occur. Then once we have a fully uptodate page we can return with VM_FAULT_RETRY and come back again to find our nicely in-cache page that was gotten outside of the mmap_sem. This patch also adds a new helper for locking the page with the mmap_sem dropped. This doesn't make sense currently as generally speaking if the page is already locked it'll have been read in (unless there was an error) before it was unlocked. However a forthcoming patchset will change this with the ability to abort read-ahead bio's if necessary, making it more likely that we could contend for a page lock and still have a not uptodate page. This allows us to deal with this case by grabbing the lock and issuing the IO without the mmap_sem held, and then returning VM_FAULT_RETRY to come back around. [josef@toxicpanda.com: v6] Link: http://lkml.kernel.org/r/20181212152757.10017-1-josef@toxicpanda.com [kirill@shutemov.name: fix race in filemap_fault()] Link: http://lkml.kernel.org/r/20181228235106.okk3oastsnpxusxs@kshutemo-mobl1 [akpm@linux-foundation.org: coding style fixes] Link: http://lkml.kernel.org/r/20181211173801.29535-4-josef@toxicpanda.com Signed-off-by: Josef Bacik <josef@toxicpanda.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Jan Kara <jack@suse.cz> Tested-by: syzbot+b437b5a429d680cf2217@syzkaller.appspotmail.com Cc: Dave Chinner <david@fromorbit.com> Cc: Rik van Riel <riel@redhat.com> Cc: Tejun Heo <tj@kernel.org> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-13 18:44:22 +00:00
return fpin;
if (!ra->ra_pages)
filemap: drop the mmap_sem for all blocking operations Currently we only drop the mmap_sem if there is contention on the page lock. The idea is that we issue readahead and then go to lock the page while it is under IO and we want to not hold the mmap_sem during the IO. The problem with this is the assumption that the readahead does anything. In the case that the box is under extreme memory or IO pressure we may end up not reading anything at all for readahead, which means we will end up reading in the page under the mmap_sem. Even if the readahead does something, it could get throttled because of io pressure on the system and the process is in a lower priority cgroup. Holding the mmap_sem while doing IO is problematic because it can cause system-wide priority inversions. Consider some large company that does a lot of web traffic. This large company has load balancing logic in it's core web server, cause some engineer thought this was a brilliant plan. This load balancing logic gets statistics from /proc about the system, which trip over processes mmap_sem for various reasons. Now the web server application is in a protected cgroup, but these other processes may not be, and if they are being throttled while their mmap_sem is held we'll stall, and cause this nice death spiral. Instead rework filemap fault path to drop the mmap sem at any point that we may do IO or block for an extended period of time. This includes while issuing readahead, locking the page, or needing to call ->readpage because readahead did not occur. Then once we have a fully uptodate page we can return with VM_FAULT_RETRY and come back again to find our nicely in-cache page that was gotten outside of the mmap_sem. This patch also adds a new helper for locking the page with the mmap_sem dropped. This doesn't make sense currently as generally speaking if the page is already locked it'll have been read in (unless there was an error) before it was unlocked. However a forthcoming patchset will change this with the ability to abort read-ahead bio's if necessary, making it more likely that we could contend for a page lock and still have a not uptodate page. This allows us to deal with this case by grabbing the lock and issuing the IO without the mmap_sem held, and then returning VM_FAULT_RETRY to come back around. [josef@toxicpanda.com: v6] Link: http://lkml.kernel.org/r/20181212152757.10017-1-josef@toxicpanda.com [kirill@shutemov.name: fix race in filemap_fault()] Link: http://lkml.kernel.org/r/20181228235106.okk3oastsnpxusxs@kshutemo-mobl1 [akpm@linux-foundation.org: coding style fixes] Link: http://lkml.kernel.org/r/20181211173801.29535-4-josef@toxicpanda.com Signed-off-by: Josef Bacik <josef@toxicpanda.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Jan Kara <jack@suse.cz> Tested-by: syzbot+b437b5a429d680cf2217@syzkaller.appspotmail.com Cc: Dave Chinner <david@fromorbit.com> Cc: Rik van Riel <riel@redhat.com> Cc: Tejun Heo <tj@kernel.org> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-13 18:44:22 +00:00
return fpin;
if (vm_flags & VM_SEQ_READ) {
filemap: drop the mmap_sem for all blocking operations Currently we only drop the mmap_sem if there is contention on the page lock. The idea is that we issue readahead and then go to lock the page while it is under IO and we want to not hold the mmap_sem during the IO. The problem with this is the assumption that the readahead does anything. In the case that the box is under extreme memory or IO pressure we may end up not reading anything at all for readahead, which means we will end up reading in the page under the mmap_sem. Even if the readahead does something, it could get throttled because of io pressure on the system and the process is in a lower priority cgroup. Holding the mmap_sem while doing IO is problematic because it can cause system-wide priority inversions. Consider some large company that does a lot of web traffic. This large company has load balancing logic in it's core web server, cause some engineer thought this was a brilliant plan. This load balancing logic gets statistics from /proc about the system, which trip over processes mmap_sem for various reasons. Now the web server application is in a protected cgroup, but these other processes may not be, and if they are being throttled while their mmap_sem is held we'll stall, and cause this nice death spiral. Instead rework filemap fault path to drop the mmap sem at any point that we may do IO or block for an extended period of time. This includes while issuing readahead, locking the page, or needing to call ->readpage because readahead did not occur. Then once we have a fully uptodate page we can return with VM_FAULT_RETRY and come back again to find our nicely in-cache page that was gotten outside of the mmap_sem. This patch also adds a new helper for locking the page with the mmap_sem dropped. This doesn't make sense currently as generally speaking if the page is already locked it'll have been read in (unless there was an error) before it was unlocked. However a forthcoming patchset will change this with the ability to abort read-ahead bio's if necessary, making it more likely that we could contend for a page lock and still have a not uptodate page. This allows us to deal with this case by grabbing the lock and issuing the IO without the mmap_sem held, and then returning VM_FAULT_RETRY to come back around. [josef@toxicpanda.com: v6] Link: http://lkml.kernel.org/r/20181212152757.10017-1-josef@toxicpanda.com [kirill@shutemov.name: fix race in filemap_fault()] Link: http://lkml.kernel.org/r/20181228235106.okk3oastsnpxusxs@kshutemo-mobl1 [akpm@linux-foundation.org: coding style fixes] Link: http://lkml.kernel.org/r/20181211173801.29535-4-josef@toxicpanda.com Signed-off-by: Josef Bacik <josef@toxicpanda.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Jan Kara <jack@suse.cz> Tested-by: syzbot+b437b5a429d680cf2217@syzkaller.appspotmail.com Cc: Dave Chinner <david@fromorbit.com> Cc: Rik van Riel <riel@redhat.com> Cc: Tejun Heo <tj@kernel.org> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-13 18:44:22 +00:00
fpin = maybe_unlock_mmap_for_io(vmf, fpin);
page_cache_sync_ra(&ractl, ra->ra_pages);
filemap: drop the mmap_sem for all blocking operations Currently we only drop the mmap_sem if there is contention on the page lock. The idea is that we issue readahead and then go to lock the page while it is under IO and we want to not hold the mmap_sem during the IO. The problem with this is the assumption that the readahead does anything. In the case that the box is under extreme memory or IO pressure we may end up not reading anything at all for readahead, which means we will end up reading in the page under the mmap_sem. Even if the readahead does something, it could get throttled because of io pressure on the system and the process is in a lower priority cgroup. Holding the mmap_sem while doing IO is problematic because it can cause system-wide priority inversions. Consider some large company that does a lot of web traffic. This large company has load balancing logic in it's core web server, cause some engineer thought this was a brilliant plan. This load balancing logic gets statistics from /proc about the system, which trip over processes mmap_sem for various reasons. Now the web server application is in a protected cgroup, but these other processes may not be, and if they are being throttled while their mmap_sem is held we'll stall, and cause this nice death spiral. Instead rework filemap fault path to drop the mmap sem at any point that we may do IO or block for an extended period of time. This includes while issuing readahead, locking the page, or needing to call ->readpage because readahead did not occur. Then once we have a fully uptodate page we can return with VM_FAULT_RETRY and come back again to find our nicely in-cache page that was gotten outside of the mmap_sem. This patch also adds a new helper for locking the page with the mmap_sem dropped. This doesn't make sense currently as generally speaking if the page is already locked it'll have been read in (unless there was an error) before it was unlocked. However a forthcoming patchset will change this with the ability to abort read-ahead bio's if necessary, making it more likely that we could contend for a page lock and still have a not uptodate page. This allows us to deal with this case by grabbing the lock and issuing the IO without the mmap_sem held, and then returning VM_FAULT_RETRY to come back around. [josef@toxicpanda.com: v6] Link: http://lkml.kernel.org/r/20181212152757.10017-1-josef@toxicpanda.com [kirill@shutemov.name: fix race in filemap_fault()] Link: http://lkml.kernel.org/r/20181228235106.okk3oastsnpxusxs@kshutemo-mobl1 [akpm@linux-foundation.org: coding style fixes] Link: http://lkml.kernel.org/r/20181211173801.29535-4-josef@toxicpanda.com Signed-off-by: Josef Bacik <josef@toxicpanda.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Jan Kara <jack@suse.cz> Tested-by: syzbot+b437b5a429d680cf2217@syzkaller.appspotmail.com Cc: Dave Chinner <david@fromorbit.com> Cc: Rik van Riel <riel@redhat.com> Cc: Tejun Heo <tj@kernel.org> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-13 18:44:22 +00:00
return fpin;
}
/* Avoid banging the cache line if not needed */
mm/filemap.c: fix a data race in filemap_fault() struct file_ra_state ra.mmap_miss could be accessed concurrently during page faults as noticed by KCSAN, BUG: KCSAN: data-race in filemap_fault / filemap_map_pages write to 0xffff9b1700a2c1b4 of 4 bytes by task 3292 on cpu 30: filemap_fault+0x920/0xfc0 do_sync_mmap_readahead at mm/filemap.c:2384 (inlined by) filemap_fault at mm/filemap.c:2486 __xfs_filemap_fault+0x112/0x3e0 [xfs] xfs_filemap_fault+0x74/0x90 [xfs] __do_fault+0x9e/0x220 do_fault+0x4a0/0x920 __handle_mm_fault+0xc69/0xd00 handle_mm_fault+0xfc/0x2f0 do_page_fault+0x263/0x6f9 page_fault+0x34/0x40 read to 0xffff9b1700a2c1b4 of 4 bytes by task 3313 on cpu 32: filemap_map_pages+0xc2e/0xd80 filemap_map_pages at mm/filemap.c:2625 do_fault+0x3da/0x920 __handle_mm_fault+0xc69/0xd00 handle_mm_fault+0xfc/0x2f0 do_page_fault+0x263/0x6f9 page_fault+0x34/0x40 Reported by Kernel Concurrency Sanitizer on: CPU: 32 PID: 3313 Comm: systemd-udevd Tainted: G W L 5.5.0-next-20200210+ #1 Hardware name: HPE ProLiant DL385 Gen10/ProLiant DL385 Gen10, BIOS A40 07/10/2019 ra.mmap_miss is used to contribute the readahead decisions, a data race could be undesirable. Both the read and write is only under non-exclusive mmap_sem, two concurrent writers could even underflow the counter. Fix the underflow by writing to a local variable before committing a final store to ra.mmap_miss given a small inaccuracy of the counter should be acceptable. Signed-off-by: Kirill A. Shutemov <kirill@shutemov.name> Signed-off-by: Qian Cai <cai@lca.pw> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Tested-by: Qian Cai <cai@lca.pw> Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Marco Elver <elver@google.com> Link: http://lkml.kernel.org/r/20200211030134.1847-1-cai@lca.pw Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-08-15 00:31:27 +00:00
mmap_miss = READ_ONCE(ra->mmap_miss);
if (mmap_miss < MMAP_LOTSAMISS * 10)
WRITE_ONCE(ra->mmap_miss, ++mmap_miss);
/*
* Do we miss much more than hit in this file? If so,
* stop bothering with read-ahead. It will only hurt.
*/
mm/filemap.c: fix a data race in filemap_fault() struct file_ra_state ra.mmap_miss could be accessed concurrently during page faults as noticed by KCSAN, BUG: KCSAN: data-race in filemap_fault / filemap_map_pages write to 0xffff9b1700a2c1b4 of 4 bytes by task 3292 on cpu 30: filemap_fault+0x920/0xfc0 do_sync_mmap_readahead at mm/filemap.c:2384 (inlined by) filemap_fault at mm/filemap.c:2486 __xfs_filemap_fault+0x112/0x3e0 [xfs] xfs_filemap_fault+0x74/0x90 [xfs] __do_fault+0x9e/0x220 do_fault+0x4a0/0x920 __handle_mm_fault+0xc69/0xd00 handle_mm_fault+0xfc/0x2f0 do_page_fault+0x263/0x6f9 page_fault+0x34/0x40 read to 0xffff9b1700a2c1b4 of 4 bytes by task 3313 on cpu 32: filemap_map_pages+0xc2e/0xd80 filemap_map_pages at mm/filemap.c:2625 do_fault+0x3da/0x920 __handle_mm_fault+0xc69/0xd00 handle_mm_fault+0xfc/0x2f0 do_page_fault+0x263/0x6f9 page_fault+0x34/0x40 Reported by Kernel Concurrency Sanitizer on: CPU: 32 PID: 3313 Comm: systemd-udevd Tainted: G W L 5.5.0-next-20200210+ #1 Hardware name: HPE ProLiant DL385 Gen10/ProLiant DL385 Gen10, BIOS A40 07/10/2019 ra.mmap_miss is used to contribute the readahead decisions, a data race could be undesirable. Both the read and write is only under non-exclusive mmap_sem, two concurrent writers could even underflow the counter. Fix the underflow by writing to a local variable before committing a final store to ra.mmap_miss given a small inaccuracy of the counter should be acceptable. Signed-off-by: Kirill A. Shutemov <kirill@shutemov.name> Signed-off-by: Qian Cai <cai@lca.pw> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Tested-by: Qian Cai <cai@lca.pw> Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Marco Elver <elver@google.com> Link: http://lkml.kernel.org/r/20200211030134.1847-1-cai@lca.pw Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-08-15 00:31:27 +00:00
if (mmap_miss > MMAP_LOTSAMISS)
filemap: drop the mmap_sem for all blocking operations Currently we only drop the mmap_sem if there is contention on the page lock. The idea is that we issue readahead and then go to lock the page while it is under IO and we want to not hold the mmap_sem during the IO. The problem with this is the assumption that the readahead does anything. In the case that the box is under extreme memory or IO pressure we may end up not reading anything at all for readahead, which means we will end up reading in the page under the mmap_sem. Even if the readahead does something, it could get throttled because of io pressure on the system and the process is in a lower priority cgroup. Holding the mmap_sem while doing IO is problematic because it can cause system-wide priority inversions. Consider some large company that does a lot of web traffic. This large company has load balancing logic in it's core web server, cause some engineer thought this was a brilliant plan. This load balancing logic gets statistics from /proc about the system, which trip over processes mmap_sem for various reasons. Now the web server application is in a protected cgroup, but these other processes may not be, and if they are being throttled while their mmap_sem is held we'll stall, and cause this nice death spiral. Instead rework filemap fault path to drop the mmap sem at any point that we may do IO or block for an extended period of time. This includes while issuing readahead, locking the page, or needing to call ->readpage because readahead did not occur. Then once we have a fully uptodate page we can return with VM_FAULT_RETRY and come back again to find our nicely in-cache page that was gotten outside of the mmap_sem. This patch also adds a new helper for locking the page with the mmap_sem dropped. This doesn't make sense currently as generally speaking if the page is already locked it'll have been read in (unless there was an error) before it was unlocked. However a forthcoming patchset will change this with the ability to abort read-ahead bio's if necessary, making it more likely that we could contend for a page lock and still have a not uptodate page. This allows us to deal with this case by grabbing the lock and issuing the IO without the mmap_sem held, and then returning VM_FAULT_RETRY to come back around. [josef@toxicpanda.com: v6] Link: http://lkml.kernel.org/r/20181212152757.10017-1-josef@toxicpanda.com [kirill@shutemov.name: fix race in filemap_fault()] Link: http://lkml.kernel.org/r/20181228235106.okk3oastsnpxusxs@kshutemo-mobl1 [akpm@linux-foundation.org: coding style fixes] Link: http://lkml.kernel.org/r/20181211173801.29535-4-josef@toxicpanda.com Signed-off-by: Josef Bacik <josef@toxicpanda.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Jan Kara <jack@suse.cz> Tested-by: syzbot+b437b5a429d680cf2217@syzkaller.appspotmail.com Cc: Dave Chinner <david@fromorbit.com> Cc: Rik van Riel <riel@redhat.com> Cc: Tejun Heo <tj@kernel.org> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-13 18:44:22 +00:00
return fpin;
/*
* mmap read-around
*/
filemap: drop the mmap_sem for all blocking operations Currently we only drop the mmap_sem if there is contention on the page lock. The idea is that we issue readahead and then go to lock the page while it is under IO and we want to not hold the mmap_sem during the IO. The problem with this is the assumption that the readahead does anything. In the case that the box is under extreme memory or IO pressure we may end up not reading anything at all for readahead, which means we will end up reading in the page under the mmap_sem. Even if the readahead does something, it could get throttled because of io pressure on the system and the process is in a lower priority cgroup. Holding the mmap_sem while doing IO is problematic because it can cause system-wide priority inversions. Consider some large company that does a lot of web traffic. This large company has load balancing logic in it's core web server, cause some engineer thought this was a brilliant plan. This load balancing logic gets statistics from /proc about the system, which trip over processes mmap_sem for various reasons. Now the web server application is in a protected cgroup, but these other processes may not be, and if they are being throttled while their mmap_sem is held we'll stall, and cause this nice death spiral. Instead rework filemap fault path to drop the mmap sem at any point that we may do IO or block for an extended period of time. This includes while issuing readahead, locking the page, or needing to call ->readpage because readahead did not occur. Then once we have a fully uptodate page we can return with VM_FAULT_RETRY and come back again to find our nicely in-cache page that was gotten outside of the mmap_sem. This patch also adds a new helper for locking the page with the mmap_sem dropped. This doesn't make sense currently as generally speaking if the page is already locked it'll have been read in (unless there was an error) before it was unlocked. However a forthcoming patchset will change this with the ability to abort read-ahead bio's if necessary, making it more likely that we could contend for a page lock and still have a not uptodate page. This allows us to deal with this case by grabbing the lock and issuing the IO without the mmap_sem held, and then returning VM_FAULT_RETRY to come back around. [josef@toxicpanda.com: v6] Link: http://lkml.kernel.org/r/20181212152757.10017-1-josef@toxicpanda.com [kirill@shutemov.name: fix race in filemap_fault()] Link: http://lkml.kernel.org/r/20181228235106.okk3oastsnpxusxs@kshutemo-mobl1 [akpm@linux-foundation.org: coding style fixes] Link: http://lkml.kernel.org/r/20181211173801.29535-4-josef@toxicpanda.com Signed-off-by: Josef Bacik <josef@toxicpanda.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Jan Kara <jack@suse.cz> Tested-by: syzbot+b437b5a429d680cf2217@syzkaller.appspotmail.com Cc: Dave Chinner <david@fromorbit.com> Cc: Rik van Riel <riel@redhat.com> Cc: Tejun Heo <tj@kernel.org> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-13 18:44:22 +00:00
fpin = maybe_unlock_mmap_for_io(vmf, fpin);
ra->start = max_t(long, 0, vmf->pgoff - ra->ra_pages / 2);
mm: use only per-device readahead limit Maximal readahead size is limited now by two values: 1) by global 2Mb constant (MAX_READAHEAD in max_sane_readahead()) 2) by configurable per-device value* (bdi->ra_pages) There are devices, which require custom readahead limit. For instance, for RAIDs it's calculated as number of devices multiplied by chunk size times 2. Readahead size can never be larger than bdi->ra_pages * 2 value (POSIX_FADV_SEQUNTIAL doubles readahead size). If so, why do we need two limits? I suggest to completely remove this max_sane_readahead() stuff and use per-device readahead limit everywhere. Also, using right readahead size for RAID disks can significantly increase i/o performance: before: dd if=/dev/md2 of=/dev/null bs=100M count=100 100+0 records in 100+0 records out 10485760000 bytes (10 GB) copied, 12.9741 s, 808 MB/s after: $ dd if=/dev/md2 of=/dev/null bs=100M count=100 100+0 records in 100+0 records out 10485760000 bytes (10 GB) copied, 8.91317 s, 1.2 GB/s (It's an 8-disks RAID5 storage). This patch doesn't change sys_readahead and madvise(MADV_WILLNEED) behavior introduced by 6d2be915e589b58 ("mm/readahead.c: fix readahead failure for memoryless NUMA nodes and limit readahead pages"). Signed-off-by: Roman Gushchin <klamm@yandex-team.ru> Cc: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com> Cc: Jan Kara <jack@suse.cz> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: David Rientjes <rientjes@google.com> Cc: onstantin Khlebnikov <khlebnikov@yandex-team.ru> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-11-06 02:47:08 +00:00
ra->size = ra->ra_pages;
ra->async_size = ra->ra_pages / 4;
ractl._index = ra->start;
page_cache_ra_order(&ractl, ra, 0);
filemap: drop the mmap_sem for all blocking operations Currently we only drop the mmap_sem if there is contention on the page lock. The idea is that we issue readahead and then go to lock the page while it is under IO and we want to not hold the mmap_sem during the IO. The problem with this is the assumption that the readahead does anything. In the case that the box is under extreme memory or IO pressure we may end up not reading anything at all for readahead, which means we will end up reading in the page under the mmap_sem. Even if the readahead does something, it could get throttled because of io pressure on the system and the process is in a lower priority cgroup. Holding the mmap_sem while doing IO is problematic because it can cause system-wide priority inversions. Consider some large company that does a lot of web traffic. This large company has load balancing logic in it's core web server, cause some engineer thought this was a brilliant plan. This load balancing logic gets statistics from /proc about the system, which trip over processes mmap_sem for various reasons. Now the web server application is in a protected cgroup, but these other processes may not be, and if they are being throttled while their mmap_sem is held we'll stall, and cause this nice death spiral. Instead rework filemap fault path to drop the mmap sem at any point that we may do IO or block for an extended period of time. This includes while issuing readahead, locking the page, or needing to call ->readpage because readahead did not occur. Then once we have a fully uptodate page we can return with VM_FAULT_RETRY and come back again to find our nicely in-cache page that was gotten outside of the mmap_sem. This patch also adds a new helper for locking the page with the mmap_sem dropped. This doesn't make sense currently as generally speaking if the page is already locked it'll have been read in (unless there was an error) before it was unlocked. However a forthcoming patchset will change this with the ability to abort read-ahead bio's if necessary, making it more likely that we could contend for a page lock and still have a not uptodate page. This allows us to deal with this case by grabbing the lock and issuing the IO without the mmap_sem held, and then returning VM_FAULT_RETRY to come back around. [josef@toxicpanda.com: v6] Link: http://lkml.kernel.org/r/20181212152757.10017-1-josef@toxicpanda.com [kirill@shutemov.name: fix race in filemap_fault()] Link: http://lkml.kernel.org/r/20181228235106.okk3oastsnpxusxs@kshutemo-mobl1 [akpm@linux-foundation.org: coding style fixes] Link: http://lkml.kernel.org/r/20181211173801.29535-4-josef@toxicpanda.com Signed-off-by: Josef Bacik <josef@toxicpanda.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Jan Kara <jack@suse.cz> Tested-by: syzbot+b437b5a429d680cf2217@syzkaller.appspotmail.com Cc: Dave Chinner <david@fromorbit.com> Cc: Rik van Riel <riel@redhat.com> Cc: Tejun Heo <tj@kernel.org> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-13 18:44:22 +00:00
return fpin;
}
/*
* Asynchronous readahead happens when we find the page and PG_readahead,
filemap: drop the mmap_sem for all blocking operations Currently we only drop the mmap_sem if there is contention on the page lock. The idea is that we issue readahead and then go to lock the page while it is under IO and we want to not hold the mmap_sem during the IO. The problem with this is the assumption that the readahead does anything. In the case that the box is under extreme memory or IO pressure we may end up not reading anything at all for readahead, which means we will end up reading in the page under the mmap_sem. Even if the readahead does something, it could get throttled because of io pressure on the system and the process is in a lower priority cgroup. Holding the mmap_sem while doing IO is problematic because it can cause system-wide priority inversions. Consider some large company that does a lot of web traffic. This large company has load balancing logic in it's core web server, cause some engineer thought this was a brilliant plan. This load balancing logic gets statistics from /proc about the system, which trip over processes mmap_sem for various reasons. Now the web server application is in a protected cgroup, but these other processes may not be, and if they are being throttled while their mmap_sem is held we'll stall, and cause this nice death spiral. Instead rework filemap fault path to drop the mmap sem at any point that we may do IO or block for an extended period of time. This includes while issuing readahead, locking the page, or needing to call ->readpage because readahead did not occur. Then once we have a fully uptodate page we can return with VM_FAULT_RETRY and come back again to find our nicely in-cache page that was gotten outside of the mmap_sem. This patch also adds a new helper for locking the page with the mmap_sem dropped. This doesn't make sense currently as generally speaking if the page is already locked it'll have been read in (unless there was an error) before it was unlocked. However a forthcoming patchset will change this with the ability to abort read-ahead bio's if necessary, making it more likely that we could contend for a page lock and still have a not uptodate page. This allows us to deal with this case by grabbing the lock and issuing the IO without the mmap_sem held, and then returning VM_FAULT_RETRY to come back around. [josef@toxicpanda.com: v6] Link: http://lkml.kernel.org/r/20181212152757.10017-1-josef@toxicpanda.com [kirill@shutemov.name: fix race in filemap_fault()] Link: http://lkml.kernel.org/r/20181228235106.okk3oastsnpxusxs@kshutemo-mobl1 [akpm@linux-foundation.org: coding style fixes] Link: http://lkml.kernel.org/r/20181211173801.29535-4-josef@toxicpanda.com Signed-off-by: Josef Bacik <josef@toxicpanda.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Jan Kara <jack@suse.cz> Tested-by: syzbot+b437b5a429d680cf2217@syzkaller.appspotmail.com Cc: Dave Chinner <david@fromorbit.com> Cc: Rik van Riel <riel@redhat.com> Cc: Tejun Heo <tj@kernel.org> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-13 18:44:22 +00:00
* so we want to possibly extend the readahead further. We return the file that
* was pinned if we have to drop the mmap_lock in order to do IO.
*/
filemap: drop the mmap_sem for all blocking operations Currently we only drop the mmap_sem if there is contention on the page lock. The idea is that we issue readahead and then go to lock the page while it is under IO and we want to not hold the mmap_sem during the IO. The problem with this is the assumption that the readahead does anything. In the case that the box is under extreme memory or IO pressure we may end up not reading anything at all for readahead, which means we will end up reading in the page under the mmap_sem. Even if the readahead does something, it could get throttled because of io pressure on the system and the process is in a lower priority cgroup. Holding the mmap_sem while doing IO is problematic because it can cause system-wide priority inversions. Consider some large company that does a lot of web traffic. This large company has load balancing logic in it's core web server, cause some engineer thought this was a brilliant plan. This load balancing logic gets statistics from /proc about the system, which trip over processes mmap_sem for various reasons. Now the web server application is in a protected cgroup, but these other processes may not be, and if they are being throttled while their mmap_sem is held we'll stall, and cause this nice death spiral. Instead rework filemap fault path to drop the mmap sem at any point that we may do IO or block for an extended period of time. This includes while issuing readahead, locking the page, or needing to call ->readpage because readahead did not occur. Then once we have a fully uptodate page we can return with VM_FAULT_RETRY and come back again to find our nicely in-cache page that was gotten outside of the mmap_sem. This patch also adds a new helper for locking the page with the mmap_sem dropped. This doesn't make sense currently as generally speaking if the page is already locked it'll have been read in (unless there was an error) before it was unlocked. However a forthcoming patchset will change this with the ability to abort read-ahead bio's if necessary, making it more likely that we could contend for a page lock and still have a not uptodate page. This allows us to deal with this case by grabbing the lock and issuing the IO without the mmap_sem held, and then returning VM_FAULT_RETRY to come back around. [josef@toxicpanda.com: v6] Link: http://lkml.kernel.org/r/20181212152757.10017-1-josef@toxicpanda.com [kirill@shutemov.name: fix race in filemap_fault()] Link: http://lkml.kernel.org/r/20181228235106.okk3oastsnpxusxs@kshutemo-mobl1 [akpm@linux-foundation.org: coding style fixes] Link: http://lkml.kernel.org/r/20181211173801.29535-4-josef@toxicpanda.com Signed-off-by: Josef Bacik <josef@toxicpanda.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Jan Kara <jack@suse.cz> Tested-by: syzbot+b437b5a429d680cf2217@syzkaller.appspotmail.com Cc: Dave Chinner <david@fromorbit.com> Cc: Rik van Riel <riel@redhat.com> Cc: Tejun Heo <tj@kernel.org> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-13 18:44:22 +00:00
static struct file *do_async_mmap_readahead(struct vm_fault *vmf,
struct folio *folio)
{
struct file *file = vmf->vma->vm_file;
struct file_ra_state *ra = &file->f_ra;
DEFINE_READAHEAD(ractl, file, ra, file->f_mapping, vmf->pgoff);
filemap: drop the mmap_sem for all blocking operations Currently we only drop the mmap_sem if there is contention on the page lock. The idea is that we issue readahead and then go to lock the page while it is under IO and we want to not hold the mmap_sem during the IO. The problem with this is the assumption that the readahead does anything. In the case that the box is under extreme memory or IO pressure we may end up not reading anything at all for readahead, which means we will end up reading in the page under the mmap_sem. Even if the readahead does something, it could get throttled because of io pressure on the system and the process is in a lower priority cgroup. Holding the mmap_sem while doing IO is problematic because it can cause system-wide priority inversions. Consider some large company that does a lot of web traffic. This large company has load balancing logic in it's core web server, cause some engineer thought this was a brilliant plan. This load balancing logic gets statistics from /proc about the system, which trip over processes mmap_sem for various reasons. Now the web server application is in a protected cgroup, but these other processes may not be, and if they are being throttled while their mmap_sem is held we'll stall, and cause this nice death spiral. Instead rework filemap fault path to drop the mmap sem at any point that we may do IO or block for an extended period of time. This includes while issuing readahead, locking the page, or needing to call ->readpage because readahead did not occur. Then once we have a fully uptodate page we can return with VM_FAULT_RETRY and come back again to find our nicely in-cache page that was gotten outside of the mmap_sem. This patch also adds a new helper for locking the page with the mmap_sem dropped. This doesn't make sense currently as generally speaking if the page is already locked it'll have been read in (unless there was an error) before it was unlocked. However a forthcoming patchset will change this with the ability to abort read-ahead bio's if necessary, making it more likely that we could contend for a page lock and still have a not uptodate page. This allows us to deal with this case by grabbing the lock and issuing the IO without the mmap_sem held, and then returning VM_FAULT_RETRY to come back around. [josef@toxicpanda.com: v6] Link: http://lkml.kernel.org/r/20181212152757.10017-1-josef@toxicpanda.com [kirill@shutemov.name: fix race in filemap_fault()] Link: http://lkml.kernel.org/r/20181228235106.okk3oastsnpxusxs@kshutemo-mobl1 [akpm@linux-foundation.org: coding style fixes] Link: http://lkml.kernel.org/r/20181211173801.29535-4-josef@toxicpanda.com Signed-off-by: Josef Bacik <josef@toxicpanda.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Jan Kara <jack@suse.cz> Tested-by: syzbot+b437b5a429d680cf2217@syzkaller.appspotmail.com Cc: Dave Chinner <david@fromorbit.com> Cc: Rik van Riel <riel@redhat.com> Cc: Tejun Heo <tj@kernel.org> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-13 18:44:22 +00:00
struct file *fpin = NULL;
mm/filemap.c: fix a data race in filemap_fault() struct file_ra_state ra.mmap_miss could be accessed concurrently during page faults as noticed by KCSAN, BUG: KCSAN: data-race in filemap_fault / filemap_map_pages write to 0xffff9b1700a2c1b4 of 4 bytes by task 3292 on cpu 30: filemap_fault+0x920/0xfc0 do_sync_mmap_readahead at mm/filemap.c:2384 (inlined by) filemap_fault at mm/filemap.c:2486 __xfs_filemap_fault+0x112/0x3e0 [xfs] xfs_filemap_fault+0x74/0x90 [xfs] __do_fault+0x9e/0x220 do_fault+0x4a0/0x920 __handle_mm_fault+0xc69/0xd00 handle_mm_fault+0xfc/0x2f0 do_page_fault+0x263/0x6f9 page_fault+0x34/0x40 read to 0xffff9b1700a2c1b4 of 4 bytes by task 3313 on cpu 32: filemap_map_pages+0xc2e/0xd80 filemap_map_pages at mm/filemap.c:2625 do_fault+0x3da/0x920 __handle_mm_fault+0xc69/0xd00 handle_mm_fault+0xfc/0x2f0 do_page_fault+0x263/0x6f9 page_fault+0x34/0x40 Reported by Kernel Concurrency Sanitizer on: CPU: 32 PID: 3313 Comm: systemd-udevd Tainted: G W L 5.5.0-next-20200210+ #1 Hardware name: HPE ProLiant DL385 Gen10/ProLiant DL385 Gen10, BIOS A40 07/10/2019 ra.mmap_miss is used to contribute the readahead decisions, a data race could be undesirable. Both the read and write is only under non-exclusive mmap_sem, two concurrent writers could even underflow the counter. Fix the underflow by writing to a local variable before committing a final store to ra.mmap_miss given a small inaccuracy of the counter should be acceptable. Signed-off-by: Kirill A. Shutemov <kirill@shutemov.name> Signed-off-by: Qian Cai <cai@lca.pw> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Tested-by: Qian Cai <cai@lca.pw> Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Marco Elver <elver@google.com> Link: http://lkml.kernel.org/r/20200211030134.1847-1-cai@lca.pw Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-08-15 00:31:27 +00:00
unsigned int mmap_miss;
/* If we don't want any read-ahead, don't bother */
if (vmf->vma->vm_flags & VM_RAND_READ || !ra->ra_pages)
filemap: drop the mmap_sem for all blocking operations Currently we only drop the mmap_sem if there is contention on the page lock. The idea is that we issue readahead and then go to lock the page while it is under IO and we want to not hold the mmap_sem during the IO. The problem with this is the assumption that the readahead does anything. In the case that the box is under extreme memory or IO pressure we may end up not reading anything at all for readahead, which means we will end up reading in the page under the mmap_sem. Even if the readahead does something, it could get throttled because of io pressure on the system and the process is in a lower priority cgroup. Holding the mmap_sem while doing IO is problematic because it can cause system-wide priority inversions. Consider some large company that does a lot of web traffic. This large company has load balancing logic in it's core web server, cause some engineer thought this was a brilliant plan. This load balancing logic gets statistics from /proc about the system, which trip over processes mmap_sem for various reasons. Now the web server application is in a protected cgroup, but these other processes may not be, and if they are being throttled while their mmap_sem is held we'll stall, and cause this nice death spiral. Instead rework filemap fault path to drop the mmap sem at any point that we may do IO or block for an extended period of time. This includes while issuing readahead, locking the page, or needing to call ->readpage because readahead did not occur. Then once we have a fully uptodate page we can return with VM_FAULT_RETRY and come back again to find our nicely in-cache page that was gotten outside of the mmap_sem. This patch also adds a new helper for locking the page with the mmap_sem dropped. This doesn't make sense currently as generally speaking if the page is already locked it'll have been read in (unless there was an error) before it was unlocked. However a forthcoming patchset will change this with the ability to abort read-ahead bio's if necessary, making it more likely that we could contend for a page lock and still have a not uptodate page. This allows us to deal with this case by grabbing the lock and issuing the IO without the mmap_sem held, and then returning VM_FAULT_RETRY to come back around. [josef@toxicpanda.com: v6] Link: http://lkml.kernel.org/r/20181212152757.10017-1-josef@toxicpanda.com [kirill@shutemov.name: fix race in filemap_fault()] Link: http://lkml.kernel.org/r/20181228235106.okk3oastsnpxusxs@kshutemo-mobl1 [akpm@linux-foundation.org: coding style fixes] Link: http://lkml.kernel.org/r/20181211173801.29535-4-josef@toxicpanda.com Signed-off-by: Josef Bacik <josef@toxicpanda.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Jan Kara <jack@suse.cz> Tested-by: syzbot+b437b5a429d680cf2217@syzkaller.appspotmail.com Cc: Dave Chinner <david@fromorbit.com> Cc: Rik van Riel <riel@redhat.com> Cc: Tejun Heo <tj@kernel.org> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-13 18:44:22 +00:00
return fpin;
mm/filemap.c: fix a data race in filemap_fault() struct file_ra_state ra.mmap_miss could be accessed concurrently during page faults as noticed by KCSAN, BUG: KCSAN: data-race in filemap_fault / filemap_map_pages write to 0xffff9b1700a2c1b4 of 4 bytes by task 3292 on cpu 30: filemap_fault+0x920/0xfc0 do_sync_mmap_readahead at mm/filemap.c:2384 (inlined by) filemap_fault at mm/filemap.c:2486 __xfs_filemap_fault+0x112/0x3e0 [xfs] xfs_filemap_fault+0x74/0x90 [xfs] __do_fault+0x9e/0x220 do_fault+0x4a0/0x920 __handle_mm_fault+0xc69/0xd00 handle_mm_fault+0xfc/0x2f0 do_page_fault+0x263/0x6f9 page_fault+0x34/0x40 read to 0xffff9b1700a2c1b4 of 4 bytes by task 3313 on cpu 32: filemap_map_pages+0xc2e/0xd80 filemap_map_pages at mm/filemap.c:2625 do_fault+0x3da/0x920 __handle_mm_fault+0xc69/0xd00 handle_mm_fault+0xfc/0x2f0 do_page_fault+0x263/0x6f9 page_fault+0x34/0x40 Reported by Kernel Concurrency Sanitizer on: CPU: 32 PID: 3313 Comm: systemd-udevd Tainted: G W L 5.5.0-next-20200210+ #1 Hardware name: HPE ProLiant DL385 Gen10/ProLiant DL385 Gen10, BIOS A40 07/10/2019 ra.mmap_miss is used to contribute the readahead decisions, a data race could be undesirable. Both the read and write is only under non-exclusive mmap_sem, two concurrent writers could even underflow the counter. Fix the underflow by writing to a local variable before committing a final store to ra.mmap_miss given a small inaccuracy of the counter should be acceptable. Signed-off-by: Kirill A. Shutemov <kirill@shutemov.name> Signed-off-by: Qian Cai <cai@lca.pw> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Tested-by: Qian Cai <cai@lca.pw> Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Marco Elver <elver@google.com> Link: http://lkml.kernel.org/r/20200211030134.1847-1-cai@lca.pw Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-08-15 00:31:27 +00:00
mmap_miss = READ_ONCE(ra->mmap_miss);
if (mmap_miss)
WRITE_ONCE(ra->mmap_miss, --mmap_miss);
if (folio_test_readahead(folio)) {
filemap: drop the mmap_sem for all blocking operations Currently we only drop the mmap_sem if there is contention on the page lock. The idea is that we issue readahead and then go to lock the page while it is under IO and we want to not hold the mmap_sem during the IO. The problem with this is the assumption that the readahead does anything. In the case that the box is under extreme memory or IO pressure we may end up not reading anything at all for readahead, which means we will end up reading in the page under the mmap_sem. Even if the readahead does something, it could get throttled because of io pressure on the system and the process is in a lower priority cgroup. Holding the mmap_sem while doing IO is problematic because it can cause system-wide priority inversions. Consider some large company that does a lot of web traffic. This large company has load balancing logic in it's core web server, cause some engineer thought this was a brilliant plan. This load balancing logic gets statistics from /proc about the system, which trip over processes mmap_sem for various reasons. Now the web server application is in a protected cgroup, but these other processes may not be, and if they are being throttled while their mmap_sem is held we'll stall, and cause this nice death spiral. Instead rework filemap fault path to drop the mmap sem at any point that we may do IO or block for an extended period of time. This includes while issuing readahead, locking the page, or needing to call ->readpage because readahead did not occur. Then once we have a fully uptodate page we can return with VM_FAULT_RETRY and come back again to find our nicely in-cache page that was gotten outside of the mmap_sem. This patch also adds a new helper for locking the page with the mmap_sem dropped. This doesn't make sense currently as generally speaking if the page is already locked it'll have been read in (unless there was an error) before it was unlocked. However a forthcoming patchset will change this with the ability to abort read-ahead bio's if necessary, making it more likely that we could contend for a page lock and still have a not uptodate page. This allows us to deal with this case by grabbing the lock and issuing the IO without the mmap_sem held, and then returning VM_FAULT_RETRY to come back around. [josef@toxicpanda.com: v6] Link: http://lkml.kernel.org/r/20181212152757.10017-1-josef@toxicpanda.com [kirill@shutemov.name: fix race in filemap_fault()] Link: http://lkml.kernel.org/r/20181228235106.okk3oastsnpxusxs@kshutemo-mobl1 [akpm@linux-foundation.org: coding style fixes] Link: http://lkml.kernel.org/r/20181211173801.29535-4-josef@toxicpanda.com Signed-off-by: Josef Bacik <josef@toxicpanda.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Jan Kara <jack@suse.cz> Tested-by: syzbot+b437b5a429d680cf2217@syzkaller.appspotmail.com Cc: Dave Chinner <david@fromorbit.com> Cc: Rik van Riel <riel@redhat.com> Cc: Tejun Heo <tj@kernel.org> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-13 18:44:22 +00:00
fpin = maybe_unlock_mmap_for_io(vmf, fpin);
page_cache_async_ra(&ractl, folio, ra->ra_pages);
filemap: drop the mmap_sem for all blocking operations Currently we only drop the mmap_sem if there is contention on the page lock. The idea is that we issue readahead and then go to lock the page while it is under IO and we want to not hold the mmap_sem during the IO. The problem with this is the assumption that the readahead does anything. In the case that the box is under extreme memory or IO pressure we may end up not reading anything at all for readahead, which means we will end up reading in the page under the mmap_sem. Even if the readahead does something, it could get throttled because of io pressure on the system and the process is in a lower priority cgroup. Holding the mmap_sem while doing IO is problematic because it can cause system-wide priority inversions. Consider some large company that does a lot of web traffic. This large company has load balancing logic in it's core web server, cause some engineer thought this was a brilliant plan. This load balancing logic gets statistics from /proc about the system, which trip over processes mmap_sem for various reasons. Now the web server application is in a protected cgroup, but these other processes may not be, and if they are being throttled while their mmap_sem is held we'll stall, and cause this nice death spiral. Instead rework filemap fault path to drop the mmap sem at any point that we may do IO or block for an extended period of time. This includes while issuing readahead, locking the page, or needing to call ->readpage because readahead did not occur. Then once we have a fully uptodate page we can return with VM_FAULT_RETRY and come back again to find our nicely in-cache page that was gotten outside of the mmap_sem. This patch also adds a new helper for locking the page with the mmap_sem dropped. This doesn't make sense currently as generally speaking if the page is already locked it'll have been read in (unless there was an error) before it was unlocked. However a forthcoming patchset will change this with the ability to abort read-ahead bio's if necessary, making it more likely that we could contend for a page lock and still have a not uptodate page. This allows us to deal with this case by grabbing the lock and issuing the IO without the mmap_sem held, and then returning VM_FAULT_RETRY to come back around. [josef@toxicpanda.com: v6] Link: http://lkml.kernel.org/r/20181212152757.10017-1-josef@toxicpanda.com [kirill@shutemov.name: fix race in filemap_fault()] Link: http://lkml.kernel.org/r/20181228235106.okk3oastsnpxusxs@kshutemo-mobl1 [akpm@linux-foundation.org: coding style fixes] Link: http://lkml.kernel.org/r/20181211173801.29535-4-josef@toxicpanda.com Signed-off-by: Josef Bacik <josef@toxicpanda.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Jan Kara <jack@suse.cz> Tested-by: syzbot+b437b5a429d680cf2217@syzkaller.appspotmail.com Cc: Dave Chinner <david@fromorbit.com> Cc: Rik van Riel <riel@redhat.com> Cc: Tejun Heo <tj@kernel.org> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-13 18:44:22 +00:00
}
return fpin;
}
filemap: avoid unnecessary major faults in filemap_fault() A major fault occurred when using mlockall(MCL_CURRENT | MCL_FUTURE) in application, which leading to an unexpected issue[1]. This is caused by temporarily cleared PTE during a read+clear/modify/write update of the PTE, eg, do_numa_page()/change_pte_range(). For the data segment of the user-mode program, the global variable area is a private mapping. After the pagecache is loaded, the private anonymous page is generated after the COW is triggered. Mlockall can lock COW pages (anonymous pages), but the original file pages cannot be locked and may be reclaimed. If the global variable (private anon page) is accessed when vmf->pte is zeroed in numa fault, a file page fault will be triggered. At this time, the original private file page may have been reclaimed. If the page cache is not available at this time, a major fault will be triggered and the file will be read, causing additional overhead. This issue affects our traffic analysis service. The inbound traffic is heavy. If a major fault occurs, the I/O schedule is triggered and the original I/O is suspended. Generally, the I/O schedule is 0.7 ms. If other applications are operating disks, the system needs to wait for more than 10 ms. However, the inbound traffic is heavy and the NIC buffer is small. As a result, packet loss occurs. But the traffic analysis service can't tolerate packet loss. Fix this by holding PTL and rechecking the PTE in filemap_fault() before triggering a major fault. We do this check only if vma is VM_LOCKED to reduce the performance impact in common scenarios. In our product environment, there were 7 major faults every 12 hours. After the patch is applied, no major fault have been triggered. Testing file page read and write page fault performance in ext4 and ramdisk using will-it-scale[2] on a x86 physical machine. The data is the average change compared with the mainline after the patch is applied. The test results are within the range of fluctuation. We do this check only if vma is VM_LOCKED, therefore, no performance regressions is caused for most common cases. The test results are as follows: processes processes_idle threads threads_idle ext4 private file write: 0.22% 0.26% 1.21% -0.15% ext4 private file read: 0.03% 1.00% 1.39% 0.34% ext4 shared file write: -0.50% -0.02% -0.14% -0.02% ramdisk private file write: 0.07% 0.02% 0.53% 0.04% ramdisk private file read: 0.01% 1.60% -0.32% -0.02% [1] https://lore.kernel.org/linux-mm/9e62fd9a-bee0-52bf-50a7-498fa17434ee@huawei.com/ [2] https://github.com/antonblanchard/will-it-scale/ Link: https://lkml.kernel.org/r/20240306083809.1236634-1-zhangpeng362@huawei.com Signed-off-by: ZhangPeng <zhangpeng362@huawei.com> Signed-off-by: Kefeng Wang <wangkefeng.wang@huawei.com> Suggested-by: "Huang, Ying" <ying.huang@intel.com> Suggested-by: David Hildenbrand <david@redhat.com> Reviewed-by: "Huang, Ying" <ying.huang@intel.com> Reviewed-by: David Hildenbrand <david@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-03-06 08:38:09 +00:00
static vm_fault_t filemap_fault_recheck_pte_none(struct vm_fault *vmf)
{
struct vm_area_struct *vma = vmf->vma;
vm_fault_t ret = 0;
pte_t *ptep;
/*
* We might have COW'ed a pagecache folio and might now have an mlocked
* anon folio mapped. The original pagecache folio is not mlocked and
* might have been evicted. During a read+clear/modify/write update of
* the PTE, such as done in do_numa_page()/change_pte_range(), we
* temporarily clear the PTE under PT lock and might detect it here as
* "none" when not holding the PT lock.
*
* Not rechecking the PTE under PT lock could result in an unexpected
* major fault in an mlock'ed region. Recheck only for this special
* scenario while holding the PT lock, to not degrade non-mlocked
* scenarios. Recheck the PTE without PT lock firstly, thereby reducing
* the number of times we hold PT lock.
*/
if (!(vma->vm_flags & VM_LOCKED))
return 0;
if (!(vmf->flags & FAULT_FLAG_ORIG_PTE_VALID))
return 0;
ptep = pte_offset_map(vmf->pmd, vmf->address);
if (unlikely(!ptep))
return VM_FAULT_NOPAGE;
if (unlikely(!pte_none(ptep_get_lockless(ptep)))) {
ret = VM_FAULT_NOPAGE;
} else {
spin_lock(vmf->ptl);
if (unlikely(!pte_none(ptep_get(ptep))))
ret = VM_FAULT_NOPAGE;
spin_unlock(vmf->ptl);
}
pte_unmap(ptep);
return ret;
}
/**
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
* @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_lock must be held on entry.
*
* If our return value has VM_FAULT_RETRY set, it's because the mmap_lock
* may be dropped before doing I/O or by lock_folio_maybe_drop_mmap().
*
* If our return value does not have VM_FAULT_RETRY set, the mmap_lock
* has not been released.
*
* We never return with VM_FAULT_RETRY and a bit from VM_FAULT_ERROR set.
*
* Return: bitwise-OR of %VM_FAULT_ codes.
*/
vm_fault_t filemap_fault(struct vm_fault *vmf)
{
int error;
struct file *file = vmf->vma->vm_file;
filemap: drop the mmap_sem for all blocking operations Currently we only drop the mmap_sem if there is contention on the page lock. The idea is that we issue readahead and then go to lock the page while it is under IO and we want to not hold the mmap_sem during the IO. The problem with this is the assumption that the readahead does anything. In the case that the box is under extreme memory or IO pressure we may end up not reading anything at all for readahead, which means we will end up reading in the page under the mmap_sem. Even if the readahead does something, it could get throttled because of io pressure on the system and the process is in a lower priority cgroup. Holding the mmap_sem while doing IO is problematic because it can cause system-wide priority inversions. Consider some large company that does a lot of web traffic. This large company has load balancing logic in it's core web server, cause some engineer thought this was a brilliant plan. This load balancing logic gets statistics from /proc about the system, which trip over processes mmap_sem for various reasons. Now the web server application is in a protected cgroup, but these other processes may not be, and if they are being throttled while their mmap_sem is held we'll stall, and cause this nice death spiral. Instead rework filemap fault path to drop the mmap sem at any point that we may do IO or block for an extended period of time. This includes while issuing readahead, locking the page, or needing to call ->readpage because readahead did not occur. Then once we have a fully uptodate page we can return with VM_FAULT_RETRY and come back again to find our nicely in-cache page that was gotten outside of the mmap_sem. This patch also adds a new helper for locking the page with the mmap_sem dropped. This doesn't make sense currently as generally speaking if the page is already locked it'll have been read in (unless there was an error) before it was unlocked. However a forthcoming patchset will change this with the ability to abort read-ahead bio's if necessary, making it more likely that we could contend for a page lock and still have a not uptodate page. This allows us to deal with this case by grabbing the lock and issuing the IO without the mmap_sem held, and then returning VM_FAULT_RETRY to come back around. [josef@toxicpanda.com: v6] Link: http://lkml.kernel.org/r/20181212152757.10017-1-josef@toxicpanda.com [kirill@shutemov.name: fix race in filemap_fault()] Link: http://lkml.kernel.org/r/20181228235106.okk3oastsnpxusxs@kshutemo-mobl1 [akpm@linux-foundation.org: coding style fixes] Link: http://lkml.kernel.org/r/20181211173801.29535-4-josef@toxicpanda.com Signed-off-by: Josef Bacik <josef@toxicpanda.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Jan Kara <jack@suse.cz> Tested-by: syzbot+b437b5a429d680cf2217@syzkaller.appspotmail.com Cc: Dave Chinner <david@fromorbit.com> Cc: Rik van Riel <riel@redhat.com> Cc: Tejun Heo <tj@kernel.org> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-13 18:44:22 +00:00
struct file *fpin = NULL;
struct address_space *mapping = file->f_mapping;
struct inode *inode = mapping->host;
pgoff_t max_idx, index = vmf->pgoff;
struct folio *folio;
vm_fault_t ret = 0;
bool mapping_locked = false;
max_idx = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
if (unlikely(index >= max_idx))
return VM_FAULT_SIGBUS;
/*
* Do we have something in the page cache already?
*/
folio = filemap_get_folio(mapping, index);
if (likely(!IS_ERR(folio))) {
/*
* We found the page, so try async readahead before waiting for
* the lock.
*/
if (!(vmf->flags & FAULT_FLAG_TRIED))
fpin = do_async_mmap_readahead(vmf, folio);
if (unlikely(!folio_test_uptodate(folio))) {
filemap_invalidate_lock_shared(mapping);
mapping_locked = true;
}
} else {
filemap: avoid unnecessary major faults in filemap_fault() A major fault occurred when using mlockall(MCL_CURRENT | MCL_FUTURE) in application, which leading to an unexpected issue[1]. This is caused by temporarily cleared PTE during a read+clear/modify/write update of the PTE, eg, do_numa_page()/change_pte_range(). For the data segment of the user-mode program, the global variable area is a private mapping. After the pagecache is loaded, the private anonymous page is generated after the COW is triggered. Mlockall can lock COW pages (anonymous pages), but the original file pages cannot be locked and may be reclaimed. If the global variable (private anon page) is accessed when vmf->pte is zeroed in numa fault, a file page fault will be triggered. At this time, the original private file page may have been reclaimed. If the page cache is not available at this time, a major fault will be triggered and the file will be read, causing additional overhead. This issue affects our traffic analysis service. The inbound traffic is heavy. If a major fault occurs, the I/O schedule is triggered and the original I/O is suspended. Generally, the I/O schedule is 0.7 ms. If other applications are operating disks, the system needs to wait for more than 10 ms. However, the inbound traffic is heavy and the NIC buffer is small. As a result, packet loss occurs. But the traffic analysis service can't tolerate packet loss. Fix this by holding PTL and rechecking the PTE in filemap_fault() before triggering a major fault. We do this check only if vma is VM_LOCKED to reduce the performance impact in common scenarios. In our product environment, there were 7 major faults every 12 hours. After the patch is applied, no major fault have been triggered. Testing file page read and write page fault performance in ext4 and ramdisk using will-it-scale[2] on a x86 physical machine. The data is the average change compared with the mainline after the patch is applied. The test results are within the range of fluctuation. We do this check only if vma is VM_LOCKED, therefore, no performance regressions is caused for most common cases. The test results are as follows: processes processes_idle threads threads_idle ext4 private file write: 0.22% 0.26% 1.21% -0.15% ext4 private file read: 0.03% 1.00% 1.39% 0.34% ext4 shared file write: -0.50% -0.02% -0.14% -0.02% ramdisk private file write: 0.07% 0.02% 0.53% 0.04% ramdisk private file read: 0.01% 1.60% -0.32% -0.02% [1] https://lore.kernel.org/linux-mm/9e62fd9a-bee0-52bf-50a7-498fa17434ee@huawei.com/ [2] https://github.com/antonblanchard/will-it-scale/ Link: https://lkml.kernel.org/r/20240306083809.1236634-1-zhangpeng362@huawei.com Signed-off-by: ZhangPeng <zhangpeng362@huawei.com> Signed-off-by: Kefeng Wang <wangkefeng.wang@huawei.com> Suggested-by: "Huang, Ying" <ying.huang@intel.com> Suggested-by: David Hildenbrand <david@redhat.com> Reviewed-by: "Huang, Ying" <ying.huang@intel.com> Reviewed-by: David Hildenbrand <david@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-03-06 08:38:09 +00:00
ret = filemap_fault_recheck_pte_none(vmf);
if (unlikely(ret))
return ret;
/* No page in the page cache at all */
count_vm_event(PGMAJFAULT);
count_memcg_event_mm(vmf->vma->vm_mm, PGMAJFAULT);
ret = VM_FAULT_MAJOR;
filemap: drop the mmap_sem for all blocking operations Currently we only drop the mmap_sem if there is contention on the page lock. The idea is that we issue readahead and then go to lock the page while it is under IO and we want to not hold the mmap_sem during the IO. The problem with this is the assumption that the readahead does anything. In the case that the box is under extreme memory or IO pressure we may end up not reading anything at all for readahead, which means we will end up reading in the page under the mmap_sem. Even if the readahead does something, it could get throttled because of io pressure on the system and the process is in a lower priority cgroup. Holding the mmap_sem while doing IO is problematic because it can cause system-wide priority inversions. Consider some large company that does a lot of web traffic. This large company has load balancing logic in it's core web server, cause some engineer thought this was a brilliant plan. This load balancing logic gets statistics from /proc about the system, which trip over processes mmap_sem for various reasons. Now the web server application is in a protected cgroup, but these other processes may not be, and if they are being throttled while their mmap_sem is held we'll stall, and cause this nice death spiral. Instead rework filemap fault path to drop the mmap sem at any point that we may do IO or block for an extended period of time. This includes while issuing readahead, locking the page, or needing to call ->readpage because readahead did not occur. Then once we have a fully uptodate page we can return with VM_FAULT_RETRY and come back again to find our nicely in-cache page that was gotten outside of the mmap_sem. This patch also adds a new helper for locking the page with the mmap_sem dropped. This doesn't make sense currently as generally speaking if the page is already locked it'll have been read in (unless there was an error) before it was unlocked. However a forthcoming patchset will change this with the ability to abort read-ahead bio's if necessary, making it more likely that we could contend for a page lock and still have a not uptodate page. This allows us to deal with this case by grabbing the lock and issuing the IO without the mmap_sem held, and then returning VM_FAULT_RETRY to come back around. [josef@toxicpanda.com: v6] Link: http://lkml.kernel.org/r/20181212152757.10017-1-josef@toxicpanda.com [kirill@shutemov.name: fix race in filemap_fault()] Link: http://lkml.kernel.org/r/20181228235106.okk3oastsnpxusxs@kshutemo-mobl1 [akpm@linux-foundation.org: coding style fixes] Link: http://lkml.kernel.org/r/20181211173801.29535-4-josef@toxicpanda.com Signed-off-by: Josef Bacik <josef@toxicpanda.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Jan Kara <jack@suse.cz> Tested-by: syzbot+b437b5a429d680cf2217@syzkaller.appspotmail.com Cc: Dave Chinner <david@fromorbit.com> Cc: Rik van Riel <riel@redhat.com> Cc: Tejun Heo <tj@kernel.org> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-13 18:44:22 +00:00
fpin = do_sync_mmap_readahead(vmf);
retry_find:
/*
* See comment in filemap_create_folio() why we need
* invalidate_lock
*/
if (!mapping_locked) {
filemap_invalidate_lock_shared(mapping);
mapping_locked = true;
}
folio = __filemap_get_folio(mapping, index,
filemap: kill page_cache_read usage in filemap_fault Patch series "drop the mmap_sem when doing IO in the fault path", v6. Now that we have proper isolation in place with cgroups2 we have started going through and fixing the various priority inversions. Most are all gone now, but this one is sort of weird since it's not necessarily a priority inversion that happens within the kernel, but rather because of something userspace does. We have giant applications that we want to protect, and parts of these giant applications do things like watch the system state to determine how healthy the box is for load balancing and such. This involves running 'ps' or other such utilities. These utilities will often walk /proc/<pid>/whatever, and these files can sometimes need to down_read(&task->mmap_sem). Not usually a big deal, but we noticed when we are stress testing that sometimes our protected application has latency spikes trying to get the mmap_sem for tasks that are in lower priority cgroups. This is because any down_write() on a semaphore essentially turns it into a mutex, so even if we currently have it held for reading, any new readers will not be allowed on to keep from starving the writer. This is fine, except a lower priority task could be stuck doing IO because it has been throttled to the point that its IO is taking much longer than normal. But because a higher priority group depends on this completing it is now stuck behind lower priority work. In order to avoid this particular priority inversion we want to use the existing retry mechanism to stop from holding the mmap_sem at all if we are going to do IO. This already exists in the read case sort of, but needed to be extended for more than just grabbing the page lock. With io.latency we throttle at submit_bio() time, so the readahead stuff can block and even page_cache_read can block, so all these paths need to have the mmap_sem dropped. The other big thing is ->page_mkwrite. btrfs is particularly shitty here because we have to reserve space for the dirty page, which can be a very expensive operation. We use the same retry method as the read path, and simply cache the page and verify the page is still setup properly the next pass through ->page_mkwrite(). I've tested these patches with xfstests and there are no regressions. This patch (of 3): If we do not have a page at filemap_fault time we'll do this weird forced page_cache_read thing to populate the page, and then drop it again and loop around and find it. This makes for 2 ways we can read a page in filemap_fault, and it's not really needed. Instead add a FGP_FOR_MMAP flag so that pagecache_get_page() will return a unlocked page that's in pagecache. Then use the normal page locking and readpage logic already in filemap_fault. This simplifies the no page in page cache case significantly. [akpm@linux-foundation.org: fix comment text] [josef@toxicpanda.com: don't unlock null page in FGP_FOR_MMAP case] Link: http://lkml.kernel.org/r/20190312201742.22935-1-josef@toxicpanda.com Link: http://lkml.kernel.org/r/20181211173801.29535-2-josef@toxicpanda.com Signed-off-by: Josef Bacik <josef@toxicpanda.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Jan Kara <jack@suse.cz> Reviewed-by: Andrew Morton <akpm@linux-foundation.org> Cc: Tejun Heo <tj@kernel.org> Cc: Dave Chinner <david@fromorbit.com> Cc: Rik van Riel <riel@redhat.com> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-13 18:44:14 +00:00
FGP_CREAT|FGP_FOR_MMAP,
vmf->gfp_mask);
if (IS_ERR(folio)) {
filemap: drop the mmap_sem for all blocking operations Currently we only drop the mmap_sem if there is contention on the page lock. The idea is that we issue readahead and then go to lock the page while it is under IO and we want to not hold the mmap_sem during the IO. The problem with this is the assumption that the readahead does anything. In the case that the box is under extreme memory or IO pressure we may end up not reading anything at all for readahead, which means we will end up reading in the page under the mmap_sem. Even if the readahead does something, it could get throttled because of io pressure on the system and the process is in a lower priority cgroup. Holding the mmap_sem while doing IO is problematic because it can cause system-wide priority inversions. Consider some large company that does a lot of web traffic. This large company has load balancing logic in it's core web server, cause some engineer thought this was a brilliant plan. This load balancing logic gets statistics from /proc about the system, which trip over processes mmap_sem for various reasons. Now the web server application is in a protected cgroup, but these other processes may not be, and if they are being throttled while their mmap_sem is held we'll stall, and cause this nice death spiral. Instead rework filemap fault path to drop the mmap sem at any point that we may do IO or block for an extended period of time. This includes while issuing readahead, locking the page, or needing to call ->readpage because readahead did not occur. Then once we have a fully uptodate page we can return with VM_FAULT_RETRY and come back again to find our nicely in-cache page that was gotten outside of the mmap_sem. This patch also adds a new helper for locking the page with the mmap_sem dropped. This doesn't make sense currently as generally speaking if the page is already locked it'll have been read in (unless there was an error) before it was unlocked. However a forthcoming patchset will change this with the ability to abort read-ahead bio's if necessary, making it more likely that we could contend for a page lock and still have a not uptodate page. This allows us to deal with this case by grabbing the lock and issuing the IO without the mmap_sem held, and then returning VM_FAULT_RETRY to come back around. [josef@toxicpanda.com: v6] Link: http://lkml.kernel.org/r/20181212152757.10017-1-josef@toxicpanda.com [kirill@shutemov.name: fix race in filemap_fault()] Link: http://lkml.kernel.org/r/20181228235106.okk3oastsnpxusxs@kshutemo-mobl1 [akpm@linux-foundation.org: coding style fixes] Link: http://lkml.kernel.org/r/20181211173801.29535-4-josef@toxicpanda.com Signed-off-by: Josef Bacik <josef@toxicpanda.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Jan Kara <jack@suse.cz> Tested-by: syzbot+b437b5a429d680cf2217@syzkaller.appspotmail.com Cc: Dave Chinner <david@fromorbit.com> Cc: Rik van Riel <riel@redhat.com> Cc: Tejun Heo <tj@kernel.org> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-13 18:44:22 +00:00
if (fpin)
goto out_retry;
filemap_invalidate_unlock_shared(mapping);
return VM_FAULT_OOM;
filemap: drop the mmap_sem for all blocking operations Currently we only drop the mmap_sem if there is contention on the page lock. The idea is that we issue readahead and then go to lock the page while it is under IO and we want to not hold the mmap_sem during the IO. The problem with this is the assumption that the readahead does anything. In the case that the box is under extreme memory or IO pressure we may end up not reading anything at all for readahead, which means we will end up reading in the page under the mmap_sem. Even if the readahead does something, it could get throttled because of io pressure on the system and the process is in a lower priority cgroup. Holding the mmap_sem while doing IO is problematic because it can cause system-wide priority inversions. Consider some large company that does a lot of web traffic. This large company has load balancing logic in it's core web server, cause some engineer thought this was a brilliant plan. This load balancing logic gets statistics from /proc about the system, which trip over processes mmap_sem for various reasons. Now the web server application is in a protected cgroup, but these other processes may not be, and if they are being throttled while their mmap_sem is held we'll stall, and cause this nice death spiral. Instead rework filemap fault path to drop the mmap sem at any point that we may do IO or block for an extended period of time. This includes while issuing readahead, locking the page, or needing to call ->readpage because readahead did not occur. Then once we have a fully uptodate page we can return with VM_FAULT_RETRY and come back again to find our nicely in-cache page that was gotten outside of the mmap_sem. This patch also adds a new helper for locking the page with the mmap_sem dropped. This doesn't make sense currently as generally speaking if the page is already locked it'll have been read in (unless there was an error) before it was unlocked. However a forthcoming patchset will change this with the ability to abort read-ahead bio's if necessary, making it more likely that we could contend for a page lock and still have a not uptodate page. This allows us to deal with this case by grabbing the lock and issuing the IO without the mmap_sem held, and then returning VM_FAULT_RETRY to come back around. [josef@toxicpanda.com: v6] Link: http://lkml.kernel.org/r/20181212152757.10017-1-josef@toxicpanda.com [kirill@shutemov.name: fix race in filemap_fault()] Link: http://lkml.kernel.org/r/20181228235106.okk3oastsnpxusxs@kshutemo-mobl1 [akpm@linux-foundation.org: coding style fixes] Link: http://lkml.kernel.org/r/20181211173801.29535-4-josef@toxicpanda.com Signed-off-by: Josef Bacik <josef@toxicpanda.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Jan Kara <jack@suse.cz> Tested-by: syzbot+b437b5a429d680cf2217@syzkaller.appspotmail.com Cc: Dave Chinner <david@fromorbit.com> Cc: Rik van Riel <riel@redhat.com> Cc: Tejun Heo <tj@kernel.org> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-13 18:44:22 +00:00
}
}
if (!lock_folio_maybe_drop_mmap(vmf, folio, &fpin))
filemap: drop the mmap_sem for all blocking operations Currently we only drop the mmap_sem if there is contention on the page lock. The idea is that we issue readahead and then go to lock the page while it is under IO and we want to not hold the mmap_sem during the IO. The problem with this is the assumption that the readahead does anything. In the case that the box is under extreme memory or IO pressure we may end up not reading anything at all for readahead, which means we will end up reading in the page under the mmap_sem. Even if the readahead does something, it could get throttled because of io pressure on the system and the process is in a lower priority cgroup. Holding the mmap_sem while doing IO is problematic because it can cause system-wide priority inversions. Consider some large company that does a lot of web traffic. This large company has load balancing logic in it's core web server, cause some engineer thought this was a brilliant plan. This load balancing logic gets statistics from /proc about the system, which trip over processes mmap_sem for various reasons. Now the web server application is in a protected cgroup, but these other processes may not be, and if they are being throttled while their mmap_sem is held we'll stall, and cause this nice death spiral. Instead rework filemap fault path to drop the mmap sem at any point that we may do IO or block for an extended period of time. This includes while issuing readahead, locking the page, or needing to call ->readpage because readahead did not occur. Then once we have a fully uptodate page we can return with VM_FAULT_RETRY and come back again to find our nicely in-cache page that was gotten outside of the mmap_sem. This patch also adds a new helper for locking the page with the mmap_sem dropped. This doesn't make sense currently as generally speaking if the page is already locked it'll have been read in (unless there was an error) before it was unlocked. However a forthcoming patchset will change this with the ability to abort read-ahead bio's if necessary, making it more likely that we could contend for a page lock and still have a not uptodate page. This allows us to deal with this case by grabbing the lock and issuing the IO without the mmap_sem held, and then returning VM_FAULT_RETRY to come back around. [josef@toxicpanda.com: v6] Link: http://lkml.kernel.org/r/20181212152757.10017-1-josef@toxicpanda.com [kirill@shutemov.name: fix race in filemap_fault()] Link: http://lkml.kernel.org/r/20181228235106.okk3oastsnpxusxs@kshutemo-mobl1 [akpm@linux-foundation.org: coding style fixes] Link: http://lkml.kernel.org/r/20181211173801.29535-4-josef@toxicpanda.com Signed-off-by: Josef Bacik <josef@toxicpanda.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Jan Kara <jack@suse.cz> Tested-by: syzbot+b437b5a429d680cf2217@syzkaller.appspotmail.com Cc: Dave Chinner <david@fromorbit.com> Cc: Rik van Riel <riel@redhat.com> Cc: Tejun Heo <tj@kernel.org> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-13 18:44:22 +00:00
goto out_retry;
/* Did it get truncated? */
if (unlikely(folio->mapping != mapping)) {
folio_unlock(folio);
folio_put(folio);
goto retry_find;
}
VM_BUG_ON_FOLIO(!folio_contains(folio, index), folio);
/*
mm/filemap: clarify filemap_fault() comments for not uptodate case The existing comments in filemap_fault() suggest that, after either a minor fault has occurred and filemap_get_folio() found a folio in the page cache, or a major fault arose and __filemap_get_folio(FGP_CREATE...) did the job (having relied on do_sync_mmap_readahead() or filemap_read_folio() to read in the folio), the only possible reason it could not be uptodate is because of an error. This is not so, as if, for instance, the fault occurred within a VMA which had the VM_RAND_READ flag set (via madvise() with the MADV_RANDOM flag specified), this would cause even synchronous readahead to fail to read in the folio. I confirmed this by dropping page caches and faulting in memory madvise()'d this way, observing that this code path was reached on each occasion. Clarify the comments to include this case, and additionally update the comment recently added around the invalidate lock logic to make it clear the comment explicitly refers to the minor fault case. In addition, while we're here, refer to folios rather than pages. [lstoakes@gmail.com: correct identation as per Christopher's feedback] Link: https://lkml.kernel.org/r/2c7014c0-6343-4e76-8697-3f84f54350bd@lucifer.local Link: https://lkml.kernel.org/r/20230930231029.88196-1-lstoakes@gmail.com Signed-off-by: Lorenzo Stoakes <lstoakes@gmail.com> Reviewed-by: Jan Kara <jack@suse.cz> Reviewed-by: Christoph Hellwig <hch@lst.de> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-09-30 23:10:29 +00:00
* We have a locked folio 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,
* or because readahead was otherwise unable to retrieve it.
*/
if (unlikely(!folio_test_uptodate(folio))) {
/*
mm/filemap: clarify filemap_fault() comments for not uptodate case The existing comments in filemap_fault() suggest that, after either a minor fault has occurred and filemap_get_folio() found a folio in the page cache, or a major fault arose and __filemap_get_folio(FGP_CREATE...) did the job (having relied on do_sync_mmap_readahead() or filemap_read_folio() to read in the folio), the only possible reason it could not be uptodate is because of an error. This is not so, as if, for instance, the fault occurred within a VMA which had the VM_RAND_READ flag set (via madvise() with the MADV_RANDOM flag specified), this would cause even synchronous readahead to fail to read in the folio. I confirmed this by dropping page caches and faulting in memory madvise()'d this way, observing that this code path was reached on each occasion. Clarify the comments to include this case, and additionally update the comment recently added around the invalidate lock logic to make it clear the comment explicitly refers to the minor fault case. In addition, while we're here, refer to folios rather than pages. [lstoakes@gmail.com: correct identation as per Christopher's feedback] Link: https://lkml.kernel.org/r/2c7014c0-6343-4e76-8697-3f84f54350bd@lucifer.local Link: https://lkml.kernel.org/r/20230930231029.88196-1-lstoakes@gmail.com Signed-off-by: Lorenzo Stoakes <lstoakes@gmail.com> Reviewed-by: Jan Kara <jack@suse.cz> Reviewed-by: Christoph Hellwig <hch@lst.de> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-09-30 23:10:29 +00:00
* If the invalidate lock is not held, the folio was in cache
* and uptodate and now it is not. Strange but possible since we
* didn't hold the page lock all the time. Let's drop
* everything, get the invalidate lock and try again.
*/
if (!mapping_locked) {
folio_unlock(folio);
folio_put(folio);
goto retry_find;
}
mm/filemap: clarify filemap_fault() comments for not uptodate case The existing comments in filemap_fault() suggest that, after either a minor fault has occurred and filemap_get_folio() found a folio in the page cache, or a major fault arose and __filemap_get_folio(FGP_CREATE...) did the job (having relied on do_sync_mmap_readahead() or filemap_read_folio() to read in the folio), the only possible reason it could not be uptodate is because of an error. This is not so, as if, for instance, the fault occurred within a VMA which had the VM_RAND_READ flag set (via madvise() with the MADV_RANDOM flag specified), this would cause even synchronous readahead to fail to read in the folio. I confirmed this by dropping page caches and faulting in memory madvise()'d this way, observing that this code path was reached on each occasion. Clarify the comments to include this case, and additionally update the comment recently added around the invalidate lock logic to make it clear the comment explicitly refers to the minor fault case. In addition, while we're here, refer to folios rather than pages. [lstoakes@gmail.com: correct identation as per Christopher's feedback] Link: https://lkml.kernel.org/r/2c7014c0-6343-4e76-8697-3f84f54350bd@lucifer.local Link: https://lkml.kernel.org/r/20230930231029.88196-1-lstoakes@gmail.com Signed-off-by: Lorenzo Stoakes <lstoakes@gmail.com> Reviewed-by: Jan Kara <jack@suse.cz> Reviewed-by: Christoph Hellwig <hch@lst.de> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-09-30 23:10:29 +00:00
/*
* OK, the folio is really not uptodate. This can be because the
* VMA has the VM_RAND_READ flag set, or because an error
* arose. Let's read it in directly.
*/
goto page_not_uptodate;
}
filemap: drop the mmap_sem for all blocking operations Currently we only drop the mmap_sem if there is contention on the page lock. The idea is that we issue readahead and then go to lock the page while it is under IO and we want to not hold the mmap_sem during the IO. The problem with this is the assumption that the readahead does anything. In the case that the box is under extreme memory or IO pressure we may end up not reading anything at all for readahead, which means we will end up reading in the page under the mmap_sem. Even if the readahead does something, it could get throttled because of io pressure on the system and the process is in a lower priority cgroup. Holding the mmap_sem while doing IO is problematic because it can cause system-wide priority inversions. Consider some large company that does a lot of web traffic. This large company has load balancing logic in it's core web server, cause some engineer thought this was a brilliant plan. This load balancing logic gets statistics from /proc about the system, which trip over processes mmap_sem for various reasons. Now the web server application is in a protected cgroup, but these other processes may not be, and if they are being throttled while their mmap_sem is held we'll stall, and cause this nice death spiral. Instead rework filemap fault path to drop the mmap sem at any point that we may do IO or block for an extended period of time. This includes while issuing readahead, locking the page, or needing to call ->readpage because readahead did not occur. Then once we have a fully uptodate page we can return with VM_FAULT_RETRY and come back again to find our nicely in-cache page that was gotten outside of the mmap_sem. This patch also adds a new helper for locking the page with the mmap_sem dropped. This doesn't make sense currently as generally speaking if the page is already locked it'll have been read in (unless there was an error) before it was unlocked. However a forthcoming patchset will change this with the ability to abort read-ahead bio's if necessary, making it more likely that we could contend for a page lock and still have a not uptodate page. This allows us to deal with this case by grabbing the lock and issuing the IO without the mmap_sem held, and then returning VM_FAULT_RETRY to come back around. [josef@toxicpanda.com: v6] Link: http://lkml.kernel.org/r/20181212152757.10017-1-josef@toxicpanda.com [kirill@shutemov.name: fix race in filemap_fault()] Link: http://lkml.kernel.org/r/20181228235106.okk3oastsnpxusxs@kshutemo-mobl1 [akpm@linux-foundation.org: coding style fixes] Link: http://lkml.kernel.org/r/20181211173801.29535-4-josef@toxicpanda.com Signed-off-by: Josef Bacik <josef@toxicpanda.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Jan Kara <jack@suse.cz> Tested-by: syzbot+b437b5a429d680cf2217@syzkaller.appspotmail.com Cc: Dave Chinner <david@fromorbit.com> Cc: Rik van Riel <riel@redhat.com> Cc: Tejun Heo <tj@kernel.org> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-13 18:44:22 +00:00
/*
* We've made it this far and we had to drop our mmap_lock, now is the
filemap: drop the mmap_sem for all blocking operations Currently we only drop the mmap_sem if there is contention on the page lock. The idea is that we issue readahead and then go to lock the page while it is under IO and we want to not hold the mmap_sem during the IO. The problem with this is the assumption that the readahead does anything. In the case that the box is under extreme memory or IO pressure we may end up not reading anything at all for readahead, which means we will end up reading in the page under the mmap_sem. Even if the readahead does something, it could get throttled because of io pressure on the system and the process is in a lower priority cgroup. Holding the mmap_sem while doing IO is problematic because it can cause system-wide priority inversions. Consider some large company that does a lot of web traffic. This large company has load balancing logic in it's core web server, cause some engineer thought this was a brilliant plan. This load balancing logic gets statistics from /proc about the system, which trip over processes mmap_sem for various reasons. Now the web server application is in a protected cgroup, but these other processes may not be, and if they are being throttled while their mmap_sem is held we'll stall, and cause this nice death spiral. Instead rework filemap fault path to drop the mmap sem at any point that we may do IO or block for an extended period of time. This includes while issuing readahead, locking the page, or needing to call ->readpage because readahead did not occur. Then once we have a fully uptodate page we can return with VM_FAULT_RETRY and come back again to find our nicely in-cache page that was gotten outside of the mmap_sem. This patch also adds a new helper for locking the page with the mmap_sem dropped. This doesn't make sense currently as generally speaking if the page is already locked it'll have been read in (unless there was an error) before it was unlocked. However a forthcoming patchset will change this with the ability to abort read-ahead bio's if necessary, making it more likely that we could contend for a page lock and still have a not uptodate page. This allows us to deal with this case by grabbing the lock and issuing the IO without the mmap_sem held, and then returning VM_FAULT_RETRY to come back around. [josef@toxicpanda.com: v6] Link: http://lkml.kernel.org/r/20181212152757.10017-1-josef@toxicpanda.com [kirill@shutemov.name: fix race in filemap_fault()] Link: http://lkml.kernel.org/r/20181228235106.okk3oastsnpxusxs@kshutemo-mobl1 [akpm@linux-foundation.org: coding style fixes] Link: http://lkml.kernel.org/r/20181211173801.29535-4-josef@toxicpanda.com Signed-off-by: Josef Bacik <josef@toxicpanda.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Jan Kara <jack@suse.cz> Tested-by: syzbot+b437b5a429d680cf2217@syzkaller.appspotmail.com Cc: Dave Chinner <david@fromorbit.com> Cc: Rik van Riel <riel@redhat.com> Cc: Tejun Heo <tj@kernel.org> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-13 18:44:22 +00:00
* time to return to the upper layer and have it re-find the vma and
* redo the fault.
*/
if (fpin) {
folio_unlock(folio);
filemap: drop the mmap_sem for all blocking operations Currently we only drop the mmap_sem if there is contention on the page lock. The idea is that we issue readahead and then go to lock the page while it is under IO and we want to not hold the mmap_sem during the IO. The problem with this is the assumption that the readahead does anything. In the case that the box is under extreme memory or IO pressure we may end up not reading anything at all for readahead, which means we will end up reading in the page under the mmap_sem. Even if the readahead does something, it could get throttled because of io pressure on the system and the process is in a lower priority cgroup. Holding the mmap_sem while doing IO is problematic because it can cause system-wide priority inversions. Consider some large company that does a lot of web traffic. This large company has load balancing logic in it's core web server, cause some engineer thought this was a brilliant plan. This load balancing logic gets statistics from /proc about the system, which trip over processes mmap_sem for various reasons. Now the web server application is in a protected cgroup, but these other processes may not be, and if they are being throttled while their mmap_sem is held we'll stall, and cause this nice death spiral. Instead rework filemap fault path to drop the mmap sem at any point that we may do IO or block for an extended period of time. This includes while issuing readahead, locking the page, or needing to call ->readpage because readahead did not occur. Then once we have a fully uptodate page we can return with VM_FAULT_RETRY and come back again to find our nicely in-cache page that was gotten outside of the mmap_sem. This patch also adds a new helper for locking the page with the mmap_sem dropped. This doesn't make sense currently as generally speaking if the page is already locked it'll have been read in (unless there was an error) before it was unlocked. However a forthcoming patchset will change this with the ability to abort read-ahead bio's if necessary, making it more likely that we could contend for a page lock and still have a not uptodate page. This allows us to deal with this case by grabbing the lock and issuing the IO without the mmap_sem held, and then returning VM_FAULT_RETRY to come back around. [josef@toxicpanda.com: v6] Link: http://lkml.kernel.org/r/20181212152757.10017-1-josef@toxicpanda.com [kirill@shutemov.name: fix race in filemap_fault()] Link: http://lkml.kernel.org/r/20181228235106.okk3oastsnpxusxs@kshutemo-mobl1 [akpm@linux-foundation.org: coding style fixes] Link: http://lkml.kernel.org/r/20181211173801.29535-4-josef@toxicpanda.com Signed-off-by: Josef Bacik <josef@toxicpanda.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Jan Kara <jack@suse.cz> Tested-by: syzbot+b437b5a429d680cf2217@syzkaller.appspotmail.com Cc: Dave Chinner <david@fromorbit.com> Cc: Rik van Riel <riel@redhat.com> Cc: Tejun Heo <tj@kernel.org> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-13 18:44:22 +00:00
goto out_retry;
}
if (mapping_locked)
filemap_invalidate_unlock_shared(mapping);
filemap: drop the mmap_sem for all blocking operations Currently we only drop the mmap_sem if there is contention on the page lock. The idea is that we issue readahead and then go to lock the page while it is under IO and we want to not hold the mmap_sem during the IO. The problem with this is the assumption that the readahead does anything. In the case that the box is under extreme memory or IO pressure we may end up not reading anything at all for readahead, which means we will end up reading in the page under the mmap_sem. Even if the readahead does something, it could get throttled because of io pressure on the system and the process is in a lower priority cgroup. Holding the mmap_sem while doing IO is problematic because it can cause system-wide priority inversions. Consider some large company that does a lot of web traffic. This large company has load balancing logic in it's core web server, cause some engineer thought this was a brilliant plan. This load balancing logic gets statistics from /proc about the system, which trip over processes mmap_sem for various reasons. Now the web server application is in a protected cgroup, but these other processes may not be, and if they are being throttled while their mmap_sem is held we'll stall, and cause this nice death spiral. Instead rework filemap fault path to drop the mmap sem at any point that we may do IO or block for an extended period of time. This includes while issuing readahead, locking the page, or needing to call ->readpage because readahead did not occur. Then once we have a fully uptodate page we can return with VM_FAULT_RETRY and come back again to find our nicely in-cache page that was gotten outside of the mmap_sem. This patch also adds a new helper for locking the page with the mmap_sem dropped. This doesn't make sense currently as generally speaking if the page is already locked it'll have been read in (unless there was an error) before it was unlocked. However a forthcoming patchset will change this with the ability to abort read-ahead bio's if necessary, making it more likely that we could contend for a page lock and still have a not uptodate page. This allows us to deal with this case by grabbing the lock and issuing the IO without the mmap_sem held, and then returning VM_FAULT_RETRY to come back around. [josef@toxicpanda.com: v6] Link: http://lkml.kernel.org/r/20181212152757.10017-1-josef@toxicpanda.com [kirill@shutemov.name: fix race in filemap_fault()] Link: http://lkml.kernel.org/r/20181228235106.okk3oastsnpxusxs@kshutemo-mobl1 [akpm@linux-foundation.org: coding style fixes] Link: http://lkml.kernel.org/r/20181211173801.29535-4-josef@toxicpanda.com Signed-off-by: Josef Bacik <josef@toxicpanda.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Jan Kara <jack@suse.cz> Tested-by: syzbot+b437b5a429d680cf2217@syzkaller.appspotmail.com Cc: Dave Chinner <david@fromorbit.com> Cc: Rik van Riel <riel@redhat.com> Cc: Tejun Heo <tj@kernel.org> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-13 18:44:22 +00:00
/*
* Found the page and have a reference on it.
* We must recheck i_size under page lock.
*/
max_idx = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
if (unlikely(index >= max_idx)) {
folio_unlock(folio);
folio_put(folio);
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 = folio_file_page(folio, index);
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;
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.
*/
filemap: drop the mmap_sem for all blocking operations Currently we only drop the mmap_sem if there is contention on the page lock. The idea is that we issue readahead and then go to lock the page while it is under IO and we want to not hold the mmap_sem during the IO. The problem with this is the assumption that the readahead does anything. In the case that the box is under extreme memory or IO pressure we may end up not reading anything at all for readahead, which means we will end up reading in the page under the mmap_sem. Even if the readahead does something, it could get throttled because of io pressure on the system and the process is in a lower priority cgroup. Holding the mmap_sem while doing IO is problematic because it can cause system-wide priority inversions. Consider some large company that does a lot of web traffic. This large company has load balancing logic in it's core web server, cause some engineer thought this was a brilliant plan. This load balancing logic gets statistics from /proc about the system, which trip over processes mmap_sem for various reasons. Now the web server application is in a protected cgroup, but these other processes may not be, and if they are being throttled while their mmap_sem is held we'll stall, and cause this nice death spiral. Instead rework filemap fault path to drop the mmap sem at any point that we may do IO or block for an extended period of time. This includes while issuing readahead, locking the page, or needing to call ->readpage because readahead did not occur. Then once we have a fully uptodate page we can return with VM_FAULT_RETRY and come back again to find our nicely in-cache page that was gotten outside of the mmap_sem. This patch also adds a new helper for locking the page with the mmap_sem dropped. This doesn't make sense currently as generally speaking if the page is already locked it'll have been read in (unless there was an error) before it was unlocked. However a forthcoming patchset will change this with the ability to abort read-ahead bio's if necessary, making it more likely that we could contend for a page lock and still have a not uptodate page. This allows us to deal with this case by grabbing the lock and issuing the IO without the mmap_sem held, and then returning VM_FAULT_RETRY to come back around. [josef@toxicpanda.com: v6] Link: http://lkml.kernel.org/r/20181212152757.10017-1-josef@toxicpanda.com [kirill@shutemov.name: fix race in filemap_fault()] Link: http://lkml.kernel.org/r/20181228235106.okk3oastsnpxusxs@kshutemo-mobl1 [akpm@linux-foundation.org: coding style fixes] Link: http://lkml.kernel.org/r/20181211173801.29535-4-josef@toxicpanda.com Signed-off-by: Josef Bacik <josef@toxicpanda.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Jan Kara <jack@suse.cz> Tested-by: syzbot+b437b5a429d680cf2217@syzkaller.appspotmail.com Cc: Dave Chinner <david@fromorbit.com> Cc: Rik van Riel <riel@redhat.com> Cc: Tejun Heo <tj@kernel.org> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-13 18:44:22 +00:00
fpin = maybe_unlock_mmap_for_io(vmf, fpin);
error = filemap_read_folio(file, mapping->a_ops->read_folio, folio);
filemap: drop the mmap_sem for all blocking operations Currently we only drop the mmap_sem if there is contention on the page lock. The idea is that we issue readahead and then go to lock the page while it is under IO and we want to not hold the mmap_sem during the IO. The problem with this is the assumption that the readahead does anything. In the case that the box is under extreme memory or IO pressure we may end up not reading anything at all for readahead, which means we will end up reading in the page under the mmap_sem. Even if the readahead does something, it could get throttled because of io pressure on the system and the process is in a lower priority cgroup. Holding the mmap_sem while doing IO is problematic because it can cause system-wide priority inversions. Consider some large company that does a lot of web traffic. This large company has load balancing logic in it's core web server, cause some engineer thought this was a brilliant plan. This load balancing logic gets statistics from /proc about the system, which trip over processes mmap_sem for various reasons. Now the web server application is in a protected cgroup, but these other processes may not be, and if they are being throttled while their mmap_sem is held we'll stall, and cause this nice death spiral. Instead rework filemap fault path to drop the mmap sem at any point that we may do IO or block for an extended period of time. This includes while issuing readahead, locking the page, or needing to call ->readpage because readahead did not occur. Then once we have a fully uptodate page we can return with VM_FAULT_RETRY and come back again to find our nicely in-cache page that was gotten outside of the mmap_sem. This patch also adds a new helper for locking the page with the mmap_sem dropped. This doesn't make sense currently as generally speaking if the page is already locked it'll have been read in (unless there was an error) before it was unlocked. However a forthcoming patchset will change this with the ability to abort read-ahead bio's if necessary, making it more likely that we could contend for a page lock and still have a not uptodate page. This allows us to deal with this case by grabbing the lock and issuing the IO without the mmap_sem held, and then returning VM_FAULT_RETRY to come back around. [josef@toxicpanda.com: v6] Link: http://lkml.kernel.org/r/20181212152757.10017-1-josef@toxicpanda.com [kirill@shutemov.name: fix race in filemap_fault()] Link: http://lkml.kernel.org/r/20181228235106.okk3oastsnpxusxs@kshutemo-mobl1 [akpm@linux-foundation.org: coding style fixes] Link: http://lkml.kernel.org/r/20181211173801.29535-4-josef@toxicpanda.com Signed-off-by: Josef Bacik <josef@toxicpanda.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Jan Kara <jack@suse.cz> Tested-by: syzbot+b437b5a429d680cf2217@syzkaller.appspotmail.com Cc: Dave Chinner <david@fromorbit.com> Cc: Rik van Riel <riel@redhat.com> Cc: Tejun Heo <tj@kernel.org> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-13 18:44:22 +00:00
if (fpin)
goto out_retry;
folio_put(folio);
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 (!error || error == AOP_TRUNCATED_PAGE)
goto retry_find;
filemap_invalidate_unlock_shared(mapping);
return VM_FAULT_SIGBUS;
filemap: drop the mmap_sem for all blocking operations Currently we only drop the mmap_sem if there is contention on the page lock. The idea is that we issue readahead and then go to lock the page while it is under IO and we want to not hold the mmap_sem during the IO. The problem with this is the assumption that the readahead does anything. In the case that the box is under extreme memory or IO pressure we may end up not reading anything at all for readahead, which means we will end up reading in the page under the mmap_sem. Even if the readahead does something, it could get throttled because of io pressure on the system and the process is in a lower priority cgroup. Holding the mmap_sem while doing IO is problematic because it can cause system-wide priority inversions. Consider some large company that does a lot of web traffic. This large company has load balancing logic in it's core web server, cause some engineer thought this was a brilliant plan. This load balancing logic gets statistics from /proc about the system, which trip over processes mmap_sem for various reasons. Now the web server application is in a protected cgroup, but these other processes may not be, and if they are being throttled while their mmap_sem is held we'll stall, and cause this nice death spiral. Instead rework filemap fault path to drop the mmap sem at any point that we may do IO or block for an extended period of time. This includes while issuing readahead, locking the page, or needing to call ->readpage because readahead did not occur. Then once we have a fully uptodate page we can return with VM_FAULT_RETRY and come back again to find our nicely in-cache page that was gotten outside of the mmap_sem. This patch also adds a new helper for locking the page with the mmap_sem dropped. This doesn't make sense currently as generally speaking if the page is already locked it'll have been read in (unless there was an error) before it was unlocked. However a forthcoming patchset will change this with the ability to abort read-ahead bio's if necessary, making it more likely that we could contend for a page lock and still have a not uptodate page. This allows us to deal with this case by grabbing the lock and issuing the IO without the mmap_sem held, and then returning VM_FAULT_RETRY to come back around. [josef@toxicpanda.com: v6] Link: http://lkml.kernel.org/r/20181212152757.10017-1-josef@toxicpanda.com [kirill@shutemov.name: fix race in filemap_fault()] Link: http://lkml.kernel.org/r/20181228235106.okk3oastsnpxusxs@kshutemo-mobl1 [akpm@linux-foundation.org: coding style fixes] Link: http://lkml.kernel.org/r/20181211173801.29535-4-josef@toxicpanda.com Signed-off-by: Josef Bacik <josef@toxicpanda.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Jan Kara <jack@suse.cz> Tested-by: syzbot+b437b5a429d680cf2217@syzkaller.appspotmail.com Cc: Dave Chinner <david@fromorbit.com> Cc: Rik van Riel <riel@redhat.com> Cc: Tejun Heo <tj@kernel.org> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-13 18:44:22 +00:00
out_retry:
/*
* We dropped the mmap_lock, we need to return to the fault handler to
filemap: drop the mmap_sem for all blocking operations Currently we only drop the mmap_sem if there is contention on the page lock. The idea is that we issue readahead and then go to lock the page while it is under IO and we want to not hold the mmap_sem during the IO. The problem with this is the assumption that the readahead does anything. In the case that the box is under extreme memory or IO pressure we may end up not reading anything at all for readahead, which means we will end up reading in the page under the mmap_sem. Even if the readahead does something, it could get throttled because of io pressure on the system and the process is in a lower priority cgroup. Holding the mmap_sem while doing IO is problematic because it can cause system-wide priority inversions. Consider some large company that does a lot of web traffic. This large company has load balancing logic in it's core web server, cause some engineer thought this was a brilliant plan. This load balancing logic gets statistics from /proc about the system, which trip over processes mmap_sem for various reasons. Now the web server application is in a protected cgroup, but these other processes may not be, and if they are being throttled while their mmap_sem is held we'll stall, and cause this nice death spiral. Instead rework filemap fault path to drop the mmap sem at any point that we may do IO or block for an extended period of time. This includes while issuing readahead, locking the page, or needing to call ->readpage because readahead did not occur. Then once we have a fully uptodate page we can return with VM_FAULT_RETRY and come back again to find our nicely in-cache page that was gotten outside of the mmap_sem. This patch also adds a new helper for locking the page with the mmap_sem dropped. This doesn't make sense currently as generally speaking if the page is already locked it'll have been read in (unless there was an error) before it was unlocked. However a forthcoming patchset will change this with the ability to abort read-ahead bio's if necessary, making it more likely that we could contend for a page lock and still have a not uptodate page. This allows us to deal with this case by grabbing the lock and issuing the IO without the mmap_sem held, and then returning VM_FAULT_RETRY to come back around. [josef@toxicpanda.com: v6] Link: http://lkml.kernel.org/r/20181212152757.10017-1-josef@toxicpanda.com [kirill@shutemov.name: fix race in filemap_fault()] Link: http://lkml.kernel.org/r/20181228235106.okk3oastsnpxusxs@kshutemo-mobl1 [akpm@linux-foundation.org: coding style fixes] Link: http://lkml.kernel.org/r/20181211173801.29535-4-josef@toxicpanda.com Signed-off-by: Josef Bacik <josef@toxicpanda.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Jan Kara <jack@suse.cz> Tested-by: syzbot+b437b5a429d680cf2217@syzkaller.appspotmail.com Cc: Dave Chinner <david@fromorbit.com> Cc: Rik van Riel <riel@redhat.com> Cc: Tejun Heo <tj@kernel.org> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-13 18:44:22 +00:00
* re-find the vma and come back and find our hopefully still populated
* page.
*/
if (!IS_ERR(folio))
folio_put(folio);
if (mapping_locked)
filemap_invalidate_unlock_shared(mapping);
filemap: drop the mmap_sem for all blocking operations Currently we only drop the mmap_sem if there is contention on the page lock. The idea is that we issue readahead and then go to lock the page while it is under IO and we want to not hold the mmap_sem during the IO. The problem with this is the assumption that the readahead does anything. In the case that the box is under extreme memory or IO pressure we may end up not reading anything at all for readahead, which means we will end up reading in the page under the mmap_sem. Even if the readahead does something, it could get throttled because of io pressure on the system and the process is in a lower priority cgroup. Holding the mmap_sem while doing IO is problematic because it can cause system-wide priority inversions. Consider some large company that does a lot of web traffic. This large company has load balancing logic in it's core web server, cause some engineer thought this was a brilliant plan. This load balancing logic gets statistics from /proc about the system, which trip over processes mmap_sem for various reasons. Now the web server application is in a protected cgroup, but these other processes may not be, and if they are being throttled while their mmap_sem is held we'll stall, and cause this nice death spiral. Instead rework filemap fault path to drop the mmap sem at any point that we may do IO or block for an extended period of time. This includes while issuing readahead, locking the page, or needing to call ->readpage because readahead did not occur. Then once we have a fully uptodate page we can return with VM_FAULT_RETRY and come back again to find our nicely in-cache page that was gotten outside of the mmap_sem. This patch also adds a new helper for locking the page with the mmap_sem dropped. This doesn't make sense currently as generally speaking if the page is already locked it'll have been read in (unless there was an error) before it was unlocked. However a forthcoming patchset will change this with the ability to abort read-ahead bio's if necessary, making it more likely that we could contend for a page lock and still have a not uptodate page. This allows us to deal with this case by grabbing the lock and issuing the IO without the mmap_sem held, and then returning VM_FAULT_RETRY to come back around. [josef@toxicpanda.com: v6] Link: http://lkml.kernel.org/r/20181212152757.10017-1-josef@toxicpanda.com [kirill@shutemov.name: fix race in filemap_fault()] Link: http://lkml.kernel.org/r/20181228235106.okk3oastsnpxusxs@kshutemo-mobl1 [akpm@linux-foundation.org: coding style fixes] Link: http://lkml.kernel.org/r/20181211173801.29535-4-josef@toxicpanda.com Signed-off-by: Josef Bacik <josef@toxicpanda.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Jan Kara <jack@suse.cz> Tested-by: syzbot+b437b5a429d680cf2217@syzkaller.appspotmail.com Cc: Dave Chinner <david@fromorbit.com> Cc: Rik van Riel <riel@redhat.com> Cc: Tejun Heo <tj@kernel.org> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-13 18:44:22 +00:00
if (fpin)
fput(fpin);
return ret | VM_FAULT_RETRY;
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);
static bool filemap_map_pmd(struct vm_fault *vmf, struct folio *folio,
pgoff_t start)
{
struct mm_struct *mm = vmf->vma->vm_mm;
/* Huge page is mapped? No need to proceed. */
if (pmd_trans_huge(*vmf->pmd)) {
folio_unlock(folio);
folio_put(folio);
return true;
}
if (pmd_none(*vmf->pmd) && folio_test_pmd_mappable(folio)) {
struct page *page = folio_file_page(folio, start);
mm: filemap: coding style cleanup for filemap_map_pmd() Patch series "Solve silent data loss caused by poisoned page cache (shmem/tmpfs)", v5. When discussing the patch that splits page cache THP in order to offline the poisoned page, Noaya mentioned there is a bigger problem [1] that prevents this from working since the page cache page will be truncated if uncorrectable errors happen. By looking this deeper it turns out this approach (truncating poisoned page) may incur silent data loss for all non-readonly filesystems if the page is dirty. It may be worse for in-memory filesystem, e.g. shmem/tmpfs since the data blocks are actually gone. To solve this problem we could keep the poisoned dirty page in page cache then notify the users on any later access, e.g. page fault, read/write, etc. The clean page could be truncated as is since they can be reread from disk later on. The consequence is the filesystems may find poisoned page and manipulate it as healthy page since all the filesystems actually don't check if the page is poisoned or not in all the relevant paths except page fault. In general, we need make the filesystems be aware of poisoned page before we could keep the poisoned page in page cache in order to solve the data loss problem. To make filesystems be aware of poisoned page we should consider: - The page should be not written back: clearing dirty flag could prevent from writeback. - The page should not be dropped (it shows as a clean page) by drop caches or other callers: the refcount pin from hwpoison could prevent from invalidating (called by cache drop, inode cache shrinking, etc), but it doesn't avoid invalidation in DIO path. - The page should be able to get truncated/hole punched/unlinked: it works as it is. - Notify users when the page is accessed, e.g. read/write, page fault and other paths (compression, encryption, etc). The scope of the last one is huge since almost all filesystems need do it once a page is returned from page cache lookup. There are a couple of options to do it: 1. Check hwpoison flag for every path, the most straightforward way. 2. Return NULL for poisoned page from page cache lookup, the most callsites check if NULL is returned, this should have least work I think. But the error handling in filesystems just return -ENOMEM, the error code will incur confusion to the users obviously. 3. To improve #2, we could return error pointer, e.g. ERR_PTR(-EIO), but this will involve significant amount of code change as well since all the paths need check if the pointer is ERR or not just like option #1. I did prototypes for both #1 and #3, but it seems #3 may require more changes than #1. For #3 ERR_PTR will be returned so all the callers need to check the return value otherwise invalid pointer may be dereferenced, but not all callers really care about the content of the page, for example, partial truncate which just sets the truncated range in one page to 0. So for such paths it needs additional modification if ERR_PTR is returned. And if the callers have their own way to handle the problematic pages we need to add a new FGP flag to tell FGP functions to return the pointer to the page. It may happen very rarely, but once it happens the consequence (data corruption) could be very bad and it is very hard to debug. It seems this problem had been slightly discussed before, but seems no action was taken at that time. [2] As the aforementioned investigation, it needs huge amount of work to solve the potential data loss for all filesystems. But it is much easier for in-memory filesystems and such filesystems actually suffer more than others since even the data blocks are gone due to truncating. So this patchset starts from shmem/tmpfs by taking option #1. TODO: * The unpoison has been broken since commit 0ed950d1f281 ("mm,hwpoison: make get_hwpoison_page() call get_any_page()"), and this patch series make refcount check for unpoisoning shmem page fail. * Expand to other filesystems. But I haven't heard feedback from filesystem developers yet. Patch breakdown: Patch #1: cleanup, depended by patch #2 Patch #2: fix THP with hwpoisoned subpage(s) PMD map bug Patch #3: coding style cleanup Patch #4: refactor and preparation. Patch #5: keep the poisoned page in page cache and handle such case for all the paths. Patch #6: the previous patches unblock page cache THP split, so this patch add page cache THP split support. This patch (of 4): A minor cleanup to the indent. Link: https://lkml.kernel.org/r/20211020210755.23964-1-shy828301@gmail.com Link: https://lkml.kernel.org/r/20211020210755.23964-4-shy828301@gmail.com Signed-off-by: Yang Shi <shy828301@gmail.com> Reviewed-by: Naoya Horiguchi <naoya.horiguchi@nec.com> Cc: Hugh Dickins <hughd@google.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Oscar Salvador <osalvador@suse.de> Cc: Peter Xu <peterx@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-11-05 20:41:04 +00:00
vm_fault_t ret = do_set_pmd(vmf, page);
if (!ret) {
/* The page is mapped successfully, reference consumed. */
folio_unlock(folio);
mm: filemap: coding style cleanup for filemap_map_pmd() Patch series "Solve silent data loss caused by poisoned page cache (shmem/tmpfs)", v5. When discussing the patch that splits page cache THP in order to offline the poisoned page, Noaya mentioned there is a bigger problem [1] that prevents this from working since the page cache page will be truncated if uncorrectable errors happen. By looking this deeper it turns out this approach (truncating poisoned page) may incur silent data loss for all non-readonly filesystems if the page is dirty. It may be worse for in-memory filesystem, e.g. shmem/tmpfs since the data blocks are actually gone. To solve this problem we could keep the poisoned dirty page in page cache then notify the users on any later access, e.g. page fault, read/write, etc. The clean page could be truncated as is since they can be reread from disk later on. The consequence is the filesystems may find poisoned page and manipulate it as healthy page since all the filesystems actually don't check if the page is poisoned or not in all the relevant paths except page fault. In general, we need make the filesystems be aware of poisoned page before we could keep the poisoned page in page cache in order to solve the data loss problem. To make filesystems be aware of poisoned page we should consider: - The page should be not written back: clearing dirty flag could prevent from writeback. - The page should not be dropped (it shows as a clean page) by drop caches or other callers: the refcount pin from hwpoison could prevent from invalidating (called by cache drop, inode cache shrinking, etc), but it doesn't avoid invalidation in DIO path. - The page should be able to get truncated/hole punched/unlinked: it works as it is. - Notify users when the page is accessed, e.g. read/write, page fault and other paths (compression, encryption, etc). The scope of the last one is huge since almost all filesystems need do it once a page is returned from page cache lookup. There are a couple of options to do it: 1. Check hwpoison flag for every path, the most straightforward way. 2. Return NULL for poisoned page from page cache lookup, the most callsites check if NULL is returned, this should have least work I think. But the error handling in filesystems just return -ENOMEM, the error code will incur confusion to the users obviously. 3. To improve #2, we could return error pointer, e.g. ERR_PTR(-EIO), but this will involve significant amount of code change as well since all the paths need check if the pointer is ERR or not just like option #1. I did prototypes for both #1 and #3, but it seems #3 may require more changes than #1. For #3 ERR_PTR will be returned so all the callers need to check the return value otherwise invalid pointer may be dereferenced, but not all callers really care about the content of the page, for example, partial truncate which just sets the truncated range in one page to 0. So for such paths it needs additional modification if ERR_PTR is returned. And if the callers have their own way to handle the problematic pages we need to add a new FGP flag to tell FGP functions to return the pointer to the page. It may happen very rarely, but once it happens the consequence (data corruption) could be very bad and it is very hard to debug. It seems this problem had been slightly discussed before, but seems no action was taken at that time. [2] As the aforementioned investigation, it needs huge amount of work to solve the potential data loss for all filesystems. But it is much easier for in-memory filesystems and such filesystems actually suffer more than others since even the data blocks are gone due to truncating. So this patchset starts from shmem/tmpfs by taking option #1. TODO: * The unpoison has been broken since commit 0ed950d1f281 ("mm,hwpoison: make get_hwpoison_page() call get_any_page()"), and this patch series make refcount check for unpoisoning shmem page fail. * Expand to other filesystems. But I haven't heard feedback from filesystem developers yet. Patch breakdown: Patch #1: cleanup, depended by patch #2 Patch #2: fix THP with hwpoisoned subpage(s) PMD map bug Patch #3: coding style cleanup Patch #4: refactor and preparation. Patch #5: keep the poisoned page in page cache and handle such case for all the paths. Patch #6: the previous patches unblock page cache THP split, so this patch add page cache THP split support. This patch (of 4): A minor cleanup to the indent. Link: https://lkml.kernel.org/r/20211020210755.23964-1-shy828301@gmail.com Link: https://lkml.kernel.org/r/20211020210755.23964-4-shy828301@gmail.com Signed-off-by: Yang Shi <shy828301@gmail.com> Reviewed-by: Naoya Horiguchi <naoya.horiguchi@nec.com> Cc: Hugh Dickins <hughd@google.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Oscar Salvador <osalvador@suse.de> Cc: Peter Xu <peterx@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-11-05 20:41:04 +00:00
return true;
}
}
mm: fix oops when filemap_map_pmd() without prealloc_pte syzbot reports oops in lockdep's __lock_acquire(), called from __pte_offset_map_lock() called from filemap_map_pages(); or when I run the repro, the oops comes in pmd_install(), called from filemap_map_pmd() called from filemap_map_pages(), just before the __pte_offset_map_lock(). The problem is that filemap_map_pmd() has been assuming that when it finds pmd_none(), a page table has already been prepared in prealloc_pte; and indeed do_fault_around() has been careful to preallocate one there, when it finds pmd_none(): but what if *pmd became none in between? My 6.6 mods in mm/khugepaged.c, avoiding mmap_lock for write, have made it easy for *pmd to be cleared while servicing a page fault; but even before those, a huge *pmd might be zapped while a fault is serviced. The difference in symptomatic stack traces comes from the "memory model" in use: pmd_install() uses pmd_populate() uses page_to_pfn(): in some models that is strict, and will oops on the NULL prealloc_pte; in other models, it will construct a bogus value to be populated into *pmd, then __pte_offset_map_lock() oops when trying to access split ptlock pointer (or some other symptom in normal case of ptlock embedded not pointer). Link: https://lore.kernel.org/linux-mm/20231115065506.19780-1-jose.pekkarinen@foxhound.fi/ Link: https://lkml.kernel.org/r/6ed0c50c-78ef-0719-b3c5-60c0c010431c@google.com Fixes: f9ce0be71d1f ("mm: Cleanup faultaround and finish_fault() codepaths") Signed-off-by: Hugh Dickins <hughd@google.com> Reported-and-tested-by: syzbot+89edd67979b52675ddec@syzkaller.appspotmail.com Closes: https://lore.kernel.org/linux-mm/0000000000005e44550608a0806c@google.com/ Reviewed-by: David Hildenbrand <david@redhat.com> Cc: Jann Horn <jannh@google.com>, Cc: José Pekkarinen <jose.pekkarinen@foxhound.fi> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: <stable@vger.kernel.org> [5.12+] Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-11-17 08:49:18 +00:00
if (pmd_none(*vmf->pmd) && vmf->prealloc_pte)
pmd_install(mm, vmf->pmd, &vmf->prealloc_pte);
return false;
}
static struct folio *next_uptodate_folio(struct xa_state *xas,
struct address_space *mapping, pgoff_t end_pgoff)
{
struct folio *folio = xas_next_entry(xas, end_pgoff);
unsigned long max_idx;
do {
if (!folio)
return NULL;
if (xas_retry(xas, folio))
continue;
if (xa_is_value(folio))
continue;
if (folio_test_locked(folio))
continue;
if (!folio_try_get_rcu(folio))
continue;
/* Has the page moved or been split? */
if (unlikely(folio != xas_reload(xas)))
goto skip;
if (!folio_test_uptodate(folio) || folio_test_readahead(folio))
goto skip;
if (!folio_trylock(folio))
goto skip;
if (folio->mapping != mapping)
goto unlock;
if (!folio_test_uptodate(folio))
goto unlock;
max_idx = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE);
if (xas->xa_index >= max_idx)
goto unlock;
return folio;
unlock:
folio_unlock(folio);
skip:
folio_put(folio);
} while ((folio = xas_next_entry(xas, end_pgoff)) != NULL);
return NULL;
}
/*
* Map page range [start_page, start_page + nr_pages) of folio.
* start_page is gotten from start by folio_page(folio, start)
*/
static vm_fault_t filemap_map_folio_range(struct vm_fault *vmf,
struct folio *folio, unsigned long start,
filemap: add filemap_map_order0_folio() to handle order0 folio Kernel test robot reported regressions for several benchmarks [1]. The regression are related with commit: de74976eb65151a2f568e477fc2e0032df5b22b4 ("filemap: add filemap_map_folio_range()") It turned out that function filemap_map_folio_range() brings these regressions when handle folio with order0. Add filemap_map_order0_folio() to handle order0 folio. The benefit come from two perspectives: - the code size is smaller (around 126 bytes) - no loop Testing showed the regressions reported by 0day [1] all are fixed: commit 9f1f5b60e76d44fa: parent commit of de74976eb65151a2 commit fbdf9263a3d7fdbd: latest mm-unstable commit commit 7fbfe2003f84686d: this fixing patch 9f1f5b60e76d44fa fbdf9263a3d7fdbd 7fbfe2003f84686d ---------------- --------------------------- --------------------------- 3843810 -21.4% 3020268 +4.6% 4018708 stress-ng.bad-altstack.ops 64061 -21.4% 50336 +4.6% 66977 stress-ng.bad-altstack.ops_per_sec 1709026 -14.4% 1462102 +2.4% 1750757 stress-ng.fork.ops 28483 -14.4% 24368 +2.4% 29179 stress-ng.fork.ops_per_sec 3685088 -53.6% 1710976 +0.5% 3702454 stress-ng.zombie.ops 56732 -65.3% 19667 +0.7% 57107 stress-ng.zombie.ops_per_sec 61874 -12.1% 54416 +0.4% 62136 vm-scalability.median 13527663 -11.7% 11942117 -0.1% 13513946 vm-scalability.throughput 4.066e+09 -11.7% 3.59e+09 -0.1% 4.061e+09 vm-scalability.workload [1]: https://lore.kernel.org/oe-lkp/72e017b9-deb6-44fa-91d6-716ee2c39cbc@intel.com/T/#m7d2bba30f75a9cee8eab07e5809abd9b3b206c84 Link: https://lkml.kernel.org/r/20230914134741.1937654-1-fengwei.yin@intel.com Fixes: de74976eb65151a2f568e477fc2e0032df5b22b4 ("filemap: add filemap_map_folio_range()") Signed-off-by: Yin Fengwei <fengwei.yin@intel.com> Reported-by: kernel test robot <oliver.sang@intel.com> Closes: https://lore.kernel.org/oe-lkp/202309111556.b2aa3d7a-oliver.sang@intel.com Cc: Feng Tang <feng.tang@intel.com> Cc: Huang Ying <ying.huang@intel.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-09-14 13:47:41 +00:00
unsigned long addr, unsigned int nr_pages,
unsigned long *rss, unsigned int *mmap_miss)
{
vm_fault_t ret = 0;
struct page *page = folio_page(folio, start);
unsigned int count = 0;
pte_t *old_ptep = vmf->pte;
do {
if (PageHWPoison(page + count))
goto skip;
/*
* If there are too many folios that are recently evicted
* in a file, they will probably continue to be evicted.
* In such situation, read-ahead is only a waste of IO.
* Don't decrease mmap_miss in this scenario to make sure
* we can stop read-ahead.
*/
if (!folio_test_workingset(folio))
(*mmap_miss)++;
/*
* NOTE: If there're PTE markers, we'll leave them to be
* handled in the specific fault path, and it'll prohibit the
* fault-around logic.
*/
if (!pte_none(ptep_get(&vmf->pte[count])))
goto skip;
count++;
continue;
skip:
if (count) {
set_pte_range(vmf, folio, page, count, addr);
*rss += count;
folio_ref_add(folio, count);
if (in_range(vmf->address, addr, count * PAGE_SIZE))
ret = VM_FAULT_NOPAGE;
}
count++;
page += count;
vmf->pte += count;
addr += count * PAGE_SIZE;
count = 0;
} while (--nr_pages > 0);
if (count) {
set_pte_range(vmf, folio, page, count, addr);
*rss += count;
folio_ref_add(folio, count);
if (in_range(vmf->address, addr, count * PAGE_SIZE))
ret = VM_FAULT_NOPAGE;
}
vmf->pte = old_ptep;
filemap: add filemap_map_order0_folio() to handle order0 folio Kernel test robot reported regressions for several benchmarks [1]. The regression are related with commit: de74976eb65151a2f568e477fc2e0032df5b22b4 ("filemap: add filemap_map_folio_range()") It turned out that function filemap_map_folio_range() brings these regressions when handle folio with order0. Add filemap_map_order0_folio() to handle order0 folio. The benefit come from two perspectives: - the code size is smaller (around 126 bytes) - no loop Testing showed the regressions reported by 0day [1] all are fixed: commit 9f1f5b60e76d44fa: parent commit of de74976eb65151a2 commit fbdf9263a3d7fdbd: latest mm-unstable commit commit 7fbfe2003f84686d: this fixing patch 9f1f5b60e76d44fa fbdf9263a3d7fdbd 7fbfe2003f84686d ---------------- --------------------------- --------------------------- 3843810 -21.4% 3020268 +4.6% 4018708 stress-ng.bad-altstack.ops 64061 -21.4% 50336 +4.6% 66977 stress-ng.bad-altstack.ops_per_sec 1709026 -14.4% 1462102 +2.4% 1750757 stress-ng.fork.ops 28483 -14.4% 24368 +2.4% 29179 stress-ng.fork.ops_per_sec 3685088 -53.6% 1710976 +0.5% 3702454 stress-ng.zombie.ops 56732 -65.3% 19667 +0.7% 57107 stress-ng.zombie.ops_per_sec 61874 -12.1% 54416 +0.4% 62136 vm-scalability.median 13527663 -11.7% 11942117 -0.1% 13513946 vm-scalability.throughput 4.066e+09 -11.7% 3.59e+09 -0.1% 4.061e+09 vm-scalability.workload [1]: https://lore.kernel.org/oe-lkp/72e017b9-deb6-44fa-91d6-716ee2c39cbc@intel.com/T/#m7d2bba30f75a9cee8eab07e5809abd9b3b206c84 Link: https://lkml.kernel.org/r/20230914134741.1937654-1-fengwei.yin@intel.com Fixes: de74976eb65151a2f568e477fc2e0032df5b22b4 ("filemap: add filemap_map_folio_range()") Signed-off-by: Yin Fengwei <fengwei.yin@intel.com> Reported-by: kernel test robot <oliver.sang@intel.com> Closes: https://lore.kernel.org/oe-lkp/202309111556.b2aa3d7a-oliver.sang@intel.com Cc: Feng Tang <feng.tang@intel.com> Cc: Huang Ying <ying.huang@intel.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-09-14 13:47:41 +00:00
return ret;
}
static vm_fault_t filemap_map_order0_folio(struct vm_fault *vmf,
struct folio *folio, unsigned long addr,
unsigned long *rss, unsigned int *mmap_miss)
filemap: add filemap_map_order0_folio() to handle order0 folio Kernel test robot reported regressions for several benchmarks [1]. The regression are related with commit: de74976eb65151a2f568e477fc2e0032df5b22b4 ("filemap: add filemap_map_folio_range()") It turned out that function filemap_map_folio_range() brings these regressions when handle folio with order0. Add filemap_map_order0_folio() to handle order0 folio. The benefit come from two perspectives: - the code size is smaller (around 126 bytes) - no loop Testing showed the regressions reported by 0day [1] all are fixed: commit 9f1f5b60e76d44fa: parent commit of de74976eb65151a2 commit fbdf9263a3d7fdbd: latest mm-unstable commit commit 7fbfe2003f84686d: this fixing patch 9f1f5b60e76d44fa fbdf9263a3d7fdbd 7fbfe2003f84686d ---------------- --------------------------- --------------------------- 3843810 -21.4% 3020268 +4.6% 4018708 stress-ng.bad-altstack.ops 64061 -21.4% 50336 +4.6% 66977 stress-ng.bad-altstack.ops_per_sec 1709026 -14.4% 1462102 +2.4% 1750757 stress-ng.fork.ops 28483 -14.4% 24368 +2.4% 29179 stress-ng.fork.ops_per_sec 3685088 -53.6% 1710976 +0.5% 3702454 stress-ng.zombie.ops 56732 -65.3% 19667 +0.7% 57107 stress-ng.zombie.ops_per_sec 61874 -12.1% 54416 +0.4% 62136 vm-scalability.median 13527663 -11.7% 11942117 -0.1% 13513946 vm-scalability.throughput 4.066e+09 -11.7% 3.59e+09 -0.1% 4.061e+09 vm-scalability.workload [1]: https://lore.kernel.org/oe-lkp/72e017b9-deb6-44fa-91d6-716ee2c39cbc@intel.com/T/#m7d2bba30f75a9cee8eab07e5809abd9b3b206c84 Link: https://lkml.kernel.org/r/20230914134741.1937654-1-fengwei.yin@intel.com Fixes: de74976eb65151a2f568e477fc2e0032df5b22b4 ("filemap: add filemap_map_folio_range()") Signed-off-by: Yin Fengwei <fengwei.yin@intel.com> Reported-by: kernel test robot <oliver.sang@intel.com> Closes: https://lore.kernel.org/oe-lkp/202309111556.b2aa3d7a-oliver.sang@intel.com Cc: Feng Tang <feng.tang@intel.com> Cc: Huang Ying <ying.huang@intel.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-09-14 13:47:41 +00:00
{
vm_fault_t ret = 0;
struct page *page = &folio->page;
if (PageHWPoison(page))
return ret;
/* See comment of filemap_map_folio_range() */
if (!folio_test_workingset(folio))
(*mmap_miss)++;
filemap: add filemap_map_order0_folio() to handle order0 folio Kernel test robot reported regressions for several benchmarks [1]. The regression are related with commit: de74976eb65151a2f568e477fc2e0032df5b22b4 ("filemap: add filemap_map_folio_range()") It turned out that function filemap_map_folio_range() brings these regressions when handle folio with order0. Add filemap_map_order0_folio() to handle order0 folio. The benefit come from two perspectives: - the code size is smaller (around 126 bytes) - no loop Testing showed the regressions reported by 0day [1] all are fixed: commit 9f1f5b60e76d44fa: parent commit of de74976eb65151a2 commit fbdf9263a3d7fdbd: latest mm-unstable commit commit 7fbfe2003f84686d: this fixing patch 9f1f5b60e76d44fa fbdf9263a3d7fdbd 7fbfe2003f84686d ---------------- --------------------------- --------------------------- 3843810 -21.4% 3020268 +4.6% 4018708 stress-ng.bad-altstack.ops 64061 -21.4% 50336 +4.6% 66977 stress-ng.bad-altstack.ops_per_sec 1709026 -14.4% 1462102 +2.4% 1750757 stress-ng.fork.ops 28483 -14.4% 24368 +2.4% 29179 stress-ng.fork.ops_per_sec 3685088 -53.6% 1710976 +0.5% 3702454 stress-ng.zombie.ops 56732 -65.3% 19667 +0.7% 57107 stress-ng.zombie.ops_per_sec 61874 -12.1% 54416 +0.4% 62136 vm-scalability.median 13527663 -11.7% 11942117 -0.1% 13513946 vm-scalability.throughput 4.066e+09 -11.7% 3.59e+09 -0.1% 4.061e+09 vm-scalability.workload [1]: https://lore.kernel.org/oe-lkp/72e017b9-deb6-44fa-91d6-716ee2c39cbc@intel.com/T/#m7d2bba30f75a9cee8eab07e5809abd9b3b206c84 Link: https://lkml.kernel.org/r/20230914134741.1937654-1-fengwei.yin@intel.com Fixes: de74976eb65151a2f568e477fc2e0032df5b22b4 ("filemap: add filemap_map_folio_range()") Signed-off-by: Yin Fengwei <fengwei.yin@intel.com> Reported-by: kernel test robot <oliver.sang@intel.com> Closes: https://lore.kernel.org/oe-lkp/202309111556.b2aa3d7a-oliver.sang@intel.com Cc: Feng Tang <feng.tang@intel.com> Cc: Huang Ying <ying.huang@intel.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-09-14 13:47:41 +00:00
/*
* NOTE: If there're PTE markers, we'll leave them to be
* handled in the specific fault path, and it'll prohibit
* the fault-around logic.
*/
if (!pte_none(ptep_get(vmf->pte)))
return ret;
if (vmf->address == addr)
ret = VM_FAULT_NOPAGE;
set_pte_range(vmf, folio, page, 1, addr);
(*rss)++;
filemap: add filemap_map_order0_folio() to handle order0 folio Kernel test robot reported regressions for several benchmarks [1]. The regression are related with commit: de74976eb65151a2f568e477fc2e0032df5b22b4 ("filemap: add filemap_map_folio_range()") It turned out that function filemap_map_folio_range() brings these regressions when handle folio with order0. Add filemap_map_order0_folio() to handle order0 folio. The benefit come from two perspectives: - the code size is smaller (around 126 bytes) - no loop Testing showed the regressions reported by 0day [1] all are fixed: commit 9f1f5b60e76d44fa: parent commit of de74976eb65151a2 commit fbdf9263a3d7fdbd: latest mm-unstable commit commit 7fbfe2003f84686d: this fixing patch 9f1f5b60e76d44fa fbdf9263a3d7fdbd 7fbfe2003f84686d ---------------- --------------------------- --------------------------- 3843810 -21.4% 3020268 +4.6% 4018708 stress-ng.bad-altstack.ops 64061 -21.4% 50336 +4.6% 66977 stress-ng.bad-altstack.ops_per_sec 1709026 -14.4% 1462102 +2.4% 1750757 stress-ng.fork.ops 28483 -14.4% 24368 +2.4% 29179 stress-ng.fork.ops_per_sec 3685088 -53.6% 1710976 +0.5% 3702454 stress-ng.zombie.ops 56732 -65.3% 19667 +0.7% 57107 stress-ng.zombie.ops_per_sec 61874 -12.1% 54416 +0.4% 62136 vm-scalability.median 13527663 -11.7% 11942117 -0.1% 13513946 vm-scalability.throughput 4.066e+09 -11.7% 3.59e+09 -0.1% 4.061e+09 vm-scalability.workload [1]: https://lore.kernel.org/oe-lkp/72e017b9-deb6-44fa-91d6-716ee2c39cbc@intel.com/T/#m7d2bba30f75a9cee8eab07e5809abd9b3b206c84 Link: https://lkml.kernel.org/r/20230914134741.1937654-1-fengwei.yin@intel.com Fixes: de74976eb65151a2f568e477fc2e0032df5b22b4 ("filemap: add filemap_map_folio_range()") Signed-off-by: Yin Fengwei <fengwei.yin@intel.com> Reported-by: kernel test robot <oliver.sang@intel.com> Closes: https://lore.kernel.org/oe-lkp/202309111556.b2aa3d7a-oliver.sang@intel.com Cc: Feng Tang <feng.tang@intel.com> Cc: Huang Ying <ying.huang@intel.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-09-14 13:47:41 +00:00
folio_ref_inc(folio);
return ret;
}
vm_fault_t filemap_map_pages(struct vm_fault *vmf,
pgoff_t start_pgoff, pgoff_t end_pgoff)
{
struct vm_area_struct *vma = vmf->vma;
struct file *file = vma->vm_file;
struct address_space *mapping = file->f_mapping;
pgoff_t last_pgoff = start_pgoff;
unsigned long addr;
XA_STATE(xas, &mapping->i_pages, start_pgoff);
struct folio *folio;
vm_fault_t ret = 0;
unsigned long rss = 0;
unsigned int nr_pages = 0, mmap_miss = 0, mmap_miss_saved, folio_type;
rcu_read_lock();
folio = next_uptodate_folio(&xas, mapping, end_pgoff);
if (!folio)
goto out;
if (filemap_map_pmd(vmf, folio, start_pgoff)) {
ret = VM_FAULT_NOPAGE;
goto out;
}
addr = vma->vm_start + ((start_pgoff - vma->vm_pgoff) << PAGE_SHIFT);
vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, addr, &vmf->ptl);
mm/filemap: allow pte_offset_map_lock() to fail filemap_map_pages() allow pte_offset_map_lock() to fail; and remove the pmd_devmap_trans_unstable() check from filemap_map_pmd(), which can safely return to filemap_map_pages() and let pte_offset_map_lock() discover that. Link: https://lkml.kernel.org/r/54607cf4-ddb6-7ef3-043-1d2de1a9a71@google.com Signed-off-by: Hugh Dickins <hughd@google.com> Cc: Alistair Popple <apopple@nvidia.com> Cc: Anshuman Khandual <anshuman.khandual@arm.com> Cc: Axel Rasmussen <axelrasmussen@google.com> Cc: Christophe Leroy <christophe.leroy@csgroup.eu> Cc: Christoph Hellwig <hch@infradead.org> Cc: David Hildenbrand <david@redhat.com> Cc: "Huang, Ying" <ying.huang@intel.com> Cc: Ira Weiny <ira.weiny@intel.com> Cc: Jason Gunthorpe <jgg@ziepe.ca> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Lorenzo Stoakes <lstoakes@gmail.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Mike Rapoport (IBM) <rppt@kernel.org> Cc: Minchan Kim <minchan@kernel.org> Cc: Naoya Horiguchi <naoya.horiguchi@nec.com> Cc: Pavel Tatashin <pasha.tatashin@soleen.com> Cc: Peter Xu <peterx@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Qi Zheng <zhengqi.arch@bytedance.com> Cc: Ralph Campbell <rcampbell@nvidia.com> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: SeongJae Park <sj@kernel.org> Cc: Song Liu <song@kernel.org> Cc: Steven Price <steven.price@arm.com> Cc: Suren Baghdasaryan <surenb@google.com> Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com> Cc: Will Deacon <will@kernel.org> Cc: Yang Shi <shy828301@gmail.com> Cc: Yu Zhao <yuzhao@google.com> Cc: Zack Rusin <zackr@vmware.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-06-09 01:11:29 +00:00
if (!vmf->pte) {
folio_unlock(folio);
folio_put(folio);
goto out;
}
folio_type = mm_counter_file(folio);
do {
unsigned long end;
addr += (xas.xa_index - last_pgoff) << PAGE_SHIFT;
vmf->pte += xas.xa_index - last_pgoff;
last_pgoff = xas.xa_index;
end = folio_next_index(folio) - 1;
nr_pages = min(end, end_pgoff) - xas.xa_index + 1;
filemap: add filemap_map_order0_folio() to handle order0 folio Kernel test robot reported regressions for several benchmarks [1]. The regression are related with commit: de74976eb65151a2f568e477fc2e0032df5b22b4 ("filemap: add filemap_map_folio_range()") It turned out that function filemap_map_folio_range() brings these regressions when handle folio with order0. Add filemap_map_order0_folio() to handle order0 folio. The benefit come from two perspectives: - the code size is smaller (around 126 bytes) - no loop Testing showed the regressions reported by 0day [1] all are fixed: commit 9f1f5b60e76d44fa: parent commit of de74976eb65151a2 commit fbdf9263a3d7fdbd: latest mm-unstable commit commit 7fbfe2003f84686d: this fixing patch 9f1f5b60e76d44fa fbdf9263a3d7fdbd 7fbfe2003f84686d ---------------- --------------------------- --------------------------- 3843810 -21.4% 3020268 +4.6% 4018708 stress-ng.bad-altstack.ops 64061 -21.4% 50336 +4.6% 66977 stress-ng.bad-altstack.ops_per_sec 1709026 -14.4% 1462102 +2.4% 1750757 stress-ng.fork.ops 28483 -14.4% 24368 +2.4% 29179 stress-ng.fork.ops_per_sec 3685088 -53.6% 1710976 +0.5% 3702454 stress-ng.zombie.ops 56732 -65.3% 19667 +0.7% 57107 stress-ng.zombie.ops_per_sec 61874 -12.1% 54416 +0.4% 62136 vm-scalability.median 13527663 -11.7% 11942117 -0.1% 13513946 vm-scalability.throughput 4.066e+09 -11.7% 3.59e+09 -0.1% 4.061e+09 vm-scalability.workload [1]: https://lore.kernel.org/oe-lkp/72e017b9-deb6-44fa-91d6-716ee2c39cbc@intel.com/T/#m7d2bba30f75a9cee8eab07e5809abd9b3b206c84 Link: https://lkml.kernel.org/r/20230914134741.1937654-1-fengwei.yin@intel.com Fixes: de74976eb65151a2f568e477fc2e0032df5b22b4 ("filemap: add filemap_map_folio_range()") Signed-off-by: Yin Fengwei <fengwei.yin@intel.com> Reported-by: kernel test robot <oliver.sang@intel.com> Closes: https://lore.kernel.org/oe-lkp/202309111556.b2aa3d7a-oliver.sang@intel.com Cc: Feng Tang <feng.tang@intel.com> Cc: Huang Ying <ying.huang@intel.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-09-14 13:47:41 +00:00
if (!folio_test_large(folio))
ret |= filemap_map_order0_folio(vmf,
folio, addr, &rss, &mmap_miss);
filemap: add filemap_map_order0_folio() to handle order0 folio Kernel test robot reported regressions for several benchmarks [1]. The regression are related with commit: de74976eb65151a2f568e477fc2e0032df5b22b4 ("filemap: add filemap_map_folio_range()") It turned out that function filemap_map_folio_range() brings these regressions when handle folio with order0. Add filemap_map_order0_folio() to handle order0 folio. The benefit come from two perspectives: - the code size is smaller (around 126 bytes) - no loop Testing showed the regressions reported by 0day [1] all are fixed: commit 9f1f5b60e76d44fa: parent commit of de74976eb65151a2 commit fbdf9263a3d7fdbd: latest mm-unstable commit commit 7fbfe2003f84686d: this fixing patch 9f1f5b60e76d44fa fbdf9263a3d7fdbd 7fbfe2003f84686d ---------------- --------------------------- --------------------------- 3843810 -21.4% 3020268 +4.6% 4018708 stress-ng.bad-altstack.ops 64061 -21.4% 50336 +4.6% 66977 stress-ng.bad-altstack.ops_per_sec 1709026 -14.4% 1462102 +2.4% 1750757 stress-ng.fork.ops 28483 -14.4% 24368 +2.4% 29179 stress-ng.fork.ops_per_sec 3685088 -53.6% 1710976 +0.5% 3702454 stress-ng.zombie.ops 56732 -65.3% 19667 +0.7% 57107 stress-ng.zombie.ops_per_sec 61874 -12.1% 54416 +0.4% 62136 vm-scalability.median 13527663 -11.7% 11942117 -0.1% 13513946 vm-scalability.throughput 4.066e+09 -11.7% 3.59e+09 -0.1% 4.061e+09 vm-scalability.workload [1]: https://lore.kernel.org/oe-lkp/72e017b9-deb6-44fa-91d6-716ee2c39cbc@intel.com/T/#m7d2bba30f75a9cee8eab07e5809abd9b3b206c84 Link: https://lkml.kernel.org/r/20230914134741.1937654-1-fengwei.yin@intel.com Fixes: de74976eb65151a2f568e477fc2e0032df5b22b4 ("filemap: add filemap_map_folio_range()") Signed-off-by: Yin Fengwei <fengwei.yin@intel.com> Reported-by: kernel test robot <oliver.sang@intel.com> Closes: https://lore.kernel.org/oe-lkp/202309111556.b2aa3d7a-oliver.sang@intel.com Cc: Feng Tang <feng.tang@intel.com> Cc: Huang Ying <ying.huang@intel.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-09-14 13:47:41 +00:00
else
ret |= filemap_map_folio_range(vmf, folio,
xas.xa_index - folio->index, addr,
nr_pages, &rss, &mmap_miss);
2020-11-24 18:48:26 +00:00
folio_unlock(folio);
folio_put(folio);
filemap: add filemap_map_order0_folio() to handle order0 folio Kernel test robot reported regressions for several benchmarks [1]. The regression are related with commit: de74976eb65151a2f568e477fc2e0032df5b22b4 ("filemap: add filemap_map_folio_range()") It turned out that function filemap_map_folio_range() brings these regressions when handle folio with order0. Add filemap_map_order0_folio() to handle order0 folio. The benefit come from two perspectives: - the code size is smaller (around 126 bytes) - no loop Testing showed the regressions reported by 0day [1] all are fixed: commit 9f1f5b60e76d44fa: parent commit of de74976eb65151a2 commit fbdf9263a3d7fdbd: latest mm-unstable commit commit 7fbfe2003f84686d: this fixing patch 9f1f5b60e76d44fa fbdf9263a3d7fdbd 7fbfe2003f84686d ---------------- --------------------------- --------------------------- 3843810 -21.4% 3020268 +4.6% 4018708 stress-ng.bad-altstack.ops 64061 -21.4% 50336 +4.6% 66977 stress-ng.bad-altstack.ops_per_sec 1709026 -14.4% 1462102 +2.4% 1750757 stress-ng.fork.ops 28483 -14.4% 24368 +2.4% 29179 stress-ng.fork.ops_per_sec 3685088 -53.6% 1710976 +0.5% 3702454 stress-ng.zombie.ops 56732 -65.3% 19667 +0.7% 57107 stress-ng.zombie.ops_per_sec 61874 -12.1% 54416 +0.4% 62136 vm-scalability.median 13527663 -11.7% 11942117 -0.1% 13513946 vm-scalability.throughput 4.066e+09 -11.7% 3.59e+09 -0.1% 4.061e+09 vm-scalability.workload [1]: https://lore.kernel.org/oe-lkp/72e017b9-deb6-44fa-91d6-716ee2c39cbc@intel.com/T/#m7d2bba30f75a9cee8eab07e5809abd9b3b206c84 Link: https://lkml.kernel.org/r/20230914134741.1937654-1-fengwei.yin@intel.com Fixes: de74976eb65151a2f568e477fc2e0032df5b22b4 ("filemap: add filemap_map_folio_range()") Signed-off-by: Yin Fengwei <fengwei.yin@intel.com> Reported-by: kernel test robot <oliver.sang@intel.com> Closes: https://lore.kernel.org/oe-lkp/202309111556.b2aa3d7a-oliver.sang@intel.com Cc: Feng Tang <feng.tang@intel.com> Cc: Huang Ying <ying.huang@intel.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-09-14 13:47:41 +00:00
} while ((folio = next_uptodate_folio(&xas, mapping, end_pgoff)) != NULL);
add_mm_counter(vma->vm_mm, folio_type, rss);
pte_unmap_unlock(vmf->pte, vmf->ptl);
out:
rcu_read_unlock();
filemap: add filemap_map_order0_folio() to handle order0 folio Kernel test robot reported regressions for several benchmarks [1]. The regression are related with commit: de74976eb65151a2f568e477fc2e0032df5b22b4 ("filemap: add filemap_map_folio_range()") It turned out that function filemap_map_folio_range() brings these regressions when handle folio with order0. Add filemap_map_order0_folio() to handle order0 folio. The benefit come from two perspectives: - the code size is smaller (around 126 bytes) - no loop Testing showed the regressions reported by 0day [1] all are fixed: commit 9f1f5b60e76d44fa: parent commit of de74976eb65151a2 commit fbdf9263a3d7fdbd: latest mm-unstable commit commit 7fbfe2003f84686d: this fixing patch 9f1f5b60e76d44fa fbdf9263a3d7fdbd 7fbfe2003f84686d ---------------- --------------------------- --------------------------- 3843810 -21.4% 3020268 +4.6% 4018708 stress-ng.bad-altstack.ops 64061 -21.4% 50336 +4.6% 66977 stress-ng.bad-altstack.ops_per_sec 1709026 -14.4% 1462102 +2.4% 1750757 stress-ng.fork.ops 28483 -14.4% 24368 +2.4% 29179 stress-ng.fork.ops_per_sec 3685088 -53.6% 1710976 +0.5% 3702454 stress-ng.zombie.ops 56732 -65.3% 19667 +0.7% 57107 stress-ng.zombie.ops_per_sec 61874 -12.1% 54416 +0.4% 62136 vm-scalability.median 13527663 -11.7% 11942117 -0.1% 13513946 vm-scalability.throughput 4.066e+09 -11.7% 3.59e+09 -0.1% 4.061e+09 vm-scalability.workload [1]: https://lore.kernel.org/oe-lkp/72e017b9-deb6-44fa-91d6-716ee2c39cbc@intel.com/T/#m7d2bba30f75a9cee8eab07e5809abd9b3b206c84 Link: https://lkml.kernel.org/r/20230914134741.1937654-1-fengwei.yin@intel.com Fixes: de74976eb65151a2f568e477fc2e0032df5b22b4 ("filemap: add filemap_map_folio_range()") Signed-off-by: Yin Fengwei <fengwei.yin@intel.com> Reported-by: kernel test robot <oliver.sang@intel.com> Closes: https://lore.kernel.org/oe-lkp/202309111556.b2aa3d7a-oliver.sang@intel.com Cc: Feng Tang <feng.tang@intel.com> Cc: Huang Ying <ying.huang@intel.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-09-14 13:47:41 +00:00
mmap_miss_saved = READ_ONCE(file->f_ra.mmap_miss);
if (mmap_miss >= mmap_miss_saved)
WRITE_ONCE(file->f_ra.mmap_miss, 0);
else
WRITE_ONCE(file->f_ra.mmap_miss, mmap_miss_saved - mmap_miss);
return ret;
}
EXPORT_SYMBOL(filemap_map_pages);
vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf)
{
struct address_space *mapping = vmf->vma->vm_file->f_mapping;
struct folio *folio = page_folio(vmf->page);
vm_fault_t ret = VM_FAULT_LOCKED;
sb_start_pagefault(mapping->host->i_sb);
file_update_time(vmf->vma->vm_file);
folio_lock(folio);
if (folio->mapping != mapping) {
folio_unlock(folio);
ret = VM_FAULT_NOPAGE;
goto out;
}
/*
* We mark the folio dirty already here so that when freeze is in
* progress, we are guaranteed that writeback during freezing will
* see the dirty folio and writeprotect it again.
*/
folio_mark_dirty(folio);
folio_wait_stable(folio);
out:
sb_end_pagefault(mapping->host->i_sb);
return ret;
}
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 */
mm/mempool: minor coding style tweaks Various coding style tweaks to various files under mm/ [daizhiyuan@phytium.com.cn: mm/swapfile: minor coding style tweaks] Link: https://lkml.kernel.org/r/1614223624-16055-1-git-send-email-daizhiyuan@phytium.com.cn [daizhiyuan@phytium.com.cn: mm/sparse: minor coding style tweaks] Link: https://lkml.kernel.org/r/1614227288-19363-1-git-send-email-daizhiyuan@phytium.com.cn [daizhiyuan@phytium.com.cn: mm/vmscan: minor coding style tweaks] Link: https://lkml.kernel.org/r/1614227649-19853-1-git-send-email-daizhiyuan@phytium.com.cn [daizhiyuan@phytium.com.cn: mm/compaction: minor coding style tweaks] Link: https://lkml.kernel.org/r/1614228218-20770-1-git-send-email-daizhiyuan@phytium.com.cn [daizhiyuan@phytium.com.cn: mm/oom_kill: minor coding style tweaks] Link: https://lkml.kernel.org/r/1614228360-21168-1-git-send-email-daizhiyuan@phytium.com.cn [daizhiyuan@phytium.com.cn: mm/shmem: minor coding style tweaks] Link: https://lkml.kernel.org/r/1614228504-21491-1-git-send-email-daizhiyuan@phytium.com.cn [daizhiyuan@phytium.com.cn: mm/page_alloc: minor coding style tweaks] Link: https://lkml.kernel.org/r/1614228613-21754-1-git-send-email-daizhiyuan@phytium.com.cn [daizhiyuan@phytium.com.cn: mm/filemap: minor coding style tweaks] Link: https://lkml.kernel.org/r/1614228936-22337-1-git-send-email-daizhiyuan@phytium.com.cn [daizhiyuan@phytium.com.cn: mm/mlock: minor coding style tweaks] Link: https://lkml.kernel.org/r/1613956588-2453-1-git-send-email-daizhiyuan@phytium.com.cn [daizhiyuan@phytium.com.cn: mm/frontswap: minor coding style tweaks] Link: https://lkml.kernel.org/r/1613962668-15045-1-git-send-email-daizhiyuan@phytium.com.cn [daizhiyuan@phytium.com.cn: mm/vmalloc: minor coding style tweaks] Link: https://lkml.kernel.org/r/1613963379-15988-1-git-send-email-daizhiyuan@phytium.com.cn [daizhiyuan@phytium.com.cn: mm/memory_hotplug: minor coding style tweaks] Link: https://lkml.kernel.org/r/1613971784-24878-1-git-send-email-daizhiyuan@phytium.com.cn [daizhiyuan@phytium.com.cn: mm/mempolicy: minor coding style tweaks] Link: https://lkml.kernel.org/r/1613972228-25501-1-git-send-email-daizhiyuan@phytium.com.cn Link: https://lkml.kernel.org/r/1614222374-13805-1-git-send-email-daizhiyuan@phytium.com.cn Signed-off-by: Zhiyuan Dai <daizhiyuan@phytium.com.cn> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-05-05 01:40:12 +00:00
int generic_file_mmap(struct file *file, struct vm_area_struct *vma)
{
struct address_space *mapping = file->f_mapping;
if (!mapping->a_ops->read_folio)
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)
{
mm: drop the assumption that VM_SHARED always implies writable Patch series "permit write-sealed memfd read-only shared mappings", v4. The man page for fcntl() describing memfd file seals states the following about F_SEAL_WRITE:- Furthermore, trying to create new shared, writable memory-mappings via mmap(2) will also fail with EPERM. With emphasis on 'writable'. In turns out in fact that currently the kernel simply disallows all new shared memory mappings for a memfd with F_SEAL_WRITE applied, rendering this documentation inaccurate. This matters because users are therefore unable to obtain a shared mapping to a memfd after write sealing altogether, which limits their usefulness. This was reported in the discussion thread [1] originating from a bug report [2]. This is a product of both using the struct address_space->i_mmap_writable atomic counter to determine whether writing may be permitted, and the kernel adjusting this counter when any VM_SHARED mapping is performed and more generally implicitly assuming VM_SHARED implies writable. It seems sensible that we should only update this mapping if VM_MAYWRITE is specified, i.e. whether it is possible that this mapping could at any point be written to. If we do so then all we need to do to permit write seals to function as documented is to clear VM_MAYWRITE when mapping read-only. It turns out this functionality already exists for F_SEAL_FUTURE_WRITE - we can therefore simply adapt this logic to do the same for F_SEAL_WRITE. We then hit a chicken and egg situation in mmap_region() where the check for VM_MAYWRITE occurs before we are able to clear this flag. To work around this, perform this check after we invoke call_mmap(), with careful consideration of error paths. Thanks to Andy Lutomirski for the suggestion! [1]:https://lore.kernel.org/all/20230324133646.16101dfa666f253c4715d965@linux-foundation.org/ [2]:https://bugzilla.kernel.org/show_bug.cgi?id=217238 This patch (of 3): There is a general assumption that VMAs with the VM_SHARED flag set are writable. If the VM_MAYWRITE flag is not set, then this is simply not the case. Update those checks which affect the struct address_space->i_mmap_writable field to explicitly test for this by introducing [vma_]is_shared_maywrite() helper functions. This remains entirely conservative, as the lack of VM_MAYWRITE guarantees that the VMA cannot be written to. Link: https://lkml.kernel.org/r/cover.1697116581.git.lstoakes@gmail.com Link: https://lkml.kernel.org/r/d978aefefa83ec42d18dfa964ad180dbcde34795.1697116581.git.lstoakes@gmail.com Signed-off-by: Lorenzo Stoakes <lstoakes@gmail.com> Suggested-by: Andy Lutomirski <luto@kernel.org> Reviewed-by: Jan Kara <jack@suse.cz> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Christian Brauner <brauner@kernel.org> Cc: Hugh Dickins <hughd@google.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Muchun Song <muchun.song@linux.dev> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-10-12 17:04:28 +00:00
if (vma_is_shared_maywrite(vma))
return -EINVAL;
return generic_file_mmap(file, vma);
}
#else
vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf)
{
return VM_FAULT_SIGBUS;
}
mm/mempool: minor coding style tweaks Various coding style tweaks to various files under mm/ [daizhiyuan@phytium.com.cn: mm/swapfile: minor coding style tweaks] Link: https://lkml.kernel.org/r/1614223624-16055-1-git-send-email-daizhiyuan@phytium.com.cn [daizhiyuan@phytium.com.cn: mm/sparse: minor coding style tweaks] Link: https://lkml.kernel.org/r/1614227288-19363-1-git-send-email-daizhiyuan@phytium.com.cn [daizhiyuan@phytium.com.cn: mm/vmscan: minor coding style tweaks] Link: https://lkml.kernel.org/r/1614227649-19853-1-git-send-email-daizhiyuan@phytium.com.cn [daizhiyuan@phytium.com.cn: mm/compaction: minor coding style tweaks] Link: https://lkml.kernel.org/r/1614228218-20770-1-git-send-email-daizhiyuan@phytium.com.cn [daizhiyuan@phytium.com.cn: mm/oom_kill: minor coding style tweaks] Link: https://lkml.kernel.org/r/1614228360-21168-1-git-send-email-daizhiyuan@phytium.com.cn [daizhiyuan@phytium.com.cn: mm/shmem: minor coding style tweaks] Link: https://lkml.kernel.org/r/1614228504-21491-1-git-send-email-daizhiyuan@phytium.com.cn [daizhiyuan@phytium.com.cn: mm/page_alloc: minor coding style tweaks] Link: https://lkml.kernel.org/r/1614228613-21754-1-git-send-email-daizhiyuan@phytium.com.cn [daizhiyuan@phytium.com.cn: mm/filemap: minor coding style tweaks] Link: https://lkml.kernel.org/r/1614228936-22337-1-git-send-email-daizhiyuan@phytium.com.cn [daizhiyuan@phytium.com.cn: mm/mlock: minor coding style tweaks] Link: https://lkml.kernel.org/r/1613956588-2453-1-git-send-email-daizhiyuan@phytium.com.cn [daizhiyuan@phytium.com.cn: mm/frontswap: minor coding style tweaks] Link: https://lkml.kernel.org/r/1613962668-15045-1-git-send-email-daizhiyuan@phytium.com.cn [daizhiyuan@phytium.com.cn: mm/vmalloc: minor coding style tweaks] Link: https://lkml.kernel.org/r/1613963379-15988-1-git-send-email-daizhiyuan@phytium.com.cn [daizhiyuan@phytium.com.cn: mm/memory_hotplug: minor coding style tweaks] Link: https://lkml.kernel.org/r/1613971784-24878-1-git-send-email-daizhiyuan@phytium.com.cn [daizhiyuan@phytium.com.cn: mm/mempolicy: minor coding style tweaks] Link: https://lkml.kernel.org/r/1613972228-25501-1-git-send-email-daizhiyuan@phytium.com.cn Link: https://lkml.kernel.org/r/1614222374-13805-1-git-send-email-daizhiyuan@phytium.com.cn Signed-off-by: Zhiyuan Dai <daizhiyuan@phytium.com.cn> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-05-05 01:40:12 +00:00
int generic_file_mmap(struct file *file, struct vm_area_struct *vma)
{
return -ENOSYS;
}
mm/mempool: minor coding style tweaks Various coding style tweaks to various files under mm/ [daizhiyuan@phytium.com.cn: mm/swapfile: minor coding style tweaks] Link: https://lkml.kernel.org/r/1614223624-16055-1-git-send-email-daizhiyuan@phytium.com.cn [daizhiyuan@phytium.com.cn: mm/sparse: minor coding style tweaks] Link: https://lkml.kernel.org/r/1614227288-19363-1-git-send-email-daizhiyuan@phytium.com.cn [daizhiyuan@phytium.com.cn: mm/vmscan: minor coding style tweaks] Link: https://lkml.kernel.org/r/1614227649-19853-1-git-send-email-daizhiyuan@phytium.com.cn [daizhiyuan@phytium.com.cn: mm/compaction: minor coding style tweaks] Link: https://lkml.kernel.org/r/1614228218-20770-1-git-send-email-daizhiyuan@phytium.com.cn [daizhiyuan@phytium.com.cn: mm/oom_kill: minor coding style tweaks] Link: https://lkml.kernel.org/r/1614228360-21168-1-git-send-email-daizhiyuan@phytium.com.cn [daizhiyuan@phytium.com.cn: mm/shmem: minor coding style tweaks] Link: https://lkml.kernel.org/r/1614228504-21491-1-git-send-email-daizhiyuan@phytium.com.cn [daizhiyuan@phytium.com.cn: mm/page_alloc: minor coding style tweaks] Link: https://lkml.kernel.org/r/1614228613-21754-1-git-send-email-daizhiyuan@phytium.com.cn [daizhiyuan@phytium.com.cn: mm/filemap: minor coding style tweaks] Link: https://lkml.kernel.org/r/1614228936-22337-1-git-send-email-daizhiyuan@phytium.com.cn [daizhiyuan@phytium.com.cn: mm/mlock: minor coding style tweaks] Link: https://lkml.kernel.org/r/1613956588-2453-1-git-send-email-daizhiyuan@phytium.com.cn [daizhiyuan@phytium.com.cn: mm/frontswap: minor coding style tweaks] Link: https://lkml.kernel.org/r/1613962668-15045-1-git-send-email-daizhiyuan@phytium.com.cn [daizhiyuan@phytium.com.cn: mm/vmalloc: minor coding style tweaks] Link: https://lkml.kernel.org/r/1613963379-15988-1-git-send-email-daizhiyuan@phytium.com.cn [daizhiyuan@phytium.com.cn: mm/memory_hotplug: minor coding style tweaks] Link: https://lkml.kernel.org/r/1613971784-24878-1-git-send-email-daizhiyuan@phytium.com.cn [daizhiyuan@phytium.com.cn: mm/mempolicy: minor coding style tweaks] Link: https://lkml.kernel.org/r/1613972228-25501-1-git-send-email-daizhiyuan@phytium.com.cn Link: https://lkml.kernel.org/r/1614222374-13805-1-git-send-email-daizhiyuan@phytium.com.cn Signed-off-by: Zhiyuan Dai <daizhiyuan@phytium.com.cn> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-05-05 01:40:12 +00:00
int generic_file_readonly_mmap(struct file *file, struct vm_area_struct *vma)
{
return -ENOSYS;
}
#endif /* CONFIG_MMU */
EXPORT_SYMBOL(filemap_page_mkwrite);
EXPORT_SYMBOL(generic_file_mmap);
EXPORT_SYMBOL(generic_file_readonly_mmap);
static struct folio *do_read_cache_folio(struct address_space *mapping,
pgoff_t index, filler_t filler, struct file *file, gfp_t gfp)
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 folio *folio;
int err;
if (!filler)
filler = mapping->a_ops->read_folio;
repeat:
folio = filemap_get_folio(mapping, index);
if (IS_ERR(folio)) {
folio = filemap_alloc_folio(gfp, 0);
if (!folio)
return ERR_PTR(-ENOMEM);
err = filemap_add_folio(mapping, folio, index, gfp);
if (unlikely(err)) {
folio_put(folio);
if (err == -EEXIST)
goto repeat;
/* Presumably ENOMEM for xarray node */
return ERR_PTR(err);
}
goto filler;
}
if (folio_test_uptodate(folio))
goto out;
if (!folio_trylock(folio)) {
folio_put_wait_locked(folio, TASK_UNINTERRUPTIBLE);
goto repeat;
}
mm: filemap: avoid unnecessary calls to lock_page when waiting for IO to complete during a read In the generic read paths the kernel looks up a page in the page cache and if it's up to date, it is used. If not, the page lock is acquired to wait for IO to complete and then check the page. If multiple processes are waiting on IO, they all serialise against the lock and duplicate the checks. This is unnecessary. The page lock in itself does not give any guarantees to the callers about the page state as it can be immediately truncated or reclaimed after the page is unlocked. It's sufficient to wait_on_page_locked and then continue if the page is up to date on wakeup. It is possible that a truncated but up-to-date page is returned but the reference taken during read prevents it disappearing underneath the caller and the data is still valid if PageUptodate. The overall impact is small as even if processes serialise on the lock, the lock section is tiny once the IO is complete. Profiles indicated that unlock_page and friends are generally a tiny portion of a read-intensive workload. An artificial test was created that had instances of dd access a cache-cold file on an ext4 filesystem and measure how long the read took. paralleldd 4.4.0 4.4.0 vanilla avoidlock Amean Elapsd-1 5.28 ( 0.00%) 5.15 ( 2.50%) Amean Elapsd-4 5.29 ( 0.00%) 5.17 ( 2.12%) Amean Elapsd-7 5.28 ( 0.00%) 5.18 ( 1.78%) Amean Elapsd-12 5.20 ( 0.00%) 5.33 ( -2.50%) Amean Elapsd-21 5.14 ( 0.00%) 5.21 ( -1.41%) Amean Elapsd-30 5.30 ( 0.00%) 5.12 ( 3.38%) Amean Elapsd-48 5.78 ( 0.00%) 5.42 ( 6.21%) Amean Elapsd-79 6.78 ( 0.00%) 6.62 ( 2.46%) Amean Elapsd-110 9.09 ( 0.00%) 8.99 ( 1.15%) Amean Elapsd-128 10.60 ( 0.00%) 10.43 ( 1.66%) The impact is small but intuitively, it makes sense to avoid unnecessary calls to lock_page. Signed-off-by: Mel Gorman <mgorman@techsingularity.net> Reviewed-by: Jan Kara <jack@suse.cz> Cc: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-03-15 21:55:39 +00:00
/* Folio was truncated from mapping */
if (!folio->mapping) {
folio_unlock(folio);
folio_put(folio);
goto repeat;
}
mm: filemap: avoid unnecessary calls to lock_page when waiting for IO to complete during a read In the generic read paths the kernel looks up a page in the page cache and if it's up to date, it is used. If not, the page lock is acquired to wait for IO to complete and then check the page. If multiple processes are waiting on IO, they all serialise against the lock and duplicate the checks. This is unnecessary. The page lock in itself does not give any guarantees to the callers about the page state as it can be immediately truncated or reclaimed after the page is unlocked. It's sufficient to wait_on_page_locked and then continue if the page is up to date on wakeup. It is possible that a truncated but up-to-date page is returned but the reference taken during read prevents it disappearing underneath the caller and the data is still valid if PageUptodate. The overall impact is small as even if processes serialise on the lock, the lock section is tiny once the IO is complete. Profiles indicated that unlock_page and friends are generally a tiny portion of a read-intensive workload. An artificial test was created that had instances of dd access a cache-cold file on an ext4 filesystem and measure how long the read took. paralleldd 4.4.0 4.4.0 vanilla avoidlock Amean Elapsd-1 5.28 ( 0.00%) 5.15 ( 2.50%) Amean Elapsd-4 5.29 ( 0.00%) 5.17 ( 2.12%) Amean Elapsd-7 5.28 ( 0.00%) 5.18 ( 1.78%) Amean Elapsd-12 5.20 ( 0.00%) 5.33 ( -2.50%) Amean Elapsd-21 5.14 ( 0.00%) 5.21 ( -1.41%) Amean Elapsd-30 5.30 ( 0.00%) 5.12 ( 3.38%) Amean Elapsd-48 5.78 ( 0.00%) 5.42 ( 6.21%) Amean Elapsd-79 6.78 ( 0.00%) 6.62 ( 2.46%) Amean Elapsd-110 9.09 ( 0.00%) 8.99 ( 1.15%) Amean Elapsd-128 10.60 ( 0.00%) 10.43 ( 1.66%) The impact is small but intuitively, it makes sense to avoid unnecessary calls to lock_page. Signed-off-by: Mel Gorman <mgorman@techsingularity.net> Reviewed-by: Jan Kara <jack@suse.cz> Cc: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-03-15 21:55:39 +00:00
/* Someone else locked and filled the page in a very small window */
if (folio_test_uptodate(folio)) {
folio_unlock(folio);
goto out;
}
mm/filemap.c: clear page error before actual read Mount failure issue happens under the scenario: Application forked dozens of threads to mount the same number of cramfs images separately in docker, but several mounts failed with high probability. Mount failed due to the checking result of the page(read from the superblock of loop dev) is not uptodate after wait_on_page_locked(page) returned in function cramfs_read: wait_on_page_locked(page); if (!PageUptodate(page)) { ... } The reason of the checking result of the page not uptodate: systemd-udevd read the loopX dev before mount, because the status of loopX is Lo_unbound at this time, so loop_make_request directly trigger the calling of io_end handler end_buffer_async_read, which called SetPageError(page). So It caused the page can't be set to uptodate in function end_buffer_async_read: if(page_uptodate && !PageError(page)) { SetPageUptodate(page); } Then mount operation is performed, it used the same page which is just accessed by systemd-udevd above, Because this page is not uptodate, it will launch a actual read via submit_bh, then wait on this page by calling wait_on_page_locked(page). When the I/O of the page done, io_end handler end_buffer_async_read is called, because no one cleared the page error(during the whole read path of mount), which is caused by systemd-udevd reading, so this page is still in "PageError" status, which can't be set to uptodate in function end_buffer_async_read, then caused mount failure. But sometimes mount succeed even through systemd-udeved read loopX dev just before, The reason is systemd-udevd launched other loopX read just between step 3.1 and 3.2, the steps as below: 1, loopX dev default status is Lo_unbound; 2, systemd-udved read loopX dev (page is set to PageError); 3, mount operation 1) set loopX status to Lo_bound; ==>systemd-udevd read loopX dev<== 2) read loopX dev(page has no error) 3) mount succeed As the loopX dev status is set to Lo_bound after step 3.1, so the other loopX dev read by systemd-udevd will go through the whole I/O stack, part of the call trace as below: SYS_read vfs_read do_sync_read blkdev_aio_read generic_file_aio_read do_generic_file_read: ClearPageError(page); mapping->a_ops->readpage(filp, page); here, mapping->a_ops->readpage() is blkdev_readpage. In latest kernel, some function name changed, the call trace as below: blkdev_read_iter generic_file_read_iter generic_file_buffered_read: /* * A previous I/O error may have been due to temporary * failures, eg. mutipath 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(flip, page); We can see ClearPageError(page) is called before the actual read, then the read in step 3.2 succeed. This patch is to add the calling of ClearPageError just before the actual read of read path of cramfs mount. Without the patch, the call trace as below when performing cramfs mount: do_mount cramfs_read cramfs_blkdev_read read_cache_page do_read_cache_page: filler(data, page); or mapping->a_ops->readpage(data, page); With the patch, the call trace as below when performing mount: do_mount cramfs_read cramfs_blkdev_read read_cache_page: do_read_cache_page: ClearPageError(page); <== new add filler(data, page); or mapping->a_ops->readpage(data, page); With the patch, mount operation trigger the calling of ClearPageError(page) before the actual read, the page has no error if no additional page error happen when I/O done. Signed-off-by: Xianting Tian <xianting_tian@126.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Jan Kara <jack@suse.cz> Cc: <yubin@h3c.com> Link: http://lkml.kernel.org/r/1583318844-22971-1-git-send-email-xianting_tian@126.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-04-02 04:04:47 +00:00
filler:
err = filemap_read_folio(file, filler, folio);
if (err) {
folio_put(folio);
if (err == AOP_TRUNCATED_PAGE)
goto repeat;
return ERR_PTR(err);
}
out:
folio_mark_accessed(folio);
return folio;
}
/**
* read_cache_folio - Read into page cache, fill it if needed.
* @mapping: The address_space to read from.
* @index: The index to read.
* @filler: Function to perform the read, or NULL to use aops->read_folio().
* @file: Passed to filler function, may be NULL if not required.
*
* Read one page into the page cache. If it succeeds, the folio returned
* will contain @index, but it may not be the first page of the folio.
*
* If the filler function returns an error, it will be returned to the
* caller.
*
* Context: May sleep. Expects mapping->invalidate_lock to be held.
* Return: An uptodate folio on success, ERR_PTR() on failure.
*/
struct folio *read_cache_folio(struct address_space *mapping, pgoff_t index,
filler_t filler, struct file *file)
{
return do_read_cache_folio(mapping, index, filler, file,
mapping_gfp_mask(mapping));
}
EXPORT_SYMBOL(read_cache_folio);
/**
* mapping_read_folio_gfp - Read into page cache, using specified allocation flags.
* @mapping: The address_space for the folio.
* @index: The index that the allocated folio will contain.
* @gfp: The page allocator flags to use if allocating.
*
* This is the same as "read_cache_folio(mapping, index, NULL, NULL)", but with
* any new memory allocations done using the specified allocation flags.
*
* The most likely error from this function is EIO, but ENOMEM is
* possible and so is EINTR. If ->read_folio returns another error,
* that will be returned to the caller.
*
* The function expects mapping->invalidate_lock to be already held.
*
* Return: Uptodate folio on success, ERR_PTR() on failure.
*/
struct folio *mapping_read_folio_gfp(struct address_space *mapping,
pgoff_t index, gfp_t gfp)
{
return do_read_cache_folio(mapping, index, NULL, NULL, gfp);
}
EXPORT_SYMBOL(mapping_read_folio_gfp);
static struct page *do_read_cache_page(struct address_space *mapping,
pgoff_t index, filler_t *filler, struct file *file, gfp_t gfp)
{
struct folio *folio;
folio = do_read_cache_folio(mapping, index, filler, file, gfp);
if (IS_ERR(folio))
return &folio->page;
return folio_file_page(folio, index);
}
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, filler_t *filler, struct file *file)
{
return do_read_cache_page(mapping, index, filler, file,
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.
*
* The function expects mapping->invalidate_lock to be already held.
*
* Return: up to date page on success, ERR_PTR() on failure.
*/
struct page *read_cache_page_gfp(struct address_space *mapping,
pgoff_t index,
gfp_t gfp)
{
return do_read_cache_page(mapping, index, NULL, NULL, gfp);
}
EXPORT_SYMBOL(read_cache_page_gfp);
/*
* Warn about a page cache invalidation failure during a direct I/O write.
*/
static void dio_warn_stale_pagecache(struct file *filp)
{
static DEFINE_RATELIMIT_STATE(_rs, 86400 * HZ, DEFAULT_RATELIMIT_BURST);
char pathname[128];
char *path;
errseq_set(&filp->f_mapping->wb_err, -EIO);
if (__ratelimit(&_rs)) {
path = file_path(filp, pathname, sizeof(pathname));
if (IS_ERR(path))
path = "(unknown)";
pr_crit("Page cache invalidation failure on direct I/O. Possible data corruption due to collision with buffered I/O!\n");
pr_crit("File: %s PID: %d Comm: %.20s\n", path, current->pid,
current->comm);
}
}
void kiocb_invalidate_post_direct_write(struct kiocb *iocb, size_t count)
{
struct address_space *mapping = iocb->ki_filp->f_mapping;
if (mapping->nrpages &&
invalidate_inode_pages2_range(mapping,
iocb->ki_pos >> PAGE_SHIFT,
(iocb->ki_pos + count - 1) >> PAGE_SHIFT))
dio_warn_stale_pagecache(iocb->ki_filp);
}
ssize_t
generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from)
{
struct address_space *mapping = iocb->ki_filp->f_mapping;
size_t write_len = iov_iter_count(from);
ssize_t written;
fs: fix data invalidation in the cleancache during direct IO Patch series "Properly invalidate data in the cleancache", v2. We've noticed that after direct IO write, buffered read sometimes gets stale data which is coming from the cleancache. The reason for this is that some direct write hooks call call invalidate_inode_pages2[_range]() conditionally iff mapping->nrpages is not zero, so we may not invalidate data in the cleancache. Another odd thing is that we check only for ->nrpages and don't check for ->nrexceptional, but invalidate_inode_pages2[_range] also invalidates exceptional entries as well. So we invalidate exceptional entries only if ->nrpages != 0? This doesn't feel right. - Patch 1 fixes direct IO writes by removing ->nrpages check. - Patch 2 fixes similar case in invalidate_bdev(). Note: I only fixed conditional cleancache_invalidate_inode() here. Do we also need to add ->nrexceptional check in into invalidate_bdev()? - Patches 3-4: some optimizations. This patch (of 4): Some direct IO write fs hooks call invalidate_inode_pages2[_range]() conditionally iff mapping->nrpages is not zero. This can't be right, because invalidate_inode_pages2[_range]() also invalidate data in the cleancache via cleancache_invalidate_inode() call. So if page cache is empty but there is some data in the cleancache, buffered read after direct IO write would get stale data from the cleancache. Also it doesn't feel right to check only for ->nrpages because invalidate_inode_pages2[_range] invalidates exceptional entries as well. Fix this by calling invalidate_inode_pages2[_range]() regardless of nrpages state. Note: nfs,cifs,9p doesn't need similar fix because the never call cleancache_get_page() (nor directly, nor via mpage_readpage[s]()), so they are not affected by this bug. Fixes: c515e1fd361c ("mm/fs: add hooks to support cleancache") Link: http://lkml.kernel.org/r/20170424164135.22350-2-aryabinin@virtuozzo.com Signed-off-by: Andrey Ryabinin <aryabinin@virtuozzo.com> Reviewed-by: Jan Kara <jack@suse.cz> Acked-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Alexey Kuznetsov <kuznet@virtuozzo.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Nikolay Borisov <n.borisov.lkml@gmail.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-05-03 21:55:59 +00:00
/*
* If a page can not be invalidated, return 0 to fall back
* to buffered write.
*/
written = kiocb_invalidate_pages(iocb, write_len);
fs: fix data invalidation in the cleancache during direct IO Patch series "Properly invalidate data in the cleancache", v2. We've noticed that after direct IO write, buffered read sometimes gets stale data which is coming from the cleancache. The reason for this is that some direct write hooks call call invalidate_inode_pages2[_range]() conditionally iff mapping->nrpages is not zero, so we may not invalidate data in the cleancache. Another odd thing is that we check only for ->nrpages and don't check for ->nrexceptional, but invalidate_inode_pages2[_range] also invalidates exceptional entries as well. So we invalidate exceptional entries only if ->nrpages != 0? This doesn't feel right. - Patch 1 fixes direct IO writes by removing ->nrpages check. - Patch 2 fixes similar case in invalidate_bdev(). Note: I only fixed conditional cleancache_invalidate_inode() here. Do we also need to add ->nrexceptional check in into invalidate_bdev()? - Patches 3-4: some optimizations. This patch (of 4): Some direct IO write fs hooks call invalidate_inode_pages2[_range]() conditionally iff mapping->nrpages is not zero. This can't be right, because invalidate_inode_pages2[_range]() also invalidate data in the cleancache via cleancache_invalidate_inode() call. So if page cache is empty but there is some data in the cleancache, buffered read after direct IO write would get stale data from the cleancache. Also it doesn't feel right to check only for ->nrpages because invalidate_inode_pages2[_range] invalidates exceptional entries as well. Fix this by calling invalidate_inode_pages2[_range]() regardless of nrpages state. Note: nfs,cifs,9p doesn't need similar fix because the never call cleancache_get_page() (nor directly, nor via mpage_readpage[s]()), so they are not affected by this bug. Fixes: c515e1fd361c ("mm/fs: add hooks to support cleancache") Link: http://lkml.kernel.org/r/20170424164135.22350-2-aryabinin@virtuozzo.com Signed-off-by: Andrey Ryabinin <aryabinin@virtuozzo.com> Reviewed-by: Jan Kara <jack@suse.cz> Acked-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Alexey Kuznetsov <kuznet@virtuozzo.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Nikolay Borisov <n.borisov.lkml@gmail.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-05-03 21:55:59 +00:00
if (written) {
if (written == -EBUSY)
return 0;
return written;
}
written = mapping->a_ops->direct_IO(iocb, from);
/*
* 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...
*
* Most of the time we do not need this since dio_complete() will do
* the invalidation for us. However there are some file systems that
* do not end up with dio_complete() being called, so let's not break
* them by removing it completely.
*
* Noticeable example is a blkdev_direct_IO().
*
* Skip invalidation for async writes or if mapping has no pages.
*/
if (written > 0) {
struct inode *inode = mapping->host;
loff_t pos = iocb->ki_pos;
kiocb_invalidate_post_direct_write(iocb, written);
pos += written;
write_len -= 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;
}
if (written != -EIOCBQUEUED)
iov_iter_revert(from, write_len - iov_iter_count(from));
return written;
}
EXPORT_SYMBOL(generic_file_direct_write);
ssize_t generic_perform_write(struct kiocb *iocb, struct iov_iter *i)
{
struct file *file = iocb->ki_filp;
loff_t pos = iocb->ki_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;
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 */
mm: fs: initialize fsdata passed to write_begin/write_end interface Functions implementing the a_ops->write_end() interface accept the `void *fsdata` parameter that is supposed to be initialized by the corresponding a_ops->write_begin() (which accepts `void **fsdata`). However not all a_ops->write_begin() implementations initialize `fsdata` unconditionally, so it may get passed uninitialized to a_ops->write_end(), resulting in undefined behavior. Fix this by initializing fsdata with NULL before the call to write_begin(), rather than doing so in all possible a_ops implementations. This patch covers only the following cases found by running x86 KMSAN under syzkaller: - generic_perform_write() - cont_expand_zero() and generic_cont_expand_simple() - page_symlink() Other cases of passing uninitialized fsdata may persist in the codebase. Link: https://lkml.kernel.org/r/20220915150417.722975-43-glider@google.com Signed-off-by: Alexander Potapenko <glider@google.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Andrey Konovalov <andreyknvl@gmail.com> Cc: Andrey Konovalov <andreyknvl@google.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Borislav Petkov <bp@alien8.de> Cc: Christoph Hellwig <hch@lst.de> Cc: Christoph Lameter <cl@linux.com> Cc: David Rientjes <rientjes@google.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Eric Biggers <ebiggers@google.com> Cc: Eric Biggers <ebiggers@kernel.org> Cc: Eric Dumazet <edumazet@google.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Herbert Xu <herbert@gondor.apana.org.au> Cc: Ilya Leoshkevich <iii@linux.ibm.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Kees Cook <keescook@chromium.org> Cc: Marco Elver <elver@google.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Michael S. Tsirkin <mst@redhat.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Petr Mladek <pmladek@suse.com> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vasily Gorbik <gor@linux.ibm.com> Cc: Vegard Nossum <vegard.nossum@oracle.com> Cc: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-09-15 15:04:16 +00:00
void *fsdata = NULL;
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 12:29:47 +00:00
offset = (pos & (PAGE_SIZE - 1));
bytes = min_t(unsigned long, PAGE_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.
*/
if (unlikely(fault_in_iov_iter_readable(i, bytes) == bytes)) {
status = -EFAULT;
break;
}
if (fatal_signal_pending(current)) {
status = -EINTR;
break;
}
status = a_ops->write_begin(file, mapping, pos, bytes,
&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 = copy_page_from_iter_atomic(page, offset, bytes, i);
flush_dcache_page(page);
status = a_ops->write_end(file, mapping, pos, bytes, copied,
page, fsdata);
if (unlikely(status != copied)) {
iov_iter_revert(i, copied - max(status, 0L));
if (unlikely(status < 0))
break;
}
cond_resched();
if (unlikely(status == 0)) {
/*
* A short copy made ->write_end() reject the
* thing entirely. Might be memory poisoning
* halfway through, might be a race with munmap,
* might be severe memory pressure.
*/
if (copied)
bytes = copied;
goto again;
}
pos += status;
written += status;
balance_dirty_pages_ratelimited(mapping);
} while (iov_iter_count(i));
if (!written)
return status;
iocb->ki_pos += written;
return written;
}
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_rwsem 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_rwsem.
*
* Return:
* * number of bytes written, even for truncated writes
* * negative error code if no data has been written at all
*/
ssize_t __generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
struct file *file = iocb->ki_filp;
mm/mempool: minor coding style tweaks Various coding style tweaks to various files under mm/ [daizhiyuan@phytium.com.cn: mm/swapfile: minor coding style tweaks] Link: https://lkml.kernel.org/r/1614223624-16055-1-git-send-email-daizhiyuan@phytium.com.cn [daizhiyuan@phytium.com.cn: mm/sparse: minor coding style tweaks] Link: https://lkml.kernel.org/r/1614227288-19363-1-git-send-email-daizhiyuan@phytium.com.cn [daizhiyuan@phytium.com.cn: mm/vmscan: minor coding style tweaks] Link: https://lkml.kernel.org/r/1614227649-19853-1-git-send-email-daizhiyuan@phytium.com.cn [daizhiyuan@phytium.com.cn: mm/compaction: minor coding style tweaks] Link: https://lkml.kernel.org/r/1614228218-20770-1-git-send-email-daizhiyuan@phytium.com.cn [daizhiyuan@phytium.com.cn: mm/oom_kill: minor coding style tweaks] Link: https://lkml.kernel.org/r/1614228360-21168-1-git-send-email-daizhiyuan@phytium.com.cn [daizhiyuan@phytium.com.cn: mm/shmem: minor coding style tweaks] Link: https://lkml.kernel.org/r/1614228504-21491-1-git-send-email-daizhiyuan@phytium.com.cn [daizhiyuan@phytium.com.cn: mm/page_alloc: minor coding style tweaks] Link: https://lkml.kernel.org/r/1614228613-21754-1-git-send-email-daizhiyuan@phytium.com.cn [daizhiyuan@phytium.com.cn: mm/filemap: minor coding style tweaks] Link: https://lkml.kernel.org/r/1614228936-22337-1-git-send-email-daizhiyuan@phytium.com.cn [daizhiyuan@phytium.com.cn: mm/mlock: minor coding style tweaks] Link: https://lkml.kernel.org/r/1613956588-2453-1-git-send-email-daizhiyuan@phytium.com.cn [daizhiyuan@phytium.com.cn: mm/frontswap: minor coding style tweaks] Link: https://lkml.kernel.org/r/1613962668-15045-1-git-send-email-daizhiyuan@phytium.com.cn [daizhiyuan@phytium.com.cn: mm/vmalloc: minor coding style tweaks] Link: https://lkml.kernel.org/r/1613963379-15988-1-git-send-email-daizhiyuan@phytium.com.cn [daizhiyuan@phytium.com.cn: mm/memory_hotplug: minor coding style tweaks] Link: https://lkml.kernel.org/r/1613971784-24878-1-git-send-email-daizhiyuan@phytium.com.cn [daizhiyuan@phytium.com.cn: mm/mempolicy: minor coding style tweaks] Link: https://lkml.kernel.org/r/1613972228-25501-1-git-send-email-daizhiyuan@phytium.com.cn Link: https://lkml.kernel.org/r/1614222374-13805-1-git-send-email-daizhiyuan@phytium.com.cn Signed-off-by: Zhiyuan Dai <daizhiyuan@phytium.com.cn> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-05-05 01:40:12 +00:00
struct address_space *mapping = file->f_mapping;
struct inode *inode = mapping->host;
ssize_t ret;
ret = file_remove_privs(file);
if (ret)
return ret;
ret = file_update_time(file);
if (ret)
return ret;
if (iocb->ki_flags & IOCB_DIRECT) {
ret = generic_file_direct_write(iocb, from);
/*
* 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 (ret < 0 || !iov_iter_count(from) || IS_DAX(inode))
return ret;
return direct_write_fallback(iocb, from, ret,
generic_perform_write(iocb, from));
}
return generic_perform_write(iocb, from);
}
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_rwsem as needed.
* Return:
* * negative error code if no data has been written at all of
* vfs_fsync_range() failed for a synchronous write
* * number of bytes written, even for truncated writes
*/
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;
inode_lock(inode);
ret = generic_write_checks(iocb, from);
if (ret > 0)
ret = __generic_file_write_iter(iocb, from);
inode_unlock(inode);
if (ret > 0)
ret = generic_write_sync(iocb, ret);
return ret;
}
EXPORT_SYMBOL(generic_file_write_iter);
/**
* filemap_release_folio() - Release fs-specific metadata on a folio.
* @folio: The folio which the kernel is trying to free.
* @gfp: Memory allocation flags (and I/O mode).
*
* The address_space is trying to release any data attached to a folio
* (presumably at folio->private).
*
* This will also be called if the private_2 flag is set on a page,
* indicating that the folio has other metadata associated with it.
*
* The @gfp argument specifies whether I/O may be performed to release
* this page (__GFP_IO), and whether the call may block
* (__GFP_RECLAIM & __GFP_FS).
*
* Return: %true if the release was successful, otherwise %false.
*/
bool filemap_release_folio(struct folio *folio, gfp_t gfp)
{
struct address_space * const mapping = folio->mapping;
BUG_ON(!folio_test_locked(folio));
mm: merge folio_has_private()/filemap_release_folio() call pairs Patch series "mm, netfs, fscache: Stop read optimisation when folio removed from pagecache", v7. This fixes an optimisation in fscache whereby we don't read from the cache for a particular file until we know that there's data there that we don't have in the pagecache. The problem is that I'm no longer using PG_fscache (aka PG_private_2) to indicate that the page is cached and so I don't get a notification when a cached page is dropped from the pagecache. The first patch merges some folio_has_private() and filemap_release_folio() pairs and introduces a helper, folio_needs_release(), to indicate if a release is required. The second patch is the actual fix. Following Willy's suggestions[1], it adds an AS_RELEASE_ALWAYS flag to an address_space that will make filemap_release_folio() always call ->release_folio(), even if PG_private/PG_private_2 aren't set. folio_needs_release() is altered to add a check for this. This patch (of 2): Make filemap_release_folio() check folio_has_private(). Then, in most cases, where a call to folio_has_private() is immediately followed by a call to filemap_release_folio(), we can get rid of the test in the pair. There are a couple of sites in mm/vscan.c that this can't so easily be done. In shrink_folio_list(), there are actually three cases (something different is done for incompletely invalidated buffers), but filemap_release_folio() elides two of them. In shrink_active_list(), we don't have have the folio lock yet, so the check allows us to avoid locking the page unnecessarily. A wrapper function to check if a folio needs release is provided for those places that still need to do it in the mm/ directory. This will acquire additional parts to the condition in a future patch. After this, the only remaining caller of folio_has_private() outside of mm/ is a check in fuse. Link: https://lkml.kernel.org/r/20230628104852.3391651-1-dhowells@redhat.com Link: https://lkml.kernel.org/r/20230628104852.3391651-2-dhowells@redhat.com Reported-by: Rohith Surabattula <rohiths.msft@gmail.com> Suggested-by: Matthew Wilcox <willy@infradead.org> Signed-off-by: David Howells <dhowells@redhat.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Steve French <sfrench@samba.org> Cc: Shyam Prasad N <nspmangalore@gmail.com> Cc: Rohith Surabattula <rohiths.msft@gmail.com> Cc: Dave Wysochanski <dwysocha@redhat.com> Cc: Dominique Martinet <asmadeus@codewreck.org> Cc: Ilya Dryomov <idryomov@gmail.com> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: Xiubo Li <xiubli@redhat.com> Cc: Jingbo Xu <jefflexu@linux.alibaba.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-06-28 10:48:51 +00:00
if (!folio_needs_release(folio))
return true;
if (folio_test_writeback(folio))
return false;
if (mapping && mapping->a_ops->release_folio)
return mapping->a_ops->release_folio(folio, gfp);
return try_to_free_buffers(folio);
}
EXPORT_SYMBOL(filemap_release_folio);
cachestat: implement cachestat syscall There is currently no good way to query the page cache state of large file sets and directory trees. There is mincore(), but it scales poorly: the kernel writes out a lot of bitmap data that userspace has to aggregate, when the user really doesn not care about per-page information in that case. The user also needs to mmap and unmap each file as it goes along, which can be quite slow as well. Some use cases where this information could come in handy: * Allowing database to decide whether to perform an index scan or direct table queries based on the in-memory cache state of the index. * Visibility into the writeback algorithm, for performance issues diagnostic. * Workload-aware writeback pacing: estimating IO fulfilled by page cache (and IO to be done) within a range of a file, allowing for more frequent syncing when and where there is IO capacity, and batching when there is not. * Computing memory usage of large files/directory trees, analogous to the du tool for disk usage. More information about these use cases could be found in the following thread: https://lore.kernel.org/lkml/20230315170934.GA97793@cmpxchg.org/ This patch implements a new syscall that queries cache state of a file and summarizes the number of cached pages, number of dirty pages, number of pages marked for writeback, number of (recently) evicted pages, etc. in a given range. Currently, the syscall is only wired in for x86 architecture. NAME cachestat - query the page cache statistics of a file. SYNOPSIS #include <sys/mman.h> struct cachestat_range { __u64 off; __u64 len; }; struct cachestat { __u64 nr_cache; __u64 nr_dirty; __u64 nr_writeback; __u64 nr_evicted; __u64 nr_recently_evicted; }; int cachestat(unsigned int fd, struct cachestat_range *cstat_range, struct cachestat *cstat, unsigned int flags); DESCRIPTION cachestat() queries the number of cached pages, number of dirty pages, number of pages marked for writeback, number of evicted pages, number of recently evicted pages, in the bytes range given by `off` and `len`. An evicted page is a page that is previously in the page cache but has been evicted since. A page is recently evicted if its last eviction was recent enough that its reentry to the cache would indicate that it is actively being used by the system, and that there is memory pressure on the system. These values are returned in a cachestat struct, whose address is given by the `cstat` argument. The `off` and `len` arguments must be non-negative integers. If `len` > 0, the queried range is [`off`, `off` + `len`]. If `len` == 0, we will query in the range from `off` to the end of the file. The `flags` argument is unused for now, but is included for future extensibility. User should pass 0 (i.e no flag specified). Currently, hugetlbfs is not supported. Because the status of a page can change after cachestat() checks it but before it returns to the application, the returned values may contain stale information. RETURN VALUE On success, cachestat returns 0. On error, -1 is returned, and errno is set to indicate the error. ERRORS EFAULT cstat or cstat_args points to an invalid address. EINVAL invalid flags. EBADF invalid file descriptor. EOPNOTSUPP file descriptor is of a hugetlbfs file [nphamcs@gmail.com: replace rounddown logic with the existing helper] Link: https://lkml.kernel.org/r/20230504022044.3675469-1-nphamcs@gmail.com Link: https://lkml.kernel.org/r/20230503013608.2431726-3-nphamcs@gmail.com Signed-off-by: Nhat Pham <nphamcs@gmail.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Brian Foster <bfoster@redhat.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-05-03 01:36:07 +00:00
mm: Provide a means of invalidation without using launder_folio Implement a replacement for launder_folio. The key feature of invalidate_inode_pages2() is that it locks each folio individually, unmaps it to prevent mmap'd accesses interfering and calls the ->launder_folio() address_space op to flush it. This has problems: firstly, each folio is written individually as one or more small writes; secondly, adjacent folios cannot be added so easily into the laundry; thirdly, it's yet another op to implement. Instead, use the invalidate lock to cause anyone wanting to add a folio to the inode to wait, then unmap all the folios if we have mmaps, then, conditionally, use ->writepages() to flush any dirty data back and then discard all pages. The invalidate lock prevents ->read_iter(), ->write_iter() and faulting through mmap all from adding pages for the duration. This is then used from netfslib to handle the flusing in unbuffered and direct writes. Signed-off-by: David Howells <dhowells@redhat.com> cc: Matthew Wilcox <willy@infradead.org> cc: Miklos Szeredi <miklos@szeredi.hu> cc: Trond Myklebust <trond.myklebust@hammerspace.com> cc: Christoph Hellwig <hch@lst.de> cc: Andrew Morton <akpm@linux-foundation.org> cc: Alexander Viro <viro@zeniv.linux.org.uk> cc: Christian Brauner <brauner@kernel.org> cc: Jeff Layton <jlayton@kernel.org> cc: linux-mm@kvack.org cc: linux-fsdevel@vger.kernel.org cc: netfs@lists.linux.dev cc: v9fs@lists.linux.dev cc: linux-afs@lists.infradead.org cc: ceph-devel@vger.kernel.org cc: linux-cifs@vger.kernel.org cc: linux-nfs@vger.kernel.org cc: devel@lists.orangefs.org
2024-03-27 08:51:38 +00:00
/**
* filemap_invalidate_inode - Invalidate/forcibly write back a range of an inode's pagecache
* @inode: The inode to flush
* @flush: Set to write back rather than simply invalidate.
* @start: First byte to in range.
* @end: Last byte in range (inclusive), or LLONG_MAX for everything from start
* onwards.
*
* Invalidate all the folios on an inode that contribute to the specified
* range, possibly writing them back first. Whilst the operation is
* undertaken, the invalidate lock is held to prevent new folios from being
* installed.
*/
int filemap_invalidate_inode(struct inode *inode, bool flush,
loff_t start, loff_t end)
{
struct address_space *mapping = inode->i_mapping;
pgoff_t first = start >> PAGE_SHIFT;
pgoff_t last = end >> PAGE_SHIFT;
pgoff_t nr = end == LLONG_MAX ? ULONG_MAX : last - first + 1;
if (!mapping || !mapping->nrpages || end < start)
goto out;
/* Prevent new folios from being added to the inode. */
filemap_invalidate_lock(mapping);
if (!mapping->nrpages)
goto unlock;
unmap_mapping_pages(mapping, first, nr, false);
/* Write back the data if we're asked to. */
if (flush) {
struct writeback_control wbc = {
.sync_mode = WB_SYNC_ALL,
.nr_to_write = LONG_MAX,
.range_start = start,
.range_end = end,
};
filemap_fdatawrite_wbc(mapping, &wbc);
}
/* Wait for writeback to complete on all folios and discard. */
truncate_inode_pages_range(mapping, start, end);
unlock:
filemap_invalidate_unlock(mapping);
out:
return filemap_check_errors(mapping);
}
EXPORT_SYMBOL_GPL(filemap_invalidate_inode);
cachestat: implement cachestat syscall There is currently no good way to query the page cache state of large file sets and directory trees. There is mincore(), but it scales poorly: the kernel writes out a lot of bitmap data that userspace has to aggregate, when the user really doesn not care about per-page information in that case. The user also needs to mmap and unmap each file as it goes along, which can be quite slow as well. Some use cases where this information could come in handy: * Allowing database to decide whether to perform an index scan or direct table queries based on the in-memory cache state of the index. * Visibility into the writeback algorithm, for performance issues diagnostic. * Workload-aware writeback pacing: estimating IO fulfilled by page cache (and IO to be done) within a range of a file, allowing for more frequent syncing when and where there is IO capacity, and batching when there is not. * Computing memory usage of large files/directory trees, analogous to the du tool for disk usage. More information about these use cases could be found in the following thread: https://lore.kernel.org/lkml/20230315170934.GA97793@cmpxchg.org/ This patch implements a new syscall that queries cache state of a file and summarizes the number of cached pages, number of dirty pages, number of pages marked for writeback, number of (recently) evicted pages, etc. in a given range. Currently, the syscall is only wired in for x86 architecture. NAME cachestat - query the page cache statistics of a file. SYNOPSIS #include <sys/mman.h> struct cachestat_range { __u64 off; __u64 len; }; struct cachestat { __u64 nr_cache; __u64 nr_dirty; __u64 nr_writeback; __u64 nr_evicted; __u64 nr_recently_evicted; }; int cachestat(unsigned int fd, struct cachestat_range *cstat_range, struct cachestat *cstat, unsigned int flags); DESCRIPTION cachestat() queries the number of cached pages, number of dirty pages, number of pages marked for writeback, number of evicted pages, number of recently evicted pages, in the bytes range given by `off` and `len`. An evicted page is a page that is previously in the page cache but has been evicted since. A page is recently evicted if its last eviction was recent enough that its reentry to the cache would indicate that it is actively being used by the system, and that there is memory pressure on the system. These values are returned in a cachestat struct, whose address is given by the `cstat` argument. The `off` and `len` arguments must be non-negative integers. If `len` > 0, the queried range is [`off`, `off` + `len`]. If `len` == 0, we will query in the range from `off` to the end of the file. The `flags` argument is unused for now, but is included for future extensibility. User should pass 0 (i.e no flag specified). Currently, hugetlbfs is not supported. Because the status of a page can change after cachestat() checks it but before it returns to the application, the returned values may contain stale information. RETURN VALUE On success, cachestat returns 0. On error, -1 is returned, and errno is set to indicate the error. ERRORS EFAULT cstat or cstat_args points to an invalid address. EINVAL invalid flags. EBADF invalid file descriptor. EOPNOTSUPP file descriptor is of a hugetlbfs file [nphamcs@gmail.com: replace rounddown logic with the existing helper] Link: https://lkml.kernel.org/r/20230504022044.3675469-1-nphamcs@gmail.com Link: https://lkml.kernel.org/r/20230503013608.2431726-3-nphamcs@gmail.com Signed-off-by: Nhat Pham <nphamcs@gmail.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Brian Foster <bfoster@redhat.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-05-03 01:36:07 +00:00
#ifdef CONFIG_CACHESTAT_SYSCALL
/**
* filemap_cachestat() - compute the page cache statistics of a mapping
* @mapping: The mapping to compute the statistics for.
* @first_index: The starting page cache index.
* @last_index: The final page index (inclusive).
* @cs: the cachestat struct to write the result to.
*
* This will query the page cache statistics of a mapping in the
* page range of [first_index, last_index] (inclusive). The statistics
* queried include: number of dirty pages, number of pages marked for
* writeback, and the number of (recently) evicted pages.
*/
static void filemap_cachestat(struct address_space *mapping,
pgoff_t first_index, pgoff_t last_index, struct cachestat *cs)
{
XA_STATE(xas, &mapping->i_pages, first_index);
struct folio *folio;
rcu_read_lock();
xas_for_each(&xas, folio, last_index) {
int order;
cachestat: implement cachestat syscall There is currently no good way to query the page cache state of large file sets and directory trees. There is mincore(), but it scales poorly: the kernel writes out a lot of bitmap data that userspace has to aggregate, when the user really doesn not care about per-page information in that case. The user also needs to mmap and unmap each file as it goes along, which can be quite slow as well. Some use cases where this information could come in handy: * Allowing database to decide whether to perform an index scan or direct table queries based on the in-memory cache state of the index. * Visibility into the writeback algorithm, for performance issues diagnostic. * Workload-aware writeback pacing: estimating IO fulfilled by page cache (and IO to be done) within a range of a file, allowing for more frequent syncing when and where there is IO capacity, and batching when there is not. * Computing memory usage of large files/directory trees, analogous to the du tool for disk usage. More information about these use cases could be found in the following thread: https://lore.kernel.org/lkml/20230315170934.GA97793@cmpxchg.org/ This patch implements a new syscall that queries cache state of a file and summarizes the number of cached pages, number of dirty pages, number of pages marked for writeback, number of (recently) evicted pages, etc. in a given range. Currently, the syscall is only wired in for x86 architecture. NAME cachestat - query the page cache statistics of a file. SYNOPSIS #include <sys/mman.h> struct cachestat_range { __u64 off; __u64 len; }; struct cachestat { __u64 nr_cache; __u64 nr_dirty; __u64 nr_writeback; __u64 nr_evicted; __u64 nr_recently_evicted; }; int cachestat(unsigned int fd, struct cachestat_range *cstat_range, struct cachestat *cstat, unsigned int flags); DESCRIPTION cachestat() queries the number of cached pages, number of dirty pages, number of pages marked for writeback, number of evicted pages, number of recently evicted pages, in the bytes range given by `off` and `len`. An evicted page is a page that is previously in the page cache but has been evicted since. A page is recently evicted if its last eviction was recent enough that its reentry to the cache would indicate that it is actively being used by the system, and that there is memory pressure on the system. These values are returned in a cachestat struct, whose address is given by the `cstat` argument. The `off` and `len` arguments must be non-negative integers. If `len` > 0, the queried range is [`off`, `off` + `len`]. If `len` == 0, we will query in the range from `off` to the end of the file. The `flags` argument is unused for now, but is included for future extensibility. User should pass 0 (i.e no flag specified). Currently, hugetlbfs is not supported. Because the status of a page can change after cachestat() checks it but before it returns to the application, the returned values may contain stale information. RETURN VALUE On success, cachestat returns 0. On error, -1 is returned, and errno is set to indicate the error. ERRORS EFAULT cstat or cstat_args points to an invalid address. EINVAL invalid flags. EBADF invalid file descriptor. EOPNOTSUPP file descriptor is of a hugetlbfs file [nphamcs@gmail.com: replace rounddown logic with the existing helper] Link: https://lkml.kernel.org/r/20230504022044.3675469-1-nphamcs@gmail.com Link: https://lkml.kernel.org/r/20230503013608.2431726-3-nphamcs@gmail.com Signed-off-by: Nhat Pham <nphamcs@gmail.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Brian Foster <bfoster@redhat.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-05-03 01:36:07 +00:00
unsigned long nr_pages;
pgoff_t folio_first_index, folio_last_index;
/*
* Don't deref the folio. It is not pinned, and might
* get freed (and reused) underneath us.
*
* We *could* pin it, but that would be expensive for
* what should be a fast and lightweight syscall.
*
* Instead, derive all information of interest from
* the rcu-protected xarray.
*/
cachestat: implement cachestat syscall There is currently no good way to query the page cache state of large file sets and directory trees. There is mincore(), but it scales poorly: the kernel writes out a lot of bitmap data that userspace has to aggregate, when the user really doesn not care about per-page information in that case. The user also needs to mmap and unmap each file as it goes along, which can be quite slow as well. Some use cases where this information could come in handy: * Allowing database to decide whether to perform an index scan or direct table queries based on the in-memory cache state of the index. * Visibility into the writeback algorithm, for performance issues diagnostic. * Workload-aware writeback pacing: estimating IO fulfilled by page cache (and IO to be done) within a range of a file, allowing for more frequent syncing when and where there is IO capacity, and batching when there is not. * Computing memory usage of large files/directory trees, analogous to the du tool for disk usage. More information about these use cases could be found in the following thread: https://lore.kernel.org/lkml/20230315170934.GA97793@cmpxchg.org/ This patch implements a new syscall that queries cache state of a file and summarizes the number of cached pages, number of dirty pages, number of pages marked for writeback, number of (recently) evicted pages, etc. in a given range. Currently, the syscall is only wired in for x86 architecture. NAME cachestat - query the page cache statistics of a file. SYNOPSIS #include <sys/mman.h> struct cachestat_range { __u64 off; __u64 len; }; struct cachestat { __u64 nr_cache; __u64 nr_dirty; __u64 nr_writeback; __u64 nr_evicted; __u64 nr_recently_evicted; }; int cachestat(unsigned int fd, struct cachestat_range *cstat_range, struct cachestat *cstat, unsigned int flags); DESCRIPTION cachestat() queries the number of cached pages, number of dirty pages, number of pages marked for writeback, number of evicted pages, number of recently evicted pages, in the bytes range given by `off` and `len`. An evicted page is a page that is previously in the page cache but has been evicted since. A page is recently evicted if its last eviction was recent enough that its reentry to the cache would indicate that it is actively being used by the system, and that there is memory pressure on the system. These values are returned in a cachestat struct, whose address is given by the `cstat` argument. The `off` and `len` arguments must be non-negative integers. If `len` > 0, the queried range is [`off`, `off` + `len`]. If `len` == 0, we will query in the range from `off` to the end of the file. The `flags` argument is unused for now, but is included for future extensibility. User should pass 0 (i.e no flag specified). Currently, hugetlbfs is not supported. Because the status of a page can change after cachestat() checks it but before it returns to the application, the returned values may contain stale information. RETURN VALUE On success, cachestat returns 0. On error, -1 is returned, and errno is set to indicate the error. ERRORS EFAULT cstat or cstat_args points to an invalid address. EINVAL invalid flags. EBADF invalid file descriptor. EOPNOTSUPP file descriptor is of a hugetlbfs file [nphamcs@gmail.com: replace rounddown logic with the existing helper] Link: https://lkml.kernel.org/r/20230504022044.3675469-1-nphamcs@gmail.com Link: https://lkml.kernel.org/r/20230503013608.2431726-3-nphamcs@gmail.com Signed-off-by: Nhat Pham <nphamcs@gmail.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Brian Foster <bfoster@redhat.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-05-03 01:36:07 +00:00
if (xas_retry(&xas, folio))
continue;
order = xa_get_order(xas.xa, xas.xa_index);
nr_pages = 1 << order;
folio_first_index = round_down(xas.xa_index, 1 << order);
folio_last_index = folio_first_index + nr_pages - 1;
/* Folios might straddle the range boundaries, only count covered pages */
if (folio_first_index < first_index)
nr_pages -= first_index - folio_first_index;
if (folio_last_index > last_index)
nr_pages -= folio_last_index - last_index;
cachestat: implement cachestat syscall There is currently no good way to query the page cache state of large file sets and directory trees. There is mincore(), but it scales poorly: the kernel writes out a lot of bitmap data that userspace has to aggregate, when the user really doesn not care about per-page information in that case. The user also needs to mmap and unmap each file as it goes along, which can be quite slow as well. Some use cases where this information could come in handy: * Allowing database to decide whether to perform an index scan or direct table queries based on the in-memory cache state of the index. * Visibility into the writeback algorithm, for performance issues diagnostic. * Workload-aware writeback pacing: estimating IO fulfilled by page cache (and IO to be done) within a range of a file, allowing for more frequent syncing when and where there is IO capacity, and batching when there is not. * Computing memory usage of large files/directory trees, analogous to the du tool for disk usage. More information about these use cases could be found in the following thread: https://lore.kernel.org/lkml/20230315170934.GA97793@cmpxchg.org/ This patch implements a new syscall that queries cache state of a file and summarizes the number of cached pages, number of dirty pages, number of pages marked for writeback, number of (recently) evicted pages, etc. in a given range. Currently, the syscall is only wired in for x86 architecture. NAME cachestat - query the page cache statistics of a file. SYNOPSIS #include <sys/mman.h> struct cachestat_range { __u64 off; __u64 len; }; struct cachestat { __u64 nr_cache; __u64 nr_dirty; __u64 nr_writeback; __u64 nr_evicted; __u64 nr_recently_evicted; }; int cachestat(unsigned int fd, struct cachestat_range *cstat_range, struct cachestat *cstat, unsigned int flags); DESCRIPTION cachestat() queries the number of cached pages, number of dirty pages, number of pages marked for writeback, number of evicted pages, number of recently evicted pages, in the bytes range given by `off` and `len`. An evicted page is a page that is previously in the page cache but has been evicted since. A page is recently evicted if its last eviction was recent enough that its reentry to the cache would indicate that it is actively being used by the system, and that there is memory pressure on the system. These values are returned in a cachestat struct, whose address is given by the `cstat` argument. The `off` and `len` arguments must be non-negative integers. If `len` > 0, the queried range is [`off`, `off` + `len`]. If `len` == 0, we will query in the range from `off` to the end of the file. The `flags` argument is unused for now, but is included for future extensibility. User should pass 0 (i.e no flag specified). Currently, hugetlbfs is not supported. Because the status of a page can change after cachestat() checks it but before it returns to the application, the returned values may contain stale information. RETURN VALUE On success, cachestat returns 0. On error, -1 is returned, and errno is set to indicate the error. ERRORS EFAULT cstat or cstat_args points to an invalid address. EINVAL invalid flags. EBADF invalid file descriptor. EOPNOTSUPP file descriptor is of a hugetlbfs file [nphamcs@gmail.com: replace rounddown logic with the existing helper] Link: https://lkml.kernel.org/r/20230504022044.3675469-1-nphamcs@gmail.com Link: https://lkml.kernel.org/r/20230503013608.2431726-3-nphamcs@gmail.com Signed-off-by: Nhat Pham <nphamcs@gmail.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Brian Foster <bfoster@redhat.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-05-03 01:36:07 +00:00
if (xa_is_value(folio)) {
/* page is evicted */
void *shadow = (void *)folio;
bool workingset; /* not used */
cs->nr_evicted += nr_pages;
#ifdef CONFIG_SWAP /* implies CONFIG_MMU */
if (shmem_mapping(mapping)) {
/* shmem file - in swap cache */
swp_entry_t swp = radix_to_swp_entry(folio);
mm: cachestat: fix two shmem bugs When cachestat on shmem races with swapping and invalidation, there are two possible bugs: 1) A swapin error can have resulted in a poisoned swap entry in the shmem inode's xarray. Calling get_shadow_from_swap_cache() on it will result in an out-of-bounds access to swapper_spaces[]. Validate the entry with non_swap_entry() before going further. 2) When we find a valid swap entry in the shmem's inode, the shadow entry in the swapcache might not exist yet: swap IO is still in progress and we're before __remove_mapping; swapin, invalidation, or swapoff have removed the shadow from swapcache after we saw the shmem swap entry. This will send a NULL to workingset_test_recent(). The latter purely operates on pointer bits, so it won't crash - node 0, memcg ID 0, eviction timestamp 0, etc. are all valid inputs - but it's a bogus test. In theory that could result in a false "recently evicted" count. Such a false positive wouldn't be the end of the world. But for code clarity and (future) robustness, be explicit about this case. Bail on get_shadow_from_swap_cache() returning NULL. Link: https://lkml.kernel.org/r/20240315095556.GC581298@cmpxchg.org Fixes: cf264e1329fb ("cachestat: implement cachestat syscall") Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reported-by: Chengming Zhou <chengming.zhou@linux.dev> [Bug #1] Reported-by: Jann Horn <jannh@google.com> [Bug #2] Reviewed-by: Chengming Zhou <chengming.zhou@linux.dev> Reviewed-by: Nhat Pham <nphamcs@gmail.com> Cc: <stable@vger.kernel.org> [v6.5+] Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-03-15 09:55:56 +00:00
/* swapin error results in poisoned entry */
if (non_swap_entry(swp))
goto resched;
/*
* Getting a swap entry from the shmem
* inode means we beat
* shmem_unuse(). rcu_read_lock()
* ensures swapoff waits for us before
* freeing the swapper space. However,
* we can race with swapping and
* invalidation, so there might not be
* a shadow in the swapcache (yet).
*/
cachestat: implement cachestat syscall There is currently no good way to query the page cache state of large file sets and directory trees. There is mincore(), but it scales poorly: the kernel writes out a lot of bitmap data that userspace has to aggregate, when the user really doesn not care about per-page information in that case. The user also needs to mmap and unmap each file as it goes along, which can be quite slow as well. Some use cases where this information could come in handy: * Allowing database to decide whether to perform an index scan or direct table queries based on the in-memory cache state of the index. * Visibility into the writeback algorithm, for performance issues diagnostic. * Workload-aware writeback pacing: estimating IO fulfilled by page cache (and IO to be done) within a range of a file, allowing for more frequent syncing when and where there is IO capacity, and batching when there is not. * Computing memory usage of large files/directory trees, analogous to the du tool for disk usage. More information about these use cases could be found in the following thread: https://lore.kernel.org/lkml/20230315170934.GA97793@cmpxchg.org/ This patch implements a new syscall that queries cache state of a file and summarizes the number of cached pages, number of dirty pages, number of pages marked for writeback, number of (recently) evicted pages, etc. in a given range. Currently, the syscall is only wired in for x86 architecture. NAME cachestat - query the page cache statistics of a file. SYNOPSIS #include <sys/mman.h> struct cachestat_range { __u64 off; __u64 len; }; struct cachestat { __u64 nr_cache; __u64 nr_dirty; __u64 nr_writeback; __u64 nr_evicted; __u64 nr_recently_evicted; }; int cachestat(unsigned int fd, struct cachestat_range *cstat_range, struct cachestat *cstat, unsigned int flags); DESCRIPTION cachestat() queries the number of cached pages, number of dirty pages, number of pages marked for writeback, number of evicted pages, number of recently evicted pages, in the bytes range given by `off` and `len`. An evicted page is a page that is previously in the page cache but has been evicted since. A page is recently evicted if its last eviction was recent enough that its reentry to the cache would indicate that it is actively being used by the system, and that there is memory pressure on the system. These values are returned in a cachestat struct, whose address is given by the `cstat` argument. The `off` and `len` arguments must be non-negative integers. If `len` > 0, the queried range is [`off`, `off` + `len`]. If `len` == 0, we will query in the range from `off` to the end of the file. The `flags` argument is unused for now, but is included for future extensibility. User should pass 0 (i.e no flag specified). Currently, hugetlbfs is not supported. Because the status of a page can change after cachestat() checks it but before it returns to the application, the returned values may contain stale information. RETURN VALUE On success, cachestat returns 0. On error, -1 is returned, and errno is set to indicate the error. ERRORS EFAULT cstat or cstat_args points to an invalid address. EINVAL invalid flags. EBADF invalid file descriptor. EOPNOTSUPP file descriptor is of a hugetlbfs file [nphamcs@gmail.com: replace rounddown logic with the existing helper] Link: https://lkml.kernel.org/r/20230504022044.3675469-1-nphamcs@gmail.com Link: https://lkml.kernel.org/r/20230503013608.2431726-3-nphamcs@gmail.com Signed-off-by: Nhat Pham <nphamcs@gmail.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Brian Foster <bfoster@redhat.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-05-03 01:36:07 +00:00
shadow = get_shadow_from_swap_cache(swp);
mm: cachestat: fix two shmem bugs When cachestat on shmem races with swapping and invalidation, there are two possible bugs: 1) A swapin error can have resulted in a poisoned swap entry in the shmem inode's xarray. Calling get_shadow_from_swap_cache() on it will result in an out-of-bounds access to swapper_spaces[]. Validate the entry with non_swap_entry() before going further. 2) When we find a valid swap entry in the shmem's inode, the shadow entry in the swapcache might not exist yet: swap IO is still in progress and we're before __remove_mapping; swapin, invalidation, or swapoff have removed the shadow from swapcache after we saw the shmem swap entry. This will send a NULL to workingset_test_recent(). The latter purely operates on pointer bits, so it won't crash - node 0, memcg ID 0, eviction timestamp 0, etc. are all valid inputs - but it's a bogus test. In theory that could result in a false "recently evicted" count. Such a false positive wouldn't be the end of the world. But for code clarity and (future) robustness, be explicit about this case. Bail on get_shadow_from_swap_cache() returning NULL. Link: https://lkml.kernel.org/r/20240315095556.GC581298@cmpxchg.org Fixes: cf264e1329fb ("cachestat: implement cachestat syscall") Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reported-by: Chengming Zhou <chengming.zhou@linux.dev> [Bug #1] Reported-by: Jann Horn <jannh@google.com> [Bug #2] Reviewed-by: Chengming Zhou <chengming.zhou@linux.dev> Reviewed-by: Nhat Pham <nphamcs@gmail.com> Cc: <stable@vger.kernel.org> [v6.5+] Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-03-15 09:55:56 +00:00
if (!shadow)
goto resched;
cachestat: implement cachestat syscall There is currently no good way to query the page cache state of large file sets and directory trees. There is mincore(), but it scales poorly: the kernel writes out a lot of bitmap data that userspace has to aggregate, when the user really doesn not care about per-page information in that case. The user also needs to mmap and unmap each file as it goes along, which can be quite slow as well. Some use cases where this information could come in handy: * Allowing database to decide whether to perform an index scan or direct table queries based on the in-memory cache state of the index. * Visibility into the writeback algorithm, for performance issues diagnostic. * Workload-aware writeback pacing: estimating IO fulfilled by page cache (and IO to be done) within a range of a file, allowing for more frequent syncing when and where there is IO capacity, and batching when there is not. * Computing memory usage of large files/directory trees, analogous to the du tool for disk usage. More information about these use cases could be found in the following thread: https://lore.kernel.org/lkml/20230315170934.GA97793@cmpxchg.org/ This patch implements a new syscall that queries cache state of a file and summarizes the number of cached pages, number of dirty pages, number of pages marked for writeback, number of (recently) evicted pages, etc. in a given range. Currently, the syscall is only wired in for x86 architecture. NAME cachestat - query the page cache statistics of a file. SYNOPSIS #include <sys/mman.h> struct cachestat_range { __u64 off; __u64 len; }; struct cachestat { __u64 nr_cache; __u64 nr_dirty; __u64 nr_writeback; __u64 nr_evicted; __u64 nr_recently_evicted; }; int cachestat(unsigned int fd, struct cachestat_range *cstat_range, struct cachestat *cstat, unsigned int flags); DESCRIPTION cachestat() queries the number of cached pages, number of dirty pages, number of pages marked for writeback, number of evicted pages, number of recently evicted pages, in the bytes range given by `off` and `len`. An evicted page is a page that is previously in the page cache but has been evicted since. A page is recently evicted if its last eviction was recent enough that its reentry to the cache would indicate that it is actively being used by the system, and that there is memory pressure on the system. These values are returned in a cachestat struct, whose address is given by the `cstat` argument. The `off` and `len` arguments must be non-negative integers. If `len` > 0, the queried range is [`off`, `off` + `len`]. If `len` == 0, we will query in the range from `off` to the end of the file. The `flags` argument is unused for now, but is included for future extensibility. User should pass 0 (i.e no flag specified). Currently, hugetlbfs is not supported. Because the status of a page can change after cachestat() checks it but before it returns to the application, the returned values may contain stale information. RETURN VALUE On success, cachestat returns 0. On error, -1 is returned, and errno is set to indicate the error. ERRORS EFAULT cstat or cstat_args points to an invalid address. EINVAL invalid flags. EBADF invalid file descriptor. EOPNOTSUPP file descriptor is of a hugetlbfs file [nphamcs@gmail.com: replace rounddown logic with the existing helper] Link: https://lkml.kernel.org/r/20230504022044.3675469-1-nphamcs@gmail.com Link: https://lkml.kernel.org/r/20230503013608.2431726-3-nphamcs@gmail.com Signed-off-by: Nhat Pham <nphamcs@gmail.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Brian Foster <bfoster@redhat.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-05-03 01:36:07 +00:00
}
#endif
if (workingset_test_recent(shadow, true, &workingset))
cs->nr_recently_evicted += nr_pages;
goto resched;
}
/* page is in cache */
cs->nr_cache += nr_pages;
if (xas_get_mark(&xas, PAGECACHE_TAG_DIRTY))
cachestat: implement cachestat syscall There is currently no good way to query the page cache state of large file sets and directory trees. There is mincore(), but it scales poorly: the kernel writes out a lot of bitmap data that userspace has to aggregate, when the user really doesn not care about per-page information in that case. The user also needs to mmap and unmap each file as it goes along, which can be quite slow as well. Some use cases where this information could come in handy: * Allowing database to decide whether to perform an index scan or direct table queries based on the in-memory cache state of the index. * Visibility into the writeback algorithm, for performance issues diagnostic. * Workload-aware writeback pacing: estimating IO fulfilled by page cache (and IO to be done) within a range of a file, allowing for more frequent syncing when and where there is IO capacity, and batching when there is not. * Computing memory usage of large files/directory trees, analogous to the du tool for disk usage. More information about these use cases could be found in the following thread: https://lore.kernel.org/lkml/20230315170934.GA97793@cmpxchg.org/ This patch implements a new syscall that queries cache state of a file and summarizes the number of cached pages, number of dirty pages, number of pages marked for writeback, number of (recently) evicted pages, etc. in a given range. Currently, the syscall is only wired in for x86 architecture. NAME cachestat - query the page cache statistics of a file. SYNOPSIS #include <sys/mman.h> struct cachestat_range { __u64 off; __u64 len; }; struct cachestat { __u64 nr_cache; __u64 nr_dirty; __u64 nr_writeback; __u64 nr_evicted; __u64 nr_recently_evicted; }; int cachestat(unsigned int fd, struct cachestat_range *cstat_range, struct cachestat *cstat, unsigned int flags); DESCRIPTION cachestat() queries the number of cached pages, number of dirty pages, number of pages marked for writeback, number of evicted pages, number of recently evicted pages, in the bytes range given by `off` and `len`. An evicted page is a page that is previously in the page cache but has been evicted since. A page is recently evicted if its last eviction was recent enough that its reentry to the cache would indicate that it is actively being used by the system, and that there is memory pressure on the system. These values are returned in a cachestat struct, whose address is given by the `cstat` argument. The `off` and `len` arguments must be non-negative integers. If `len` > 0, the queried range is [`off`, `off` + `len`]. If `len` == 0, we will query in the range from `off` to the end of the file. The `flags` argument is unused for now, but is included for future extensibility. User should pass 0 (i.e no flag specified). Currently, hugetlbfs is not supported. Because the status of a page can change after cachestat() checks it but before it returns to the application, the returned values may contain stale information. RETURN VALUE On success, cachestat returns 0. On error, -1 is returned, and errno is set to indicate the error. ERRORS EFAULT cstat or cstat_args points to an invalid address. EINVAL invalid flags. EBADF invalid file descriptor. EOPNOTSUPP file descriptor is of a hugetlbfs file [nphamcs@gmail.com: replace rounddown logic with the existing helper] Link: https://lkml.kernel.org/r/20230504022044.3675469-1-nphamcs@gmail.com Link: https://lkml.kernel.org/r/20230503013608.2431726-3-nphamcs@gmail.com Signed-off-by: Nhat Pham <nphamcs@gmail.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Brian Foster <bfoster@redhat.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-05-03 01:36:07 +00:00
cs->nr_dirty += nr_pages;
if (xas_get_mark(&xas, PAGECACHE_TAG_WRITEBACK))
cachestat: implement cachestat syscall There is currently no good way to query the page cache state of large file sets and directory trees. There is mincore(), but it scales poorly: the kernel writes out a lot of bitmap data that userspace has to aggregate, when the user really doesn not care about per-page information in that case. The user also needs to mmap and unmap each file as it goes along, which can be quite slow as well. Some use cases where this information could come in handy: * Allowing database to decide whether to perform an index scan or direct table queries based on the in-memory cache state of the index. * Visibility into the writeback algorithm, for performance issues diagnostic. * Workload-aware writeback pacing: estimating IO fulfilled by page cache (and IO to be done) within a range of a file, allowing for more frequent syncing when and where there is IO capacity, and batching when there is not. * Computing memory usage of large files/directory trees, analogous to the du tool for disk usage. More information about these use cases could be found in the following thread: https://lore.kernel.org/lkml/20230315170934.GA97793@cmpxchg.org/ This patch implements a new syscall that queries cache state of a file and summarizes the number of cached pages, number of dirty pages, number of pages marked for writeback, number of (recently) evicted pages, etc. in a given range. Currently, the syscall is only wired in for x86 architecture. NAME cachestat - query the page cache statistics of a file. SYNOPSIS #include <sys/mman.h> struct cachestat_range { __u64 off; __u64 len; }; struct cachestat { __u64 nr_cache; __u64 nr_dirty; __u64 nr_writeback; __u64 nr_evicted; __u64 nr_recently_evicted; }; int cachestat(unsigned int fd, struct cachestat_range *cstat_range, struct cachestat *cstat, unsigned int flags); DESCRIPTION cachestat() queries the number of cached pages, number of dirty pages, number of pages marked for writeback, number of evicted pages, number of recently evicted pages, in the bytes range given by `off` and `len`. An evicted page is a page that is previously in the page cache but has been evicted since. A page is recently evicted if its last eviction was recent enough that its reentry to the cache would indicate that it is actively being used by the system, and that there is memory pressure on the system. These values are returned in a cachestat struct, whose address is given by the `cstat` argument. The `off` and `len` arguments must be non-negative integers. If `len` > 0, the queried range is [`off`, `off` + `len`]. If `len` == 0, we will query in the range from `off` to the end of the file. The `flags` argument is unused for now, but is included for future extensibility. User should pass 0 (i.e no flag specified). Currently, hugetlbfs is not supported. Because the status of a page can change after cachestat() checks it but before it returns to the application, the returned values may contain stale information. RETURN VALUE On success, cachestat returns 0. On error, -1 is returned, and errno is set to indicate the error. ERRORS EFAULT cstat or cstat_args points to an invalid address. EINVAL invalid flags. EBADF invalid file descriptor. EOPNOTSUPP file descriptor is of a hugetlbfs file [nphamcs@gmail.com: replace rounddown logic with the existing helper] Link: https://lkml.kernel.org/r/20230504022044.3675469-1-nphamcs@gmail.com Link: https://lkml.kernel.org/r/20230503013608.2431726-3-nphamcs@gmail.com Signed-off-by: Nhat Pham <nphamcs@gmail.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Brian Foster <bfoster@redhat.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-05-03 01:36:07 +00:00
cs->nr_writeback += nr_pages;
resched:
if (need_resched()) {
xas_pause(&xas);
cond_resched_rcu();
}
}
rcu_read_unlock();
}
/*
* The cachestat(2) system call.
*
* cachestat() returns the page cache statistics of a file in the
* bytes range specified by `off` and `len`: number of cached pages,
* number of dirty pages, number of pages marked for writeback,
* number of evicted pages, and number of recently evicted pages.
*
* An evicted page is a page that is previously in the page cache
* but has been evicted since. A page is recently evicted if its last
* eviction was recent enough that its reentry to the cache would
* indicate that it is actively being used by the system, and that
* there is memory pressure on the system.
*
* `off` and `len` must be non-negative integers. If `len` > 0,
* the queried range is [`off`, `off` + `len`]. If `len` == 0,
* we will query in the range from `off` to the end of the file.
*
* The `flags` argument is unused for now, but is included for future
* extensibility. User should pass 0 (i.e no flag specified).
*
* Currently, hugetlbfs is not supported.
*
* Because the status of a page can change after cachestat() checks it
* but before it returns to the application, the returned values may
* contain stale information.
*
* return values:
* zero - success
* -EFAULT - cstat or cstat_range points to an illegal address
* -EINVAL - invalid flags
* -EBADF - invalid file descriptor
* -EOPNOTSUPP - file descriptor is of a hugetlbfs file
*/
SYSCALL_DEFINE4(cachestat, unsigned int, fd,
struct cachestat_range __user *, cstat_range,
struct cachestat __user *, cstat, unsigned int, flags)
{
struct fd f = fdget(fd);
struct address_space *mapping;
struct cachestat_range csr;
struct cachestat cs;
pgoff_t first_index, last_index;
if (!f.file)
return -EBADF;
if (copy_from_user(&csr, cstat_range,
sizeof(struct cachestat_range))) {
fdput(f);
return -EFAULT;
}
/* hugetlbfs is not supported */
if (is_file_hugepages(f.file)) {
fdput(f);
return -EOPNOTSUPP;
}
if (flags != 0) {
fdput(f);
return -EINVAL;
}
first_index = csr.off >> PAGE_SHIFT;
last_index =
csr.len == 0 ? ULONG_MAX : (csr.off + csr.len - 1) >> PAGE_SHIFT;
memset(&cs, 0, sizeof(struct cachestat));
mapping = f.file->f_mapping;
filemap_cachestat(mapping, first_index, last_index, &cs);
fdput(f);
if (copy_to_user(cstat, &cs, sizeof(struct cachestat)))
return -EFAULT;
return 0;
}
#endif /* CONFIG_CACHESTAT_SYSCALL */